Description:[001] The present invention generally relates to a user-centric culinary formulation system and method, more specifically it relates to an automated ingredient substitution platform for recommending at least one culinary recipe responsive to dynamically varying user response, learned user behavior, and user contextual information.

BACKGROUND OF THE INVENTION
[002] In food technology sector, a typical food consumer or preparer is often an amateur without specialized knowledge in areas like food science, recipe creation, and all intricate aspects of food technology. This lack of expertise poses significant challenges when it comes to preparing meals that meet specific dietary needs, budget constraints, or availability of ingredients. Recipes which include a set of ingredients and step-by-step guidelines for food preparation, are typically created by experienced cooks or chefs and are intended for dissemination to general public. These recipes assume a certain level of availability of ingredients and a standard set of culinary skills, which can be a barrier for many amateur cooks.
[003] One primary challenge that food preparers face is variability in availability of ingredients and cost of those ingredients. Local markets may not always carry certain items, or might have other forms of the items, or they might be prohibitively expensive. This issue is compounded by a general lack of knowledge about how to substitute ingredients effectively. For example, if a recipe calls for a specific type of cheese or a particular herb to prepare a dish, the food preparer might not know what could be used as a substitute without compromising flavor or texture of the dish. This lack of knowledge often leads to frustration and suboptimal culinary outcomes.
[004] Additionally, user-specific food preferences, including dietary restrictions and allergies, further complicate cooking process. A food preparer may need to modify recipes to accommodate these preferences but might not have an expertise to do so successfully. For instance, substituting a dairy product for a non-dairy alternative requires an understanding of how these substitutes will interact with other ingredients during cooking. An understanding of an interplay of the substitutes with the other ingredients at a microscopic level; and effects the substitutes would have on parameters like starch concentration, pH, overall viscosity, moisture content, to name a few, of a final dish; is nothing short of essential. Without this knowledge, the final dish may not turn out as intended, leading to an overall disappointment.
[005] Conventional approaches to addressing these challenges include simple heuristics or rules of thumb that can be learned over time. However, these heuristics often fall short due to an inherent complexity of food science and subsequent myriad interactions between different ingredients. While food preparers can attempt to seek out detailed substitution information, the information available is often inconsistent across different sources, such as cookbooks, notes, and Internet. Moreover, conducting such research requires a certain level of preexisting knowledge about what to look for, which many amateurs might not possess. This gap highlights a need for more accessible, reliable, and comprehensive resources to aid cooks in making informed decisions about ingredient substitutions and modifications to recipes.
[006] Thus, there is a need in the art for a user-centric culinary formulation method and system which addresses at least the aforementioned problems.

SUMMARY OF THE INVENTION
[007] The present invention, in one aspect is directed to user-centric culinary formulation system for recommending at least one culinary recipe responsive to dynamically varying user response, learned user behavior, and user contextual information. The system includes one or more processors; and a receiving module coupled to the processor, configured to receive data in a form of pre-existing recipes, each recipe comprising a plurality of ingredients and user-specific parameters.
[008] The system further includes a data assessment module coupled to the processor, configured assess the data received by the receiving module thereby analyzing patterns of the data; and a data combing module coupled to the processor, configured to remove multicollinearity of the data based on at least one parameter, the parameter being indicative of preferences associated with the user.
[009] According to the invention, the system further includes a feature selection module coupled to the processor, configured to select best features from the data using statistical approaches, wherein selection is reflective of significance of content represented by the data for recommending the culinary formulation to the user; and a recommendation module coupled to the processor configured to: identify ingredients from the best features selected by the feature selection module having a probability of a culinary formulation, compute ratio and proportion of the ingredients of the culinary formulation to equate to the ingredients of the pre-exiting recipes, and recommend at least one culinary recipe to the user based on the dynamically varying user response.
[010] In an embodiment of the invention, the user-specific parameters include but are not limited to starch concentration, pH levels, moisture levels, and hygroscopicity.
[011] In another embodiment of the invention, the data assessment module is configured to determine average mean, standard deviation and confidence intervals to estimate a range of each of the user-specific parameters.
[012] In a further embodiment of the invention, the system includes a clustering module coupled to the processor, configured to form a plurality of cluster groups whereby each cluster comprises the ingredients having similar physicochemical properties.
[013] In yet another embodiment of the invention, the system includes a proximity module coupled to the processor, configured to measure and assess a proximity distance with respect to at least one user-specific parameter between at least two cluster groups.
[014] In another aspect, the present invention relates to a user-centric culinary formulation method for recommending at least one culinary recipe responsive to dynamically varying user response, learned user behavior, and user contextual information. According to the method includes the steps of: receiving data in a form of pre-existing recipes, each recipe comprising a plurality of ingredients and user-specific parameters. The method further includes assessing the data received by the receiving module thereby analyzing patterns of the data. In a further step, the method includes removing multicollinearity of the data based on at least one parameter, the parameter being indicative of preferences associated with the user; and selecting best features from the data using statistical approaches, wherein selection is reflective of significance of content represented by the data for recommending the culinary formulation to the user. The method of the present invention further includes identifying ingredients from the best features selected by the feature selection module having a probability of a culinary formulation; computing ratio and proportion of the ingredients of the culinary formulation to equate to the ingredients of the pre-exiting recipes; and recommending at least one culinary recipe to the user based on the dynamically varying user response. In an embodiment of the invention, the user-specific parameters include, but are not limited to, starch concentration, pH levels, moisture levels, and hygroscopicity.
[015] In an embodiment of the invention, the method includes determining average mean, standard deviation and confidence intervals to estimate a range of each of the user-specific parameters. In a further embodiment, the method includes forming a plurality of cluster groups whereby each cluster comprises the ingredients having similar physicochemical properties. In yet another embodiment, the method includes measuring and assessing a proximity distance with respect to at least one user-specific parameter between at least two cluster groups.

