DESC:
FORM 2
THE PATENTS ACT, 1970 (39 of 1970)
&
THE PATENTS RULES, 2003
COMPLETE SPECIFICATION
[See section 10, Rule 13]

1. TITLE OF THE INVENTION:
A SYSTEM AND METHOD FOR ANALYZING VARIANTS AND ADULTERANTS
IN MILK SAMPLES

2. APPLICANT
a) Name: Beamoptics Scientific Private Limited
b) Nationality: Indian
c) Address: PAP-J-188, 2nd floor, Near Quality Circle Forum, Telco road, Mide Bhosari,
Pune - 411026, Maharashtra, India

PREAMBLE TO THE DESCRIPTION
The following specification particularly describes the invention and the manner in which it is to be performed.

FIELD OF THE INVENTION
The present invention relates to a system and method for analyzing liquid samples, more particularly it relates to a system for analyzing variants and adulterants in milk samples and a method to do the same.
BACKGROUND OF THE INVENTION
India is one of the largest producers of milk, however exports from India of milk are relatively low, because quality is non-standard, primarily due to the disaggregate production of milk – the average dairy farmer in India, owns 2 livestock. The milk from different farmers is collected at the village level in a Bulk milk collection center (BMCCs) and the farmer is compensated on two variables – amount of milk given and amount of fat in the milk. Origin of milk, variants in milk and milk composition are not considered, this leads to a lot of adulteration at the farmer level as they only focus on the two parameters being tested, which at an aggregate level reduces exports due to non-standardized quality of milk.

Further, buffalo milk is unique to the Indian subcontinent and is generally characterized by higher fat and SNF percentages, making foreign testing machines difficult to adapt to Indian milk. Within India, there are regional differences in milk due to local environmental and livestock feeding differences, these differences are neither tested nor taken into consideration throughout the milk testing process. Currently, ultrasonic machines are mostly used in BMCCs to test for components in milk, the problem with ultrasonic milk analysers is that it cannot detect variants in milk, it can only measure Fat and SNF. For measuring adulterants, currently the technology of choice is FTIR spectrometry.

However, FTIR instruments are neither made to operate in the environment of a BMCC nor are they programmed to cater to the regional differences in milk as failed to be seen in Patent Application number WO2024175879A1. Regional differences play a major role in milk analysis due to this, variations in milk are often falsely detected as adulterants by the currently used devices and systems; and adulterants present are not adequately identified or detected. There is, therefore, a need for a system and method that can at least overcome the above mentioned problems including enabling milk testing machines to identify the variants and detect adulterants in milk and milk compositions while ensuring a centralized system capable of machine learning with the continuously increasing variants and adulterants from time to time.

