DESC:DESCRIPTION
Technical Field
[001] This disclosure relates generally to developing new products including nutraceutical products, and in particular, to a system and method of developing a new product using machine learning (ML) models.

Background
[002] Developing new products, for example nutraceutical products, presents several challenges that encompass scientific, regulatory, market, and operational aspects. For example, development of nutraceutical products relies on bioactive compounds found in natural sources, necessitating extensive research to identify, isolate, and characterize these compounds. Further, regulatory requirements for nutraceutical products vary widely between countries, requiring manufacturers to navigate complex frameworks for product registration, labeling, health claims, and quality standards. As such, ensuring compliance with evolving regulations, such as novel food regulations and health claims substantiation requirements, poses significant challenges for new product development. Furthermore, formulating nutraceutical products with optimal ingredient combinations, dosage levels, and delivery systems requires expertise in chemistry, pharmacology, and food science. Therefore, achieving desired product attributes such as taste, texture, bioavailability, and stability while avoiding interactions and degradation poses formulation challenges. Moreover, balancing product quality, affordability, and profitability while meeting consumer expectations and regulatory requirements is essential for commercial success.
[003] Navigating these challenges requires strategic planning and continuous innovation throughout the nutraceutical product development lifecycle. Conventionally, the nutraceutical product development lifecycle mostly relies on manual processes for idea generation, regulatory compliance, and supply chain management. As such, these solutions were not only time-consuming but also prone to errors.
[004] Therefore, there is a need for effective and automated solutions that provide for developing new products using machine learning (ML) models, while minimizing manual intervention.

SUMMARY
[005] In an embodiment, a system configured to develop a new product. The system comprises a product development device via a machine learning (ML) model, configured to generate formulation for the new product. The one or more processing units of product development device configured to define the disease via tagging at least based on a board category and a department. Further, the data related to the disease and condition is analyzed by the processors. Further the processor runs an alteration string to determine the ingredients for the disease and condition. Further, the processor prepares the final composition of ingredients for the disease and condition.
[006] In an embodiment, the ML model may identify the disease, or the condition needs to be targeted and map the ingredients. Further, the ML model may analyze the risk factors contributing to the disease. Further, the ML model may identify related nutritional and hormonal deficiencies related to the disease. Further, the ML model may determine initial biological changes occurring due to the disease. Further, the ML model may assess changes in biomarkers associated with the disease. Further, the ML model may map an activation or inhibition of relevant biological pathways. Further, the ML model may evaluate all major response systems and symptoms related to disease via an evaluation criteria. Further, the ML model may document the clinical symptoms and diagnostic findings indicating disease onset. Further, the ML model may identify and map the ingredients, active, bioactive or molecules. Further, the ML model may provide design mechanisms of action image.
[007] In an embodiment, the ML model evaluation criteria include a synergistic potential, a receptor analysis, an ADME (absorption, distribution, metabolism, excretion) and toxicity. The ML model evaluating toxicity criteria comprises collecting ingredients data/information from a storage database. Further, the toxicity criteria may check existing evidence data of the ingredients related to the disease. Further, the toxicity criteria may populate the existing evidence data for recording toxicity in the ingredients. Further, the toxicity criteria may analyze toxic doses, contraindication, side effects and interactions for the condition or disease. Further, the toxicity criteria may generate a report for the condition or disease. Further, the toxicity criteria may send the report for review and approval.
[008] In an embodiment, the ML model identifies optimal combinations of ingredients, dosage levels, and formulation strategies tailored to specific health goals, target populations, and regulatory requirements. The ML model identifies bioactive compounds, vitamins, minerals, botanical extracts, probiotics, and other functional ingredients with documented health benefits relevant to the target indication or health condition.
[009] A method configured to develop a new product. The method comprises defining a disease and condition via tagging at least based on a board category and a department. Further, the method steps include analyzing data related to the disease and condition. Further, the method steps include running an alteration string to determine the ingredients for the disease and condition. Further, the method steps include preparing a final composition of ingredient for the disease and condition.
[010] In some embodiment, the method further comprises identifying the disease or the condition that needs to be targeted and map the ingredients. Further, the method steps include analyzing risk factors contributing to the disease. Further, the method steps include identify related nutritional and hormonal deficiencies related to the disease. Further, the method steps include determining initial biological changes occurring due to the disease. Further, the method steps include assessing changes in biomarkers associated with the disease. Further, the method steps include map an activation or inhibition of relevant biological pathways. Further, the method steps include evaluating symptoms related to disease via an evaluation criteria. Further, the method steps include a document a clinical symptoms and diagnostic findings indicating disease onset. Further, the method steps include identifying and mapping the ingredients, active, bioactive or molecules. Further, the method steps include providing design mechanisms of action image.
[011] In some embodiment, the evaluation criteria include a synergistic potential, a receptor analysis, an ADME (absorption, distribution, metabolism, excretion) and toxicity. The ML model evaluating toxicity criteria comprises collecting ingredients data/information from a storage database. Further, the toxicity criteria may check existing evidence data of the ingredients related to the disease. Further, the toxicity criteria may populate the existing evidence data for recording toxicity in the ingredients. Further, the toxicity criteria may analyze toxic doses, contraindication, side effects and interactions for the condition or disease. Further, the toxicity criteria may generate a report for the condition or disease. Further, the toxicity criteria may send the report for review and approval.

BRIEF DESCRIPTION OF THE DRAWINGS
[012] The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles.
[013] FIG. 1 is a block diagram of an exemplary system for developing a new product using Machine Learning (ML) model, in accordance with some embodiments of the present disclosure.
[014] FIG. 2 is a block diagram of the system implementing the ML model, in accordance with some embodiments.
[015] FIG. 3 is an exemplary computing system that may be employed to implement processing functionality for various embodiments.
[016] FIG. 4 is a block diagram of an example architecture of the system, in accordance with some embodiments.
[017] FIG. 5, a sequence diagram illustrates a method to identify ingredients for disease inhibition via the product development device, in accordance with some embodiments.
[018] FIG. 6, a sequence diagram illustrates a method to map positive clinical research evidence, in accordance with some embodiments.
[019] FIG. 7, a sequence diagram illustrates that a method to evaluate toxicity criteria via the product development device is illustrated, in accordance with some embodiments.
[020] FIG. 8, a block diagram illustrates an exemplary ingredient formulation for developing a new product, in accordance with some embodiments.

DETAILED DESCRIPTION
[021] Exemplary embodiments are described with reference to the accompanying drawings. Wherever convenient, the same reference numbers are used throughout the drawings to refer to the same or like parts. While examples and features of disclosed principles are described herein, modifications, adaptations, and other implementations are possible without departing from the spirit and scope of the disclosed embodiments. It is intended that the following detailed description be considered as exemplary only, with the true scope and spirit being indicated by the following claims. Additional illustrative embodiments are listed below.