BRIEF DESCRIPTION OF THE DRAWINGS
[016] 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. Reference has been made to embodiments of the invention, examples of which may be illustrated in accompanying figures. These figures constitute a part of this disclosure are intended to be illustrative, and together with the description, serve to explain the invention. Although the invention is generally described in 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 network environment of a user-centric culinary formulation system in accordance with an embodiment of the invention.
Figure 2 shows components of the user-centric culinary formulation system in accordance with an embodiment of the invention.
Figure 3 shows a user-centric culinary formulation method in accordance with an embodiment of the invention.

DETAILED DESCRIPTION OF THE INVENTION
[017] Embodiments of the present disclosure, disclose a user-centric culinary formulation system and method. The terms “comprises.... a”, “comprising”, or any other variations thereof used in the specification, are intended to cover a non-exclusive inclusion, such that a system and method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such system or method. In other words, one or more elements in an assembly proceeded by “comprises... a” does not, without more constraints, preclude the existence of other elements or additional elements in the assembly.
[018] For the purposes of promoting an understanding of the principles of the disclosure, reference will now be made to specific embodiments illustrated in the drawings and specific language will be used to describe the same. It will nevertheless be understood that no limitation of the scope of the disclosure is thereby intended, such alterations and further modifications in the illustrated methods, and such further applications of the principles of the disclosure as illustrated therein being contemplated as would normally occur to one skilled in the art to which the invention pertains.
[019] In accordance with the present invention, Figure 1 depicts a typical network environment 100 for a user-centric culinary formulation system 102 (hereinafter referred to as “system”). In an embodiment of the invention, the network environment 100 is a public network environment which includes various servers and computing devices. In yet another embodiment of the invention, the network environment 100 is a private network with a limited number of computing devices such as personal computers, servers, laptops, mobile phones, etc.
[020] Referring yet to Figure 1, in an embodiment of the invention, the system 102 is implemented in one or more user devices 106. In the same embodiment, the user devices 106 include multiple applications that may be running to perform several functions, as required by different users. In and embodiment, the system 102 is implemented in a computing device, such as a laptop computer, a desktop computer, a notebook, a workstation, a mainframe computer, a server, and the like. The user devices 106 may be implemented as, but are not limited to, desktop computers, hand-held devices, laptops or other portable computers, tablet computers, mobile phones, PDAs, Smartphones, land-line phones, and the like. In an embodiment, the user devices 106 is are capable of providing content, through a network 104.
[021] In one aspect, the present invention discloses a user-centric culinary formulation system for recommending at least one culinary recipe responsive to dynamically varying user response, learned user behavior, and user contextual information. Referring to Figure 1, in an embodiment of the invention, the network 104 is a wireless or a wired network, or a combination thereof. In yet another embodiment, the network 104 is a collection of individual networks, interconnected with each other and functioning as a single large network (e.g., the internet or an intranet). Examples of such individual networks include, but are not limited to, Global System for Mobile Communication (GSM) network, Universal Mobile Telecommunications System (UMTS) network, Personal Communications Service (PCS) network, Time Division Multiple Access (TDMA) network, Code Division Multiple Access (CDMA) network, Next Generation Network (NGN), Public Switched Telephone Network (PSTN), and Integrated Services Digital Network (ISDN).
[022] Referring to Figure 2, according to the invention, the system 102 includes one or more processor(s) 204, interface(s) 206 and a memory 208. In various embodiments, the processor 204 is a single processing unit or a number of units, all of which could include multiple computing units. In the same embodiment, the processor 204 is implemented as one or more microprocessor, microcomputers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities the processor 204 is adapted to fetch and execute computer-readable instructions stored in a memory 208. In various embodiments of the invention, the processor 204 includes without limitation, digital signal processor (DSP) hardware, network processor, application specific integrated circuit (ASIC), field programmable gate array (FPGA), read only memory (ROM) for storing software, random access memory (RAM), non-volatile storage.
[023] Referring yet to Figure 2, in an embodiment of the invention, the interface 206 includes a variety of software and hardware interfaces, or example, interface for peripheral device(s), such as a keyboard, a mouse, a microphone, an external memory, a speaker, and a printer. Further, the interface 206 includes one or more ports for connecting the system 102 with other computing devices, such as web servers, and external databases. The interface 206 facilitates multiple communications within a wide variety of protocols and networks, such as a network, including wired networks, e.g., LAN, cable, etc., and wireless networks, e.g., WLAN, cellular, satellite, etc.
[024] As seen in Figure 2, the memory 208 is coupled to the processor 204 and includes computer-readable medium known in the art including, for example, volatile memory, such as Static Random Access Memory (SRAM) and Dynamic Random Access Memory (DRAM), and/or non-volatile memory, such as Read Only Memory (ROM), Erasable Programmable ROMs (EPROMs), flash memories, hard disks, optical disks, and magnetic tapes.