SUMMARY OF THE INVENTION
An aspect of the present invention discloses a method and system for effective milk testing while maintaining an account for regional differences in milk production by employing an ML model.
Another aspect of the present invention discloses a system and method capable of learning about extended adulterant ranges which may change from time to time and differentiating adulterants from variants.
Yet another aspect of the present invention discloses a method for detecting variants and adulterants in a sample of milk, said method comprising:
(i) Receiving a request for analyzing the sample, wherein the request is configured to originate from a milk testing instrument;
(ii) Identifying, Capturing and recording the location parameters;
(iii) Selecting at least one testing model specific to the location parameters of the milk sample, milk testing instrument, or both to select the parameters to be optimized for testing the milk sample such as a limit of detection specific to said location parameters selected from the closest location, accordingly requesting the analysis;
(iv) Based on the selected testing model(s), testing the sample by employing at least one sensor and at least one model to identify the milk variety;
(v) Processing the test data to identify adulterant values exceeding the pre-defined Level of Detection after correlating between a specific variant and adulterant at the Processor;
(vi) Classifying the processed test data as a false positive, positive, false negative or negative result depending on the factors likely to impact the milk composition and communicating the test results to the server;
(vii) Recording and storing the test results in the instrument locally and at the server to record and store adulterant(s) values beyond pre-defined Level of Detection and any new variant(s) not previously recorded by the system; and
(viii) Updating all testing models including the limits of detections, in the server and accordingly updating milk testing instruments with the processed data for future testing and records.
Yet another aspect of the present invention discloses a system for detecting variants and adulterants in milk samples comprising a plurality of milk analysis instruments configured to collect samples, test milk components, and communicate with a server and with one or more other milk analysis instruments;
Wherein each instrument has at least a pipette, display screen, sensors located on said pipette and a processor connected to a server by a wireless connection, said processor located in a locally present milk analysis instrument is configured to communicate with said server and instruments located in various locations, process data and generate level of detection, and store the processed data in data storage unit located in said server;
A classifier module configured to sorting and organizing the analysis data and updating the milk analysis instruments for future analysis; and
A centralized control unit operably coupled to the instruments, user interface, processor, classifier module and data storage unit to coordinate the operation of multiple instruments, ensure synchronization, and enable communication, wherein the present system is capable of correlating between a specific variant and adulterant in selecting a relevant Level of Detection to be considered for adulterant detection, while ignoring false positives.
BRIEF DESCRIPTION OF THE DRAWINGS
Reference will be made to embodiments of the invention, examples of which may be illustrated in the accompanying figures. These figures are intended to be illustrative, not limiting. Although the invention is generally described in the context of these embodiments, it should be understood that it is not intended to limit the scope of the invention to these particular embodiments.

FIGURE 1 shows a system architecture 100 of the system in accordance with an embodiment of the present invention.
FIGURE 2 shows a classifier 200 in accordance with an embodiment of the present invention.
FIGURE 3 shows a flowchart 300 of the method in accordance with an embodiment of the present invention.
FIGURE 4 shows a flowchart 400 of the method in accordance with an embodiment of the present invention.
DETAILED DESCRIPTION OF THE INVENTION
Some embodiments of the present disclosure, illustrating all its features, will now be discussed in detail. It must also be noted that as used herein and in the appended claims, the singular forms "a", "an" and "the" include plural references unless the context clearly dictates otherwise. Although any system and method similar or equivalent to those described herein can be used to optimize the outcome of the present invention.
Glossary:
System (for example, computing system) may include one or more processors coupled with a memory, wherein the memory may store instructions which when executed by the one or more processors may cause the system to perform offloading/onloading functions or multicasting content in networks. An exemplary representation of the system for such purpose, in accordance with embodiments of the present disclosure the system may include one or more processor(s). The one or more processor(s) may be implemented as one or more microprocessors, microcomputers, microcontrollers, edge or fog microcontrollers, digital signal processors, central processing units, logic circuitries, and/or any devices that process data based on operational instructions. Among other capabilities, the one or more processor(s) may be configured to fetch and execute computer readable instructions stored in a memory of the system. The memory may be configured to store one or more computer-readable instructions or routines in a non-transitory computer readable storage medium, which may be fetched and executed to create or share data packets over a network service. The memory may comprise any non-transitory storage device including, for example, volatile memory such as Random-Access Memory (RAM), or non-volatile memory such as Electrically Erasable Programmable Read-only Memory (EPROM), flash memory, and the like. In an embodiment, the system may include an interface(s). The interface(s) may comprise a variety of interfaces, for example, interfaces for data input and output devices, referred to as input/output (I/O) devices, storage devices, and the like. The interface(s) may facilitate communication for the system. The interface(s) may also provide a communication pathway for one or more components of the system. Examples of such components include, but are not limited to, processing unit/engine(s) and a database. The processing unit/engine(s) may be implemented as a combination of hardware and programming (for example, programmable instructions) to implement one or more functionalities of the processing engine(s). In examples described herein, such combinations of hardware and programming may be implemented in several different ways. For example, the programming for the processing engine(s) may be processor executable instructions stored on a non-transitory machine-readable storage medium and the hardware for the processing engine(s) may comprise a processing resource (for example, one or more processors), to execute such instructions. In the present examples, the machine-readable storage medium may store instructions that, when executed by the processing resource, implement the processing engine(s).