[022] Referring now to FIG. 1, a block diagram of an exemplary system 100 for developing a new product using Machine Learning (ML) model is illustrated, in accordance with some embodiments of the present disclosure. The system 100 may implement a product development device 102. Further, the system 100 may include a data storage 104. In some embodiments, the data storage 104 may store at least a mapping of a plurality of ingredients, user requirements or physical conditions, and knowledge database, regulatory compliance of a plurality of geographical regions, etc. The product development device 102 may be a computing device having data processing capability. In particular, the product development device 102 may have the capability for developing a new product. Examples of the product development device 102 may include, but are not limited to a desktop, a laptop, a notebook, a netbook, a tablet, a smartphone, a mobile phone, an application server, a web server, or the like.
[023] Additionally, the product development device 102 may be communicatively coupled to an external device 108 for sending and receiving various data. Examples of the external device 108 may include, but are not limited to, a remote server, digital devices, and a computer system. The product development device 102 may connect to the external device 108 over a communication network 106. The product development device 102 may connect to external device 108 via a wired connection, for example via Universal Serial Bus (USB). A computing device, a smartphone, a mobile device, a laptop, a smartwatch, a personal digital assistant (PDA), an e-reader, and a tablet are all examples of external devices 108. For example, the communication network 120 may be a wireless network, a wired network, a cellular network, a Code Division Multiple Access (CDMA) network, a Global System for Mobile Communication (GSM) network, a Long-Term Evolution (LTE) network, a Universal Mobile Telecommunications System (UMTS) network, a Worldwide Interoperability for Microwave Access (WiMAX) network, a Dedicated Short-Range Communications (DSRC) network, a local area network, a wide area network, the Internet, satellite or any other appropriate network required for communication between the product development device 102 and the data storage 104 and the external device 108.
[024] The system 100 may further implement a machine learning (ML) model 118. As will be appreciated by those skilled in the art, the ML model 118 may be capable of learning patterns and relationships from data to make predictions or decisions without being explicitly programmed. The ML model 118 may be selected from various available ML models based on their learning approach and the nature of the task they are designed for. For example, the ML model 118 may be a supervised learning models that can learn from labeled data, where the input data is paired with corresponding output labels. As such, the supervised learning model may be a classification model (i.e. sed for predicting categorical labels or classes; for example, logistic regression, decision trees, random forests, support vector machines (SVM), and neural networks). Or, the supervised learning models may be a regression mode, that can be used for predicting continuous numerical values. Other examples of the ML model 118 may include unsupervised learning models, semi-supervised learning models, clustering models, reinforcement learning models, Deep Learning Models, etc.
[025] The product development device 102 may be configured to perform one or more functionalities that may include receiving a user requirement associated with a composition of the product, or a diagnosed physical condition of a user. The one or more functionalities that may further include receiving a geographical region associated with a user of the product. The one or more functionalities that may further include inputting to the trained ML model 118 the user requirement, the diagnosed physical condition, and the geographical region associated with a user of the product. The one or more functionalities may further include receiving from the ML model 118 a composition of the product. The composition of the product meets the user requirement and complies with regulatory data associated with the geographical region. The composition of the product may include a plurality of ingredients for the product, a proportion of each of the ingredients in the product, and at least one recommended volume of packaging for the product. For example, for an immunity-boosting nutraceutical product, the plurality of ingredients may include Vitamin C (Ascorbic Acid), Vitamin D3 (Cholecalciferol), Zinc (Zinc Gluconate), Echinacea Extract, and Probiotic Blend (Lactobacillus acidophilus, Bifidobacterium lactis, Lactobacillus plantarum). In the same example, the proportion of each of the above ingredients in the product may be as: Vitamin C - 1000 mg per serving, Vitamin D3 - 1000 IU (International Units) per serving, Zinc - 15 mg per serving, Echinacea Extract - 200 mg per serving, and Probiotic Blend - Total 10 billion CFU (Colony Forming Units) per serving. The recommended volume of the packaging (i.e. sizing) for the product may include 500 grams, 1 kilogram, etc. The one or more functionalities may further include outputting the composition of the product to the user, via a display. The above ingredients, their proportions, and sizing may be provided to the user by rendering the information on a display.
[026] To perform the above functionalities, the product development device 102 may include a processor 110 and a memory 112. The memory 112 may be communicatively coupled to the processor 110. The memory 112 stores a plurality of instructions, which upon execution by the processor 110, cause the processor 110 to perform the above functionalities. The system 100 may further include a user interface 114 which may further implement a display 116. Examples may include, but are not limited to a display, keypad, microphone, audio speakers, vibrating motor, LED lights, etc. The user interface 114 may receive input from a user and also display an output of the computation performed by the product development device 102.
[027] In particular, a user wanting to obtain a recommendation from the 100 as to the development of the new product may access the system, for example, by logging-in to the 100. The user may then input the user requirement associated with a composition of the product, or a diagnosed physical condition of a user. In other words, the user may input a functional requirement from the product. For example, the functional requirement may include a protein supplementing functional requirement, a Vitamin C supplementing functional requirement, immunity boosting functional requirement, etc. Alternatively, the user may input a diagnosed physical condition. For example, the diagnosed physical condition may include an arthritis condition, a diabetes condition, a liver weakness condition, an anxiety condition, an insomnia condition, etc. As such, the above inputs may refer to the type or category of the product to be developed, i.e. the therapeutic or nutritional value that the intended product is supposed to provide.
[028] The user may further input the geographical region associated with the product. In particular, the geographical region may refer to a country, or a state or a city within a country where the product is meant to be sold. As will be understood, each country (and even each state or city within the country) may have specific compliance and regulations that the product must comply with. Further, compliance and regulations regarding nutraceutical products may vary significantly from country to country due to differences in legislative frameworks, cultural norms, and consumer protection priorities. For example, in India, the regulation of nutraceuticals is overseen by the Food Safety and Standards Authority of India (FSSAI). Nutraceuticals are regulated under the Food Safety and Standards Act (FSSA) and the Food Safety and Standards (Health Supplements, Nutraceuticals, Food for Special Dietary Use, Food for Special Medical Purpose, Functional Food and Novel Food) Regulations, 2016. Further, nutraceuticals must comply with safety standards, labeling requirements, and permissible ingredients outlined by FSSAI. In the United States of America (USA), the regulation of nutraceuticals falls under the purview of the Food and Drug Administration (FDA). Nutraceuticals are typically regulated as dietary supplements under the Dietary Supplement Health and Education Act (DSHEA) of 1994. Further, under DSHEA, manufacturers are responsible for ensuring the safety and labeling compliance of their products, while the FDA monitors and regulates product safety post-market. Moreover, nutraceuticals must adhere to labeling requirements, including accurate ingredient listings and health claims supported by scientific evidence.
[029] Once the above inputs are received, the product development device 102 may feed the user requirement, the diagnosed physical condition, and the geographical region associated with the product to the ML model 118. The ML model 118 may be trained using training data. The training data, for example, may include a mapping of a plurality of ingredients, user requirements or physical conditions, and knowledge database. The training data may further include regulatory compliance with a plurality of geographical regions (i.e. a plurality of countries, states, cities, etc.). It should be noted that the knowledge database may include research papers, websites, and exhibitions.