[025] Referring to Figure 2, the system 102 of the present invention includes various modules 210 and data 250. The modules 210 and the data 212 are typically coupled to the processor 204. In various embodiments of the invention, the modules 210, include but are not limited to routines, programs, objects, components, data structures, etc., which perform particular tasks or implement particular abstract data types. The modules 210 may also be implemented as, signal processor(s), state machine(s), logic circuitries, and/or any other device or component that manipulate signals based on operational instructions.
[026] As seen in Figure 2, according to the invention, the module 210 includes, a receiving module 214, a data assessment module 216, data combing module 218, a feature selection module 224, and a recommendation module 226. In embodiments of the invention, the module 210 further includes a clustering module 220, and a proximity module 222. Further, the data 250 serve, as a repository for storing data obtained and processed by the modules 210. According to the present invention and as seen in Figure 2, the data 250 includes, pre-existing culinary recipes which essentially includes information of all ingredients 252 of the pre-existing culinary recipes, and user-specific parameters 254. In an embodiment of the invention, the user-specific parameters 254 include, but are not limited to, starch concentration, pH levels, moisture levels, and hygroscopicity of the ingredients.
[027] According to the invention, the system 102 has the receiving module 214. The receiving module 214 is coupled to the processor 204, as seen in Figure 2. As described hereinabove, the data 250, in the form of ingredients 252 of the pre-existing culinary recipes, and the user-specific parameters 254 is generated from various sources like the one or more user devices 106, or the Internet, or and such mediums. In various embodiments, the data 250 is unorganized and is either statistical in nature, or has categorical information from texts/ strings, or is in a form of lists, or any other form or combination thereof. This data 250 from the various source integrations is received by the receiving module 214 for being further processed by the system 102.
[028] The system 102 further has a data assessment module 216 coupled to the processor 204. According to the invention, the data assessment module 216 is configured to assess the data 250 and analyze any patterns of the data 250 reflecting any specific user behavior, or user contextual information, etc. for further processing of data feature extraction. The data feature extraction is a process of transforming raw data into meaningful features that can be used as input to a machine learning. This involves selecting and transforming variables that are relevant. Accordingly, in an embodiment of the invention, the data assessment module 216 is further configured to determine average mean, standard deviation and confidence intervals to estimate a range of each of the user-specific parameters 254.
[029] According to the invention, the system 102 has a data combing module 218 coupled to the processor 204. The data combing module 218 is configured to remove multicollinearity of the data 250 based on at least one parameter, wherein the parameter is indicative of preferences associated with the user. Multicollinearity of the data 250 refers to a situation where two or more predictor variables in a regression model are highly correlated. This may cause issues in interpreting and can lead to unstable estimates of coefficients.
[030] Referring yet to Figure 1, in an embodiment of the invention, the system 102 has a clustering module 220 coupled to the processor 204. In this embodiment, the clustering module 220 is configured to form a plurality of cluster groups. Each of the cluster groups so formed includes multiple recipes whereby all the ingredients in the multiple recipes of a particular cluster group have similar physicochemical properties.
[031] In another embodiment of the invention, the system 102 has a proximity module 222 coupled to the processor 204. The proximity module 222 is configured to measure and assess a proximity distance with respect to at least one user-specific parameter between at least two cluster groups. This is to say, the proximity module 222 measures a logical distance between the various user-specific parameters 254 amongst different clusters plotted within a same proximity of the cluster groups and calculates referenced virtual central point. The calculated distance determines homogeneity of a product when it has appeared within equidistance, among the selected ingredients and the user-specific parameters 254. Proximity data obtained from the proximity module 222 is then used to assess ratio and proportion of the user-specific parameters 254 of a final culinary recommendation by the system 102.
[032] The system 102, according to the present invention, further has a feature selection module 224 coupled to the processor 204. The feature selection module 224 is configured to select best features from the data 250 using statistical approaches. This selection is reflective of significance of content represented by the data 250 for recommending the culinary formulation to the user. The feature selection module 254 determines feature selection based on data variance and data distribution received from the aforementioned modules.
[033] According to the present invention, the system 102 further has a recommendation module 226 coupled to the processor 204. The recommendation module 226 is configured to identify ingredients from the best features selected by the feature selection module 224 having a probability of a culinary formulation. The recommendation module 226 is further configured to compute ratio and proportion of the ingredients of the culinary formulation to equate to the ingredients of the pre-exiting recipes. Based on the information, the recommendation module 226 is configured to recommend at least one culinary recipe to the user based on the dynamically varying user response.
[034] In another aspect, and as seen in Figure 3, the present invention discloses a user-centric culinary formulation method 300 for recommending at least one culinary recipe responsive to dynamically varying user response, learned user behavior, and user contextual information. According to the invention, at step 310, the method 300 includes receiving data 250 in a form of pre-existing recipes, whereby each recipe includes a plurality of ingredients 252 and user-specific parameters 254. As discussed hereinbefore, the data 250 is unorganized and is either statistical in nature, or has categorical information from texts/ strings, or is in a form of lists, or any other form or combination thereof. In an embodiment of the invention, the user-specific parameters 254 include, but are not limited to, starch concentration, pH levels, moisture levels, and hygroscopicity of the ingredients.
