DETAILED ACTION
Status of Claims
Claims 1-20 submitted on 05/08/2026 are pending and have been examined. Claims 1, 7-9, 13, and 15-17 have been amended.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Priority
No foreign priority or domestic benefit was claimed by the applicant and the application has been examined with respect to its filing date of 10/31/2024.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception without significantly more. The claims recite an abstract idea. This judicial exception is not integrated into a practical application. The claim(s) do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Step 1
Claims 1-8 are directed to a process, claims 9-16 are directed to an article of manufacture, and claims 17-20 are directed to a machine (see MPEP 2106.03).
Step 2A, Prong 1
Claim 1, taken as representative, recites at least the following limitations that recite an abstract idea:
a method, performed, the method comprising:
sending, to a user, a user interface that identifies a recipe and lists a plurality of ingredients for the recipe, wherein the user interface includes a user-selectable option to add one or more of the plurality of ingredients to an order;
receiving an instruction to identify an alternative ingredient to substitute for a particular ingredient of the plurality of ingredients of the recipe;
generating a prompt, wherein the prompt includes: a description of the recipe, a description of the particular ingredient to be substituted, and a request to suggest a different ingredient to substitute for the particular ingredient in the recipe;
providing the prompt to obtain an output therefrom;
parsing, from the output, the alternative ingredient for the recipe;
updating the user interface, wherein the user interface includes the alternative ingredient;
sending, to the user, the user interface, wherein the user device presents the user interface with the user-selectable option to add one or more of the plurality of ingredients, including the alternative ingredient, to an order;
logging a user interaction with the user interface, the user interaction including an indication about whether the user-selectable option to add one or more of the plurality of ingredients, including the alternative ingredient, to an order was selected,
wherein the user interaction is included in additional training examples; and
tuning, based in part on the additional training examples, by providing a prompt,
wherein the prompt includes the additional training examples as a first portion of the prompt and the user interaction as a second portion of the prompt.
The above limitation, under its broadest reasonable interpretation, falls within the “Certain Methods of Organizing Human Activity” grouping of abstract ideas, enumerated in MPEP 2106.04(a)(2)(II), in that it recites a commercial interaction. Claims 9 and 17 recites similar limitations as claim 1.
Thus, under Prong 1 of Step 2A, claims 1, 9, and 17 recite an abstract idea.
Step 2A, Prong 2
Claim 1 includes the following additional elements that are bolded:
a method, performed at a computer system comprising a processor and a computer-readable medium, the method comprising:
sending, to a user device, a user interface that identifies a recipe and lists a plurality of ingredients for the recipe, wherein the user interface includes a user-selectable option to add one or more of the plurality of ingredients to an order;
receiving an instruction to identify an alternative ingredient to substitute for a particular ingredient of the plurality of ingredients of the recipe;
generating a prompt for a large language model, wherein the prompt includes: a description of the recipe, a description of the particular ingredient to be substituted, and a request to suggest a different ingredient to substitute for the particular ingredient in the recipe;
providing the prompt to the large language model to obtain an output therefrom;
parsing, from the output of the large language model, the alternative ingredient for the recipe;
updating the user interface, wherein the user interface includes the alternative ingredient;
sending, to the user device, the user interface, wherein the user device presents the user interface with the user-selectable option to add one or more of the plurality of ingredients, including the alternative ingredient, to an order;
logging a user interaction with the user interface, the user interaction including an indication about whether the user-selectable option to add one or more of the plurality of ingredients, including the alternative ingredient, to an order was selected,
wherein the user interaction is included in additional training examples; and
tuning, based in part on the additional training examples, the large language model by providing a prompt for re-training the large language model,
wherein the prompt includes the additional training examples as a first portion of the prompt and the user interaction as a second portion of the prompt.
Claims 9 and 17 include the same additional elements as claim 1. In addition, claim 9 includes additional elements such as a computer program product comprising a non-transitory computer readable storage medium having instructions encoded thereon that, when executed by a processor of a computer system, cause the computer system to perform steps. In addition, claim 17 includes additional elements such as a computer system comprising: a processor; and a non-transitory computer readable storage medium having instructions encoded thereon that, when executed by the processor, cause the computer system to perform steps comprising.
The additional elements recited in claims 1, 9, and 17 merely invoke such elements as a tool to perform the abstract idea and generally link the use of the abstract idea to a particular technological environment of large language models (see MPEP 2106.05(f) and MPEP 2106.05(h). These additional elements are described at a high level in Applicant’s specification without any meaningful detail about their structure or configuration (see Fig. 1 and ¶¶0114-0117).