[030] Train the ML model 118 for developing nutraceuticals products may include various steps. For example, in the first step, research papers may be gathered from academic journals, conferences, and repositories focusing on nutraceuticals, biochemistry, pharmacology, and related fields. These papers may contain valuable information about the bioactive compounds, health benefits, and mechanisms of action associated with different nutraceutical ingredients. Similarly, data may be collected from reputable websites, databases, and online resources specializing in nutraceuticals, dietary supplements, and natural health products. These sources may provide information on product formulations, ingredient profiles, consumer preferences, and market trends. Further, in the same way, data may be collected from past exhibitions, trade shows, and conferences related to nutraceuticals and health supplements. For example, these events offer opportunities to gather data on emerging ingredients, innovative formulations, industry collaborations, and consumer preferences through presentations, exhibits, and networking.
[031] The second step may include performing data pre-processing. Relevant information may be extracted from research papers, websites, and exhibition materials using natural language processing (NLP) techniques. This may involve parsing text documents, identifying key terms, and categorizing information based on topics such as ingredient efficacy, health claims, safety concerns, and market trends. Further, the structured data from the websites and exhibitions (e.g., ingredient lists, product specifications, consumer surveys) may be converted into a format suitable for the training of the ML model 118. To this end, data cleaning, normalization, and feature extraction may be performed to prepare the dataset for analysis.
[032] As the third step, feature engineering may be performed. To this end, features representing nutraceutical ingredients, formulations, properties, and health effects may be defined. The features may include chemical composition, bioavailability, physiological effects, dosage forms, and target health conditions. Further, textual features may be extracted from research papers, websites, and exhibition materials to capture information relevant to nutraceutical development, such as ingredient names, health claims, usage instructions, and consumer reviews.
[033] Thereafter, an appropriate ML model may be selected from classification models (e.g. for predicting the efficacy, safety, and market potential of nutraceutical products), regression models (e.g. for estimating dosage-response relationships, bioavailability, and formulation optimization), Natural Language Processing (NLP) models (e.g. for analyzing textual data, extracting insights from research papers, websites, and consumer feedback), etc. The selected ML model may then be trained. Further, the trained ML model 118 may be deployed for use in nutraceutical research, product development, marketing, and regulatory compliance. The ML model 118 may be integrated into decision support systems, product formulation tools, consumer-facing applications, and quality control processes to enhance efficiency, innovation, and competitiveness in the nutraceutical industry.
[034] Once the ML model 118 has been fed with the above inputs, the ML model 118 may generate predictions (i.e. outputs). For example, the output may include a composition of the product. It should be noted that the composition outputted by the ML model 118 meets the user requirement and complies with regulatory data associated with the geographical region. The composition of the product may include a plurality of ingredients for the product, a proportion of each of the ingredients in the product, and at least one recommended volume of packaging for the product. As such, the composition outputted by the ML model 118 may reflect a data-driven approach to formulation optimization, ingredient selection, and dosage determination based on relevant factors such as efficacy, safety, bioavailability, and consumer preferences.
[035] The ML model 118 may identify optimal combinations of ingredients, dosage levels, and formulation strategies tailored to specific health goals, target populations, and regulatory requirements. As such, the composition of a nutraceutical product obtained from the ML model 118 may be based on ingredient selection, dosage optimization, synergistic combination, personalization, regulatory compliance, etc.
[036] In particular, the ingredient selection may include identifying bioactive compounds, vitamins, minerals, botanical extracts, probiotics, and other functional ingredients with documented health benefits relevant to the target indication or health condition. The dosage optimization may include estimating optimal dosage levels and delivery formats (e.g., capsules, tablets, powders, beverages) to maximize efficacy while ensuring safety, bioavailability, and consumer compliance. The synergistic combinations may include identifying synergies and interactions among ingredients to enhance therapeutic effects, promote absorption, mitigate side effects, and optimize overall product performance. Further, personalization may refer to tailoring product compositions to individual needs, preferences, and genetic profiles through personalized nutrition recommendations. The regulatory compliance may include ensuring compliance with regulatory standards and quality control guidelines governing nutraceutical product formulations, labeling, and health claims, supported by evidence-based data and documentation.
[037] Additionally, in some embodiments, the output received from the ML model 118 may include a regulatory compliance report for the geographical region. The regulatory compliance report may serve as a comprehensive assessment of adherence to legal requirements, quality standards, and safety regulations governing the manufacturing, labeling, marketing, and distribution of such products within a specific country. For example, the regulatory compliance report may include a regulatory landscape analysis that may identify relevant laws, regulations, and regulatory bodies responsible for oversight and enforcement. The regulatory compliance report may further include product classification and categorization of the nutraceutical products as defined by the geographical region’s (i.e. country's) regulatory framework. The regulatory compliance report may further include an assessment of labeling requirements specified by regulatory authorities, including mandatory labeling elements (e.g., product name, ingredients, nutrition facts, health claims), permissible language, font size, and placement on packaging. Further, the regulatory compliance report may include health claims evaluation that verifies the scientific substantiation, permissible wording, and permitted claims as per regulatory guidelines. Furthermore, the regulatory compliance report may include quality and safety standards compliance that identifies any deviations from Good Manufacturing Practices (GMP), contamination risks, or non-compliance with quality control standards. As such, the regulatory compliance report may provide actionable insights, risk assessments, and recommendations to ensure nutraceutical products comply with applicable regulations, meet quality standards, and mitigate regulatory risks within a specific country's regulatory environment.
[038] In some embodiments, the output from the ML model 118 may further include one or more formulation recommendations, such that the one or more formulation recommendations includes: a process of mixing and preparing the product based on the plurality of ingredients. The formulation recommendations may include ingredient compatibility analysis that identifies synergistic combinations and potential incompatibilities that may affect product stability or bioavailability. The formulation recommendations may further include mixing process design based on mixing parameters such as mixing speed, duration, temperature, and shear forces. These parameters may be optimized to minimize ingredient segregation, optimize particle size distribution, and maximize dissolution rates. Further, the formulation recommendations may include quality assurance and compliance.
[039] Further, in some embodiments, the output from the ML model may include one or more manufacturers, suppliers, retailers, and traders in the geographical jurisdiction. To this end, the ML model 118 may be additionally trained using training data that includes data associated with manufacturers, suppliers, retailers, and traders in each of the plurality of geographical jurisdictions.
[040] The ML model 118 may provide recommendations for manufacturers, suppliers, retailers, and traders in the geographical jurisdictions (i.e. country, state, city) based on diverse datasets encompassing market dynamics, supply chain networks, business relationships, and consumer preferences. The manufacturer recommendations may include reputable manufacturers based on factors such as production capacity, quality standards, regulatory compliance, and industry reputation. The manufacturer recommendations may be generated by the ML model 118 based on analysis of manufacturing databases, industry reports, and supplier directories, etc. further, the supplier selection recommendations may be generated by the ML model 118 based on supplier databases, trade directories, and transactional data, and factors such as product quality, pricing, delivery times, and supply chain resilience. Furthermore, retailer recommendations may be generated based on retail sales data, consumer surveys, and market segmentation analyses. The retailer recommendations may include online retailers, specialty health stores, pharmacies, supermarkets, and direct-to-consumer channels known for their product assortment, brand visibility, and customer service excellence. Further, the ML model 118 may identify trading companies, distributors, and wholesalers specializing in nutraceutical products through trade databases, industry associations, and business directories. These recommendations may prioritize traders with extensive distribution networks, logistical capabilities, and market insights to facilitate product distribution and market penetration. As such, the above recommendations generated by the ML model 118 may empower businesses to make informed decisions, optimize their operations, and capitalize on opportunities in the nutraceutical market.