[035] At step 312, the method 300 includes assessing the data 250 received by the receiving module 214. In this step the data 250 is assessed and analyzed for any patterns of the data 250 reflecting any specific user behavior, or user contextual information, etc. for further processing of data feature extraction. In an embodiment of the invention, the method 300, at step 314 includes determining average mean, standard deviation and confidence intervals to estimate a range of each of the user-specific parameters 254.
[036] According to the invention, at step 316, the method 300 includes removing 316 multicollinearities of the data based on at least one parameter, whereby the parameter is indicative of preferences associated with the user. As elaborated hereinabove, multicollinearity of the data 250 refers to a situation where two or more predictor variables in a regression model are highly correlated. This may cause issues in interpreting and can lead to unstable estimates of coefficients.
[037] In an embodiment of the invention, the method 300, at step 318 includes forming 318 a plurality of cluster groups. Thus, each of the cluster groups so formed includes multiple recipes whereby all the ingredients in the multiple recipes of a particular cluster group have similar physicochemical properties. In another embodiment of the invention, the method 300, at step 320 includes measuring and assessing a proximity distance with respect to at least one user-specific parameter between at least two cluster groups. The logical distance between the various user-specific parameters 254 amongst different clusters is plotted within a same proximity of the cluster groups and the referenced virtual central point is calculated. The calculated distance determines homogeneity of a product when it has appeared within equidistance, among the selected ingredients and the user-specific parameters 254.
[038] According to the invention, at step 322, the method 300 includes selecting best features from the data using statistical approaches. The selection is reflective of significance of content represented by the data for recommending the culinary formulation to the user. The feature selection in this method step is based on data variance and data distribution received from the aforementioned method steps.
[039] Further, as seen in Figure 3, at step 324 the method 300 of the present invention includes identifying 324 ingredients from the best features selected by the feature selection module having a probability of a culinary formulation. At step 326, ratio and proportion of the ingredients of the culinary formulation are computed to equate to the ingredients of the pre-exiting recipes. Finally, at step 328 of the method 300 of the present invention, at least one culinary recipe based on the dynamically varying user response is recommended to the user.
[040] Advantageously, the user-centric culinary formulation system and method of the present invention offers significant advantages by generating customized culinary formulations with consistency of the formulations matching original recipes, saving time, and being cost-effective. The system ensures that users can enjoy their favorite dishes without compromising on texture and flavor. This is particularly beneficial for those with dietary restrictions or preferences, as it allows them to enjoy modified versions of their favorite meals that still meet their expectations. Further, the system saves substantial amount of time in generating alternative formulations with user-defined ingredient content. This is especially useful for home cooks and professional chefs who need to adapt recipes to accommodate allergies, dietary restrictions, or ingredient availability without extensive trial and error. Finally, the system is cost-effective, reducing the need for expensive experimentation and wasted ingredients. Thus, by providing precise measurements and ingredient substitutions, users can efficiently manage their culinary creations, leading to reduced food waste and optimized spending on ingredients.
[041] While various aspects and embodiments have been disclosed hereinabove, other aspects and embodiments will be apparent to those skilled in the art. However, it will be apparent to those skilled in the art that various changes and modification may be made without departing from the scope of the invention as defined in the following claims.
, Claims:1. A user-centric culinary formulation system (102), for recommending at least one culinary recipe responsive to dynamically varying user response, learned user behavior, and user contextual information, the system (102) comprising:
one or more processors (204);
a receiving module (214) coupled to the processor (204), configured to receive data (250) in a form of pre-existing recipes, each recipe comprising a plurality of ingredients (252) and user-specific parameters (254);
a data assessment module (216) coupled to the processor (204), configured assess the data (250) received by the receiving module (214) thereby analyzing patterns of the data;
a data combing module (218) coupled to the processor (204), configured to remove multicollinearity of the data (250) based on at least one parameter, the parameter being indicative of preferences associated with the user;
a feature selection module (224) coupled to the processor (204), configured to select best features from the data (250) using statistical approaches, wherein selection is reflective of significance of content represented by the data (250) for recommending the culinary formulation to the user; and
a recommendation module (226) coupled to the processor (204) configured to:
identify ingredients from the best features selected by the feature selection module (224) having a probability of a culinary formulation,
compute ratio and proportion of the ingredients of the culinary formulation to equate to the ingredients of the pre-exiting recipes, and
recommend at least one culinary recipe to the user based on the dynamically varying user response.