In such examples, the system may include the machine-readable storage medium storing the instructions and the processing resource to execute the instructions, or the machine-readable storage medium may be separate but accessible to the system and the processing resource. In other examples, the processing engine(s) may be implemented by electronic circuitry. In an aspect, the database may comprise data that may be either stored or generated as a result of functionalities implemented by any of the components of the processor or the processing engines.

Network: may include, by way of example but not limitation, at least a portion of one or more networks having one or more nodes that transmit, receive, forward, generate, buffer, store, route, switch, process, or a combination thereof, etc. one or more messages, packets, signals, waves, voltage or current levels, some combination thereof, or so forth. The network may also include, by way of example but not limitation, one or more of a wireless network, a wired network, an internet, an intranet, a public network, a private network, a packet-switched network, a circuit-switched network, an ad hoc network, an infrastructure network, a Public Switched Telephone Network (PSTN), a cable network, a cellular network, a satellite network, a fibre optic network, or some combination thereof.
AI: shall mean “Artificial Intelligence” and may refer to a software / computing in which the simulation of human intelligence is processed by machines
ML: shall mean “Machine Learning” and may refer to a type of AI where the machine continually learns from data which is received, collected, processed, stored by the system.
Digital Twin: may refer to a virtual model designed to accurately reflect a physical object being studied in order to make predictive analysis.
Server: A server may include or comprise, by way of example but not limitation, one or more of a standalone server, a server blade, a server rack, a bank of servers, a server farm, hardware supporting a part of a cloud service or system, a home server, hardware running a virtualized server, one or more processors executing code to function as a server, one or more machines performing server-side functionality as described herein, at least a portion of any of the above, some combination thereof. In an embodiment, the entity may include, but is not limited to, a vendor, a network operator, a company, an organization, a university, a lab facility, a business enterprise, a defence facility, or any other facility that provides content.

Various embodiments of the invention provide a system and method for enabling instruments to analyze milk samples in order to identify variants and adulterants in milk and milk compositions. Further, the present invention discloses a system and method to enable milk analyzers for detecting and identifying variants and adulterants in milk samples. In an aspect, the present invention enables detecting common adulterants such as NaCl using conductive sensors to measure common adulterants in milk, as well as to provide a solute concentration in the sample from which FPD can be derived.
In another aspect, the present invention employs at least a classifier for various kinds of milk selected from Cow, Buffalo, Mixed milk, or other sources of milk. The present invention enables testing extended adulterant range including Veg Oil and NaCl (with FPD), other adulterants detected by the present invention include – Urea, Maltodextrin, Sucrose, Ammonia, Detergent, Veg oil, Starch, NaOH, Sodium Carbonate, Sodium Bicarbonate, Added water, Melamine, Formalin, Whey protein.
In another aspect, the present invention employs specific filter-based Fat and SNF chemometric models.
In an aspect, the present invention enables milk analyzers to learn and create LODs specific to a micro region such that with variations including but not limited to dietary, environmental, breed variations, etc., which result in higher/lower levels of certain milk components for example: regions where sugarcane production is high a lot of cattle feed consumes sugarcane produce, this leads to a high sucrose concentration in milk in this area. The present invention is capable of detecting the presence of a variant from the ordinary levels seen in majority of samples collected across other regions, identifying the variant (in this case high sucrose), informing the system of such variant so that it is not flagged as an adulterant, processing and storing information of such variant (creating LODs specific to micro region) so that the system is now informed of the “new normal” levels (LODs) which may be unique in a particular region.

In another aspect, the present invention is capable of learning local regional differences and tweaking LODs and algorithms effectively to prevent false-positives and false – negatives as more and more samples are tested and more information is collected from a growing list of regions.

Yet another embodiment of the present invention discloses enabling effective milk testing and adulteration testing at BMCC.

Yet another embodiment of the present invention discloses enabling effective milk testing while maintaining an account for regional differences in milk production by employing an ML model.