[041] The various outputs, as above, generated by the ML model 118 may be outputted by the system 100, via a display 116 of the UI 114.
[042] Referring now to FIG. 2, a block diagram of the system 100 implementing the ML model 118 is illustrated, in accordance with some embodiments. As mentioned above, the ML model 118 may be fed with certain inputs for obtaining outputs for the development of a product, for example, a nutraceutical product.
[043] As further mentioned above, the inputs may include a user requirement 202, a diagnosed physical condition 204, and a geographical region associated with the product 206. Each of the above inputs is explained above in conjunction with FIG. 1. The ML model 118 may generate certain outputs based on the above inputs and as required. For example, the outputs may include a composition of the product 208. The composition of the product 208 may meet the user requirement and complies with regulatory data associated with the geographical region. In particular, the composition of the product may include a plurality of ingredients for the product, a proportion of each of the ingredients in the product, and at least one recommended volume of packaging for the product. The outputs may further include a regulatory compliance report of 210 for the geographical region. The outputs may further include one or more formulation recommendations 212. The one or more formulation recommendations may include a process of mixing and preparing the product based on the plurality of ingredients. The outputs may further include recommendations for a label for the packaging for the product 214. The outputs may further include recommendations of one or more manufacturers, suppliers, retailers, and traders 216 in the plurality of geographical jurisdiction. To this end, the training data may further include data associated with manufacturers, suppliers, retailers, and traders in each of the plurality of geographical jurisdictions. Each of these outputs is already explained above in conjunction with FIG. 1.
[044] In some embodiments, the system 100 may ensure security and confidentiality of data, such that one user's data inputs are not visible or accessible to another user. Further, the system 100 may provide a capability of locking unique combinations of a 'composition of a product’, a ‘diagnosed physical condition’, and a ‘geographical region' that are already created by one user, so that users are not able to use the creations belonging to others. To this end, the system 100 may encrypt the data using strong encryption algorithms before storing it on the database, for example, a cloud-based database. The encryption ensures that even if someone gains unauthorized access to the data, they cannot read it without the encryption key. Alternatively, the system 100 may implement an authentication mechanism, for example, a multi-factor authentication (MFA) to ensure that only authorized users can access the data. Furthermore, network security mechanisms such as virtual private networks (VPNs) or secure sockets layer (SSL)/Transport Layer Security (TLS) protocols may be implemented to prevent eavesdropping and Man-in-the-Middle (MitM) attacks. Other techniques that are implemented to this end may include data masking and anonymization, data loss prevention (DLP), etc.
[045] Referring now to FIG. 3, an exemplary computing system 300 that may be employed to implement processing functionality for various embodiments (e.g., as a SIMD device, client device, server device, one or more processors, or the like) is illustrated. Those skilled in the relevant art will also recognize how to implement the invention using other computer systems or architectures. The computing system 300 may represent, for example, a user device such as a desktop, a laptop, a mobile phone, personal entertainment device, DVR, and so on, or any other type of special or general-purpose computing device as may be desirable or appropriate for a given application or environment. The computing system 300 may include one or more processors, such as a processor 302 that may be implemented using a general or special purpose processing engine such as, for example, a microprocessor, microcontroller or other control logic. In this example, the processor 302 is connected to a bus 304 or other communication media. In some embodiments, the processor 302 may be an Artificial Intelligence (AI) processor, which may be implemented as a Tensor Processing Unit (TPU), or a graphical processor unit, or a custom programmable solution Field-Programmable Gate Array (FPGA).
[046] The computing system 300 may also include a memory 306 (main memory), for example, Random Access Memory (RAM) or other dynamic memory, for storing information and instructions to be executed by the processor 302. The memory 306 also may be used for storing temporary variables or other intermediate information during the execution of instructions to be executed by processor 302. The computing system 300 may likewise include a read-only memory (“ROM”) or other static storage device coupled to bus 304 for storing static information and instructions for the processor 302.
[047] The computing system 300 may also include storage devices 308, which may include, for example, a media drive 310 and a removable storage interface. The media drive 310 may include a drive or other mechanism to support fixed or removable storage media, such as a hard disk drive, a floppy disk drive, a magnetic tape drive, an SD card port, a USB port, a micro-USB, an optical disk drive, a CD or DVD drive (R or RW), or other removable or fixed media drive. A storage media 312 may include, for example, a hard disk, magnetic tape, flash drive, or other fixed or removable media that is read by and written to by the media drive 310. As these examples illustrate, the storage media 312 may include a computer-readable storage medium having stored therein particular computer software or data.
[048] In alternative embodiments, the storage devices 308 may include other similar instrumentalities for allowing computer programs or other instructions or data to be loaded into the computing system 300. Such instrumentalities may include, for example, a removable storage unit 314 and a storage unit interface 316, such as a program cartridge and cartridge interface, a removable memory (for example, a flash memory or other removable memory module) and memory slot, and other removable storage units and interfaces that allow software and data to be transferred from the removable storage unit 314 to the computing system 300.
[049] The computing system 300 may also include a communications interface 318. The communications interface 318 may be used to allow software and data to be transferred between the computing system 300 and external devices. Examples of the communications interface 318 may include a network interface (such as an Ethernet or other NIC card), a communications port (such as for example, a USB port, a micro-USB port), Near field Communication (NFC), etc. Software and data transferred via the communications interface 318 are in the form of signals which may be electronic, electromagnetic, optical, or other signals capable of being received by the communications interface 318. These signals are provided to the communications interface 318 via a channel 320. The channel 320 may carry signals and may be implemented using a wireless medium, wire or cable, fiber optics, or another communications medium. Some examples of the channel 320 may include a phone line, a cellular phone link, an RF link, a Bluetooth link, a network interface, a local or wide area network, and other communications channels.
[050] The computing system 300 may further include Input/Output (I/O) devices 322. Examples may include, but are not limited to a display, keypad, microphone, audio speakers, vibrating motor, LED lights, etc. The I/O devices 322 may receive input from a user and also display an output of the computation performed by the processor 302. In this document, the terms “computer program product” and “computer-readable medium” may be used generally to refer to media such as, for example, the memory 306, the storage devices 308, the removable storage unit 314, or signal(s) on the channel 320. These and other forms of computer-readable media may be involved in providing one or more sequences of one or more instructions to the processor 302 for execution. Such instructions, generally referred to as “computer program code” (which may be grouped in the form of computer programs or other groupings), when executed, enable the computing system 300 to perform features or functions of embodiments of the present invention.