As such, under Prong 2 of Step 2A, when considered both individually and as a whole, the additional elements do not integrate the judicial exception into a practical application and, thus, claims 1, 9, and 17 are directed to an abstract idea.
Step 2B
As noted above, while the recitation of the additional elements in independent claims 1, 9, and 17 are acknowledged, claims 1, 9, and 17 merely invoke such additional elements as a tool to perform the abstract idea and generally link the use of the abstract idea to a particular technological environment (see MPEP 2106.05(f) and MPEP 2106.05(h)).
Even when considered as an ordered combination, the additional elements of claim 1, 9, and 17 do not add anything that is not already present when they are considered individually. Therefore, under Step 2B, there are no meaningful limitations in claims 1, 9, and 17 that transform the judicial exception into a patent eligible application such that the claims amount to significantly more than the judicial exception itself (see MPEP 2106.05).
As such, independent claims 1, 9, and 17 are ineligible.
Dependent claims 2-4, 6-8, 10-12, 14-16, and 18-20 when analyzed as a whole, are held to be patent ineligible under 35 U.S.C. 101 because they do not add “significantly more” to the abstract idea. More specifically, dependent claims 2-4, 6-8, 10-12, 14-16, and 18-20 merely further define the abstract limitations of claims 1, 9, and 17 or provide further embellishments of the limitations recited in independent claims 1, 9, and 17. Claims 2-4, 6-8, 10-12, 14-16, and 18-20 do not introduce any further additional elements. Thus, dependent claims 2-4, 6-8, 10-12, 14-16, and 18-20 are ineligible.
Furthermore, it is noted that certain dependent claims recite additional elements supplemental to those recited in independent claims 1, 9, and 17: online catalog (claims 5 and 13). However, these elements do not integrate the abstract idea into a practical application because they merely amount to using a computer to apply the abstract idea to a particular technological environment or field of use and thus do not act to integrate the abstract idea into a practical application of the abstract idea. Additionally, the additional elements do not amount to significantly more because they merely amount to using a computer to apply the abstract idea and amount to no more than a general link of the use of the abstract idea to a particular technological environment.
Thus, dependent claims 5 and 13 are ineligible.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status. This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-5, 9-13, and 17-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Rapaport et al. (US 2019/0171707 A1 [previously cited]) in view of Neumann et al. (US 2020/0380459 A1 [previously cited]) in view of Silvain et al. (US 2026/0038014 A1).
Regarding Claim 1, Rapaport et al., hereinafter, Rapaport, discloses a method, performed at a computer system comprising a processor and a computer-readable medium, the method comprising (Fig. 2; ¶0071):
sending, to a user device, a user interface that identifies a recipe and lists a plurality of ingredients for the recipe, wherein the user interface includes a user-selectable option to add one or more of the plurality of ingredients (Fig. 2[elements 204 and 220], Fig. 4; ¶¶0145-0150[At 402, a text-based food-recipe is received by computing device 204. The text-based recipe may be… a user interface of client terminal 208 (e.g., via a GUI) over network 210, transmitted from server 212 over network 210, and/or from a storage device storing text-based food-recipes… At 406, a selection of one or more ingredients appearing within the set of ingredients of the target food-recipe data structure is received… The selection may be made manually, for example, by a user manually selecting (e.g., clicking, hovering a pointer over, clicking within a box near) on the ingredient via a GUI on client terminal 208.]);
receiving an instruction to identify an alternative ingredient to substitute for a particular ingredient of the plurality of ingredients of the recipe (Fig. 4[element 406]; ¶¶0148-0150[At 406, a selection of one or more ingredients appearing within the set of ingredients of the target food-recipe data structure is received… The selection may be made manually, for example, by a user manually selecting] in view of ¶0143[Reference is now made to FIG. 4, which is a flowchart of an exemplary method of computing a substitute for one or more ingredients in a text-based food-recipe by the trained neural network]);
generating a prompt for a large language model, wherein the prompt includes: a description of the recipe, a description of the particular ingredient to be substituted, and a request to suggest a different ingredient to substitute for the particular ingredient in the recipe (Figs. 1 and 4; ¶¶0146-0148[At 404, the text-based food-recipe is converted into a target food-recipe data structure storing a representation of the text-based food-recipe. The target food-recipe data structure stores a set of ingredients, and instructions for preparation of the respective food-recipe… The target food-recipe data structure may be encoded for feeding into the input layer of the trained neural network, as described herein with reference to act 104 of FIG. 1… A 406, a selection of one or more ingredients appearing within the set of ingredients of the target food-recipe data structure is received. The ingredient is selected for substitution] in view of ¶0058[The neural network enables identification of substitute ingredients by consideration of the recipe as a whole, and/or the context of the recipe, since for example, not every ingredient substitute is suitable for every recipe. Different recipes having different contexts may require a different suitable substitute ingredient.]; Examiner notes that ¶0038 of the instant specification states, “As used herein, machine-learning model is used interchangeably with "large language model.");