Yet another embodiment of the present invention discloses a system and method capable of learning about extended adulterant ranges which may change from time to time and differentiating adulterants from variants.

In yet another embodiment of the present invention and with reference to Figures 1, 3 & 4, a method for detecting variants and adulterants in a sample of milk, said method comprising:
(i) Receiving a request (110,410) for analyzing the sample, wherein the request is configured to originate from a milk testing instrument (101);
(ii) Capturing and recording the location parameters of the milk sample, milk testing instrument, or both (111, 411) manually or automatically using GPS coordinates;
(iii) Selecting at least one testing model (112,412) specific to the location parameters of the milk sample, milk testing instrument, or both (110) to select the parameters to be optimized for testing the milk sample such as a limit of detection specific to said location parameters selected from the closest location, accordingly requesting the analysis,
(iv) Based on the selected testing model(s), testing the sample by employing at least one sensor and at least one model to identify the milk variety and defined set of parameters including at least a limit of detection to identify any adulterants and variants in the sample above the limits of detection specific to said location parameters, if available (113,413);
(v) Processing the test data to identify adulterant values exceeding the pre-defined Level of Detection after correlating between a specific variant and adulterant at the Processor (114);
(vi) Classifying the processed test data as a false positive, positive, false negative or negative result, accuracy of the location, the general and unique environmental factors, variant of bovine specie, and any other such factors which are likely to impact the milk composition (114,414) and communicating the test results (115, 415) to the server (104) containing information on whether the results are identified as false positive, positive, false negative or negative;
(vii) Recording and storing (116, 416) the test results in the instrument (101) locally and at the server (104) to record and store adulterant(s) values beyond pre-defined Level of Detection and any new variant(s) not previously recorded by the system; and
(viii) Updating all testing models including the limits of detections, in the server and accordingly updating milk testing instruments (101,103) with the processed data for future testing and records (117,417).
Wherein communicating the test results to the server containing information on whether the results are identified as false positive, positive, false negative or negative, are optionally performed after the user has manually confirmed such results (415).
In an even further aspect, based on the location and/or GPS coordinates from where the milk sample is collected, the system selects testing models unique to the location and/or GPS coordinates and processes the results by mapping the test results locally obtained against the testing models unique to the location and/or GPS coordinates, and sending the mapped and processed results to the machine/user interface. In another aspect the unique testing models are selected by the system based on the location / GPS coordinated and sent to the machine performing the test to be mapped by the machine locally.

In an embodiment of the present invention and with reference to FIG. 1, 3 & 4, the testing model(s) are updated within the instruments (101,103) by communicating with the server (104) periodically or in real time, and wherein the step of Capturing & Recording the location parameters (411) involves first identifying location parameters of the milk sample, milk testing instrument, or both by an AI/ML model trained on a preset data (411a) testing the sample by employing at least one conductive sensor located on the pipette to identify common and extended milk adulterants and at least one model for adulterants to identify the milk variety.

A person of ordinary skill in the art will readily ascertain that the illustrated steps are set out to explain the exemplary embodiments shown, and it should be anticipated that ongoing technological development will change the manner in which particular functions are performed. These examples are presented herein for purposes of illustration, and not limitation. Further, the boundaries of the functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternative boundaries can be defined so long as the specified functions and relationships thereof are appropriately performed. Alternatives (including equivalents, extensions, variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope and spirit of the disclosed embodiments.

In yet another embodiment, a system comprising of a milk analysis instrument is disclosed, wherein said system employs a digital twin model capable of receiving data from each subsystem of each unit including subsystem level components, enabling predictive analysis of maintenance, operations, and to facilitate updates to various system models, units, subsystems, components, devices, applications inter alia.

In yet another embodiment, a system comprising comprising one or more milk analyzing instrument(s) (101,103), an algorithm, a controller, a processor, at least a display screen, a user application (102), a wireless connection (105) and ancillary parts, a server (104) (selected from physical, cloud based, etc.) and AI/ML block, is disclosed.