[051] In an embodiment where the elements are implemented using software, the software may be stored in a computer-readable medium and loaded into the computing system 300 using, for example, the removable storage unit 314, the media drive 310 or the communications interface 318. The control logic (in this example, software instructions or computer program code), when executed by the processor 302, causes the processor 302 to perform the functions of the invention as described herein.
[052] One or more techniques for development of nutraceutical products are disclosed above. The techniques address the inefficiencies of traditional methods, which often relied on manual processes for idea generation, regulatory compliance, and supply chain management, and were not only time-consuming but also prone to errors. The techniques leverage artificial intelligence (AI) to streamline various processes involved in product development. AI is used to collect data from sources, including research papers, websites, and exhibitions. The techniques provide customized outputs based on the specific needs of each client. For instance, the system can suggest potential ingredient combinations for new products, generate regulatory compliance reports, and offer formulation recommendations. Therefore, the above techniques offer efficient and accurate solutions, empowering companies to navigate the complex landscape of product development with confidence. The above techniques can be implemented as a Software as a Service (SaaS), to further add to the efficiency and accuracy, thereby aiding enhanced productivity and better outcomes for businesses in the nutrition industry.
[053] Referring now to FIG. 4, a block diagram of an example architecture 400 of the system 100 is illustrated, in accordance with some embodiments. As illustrated, in some embodiments, the front-end and back-end of the system 100 may be implemented using Django or React Native frameworks. As will be appreciated, Django is a high-level Python web framework that encourages rapid development and clean, pragmatic design. Django follows a Model-View-Template (MVT) architectural pattern, which emphasizes separation of concerns and reusability of components. Further, using Django, developers can create back-end APIs (Application Programming Interfaces) to serve data and logic to front-end applications, ensuring efficient communication between the server and client. Further, React Native allows developers to write code once and deploy it across multiple systems, including iOS, Android, and web, using a single codebase. In some embodiments, Django and React Native may be combined for the front-end application development, to thereby create seamless integration between the server-side logic and the client-side interface, enabling efficient data exchange and synchronization.
[054] Further, static resources may be implemented on cloud networks such as Amazon Web Services (AWS). AWS may offer several services for hosting static resources, including Amazon S3 (Simple Storage Service), Amazon CloudFront, and AWS Amplify.
[055] In some embodiments, a PostgreSQL database may be used as will be appreciated, PostgreSQL is an open-source relational database management system (RDBMS) known for its robustness, reliability, and advanced features. It supports the SQL (Structured Query Language) standard, allowing users to interact with the database through queries, transactions, and data definition commands. PostgreSQL may also offer advanced features, including support for complex data types such as JSON, XML, arrays, and custom types.
[056] Referring now to FIG. 5, a sequence diagram is illustrated that depicts a method 500 to identify ingredients for disease inhibition via the product development device 102 is illustrated, in accordance with some embodiments. FIG. 2 is explained in conjunction with elements of FIG. 2. The product development device 102, as depicted in FIG. 2, may be configured to identify ingredients for disease inhibition via the flow chart depicted in FIG. 5. The sequence diagram of FIG. 5 depicts one or more operations performed via the product development device 102, as elaborated below.
[057] At step S502, the disease may be defined via tagging at least based on a board category and a department. Further, the board category may include a list of the disease classified into several categories including infectious, chronic, autoimmune, genetic, nutritional deficiencies, and mental health disorders. Further, the disease may be tagged based on the department such as the Anesthesiology department, Cardiology department, ENT department, Geriatric department, Gastroenterology department, General surgery, Gynaecology department, Haematology department, Pediatrics department, Neurology department, Oncology department, Opthalmology department, Orthopaedic department, Urology department, Psychiatry department, Inpatient Department (IPD), Outpatient Department (OPD). Furthermore, the broad category and department data may be stored in the data storage 104. For example, the urinal disease may be defined as infection under broad category and urology under the department.
[058] At step S504, analyzing the data related to the disease and condition. The disease data may be collected from public domains. The disease data may be characterized at least based on predetermined parameters. In an exemplary embodiment, the parameters may be list of alternate names, an analyze relevant pathway, a define metabolic pathway, biomarkers for identification and a disease mechanism of action with image. Thus, the relevant information may be gathered for the disease.
[059] At step S506, studying and classifying clinical trial data of the disease and condition. For example, the disease data may include relevant pathways for the identified disease, the biomarker and disease mechanism of action. In an embodiment, the clinical trial data may show a positive result or negative /inconclusive result. If the clinical trial data reveal negative /inconclusive results for the disease, further analysis may be terminated. When clinical trial data reveal positive results for the disease, further selection and analyzing for novel ingredients inhibition for disease may be done via the product development device 102.
[060] At step S508, running an alteration string to determine the novel ingredients for the disease and condition. For example, the product development device 102may select a plurality of novel ingredients to determine the synergy. In an exemplary embodiment, the document ingredient one details may be fetched from the data storage 104. The product development device 102 may access ingredient one characteristics and regulatory approval details. The ingredient one characteristics may be utilized to determine biomarker of ingredient one. Further, the ingredient one may be linked to a predetermined cell, organ or tissue. Further, the product development device 102 is configured to via the method 500, outlines detailed mechanism of action associate to ingredient one. Similarly, the document ingredient second details may be fetched from the data storage 104. The product development device 102 may access ingredient second characteristics and regulatory approval details. The ingredient second characteristics may be utilized to determine biomarker of ingredient second. Further, the ingredient one may be linked to a predetermined cell, organ or tissue. Further, the product development device 102 is configured to via the method 500, outline detailed mechanism of action associate to ingredient second. Similarly, the document ingredient third details may be fetched from the data storage 104. The product development device 102 may access ingredient second characteristics and regulatory approval details. The ingredient third characteristics may be utilized to determine biomarker of ingredient third. Further, the ingredient one may be linked to a predetermined cell, organ or tissue. Further, the product development device 102 is configured to via the method 500, outline detailed mechanism of action associate to ingredient third.
[061] At step S510, prepare the final composition of ingredient for the disease and condition. The product development device 102 is configured to search for the data related to synergy of the disease ingredient. In an embodiment, the synergy data available for the ingredient then retrieve data from scientific paper with reference. In an embodiment, the synergy data is not available than design synergy linking biomarkers from available scientific evidence.
[062] Referring now to FIG. 6, a sequence diagram is illustrated that depicts a method 600 to map positive clinical research evidence, in accordance with some embodiments. FIG. 6 is explained in conjunction with elements of FIG. 5. The sequence diagram of FIG. 6 depicts one or more operations performed via the product development device 102, as elaborated below. Further, the method steps S506-S508 may be further explained with an example.
[063] The product development device 102 is configured to identify disease or condition need to be targeted and map with novel ingredients. For example, the type two diabetes is a metabolic disorder. The results of metabolic disorder may be characterized by high glucose levels due to insulin resistance and beta-cell dysfunction. Further, the identification of the disease or condition allows us to generate the information for disease pathology for the subsequent steps.