providing the prompt to the large language model to obtain an output therefrom (¶0147[The target food-recipe data structure may be encoded for feeding into the input layer of the trained neural network, as described herein with reference to act 104 of FIG. 1] in view of ¶0067[the GUI presents the text-based food-recipe, and dynamically replaces each instance of a selected ingredient within the text-based food recipe with the substitute ingredient determined based on output of the neural network]);
parsing, from the output of the large language model, the alternative ingredient for the recipe (¶0151[At 408, one or more adjusted food-recipe data structures are computed. Each adjusted food-recipe data structure includes a predefined textual code that replaces one of the selected text-based ingredients for substitution] in view of ¶0067[the GUI presents the text-based food-recipe, and dynamically replaces each instance of a selected ingredient within the text-based food recipe with the substitute ingredient determined based on output of the neural network]);
updating the user interface, wherein the user interface includes the alternative ingredient (Fig. 4; ¶0157[At 416, the substitute ingredient (optional text-based version) is provided, for example, transmitted over network 210 to client terminal 208. The substitute ingredient may be presented on a display (e.g. of the client terminal) optionally within the GUI, and/or automatically substituted for the selected ingredients in the text-based food-recipe. The adjusted text-based food-recipe may be transmitted to the client terminal for presentation, and/or stored as an adjusted recipe, for example, a vegan version of a meat recipe, and/or an allergy free version of an allergy prone recipe]);
sending, to the user device, the user interface, wherein the user device presents the user interface with the user-selectable option to add one or more of the plurality of ingredients, including the alternative ingredient (Figs. 2 and 4[element 414]; ¶0019[the selected at least one text-based ingredient for substitution is automatically substituted within the GUI with the selected at least one substitute ingredient indication] in view of ¶0157[At 416, the substitute ingredient (optional text-based version) is provided, for example, transmitted over network 210 to client terminal 208. The substitute ingredient may be presented on a display (e.g. of the client terminal) optionally within the GUI, and/or automatically substituted for the selected ingredients in the text-based food-recipe. The adjusted text-based food-recipe may be transmitted to the client terminal for presentation, and/or stored as an adjusted recipe, for example, a vegan version of a meat recipe, and/or an allergy free version of an allergy prone recipe]);
a user interaction with the user interface, the user interaction including an indication about whether the user-selectable option to add one or more of the plurality of ingredients, including the alternative ingredient, was selected (¶0013[For example, the user may dynamically select the ingredient for substitution from a visually presented target food-recipe displayed within a GUI. All instances of the selected ingredient within the food-recipe may be dynamically adjusted within the GUI. The user may select different ingredients for substitution to quickly change the recipe.]),
wherein the user interaction (Fig. 1; ¶0013); and
the large language model by providing a prompt (Figs. 1 and 4; ¶¶0146-0148[At 404, the text-based food-recipe is converted into a target food-recipe data structure storing a representation of the text-based food-recipe. The target food-recipe data structure stores a set of ingredients, and instructions for preparation of the respective food-recipe… The target food-recipe data structure may be encoded for feeding into the input layer of the trained neural network, as described herein with reference to act 104 of FIG. 1… A 406, a selection of one or more ingredients appearing within the set of ingredients of the target food-recipe data structure is received. The ingredient is selected for substitution] in view of ¶0058[The neural network enables identification of substitute ingredients by consideration of the recipe as a whole, and/or the context of the recipe, since for example, not every ingredient substitute is suitable for every recipe. Different recipes having different contexts may require a different suitable substitute ingredient.]; Examiner notes that ¶0038 of the instant specification states, “As used herein, machine-learning model is used interchangeably with "large language model."),
wherein the prompt includes the as a first portion of the prompt and the user interaction as a second portion of the prompt (Figs. 1 and 4; ¶¶0146-0148[At 404, the text-based food-recipe is converted into a target food-recipe data structure storing a representation of the text-based food-recipe. The target food-recipe data structure stores a set of ingredients, and instructions for preparation of the respective food-recipe… The target food-recipe data structure may be encoded for feeding into the input layer of the trained neural network, as described herein with reference to act 104 of FIG. 1… A 406, a selection of one or more ingredients appearing within the set of ingredients of the target food-recipe data structure is received. The ingredient is selected for substitution] in view of ¶0058[The neural network enables identification of substitute ingredients by consideration of the recipe as a whole, and/or the context of the recipe, since for example, not every ingredient substitute is suitable for every recipe. Different recipes having different contexts may require a different suitable substitute ingredient.]; Examiner notes that ¶0038 of the instant specification states, “As used herein, machine-learning model is used interchangeably with "large language model.").