In yet another embodiment, a system for detecting variants and adulterants in milk samples is disclosed, said system comprising a plurality of milk analysis instruments (101,103) configured to collect samples, test milk components, and communicate with a server (104) and with one or more other milk analysis instruments (101,103);
Wherein each instrument has at least a pipette, display screen, sensors located on said pipette and a processor connected to a server (104) by a wireless connection (105), said processor located in a locally present milk analysis instrument (101) is configured to communicate with said server and instruments (104,103) located in various locations, process data and generate level of detection, and store the processed data in data storage unit located in said server (104);
a classifier module configured to sorting and organizing the analysis data and updating the milk analysis instruments for future analysis;
a centralized control unit operably coupled to the instruments, user interface, processor, classifier module and data storage unit to coordinate the operation of multiple instruments, ensure synchronization, and enable communication;
wherein the present system is capable of correlating between a specific variant and adulterant in selecting a relevant Level of Detection to be considered for adulterant detection, while ignoring false positives.
wherein the system employs a digital twin model capable of receiving data from each subsystem of each unit including subsystem level components, enabling predictive analysis of maintenance, operations, and to facilitate updates to various system models, units, subsystems, components, devices, applications inter alia.
In an embodiment, the system of the present invention employs least one classifier for various kinds of milk selected from Cow, Buffalo, Mixed milk, or other sources of milk and at least one sensor to detect common adulterants in the milk such as NaCl, preferably using conductive sensors to provide a solute concentration in the sample from which FPD can be derived.
In an embodiment, the system of the present invention employs the AI/ML block and the training model to learn and create levels of detection specific to a micro region, accounting for variations due to factors like diet, environment, breed, which influence the levels of certain milk components, wherein the system is capable of detecting the presence of a variant from the ordinary levels seen in majority of samples collected across other regions, identifying the variant distinctly from an adulterant, informing the system of such variant so that it is not flagged as an adulterant, processing and storing information of such variant as an updated level of detection so that the system is now informed of the new normal levels of detection unique to a particular region.
In an aspect of the present invention the AI/ML block includes a trained AI model loop which may be provided with training data set so to try various corrective algorithms based on the type of sample and infer if the data fits the trained AI model so as to improve accuracy of the testing method. The iterative feedback loop increases the accuracy as well as eliminates manual intervention and for any data set, the ratio is identified automatically by intelligently learning from the provided data for providing best accuracy.
In an aspect of the present invention the AI/ML block includes a task executor wherein an input dataset may be provided to or received by a task executor. The task executor, may be configured to forward the input dataset to the trained model. The trained model, may be configured to implement the AI model trained by model trainer.
In an aspect of the present invention the AI/ML block is configured to a training model which may be configured to train the AI model and the ML model. Further the training model, may be configured to generate results for the input data processed by the AI model. Said training model is capable train the AI/ML block to identify local regional differences in sample components including altered levels of detection, accordingly amending the level(s) of detection and algorithms to prevent false-tests as plurality of samples are tested, increasingly collecting data from plurality of locations, to improve accuracy and correlation of the sample components to regional differences based on the location parameters identified or received by the system. Further, a tuner may be configured to evaluate the results of the output. Further the tuner based on the feedback received on the results by evaluation is configured to optimize the training model.
In an embodiment, the system of the present invention, allows for effective milk testing while accounting for regional differences in milk production by employing an ML model capable of learning local regional differences over time and adjusting levels of detection and algorithms to minimize false-positives and false – negatives as more samples are tested and more information is collected from a growing list of regions.
In yet another aspect, the present invention employs a mechanism to add gold standard reference and adulterant measurement information in the same database via a web portal.
FIG. 1 shows a system architecture 100 in accordance with an embodiment of the present invention. The system architecture 100 discloses a communication between the various elements of the present system. Particularly disclosing the flow of analyzing the milk samples by the milk analysis instrument (101) and/or user interface (102), receiving the analysis data into the instrument (110), processing, creating LODs, sorting, updating the milk analysis (107,108, 117) instruments for future analysis after processing received data and storing of received data by the system, the system architecture also discloses a centralized set up for multiple milk analysis instruments (103).
FIG. 2 shows a classifier 200 used for testing milk samples (e.g. buffalo, cow milk) to detect the presence of various milk components such as sugar, fat etc., in accordance with an embodiment of the present invention.
A person of ordinary skill in the art will readily ascertain that the aforementioned embodiments are set out to explain the present invention, and it should be anticipated that ongoing technological development will change the manner in which particular functions are performed. The embodiments are presented herein for purposes of clarity and disclosure, and not limitation. Further, the boundaries of the functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternative boundaries can be defined so long as the specified functions and relationships thereof are appropriately performed. Alternatives (including equivalents, extensions, variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope and spirit of the disclosed embodiments.
,CLAIMS:CLAIMS