[064] Similarly, the product development device 102 is configured to analyze risk factors contributing to the disease. For example, the risk factors may be genetic such as family history of diabetes. The risk factors may be environment such as exposure to a high-fat diet. The risk factors may be lifestyle such as lack of physical activity. Further, the product development device 102 may identify risk factors that may increase the likelihood of disease onset to target interventions effectively.
[065] Similarly, the product development device 102 may identify related nutritional and hormonal deficiencies related to the disease. For example, the deficiencies related to nutritional deficiencies such as Vitamin D deficiency. The nutritional deficiencies may be hormonal such as decreased insulin secretion. Further, the product development device 102 is configured to determine that the selected ingredient is configured to address the determined deficiencies.
[066] Similarly, the product development device 102 may determine initial biological changes occurring due to the disease. For example, the biological changes may be oxidative stress such as elevated levels of reactive oxygen species (ROS). The biological changes may be cellular damage such as damage to pancreatic beta-cells. The biological changes may be immune response such as activation of macrophages. Further, the product development device 102 may determine early biological changes to target disease with ingredients.
[067] Similarly, the product development device 102 may assess changes in biomarkers associated with the disease. For example, the biomarker may be proteins such as CRP (C- reactive protein) or TNF-a (tumor necrosis factor-alpha). The biomarker may be genes such as IL-6 (interleukin-6) or NF-kB (nuclear factor kappa-light-chain-enhancer of activated B cells). The biomarkers may be metabolites such as elevated glucose or increased lactate. However, the biomarker must reduce, stabilize or lower level of biomarkers. Further, the product development device 102 is configured to identify specific biomarkers that may be modulated via the ingredients.
[068] Similarly, the product development device 102 may be configured to map an activation or inhibition of relevant biological pathways. For example, the activating pathways of NF-kB signaling and inhibition of insulin signaling pathway. The insulin signaling pathway may be Pl3K/Akt pathway. The pathway may be defined for inhibition, elevation/enhance pathways and targets. The product development device 102 is configured to understand how the ingredients may affect the key pathways involved in disease progression.
[069] Similarly, the product development device 102 may be configured to evaluate all major response systems and symptoms related to disease via an evaluation criteria. The evaluation may include inflammatory response such as chronic activation of immune cells. The evaluation may include tissue damage such as progressive damage to pancreatic tissue. The evaluation may attenuate and prevent by evaluating all the major response systems and symptoms. The product development device 102 is configured to access the ingredients characteristics to mitigate symptoms and systemic responses.
[070] Similarly, the product development device 102 may be configured to document the clinical symptoms and diagnostic findings indicating disease onset. For example, the symptoms may be Polyuria (frequent urination), Polydipsia (increased thirst), or Fatigue. The diagnostic findings may be Hyperglycemia (elevated blood glucose levels), or Increased HbA1c (glycated hemoglobin). The disease and combine the ingredient mapping information with document disease. Further, the product development device 102 is configured to provide a comprehensive overview of how the disease presents clinically.
[071] Similarly, the product development device 102 may be configured to identify and map the ingredients, active, bioactive or molecules. For example, the ingredients, active, bioactive or molecules may be chemical compound/actives/molecules, vitamins and minerals or botanicals. The product development device 102 is configured to integrate the mapped information of the ingredient with the disease characteristics to understand its potential therapeutic effects.
[072] Thus, the product development device 102 may be configured to provide design mechanisms of action image. The combined information may be used to design an image illustrating the mechanism of action of the ingredient in relation to the disease. Further, the design mechanism is backed by positive clinical and research evidence, providing a clear and scientifically grounded mechanism of action image.
[073] Referring now to FIG. 7, a sequence diagram is illustrated that depicts a method 500 to evaluate toxicity criteria via the product development device 102 is illustrated, in accordance with some embodiments. FIG. 7 is explained in conjunction with elements of FIG. 2, FIG. 5 and FIG. 6. The product development device 102, as depicted in FIG. 2, may be configured to evaluate toxicity criteria via the flow chart depicted in FIG. 7. The sequence diagram of FIG. 7 depicts one or more operations performed via the product development device 102, as elaborated below.
[074] At step S702, the ingredients data/information is collected from the storage database 104. Further, the ingredients information’s mapped in relation to the disease. The ingredients may be evaluated at least based on toxic doses, contraindication, side effects and interactions. The ingredients selected may alter at least based on the diseases and condition.
[075] At step S704, the existing evidence data of the ingredients may be checked related to the disease. The existing evidence data may be collected from the public database or data storage 104. The existing evidence data may be updated in real-time.
[076] At step S706, the existing evidence data may be populated for recording toxicity in the ingredients. The clinical trial data reveals the toxicity nature in certain conditions or diseases. The clinical trial data for other conditions is also collected. For example, the creatine ingredient may be selected for muscle strength. The clinical trials demonstrate that creatine is effective in improving muscle strength and performance. There is no cautionary evidence that is reported concerning adverse effects or safety issues in this context. The clinical trials data supports creatine’s beneficial role in enhancing muscle function and endurance, making it a well-supported choice for strength-related conditions. At step S708, collect the document insights from the clinical trial data. For example, the product development device 102 may compile the gathered information related to the ingredients.
[077] At step S710, analyzing toxic doses, contraindication, side effects and interactions for the condition or disease. For example, the creatine ingredient may be selected for bipolar disorder. The clinical trials demonstrate that creatine supplementation may exacerbate manic symptoms in individuals with bipolar disorder. The clinical studies highlighted potential risks, suggesting that creatine might worsen mania or lead to instability in mood disorders. Thus, the ingredient may pose a significant concern for the safety and well-being of individuals with bipolar disorder.
[078] At step S712, the report may be generated for the condition or disease. For example, the report may include the analysis of toxic doses, contraindication, side effects and interactions for the condition or disease.
[079] At step S714, the report may be sent to review and approval. The report may be approved or not approved/rejected. In an embodiment, the report is approved the ingredients may be stored and updated at storage database 104, at step S716. For example, the approved ingredients use enhance muscle strength. Its efficacy and safety profile make it a recommended ingredient for formulations targeting muscle performance. In another embodiment, the report is not approved/rejected then consider other ingredients for the condition or disease, at step S718. For example, the approved ingredients are not suggested for use in individuals with bipolar disorder. Due to the potential for adverse effects, it is advisable to explore alternative ingredients that do not carry similar risks and are better suited to supplement in managing bipolar disorder.
[080] Referring now to FIG. 8, a block diagram of an exemplary ingredient formulation 800 for developing a new product is illustrated, in accordance with some embodiments of the present disclosure.
[081] The disease or condition 802 may be identified by the product development device 102. Further, the data may be collected of the side effects of the disease or condition 802. For example, the side effects of GPL-1 therapies are nausea and muscle loss. Furthermore, the goal may be defined to choose the ingredients that may provide a safer muscle preserving alternative 804. The synergistic ingredients may be developed with natural weight management product 806. The compound 808 may be selected for the ingredients such as octacosanol/cyanidin-3-O-glucoside/cyanidin-3-rutinoside, green tea/L or plantarum 299 v/S. boulardii, glyinflanin/Oleoylethanolamide. Furthermore, the evaluation criteria 810 may be defined for the disease and condition. Further, the evaluation criteria 810 may include a synergistic potential 812, a receptor analysis 814, an ADME (absorption, distribution, metabolism, excretion) 816 and toxicity and safety 818.