2. The user-centric culinary formulation system (102) as claimed in claim 1, wherein the user-specific parameters (254) comprise: starch concentration, pH levels, moisture levels, and hygroscopicity.

3. The user-centric culinary formulation system (102) as claimed in claim 1, wherein the data assessment module (216) is configured to determine average mean, standard deviation and confidence intervals to estimate a range of each of the user-specific parameters (254).

4. The user-centric culinary formulation system (102) as claimed in claim 1, comprises a clustering module (220) coupled to the processor (204), configured to form a plurality of cluster groups whereby each cluster comprises the ingredients having similar physicochemical properties.

5. The user-centric culinary formulation system (102) as claimed in claim 1, comprises a proximity module (222) coupled to the processor (204), configured to measure and assess a proximity distance with respect to at least one user-specific parameter (254) between at least two cluster groups.

6. A user-centric culinary formulation method (300), for recommending at least one culinary recipe responsive to dynamically varying user response, learned user behavior, and user contextual information, the method (300) comprising the steps of:
receiving (310) data (250) in a form of pre-existing recipes, each recipe comprising a plurality of ingredients (252) and user-specific parameters (254);
assessing (312) the data (250) received by the receiving module (214) thereby analyzing patterns of the data;
removing (316) multicollinearity of the data (250) based on at least one parameter, the parameter being indicative of preferences associated with the user;
selecting (322) best features from the data (250) using statistical approaches, wherein selection is reflective of significance of content represented by the data for recommending the culinary formulation to the user;
identifying (324) ingredients from the best features selected by the feature selection module having a probability of a culinary formulation;
computing (326) ratio and proportion of the ingredients of the culinary formulation to equate to the ingredients of the pre-exiting recipes; and
recommending (328) at least one culinary recipe to the user based on the dynamically varying user response.

7. The user-centric culinary formulation method (300) as claimed in claim 6, wherein the user-specific parameters (254) comprise: starch concentration, pH levels, moisture levels, and hygroscopicity.

8. The user-centric culinary formulation method (300) as method in claim 6, comprises determining (314) average mean, standard deviation and confidence intervals to estimate a range of each of the user-specific parameters (254).

9. The user-centric culinary formulation method (300) as claimed in claim 6, comprises forming (318) a plurality of cluster groups whereby each cluster comprises the ingredients having similar physicochemical properties.

10. The user-centric culinary formulation method (300) as claimed in claim 1, comprises measuring and assessing (320) a proximity distance with respect to at least one user-specific parameter (254) between at least two cluster groups.