We Claim,
Claim 1. A method for detecting variants and adulterants in a sample of milk, said method comprising:
i. Receiving a request (110,410) for analyzing the sample, wherein the request is configured to originate from a milk testing instrument (101);
ii. Capturing and recording the location parameters of the milk sample, milk testing instrument, or both (111, 411) manually or automatically using GPS coordinates;
iii. Selecting at least one testing model (112) specific to the location parameters of the milk sample, milk testing instrument, or both (110) to select the parameters to be optimized for testing the milk sample such as a limit of detection specific to said location parameters, if available, accordingly requesting the analysis,
iv. Based on the selected testing model(s), testing the sample by employing at least one sensor and at least one model to identify the milk variety and defined set of parameters including at least a limit of detection to identify any adulterants and variants in the sample above the limits of detection specific to said location parameters, if available (413);
v. Processing the test data to identify adulterant values exceeding the pre-defined Level of Detection after correlating between a specific variant and adulterant at the Processor;
vi. Classifying the processed test data as a false positive, positive, false negative or negative result depending on the factors likely to impact the milk composition and communicating the test results (115, 415) to the server (104);
vii. Recording and storing (116, 416) the test results in the instrument (101) locally and at the server (104) to record and store adulterant(s) values beyond pre-defined Level of Detection and any new variant(s) not previously recorded by the system; and
viii. Updating all testing models including the limits of detections, in the server and accordingly updating milk testing instruments (101,103) with the processed data for future testing and records (117,417).

Claim 2. The method for detecting variants and adulterants in a sample of milk as claimed in Claim 1, wherein the testing model(s) are updated within the instruments (101,103) by communicating with the server (104) periodically or in real time, and wherein the step of Capturing & Recording the location parameters (411) involves first identifying location parameters of the milk sample, milk testing instrument, or both by an AI/ML model trained on a preset data (411a).

Claim 3. The method for detecting variants and adulterants in a sample of milk as claimed in Claim 1, wherein testing the sample by employing at least one conductive sensor located on the pipette to identify common and extended milk adulterants and at least one model for adulterants to identify the milk variety.

Claim 4. The method for detecting variants and adulterants in a sample of milk as claimed in Claim 1, wherein communicating the test results to the server containing information on whether the results are identified as false positive, positive, false negative or negative, are optionally performed after the user has manually confirmed such results (415).

Claim 5. A system for detecting variants and adulterants in milk samples comprising a plurality of milk analysis instruments (101,103) configured to collect samples, test milk components, and communicate with a server (104) and with one or more other milk analysis instruments (101,103):
Wherein each instrument has at least a pipette, display screen, sensors located on said pipette and a processor connected to a server (104) by a wireless connection (105), said processor located in a locally present milk analysis instrument (101) is configured to communicate with said server and instruments (104,103) located in various locations, process data and generate level of detection, and store the processed data in data storage unit located in said server (104);
a classifier module configured to sorting and organizing the analysis data and updating the milk analysis instruments for future analysis;
a centralized control unit operably coupled to the instruments, user interface, processor, classifier module and data storage unit to coordinate the operation of multiple instruments, ensure synchronization, and enable communication;
wherein the present system is capable of correlating between a specific variant and adulterant in selecting a relevant Level of Detection to be considered for adulterant detection, while ignoring false positives.