[082] The synergistic potential 812 may include a pathway overlap and enhancement and a molecular interaction analysis. The receptor analysis 814 may include a receptor binding profiles and overlap or antagonistic interactions. The ADME 816 may include a bioavailability and metabolism of compounds and interaction effects on absorption and excretion. The toxicity and safety 818 may include a plurality of toxicity profiles. The toxicity profiles may include long-term safety data.
[083] Further, a formulation and dosage 820 may be defined by the product development device 102. In an embodiment, the formulation and dosage 820 may include an optimal dosing strategies. The optimal dosing strategies may further include delivery methods to enhance efficacy. In another embodiment, the formulation and dosage 820 may include a computational and clinical validation. The computational and clinical validation may further include a pilot study design. The pilot study design may further include in silico analysis. The silico analysis may be configured to molecular modeling. The molecular modeling may include receptor binding simulations. The silico analysis may be configured to assess the efficacy and safety of the formulation. The efficacy and safety may include ADME and toxicity assessment. Additionally, the silico analysis may include laboratory computational profiling.
[084] Furthermore, the formulation and dosage 820 may be altered for formulation refinement 822. The formulation refinement 822 may adjust ingredient ratios and adjust dosages based on validation results.
[085] Referring now to FIG. 9, a sequence diagram of an automated validation method 900 that leverages a Retrieval-Augmented Generation (RAG) and machine learning model 118 to assess and validate complex evaluation criteria across multiple domains is illustrated, in accordance with some embodiments. FIG. 9 is explained in conjunction with elements of FIG. 1 and FIG. 2. The automated validation method 900, as depicted in FIG. 9, may be configured to assess and validate complex evaluation criteria across multiple domains. The method 900 may be designed to streamline decision-making, enhance accuracy, and improve scalability in validation frameworks, particularly in regulatory, clinical, and research environments. The sequence diagram of FIG. 9 depicts one or more operations performed via the product development device 102, as elaborated below.
[086] At step 1, determining the evidence strength via the product development device 102. In first embodiment, the method 900 may utilize metadata and content analysis, which serves as the foundation for categorizing evidence into a hierarchy. For example, the method 900 may include studies such as Meta-analyses, Randomized Controlled Trials (RCTs), and Systematic Reviews. Thus, the method 900 allows researchers and clinicians to prioritize evidence based on its rigor and relevance. In an exemplary embodiment, the Meta-analyses, which synthesize results from multiple studies, typically hold a higher position in this hierarchy due to their comprehensive nature, while individual studies may be classified lower. In second embodiment, the method 900 may utilize evidence from observational studies other than specified in first embodiment. In third embodiment, the method 900 may determine if the evidence is a new concept with biochemistry flexibility.
[087] In an embodiment, the method 900 may utilize a RAG-based (Red, Amber, Green) retrieval system. The RAG approach allows for the quick visual identification of the quality and reliability of biochemical and clinical data. The RAG system assigns colors to indicate the status of the data, with 'Red' suggesting caution or inadequate evidence, 'Amber' indicating moderate confidence, and 'Green' representing high confidence and reliability. This visual tool aids researchers and clinicians in swiftly interpreting data quality and making informed decisions based on the available evidence.
[088] Furthermore, the product development device 102 generates domain quality ratings to summarize the overall strength of the evidence evaluated. The quality ratings are categorized as “Moderate,” “Possibly High,” or “High.” A “High” rating implies a strong level of confidence in the evidence, making it suitable for guiding clinical decisions and policy. A “Possibly High” rating suggests that while the evidence is generally reliable, there may be certain limitations that warrant further investigation or caution. A “Moderate” rating indicates that while the evidence is useful, it may be compromised by variability or methodological concerns.
[089] At step 2, analyze clarity of the clinical pathway for the ingredients. The product development device 102 using the machine learning 118 identifies gaps, redundancies, and opportunities for improvement within the proposed pathways. The method 900 identify if the clinical pathway is clear or it is a new concept. If it is new concept then determine whether clinical pathway takes different path to address the same issue. The method 900 may utilize predictive models to provide insights into likely patient outcomes, resource utilization, and overall pathway efficacy, enabling decision-makers to make data-driven choices about the adoption of new clinical strategies. Further, the method 900 identify biochemistry parameters. Further, the biochemistry parameters may have affected the outcome of the ingredients. Further, the clinical pathway is subjected to an evaluation that assigns clarity ratings, which are categorized as “Moderate,” “Possibly High,” or “High.” These ratings are determined based on two key criteria: the relevance of the pathway to current clinical needs and its level of innovation.
[090] At step 3, identify the synergy and claims of the ingredients. The method 900 explores the potential synergistic effects that may arise from interactions between different agents or treatments. In an embodiment, the method 900 identify if there is evidence for synergy. In another embodiment, the method 900 identify if synergy is anticipated. The method 900 detects evidence of synergy using the machine learning model 118. By modeling these interactions, analysts can identify situations where combining treatments enhances effectiveness, reduces side effects, or improves outcomes. For example, in pharmacotherapy, interaction modeling can reveal how two medications may work together to produce a synergistic effect, offering new avenues for treatment strategies that are more effective than monotherapy
[091] In another embodiment, the method 900 identify if claims are general. In another embodiment, the method 900 identify if claims are precise. The method 900 may evaluate by employing Natural Language Processing (NLP) algorithms implemented via the machine learning model 118. The algorithms are adept at analyzing textual data to differentiate between general claims, which may lack specificity and detailed evidence, and precise claims that are well-defined and supported by robust data. By systematically categorizing claims in this manner, the evaluation helps to clarify the level of confidence that can be placed in each assertion, allowing healthcare providers and researchers to focus on the most substantiated information when making clinical or strategic decisions.
[092] Further, each claim is assigned a quality rating of “High” or “Moderate.” A High rating indicates that the claim is substantiated by strong evidence, is specific, and shows clear indications of beneficial synergy, suggesting that it can be reliably used to inform clinical practice or further research. Conversely, a claim receiving a Moderate rating indicates that while there is reasonable support for the assertion, it may still require additional scrutiny or further evidence to fully validate the interactions or outcomes expected.
[093] At step 4, analyzing the toxicology and intellectual property assessment of the ingredients. The method 900 may utilize the machine learning model 118 to access databases, scientific literature, regulatory filings, and patent repositories systematically. The method 900 streamlines the data collection process, organizations can quickly gather comprehensive information about the safety profiles of chemical substances and relevant intellectual property rights. Thus, the method 900 saves significant time compared to manual searches but also ensures that the data retrieved is current and relevant, thereby supporting informed decision-making.