Although Rapaport discloses sending a user interface that identifies a recipe with user-selectable options to add ingredients, Rapaport does not explicitly disclose adding ingredients to an order and adding alternative ingredients to an order and adding to an order.
However, Neumann et al., hereinafter, Neumann, teaches adding ingredients to an order (¶0054[User location including geographic location of a user may be utilized to generate transport request 124 that may contain orders including ingredients or selections that may be available to a user in a certain geographical location. For example, a user with an alimentary instruction set that contains a recommendation to consume dairy products may receive transport request 124 including an order for yogurts produced within a certain radius of the geolocation.]).
The method of Neumann is applicable to the method of Rapaport as they share characteristics and capabilities, namely, they are both targeted to recipes and ingredients. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the substitution of ingredients in a recipe as disclosed by Rapaport to include ordering ingredients as taught by Neumann. One of ordinary skill in the art would have been motivated to expand the method of Rapaport in order to determine relationships between elements of dietary data, in combination with or instead of alimentary labels (¶0055).
Although Rapaport discloses a user interaction, Rapaport in view of Neumann does not explicitly teach logging an interaction, wherein the interaction is included in additional training examples and tuning, based in part on the additional training examples and providing for re-training the large language model wherein the prompt includes the additional training examples.
However, Silvain et al., hereinafter, Silvain, teaches logging user interactions in order to re-train and tune a machine learning model based on the interactions (Figs. 3-4; ¶0034[Furthermore, the engine module 130 includes a training and optimization module 210 configured to enable administrators to fine-tune the large language model (LLM) based on insights generated from data analytics and to reevaluate facets and merchandizing using the updated large language model (LLM). As used herein, the term “insights” refer to the actionable findings obtained from evaluating user interactions, performance metrics, and system data. Fine-tuning involves adjusting the LLM's parameters and algorithms to improve its ability to generate relevant and contextually accurate responses based on updated information. Additionally, the training and optimization module 210 facilitates the re-evaluation of product facets and merchandising strategies by leveraging the updated LLM. Also, the term “merchandising” involves the strategies used to present and promote products. By applying the refined LLM to these elements, the training and optimization module 210 ensures that product categorizations and promotional tactics remain aligned with current customer preferences and trends. This ongoing process of training and optimization ensures that the system continuously evolves and improves, providing a more personalized and effective shopping experience.]).
The method of Silvain is applicable to the method of Rapaport in view of Neumann as they share characteristics and capabilities, namely, they are all targeted to searching for products. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the substitution of ingredients in a recipe as taught by Rapaport in view of Neumann to include logging user interactions and tuning a machine learning model as taught by Silvain. One of ordinary skill in the art would have been motivated to expand the method of Rapaport in view of Neumann in order to personalize a shopping experience in a conversational commerce platform (Abstract).
Regarding Claim 2, Rapaport in view of Neumann in view of Silvain teaches the method of claim 1, Rapaport discloses wherein sending the user interface that identifies a recipe and lists a plurality of ingredients for the recipe comprises including, in the user interface, a selectable interface element to change a dietary attribute of the recipe (¶0150[the user profile may include personal preferences of the user, including ingredients that user prefers to avoid and/or ingredients that use like. Exemplary user interface parameters include one or more of: dairy free, genetically engineered free, organic, low carb, Eatwell Apple, contains nuts, vegetarian, kosher, gluten free, sugar free, vegan, and Halal. The user may manually define and/or select the user interface parameters.] in view of ¶¶0066-0067[the ingredient substitution may be according to a personal preference of the user and/or allergy profile of the user]).