Claim 6. The system for detecting variants and adulterants in milk sample as claimed in claim 5, wherein the system employs a digital twin model capable of receiving data from each subsystem of each unit including subsystem level components, enabling predictive analysis of maintenance, operations, and to facilitate updates to various system models, units, subsystems, components, devices, applications inter alia.

Claim 7. The system for detecting variants and adulterants in milk sample as claimed in claim 5, comprising one or more milk analyzing instrument(s) (101,103), an algorithm, a controller, a processor, at least a display screen, a user application (102), a wireless connection (105) and ancillary parts, a server (104) and AI/ML block.

Claim 8. The system for detecting variants and adulterants in milk sample wherein the AI/ML block as claimed in claims 5 and 7, is configured to a training model built to train both AI and ML models to generate results for the input data processed by the AI model is capable to train the AI/ML block to identify local regional differences in sample components including altered levels of detection, accordingly amending the level(s) of detection and algorithms to prevent false-tests as plurality of samples are tested, increasingly collecting data from plurality of locations, to improve accuracy and correlation of the sample components to regional differences based on the location parameters identified or received by the system..

Claim 9. The system for detecting variants and adulterants in milk sample wherein the AI/ML block as claimed in claims 4 and 6 comprising a task executor configured to forward input dataset to the training model.

Claim 10. The system for detecting variants and adulterants in milk sample wherein the AI/ML block as claimed in claims 4 and 6 comprising of a tuner to evaluate results generated by the AI/ML block and based on feedback, is configured to optimize the training model.

Claim 11. The system for detecting variants and adulterants in milk sample wherein the AI/ML block as claimed in claims 4 and 6, employs a mechanism to add gold standard reference and adulterant measurement data in the database through a web portal.

Claim 12. The system for detecting variants and adulterants in milk samples as claimed in claims 4 and 6, wherein the system comprises of least one classifier for various kinds of milk selected from Cow, Buffalo, Mixed milk, or other sources of milk and at least one sensor to detect common adulterants in the milk such as NaCl, preferably using conductive sensors to provide a solute concentration in the sample from which FPD can be derived.

Claim 13. The system of detecting variants and adulterants in milk samples as claimed in claims 4 and 6, wherein the system enables testing extended adulterant range including Veg Oil and NaCl (with FPD), other adulterants detected by the present invention include – Urea, Maltodextrin, Sucrose, Ammonia, Detergent, Veg oil, Starch, NaOH, Sodium Carbonate, Sodium Bicarbonate, Added water, Melamine, Formalin, Whey protein.

Claim 14. The system of detecting variants and adulterants in milk samples as claimed in claims 4 and 6, wherein the system employs specific filter-based Fat and SNF chemometric models.

Claim 15. The system of detecting variants and adulterants in milk samples as claimed in claims 4 and 6, employs the AI/ML block and the training model to learn and create levels of detection specific to a micro region, accounting for variations due to factors like diet, environment, breed, which influence the levels of certain milk components, wherein the system is capable of detecting the presence of a variant from the ordinary levels seen in majority of samples collected across other regions, identifying the variant distinctly from an adulterant, informing the system of such variant so that it is not flagged as an adulterant, processing and storing information of such variant as an updated level of detection so that the system is now informed of the new normal levels of detection unique to a particular region.

Claim 16. The system of detecting variants and adulterants in milk samples, allows for effective milk testing while accounting for regional differences in milk production by employing an ML model capable of learning local regional differences over time and adjusting levels of detection and algorithms to minimize false-positives and false – negatives as more samples are tested and more information is collected from a growing list of regions.

Dated this on 9th day of April, 2024
For, Beamoptics Scientific Private Limited
Applicant’s Registered Agent

Ragini Shah
IN/PA/2898