[094] Further, the method 900 may apply RAG (Red, Amber, Green) models for dynamic access to the toxicology database. The RAG categorizes data according to risk levels, where 'Red' indicates high risk, 'Amber' signals caution or moderate risk, and 'Green' represents low or acceptable risk. By employing these visual indicators, stakeholders can quickly grasp the status of various substances and make timely decisions regarding their safety and regulatory status. The dynamic nature of this approach allows for continuous updates and evaluations, ensuring that the assessment reflects the most current understanding of toxicological risks.
[095] Further, the toxicology and intellectual property assessment, each piece of information or report is assigned a quality rating of either “Low” or “High.” A High rating signifies that the toxicological or IP data is robust, consistent, and derived from credible sources, providing a solid foundation for risk assessment and decision-making. In contrast, a Low rating indicates that the information may be unreliable, inconsistent, or sourced from less reputable submissions, signaling the need for caution and further investigation before proceeding with any related initiatives.
[096] At step 5, validating the ingredients stability, supply chain mapping and regulatory challenges. The method 900 is configured to simulate the stability of products under varying chemical and physical conditions. For example, using advanced chemical and physical models, analysts can predict how products will behave when exposed to different environmental factors, such as temperature fluctuations, humidity, light exposure, and mechanical stress. These simulations leverage principles from thermodynamics, kinetics, and materials science to assess the potential degradation or change in efficacy of the product over time. By identifying stable formulations and conditions, companies can enhance product quality, extend shelf life, and ensure that products remain effective throughout their intended duration of use.
[097] In another embodiment, the method 900 map supply chain risks using data analytics. The analyzing data from various sources, including supplier performance, transportation logistics, and market dynamics, to identify potential vulnerabilities in the supply chain. Utilizing techniques such as predictive analytics and risk modeling, organizations can evaluate factors that may disrupt the supply chain, such as geopolitical instability, natural disasters, or supplier insolvency. By visualizing these risks, businesses can strategically plan for contingencies, optimize inventory management, and implement measures to mitigate disruptions, thereby ensuring a more resilient supply chain.
[098] In another embodiment, the method 900 ensures compliance validation, the assessment dynamically queries regulatory sources to stay abreast of applicable laws, guidelines, and standards. This real-time capability allows organizations to monitor changes in regulations that could impact product development and marketability. By integrating with regulatory databases and using automated systems to retrieve and analyze updated regulatory information, companies can ensure that their products meet all necessary requirements and avoid potential legal issues or market entry delays. This proactive approach allows businesses to adapt promptly to regulatory changes, thus reducing the risk of non-compliance.
[099] Further, evaluating stability, supply chain risks, and regulatory compliance, the final step involves categorizing the overall risk as either “Moderate” or “High.” A Moderate risk rating indicates that while there are some potential concerns that require attention, the overall product stability, supply chain integrity, and compliance status are deemed manageable with existing controls and strategies. Conversely, a High risk rating signals that significant vulnerabilities exist, whether in product formulation stability, supply chain disruptions, or regulatory compliance, necessitating immediate action to address these issues and safeguard product integrity and market readiness.
[0100] The overall judgement of the formulation of ingredients is provided by the product development device 102.
[0101] It is intended that the disclosure and examples be considered as exemplary only, with a true scope and spirit of disclosed embodiments being indicated by the following claims.
,CLAIMS:Claims
What is claimed is:

1. A system configured to develop a new product, wherein the system comprises:
a product development device via a machine learning (ML) model, configured to generate formulation for the new product, and
one or more processing units of product development device configured to:
defining the disease via tagging at least based on a board category and a department;
analyzing the data related to the disease and condition;
running an alteration string to determine the ingredients for the disease and condition;
preparing final composition of ingredient for the disease and condition.

2. The system according to claim 1, wherein the ML model further comprises:
identify the disease or the condition need to be targeted and map the ingredients,
analyzes the risk factors contributing to the disease,
identify related nutritional and hormonal deficiencies related to the disease,
determine initial biological changes occurring due to the disease,
assess changes in biomarkers associated with the disease,
map an activation or inhibition of relevant biological pathways,
evaluate all major response systems and symptoms related to disease via an evaluation criteria,
document the clinical symptoms and diagnostic findings indicating disease onset,
identify and map the ingredients, active, bioactive or molecules, and
provide design mechanisms of action image.

3. The system according to claim 2, wherein the product development device comprises
determining the evidence strength via the product development device;
analyze clarity of the clinical pathway for the ingredients;
identify the synergy and claims of the ingredients;
analyzing the toxicology and intellectual property assessment of the ingredients; and
validating the ingredients stability, supply chain mapping and regulatory challenges.
4. The system according to claim 2, wherein the ML model evaluation criteria include a synergistic potential, a receptor analysis, an ADME (absorption, distribution, metabolism, excretion) and toxicity.
5. The system according to claim 4, wherein the ML model evaluating toxicity criteria comprises:
collect ingredients data/information from a storage database,
checking existing evidence data of the ingredients related to the disease,
populating the existing evidence data for recording toxicity in the ingredients,
analyzing toxic doses, contraindication, side effects and interactions for the condition or disease,
generating a report for the condition or disease, and
sending the report for review and approval.

6. The system according to claim 1, wherein the ML model identifies optimal combinations of ingredients, dosage levels, and formulation strategies tailored to specific health goals, target populations, and regulatory requirements.

7. The system according to claim 1, wherein the ML model identifies bioactive compounds, vitamins, minerals, botanical extracts, probiotics, and other functional ingredients with documented health benefits relevant to the target indication or health condition.

8. A method configured to develop a new product, wherein the method comprises:
defining a disease and condition via tagging at least based on a board category and a department;
analyzing data related to the disease and condition;
running an alteration string to determine the ingredients for the disease and condition;
preparing a final composition of ingredient for the disease and condition.

9. The method according to claim 8, further comprises
identify the disease or the condition need to be targeted and map the ingredients,
analyzes risk factors contributing to the disease,
identify related nutritional and hormonal deficiencies related to the disease,
determine initial biological changes occurring due to the disease,
assess changes in biomarkers associated with the disease,
map an activation or inhibition of relevant biological pathways,
evaluate symptoms related to disease via an evaluation criteria,
document a clinical symptoms and diagnostic findings indicating disease onset,
identify and map the ingredients, active, bioactive or molecules, and
provide design mechanisms of action image.

10. The method according to claim 8, further comprises
determining the evidence strength via the product development device;
analyze clarity of the clinical pathway for the ingredients;
identify the synergy and claims of the ingredients;
analyzing the toxicology and intellectual property assessment of the ingredients; and
validating the ingredients stability, supply chain mapping and regulatory challenges.
11. The method according to claim 9, wherein the evaluation criteria include a synergistic potential, a receptor analysis, an ADME (absorption, distribution, metabolism, excretion) and toxicity.
12. The method according to claim 9, wherein the evaluating toxicity criteria comprises:
collect ingredients data/information from a storage database,
checking existing evidence data of the ingredients related to the disease,
populating the existing evidence data for recording toxicity in the ingredients,
analyzing toxic doses, contraindication, side effects and interactions for the condition or disease,
generating a report for the condition or disease, and
sending the report for review and approval.