Regarding Claim 3, Rapaport in view of Neumann in view of Silvain teaches the method of claim 2, Rapaport discloses further comprising: receiving a selection of the selectable interface element to change a dietary attribute of the recipe (¶0150[the user profile may include personal preferences of the user, including ingredients that user prefers to avoid and/or ingredients that use like. Exemplary user interface parameters include one or more of: dairy free, genetically engineered free, organic, low carb, Eatwell Apple, contains nuts, vegetarian, kosher, gluten free, sugar free, vegan, and Halal. The user may manually define and/or select the user interface parameters.]);
wherein generating the prompt for the large language model comprises including, in the prompt, a request to suggest the different ingredient to substitute for the particular ingredient in the recipe in a way that is consistent with the request to change a dietary attribute of the recipe (Fig. 1; ¶0213[Referring now back to FIG. 1, at 112, the multi-dimensional representation of the target food-recipe data structure computed by the trained neural network is provided as input to code instructions for performing collaborative filtering. The collaborative filtering code, given past information of a population of users' preference information for a space of objects represented by a vector (i.e., ƒ(r)), outputs recommendations for objects for a user (based on the user's past preference information)] in view of ¶0066[the ingredient substitution may be according to a personal preference of the user and/or allergy profile of the user.] in view of ¶0150).
Regarding Claim 4, Rapaport in view of Neumann in view of Silvain teaches the method of claim 2, Rapaport discloses further comprising: receiving a selection of the selectable interface element to change a dietary attribute of the recipe (¶0150[the user profile may include personal preferences of the user, including ingredients that user prefers to avoid and/or ingredients that use like. Exemplary user interface parameters include one or more of: dairy free, genetically engineered free, organic, low carb, Eatwell Apple, contains nuts, vegetarian, kosher, gluten free, sugar free, vegan, and Halal. The user may manually define and/or select the user interface parameters.]); and
generating an initial prompt for the large language model, wherein the initial prompt includes a description of the recipe, a list of the plurality of ingredients for the recipe, and a request to change a dietary attribute of the recipe (Figs. 1 and 4; ¶¶0146-0148[At 404, the text-based food-recipe is converted into a target food-recipe data structure storing a representation of the text-based food-recipe. The target food-recipe data structure stores a set of ingredients, and instructions for preparation of the respective food-recipe… The target food-recipe data structure may be encoded for feeding into the input layer of the trained neural network, as described herein with reference to act 104 of FIG. 1… A 406, a selection of one or more ingredients appearing within the set of ingredients of the target food-recipe data structure is received. The ingredient is selected for substitution] in view of ¶0058[The neural network enables identification of substitute ingredients by consideration of the recipe as a whole, and/or the context of the recipe, since for example, not every ingredient substitute is suitable for every recipe. Different recipes having different contexts may require a different suitable substitute ingredient.]);
wherein receiving the instruction to identify the alternative ingredient for a particular ingredient of the plurality of ingredients of the recipe comprises parsing a response of the large language model to the particular ingredient to be substituted with the alternative ingredient (¶0151[At 408, one or more adjusted food-recipe data structures are computed. Each adjusted food-recipe data structure includes a predefined textual code that replaces one of the selected text-based ingredients for substitution] in view of ¶0067[the GUI presents the text-based food-recipe, and dynamically replaces each instance of a selected ingredient within the text-based food recipe with the substitute ingredient determined based on output of the neural network]).
Although Rapaport disclose generating a prompt for a model, Rapaport does not explicitly disclose a request to identify which of the plurality of ingredients are inconsistent with the request to change an attribute of the recipe.
Although Rapaport disclose generating a prompt for a model, Rapaport does not explicitly disclose a request parsing the response of a model to the initial prompt to identify the ingredient to be substituted.
However, Neumann teaches identifying ingredients that are inconsistent with a dietary request using machine learning (Fig. 1; ¶0041[Still referring to FIG. 1, alimentary instruction label learner 114 may be designed and configured to generate at least an alimentary instruction set by creating at least a first machine-learning model 116 relating first dietary request data 106 to alimentary labels using the training set 104 and generating the at least an alimentary instruction set using the first machine-learning model 116; at least a first machine-learning model 116 may include one or more models that determine a mathematical relationship between first dietary request data 106 and alimentary labels… Alimentary instruction set may include meals, foods, food groups, ingredients, supplements and the like that may be compatible with at least a dietary request. For example, alimentary instruction set may include a list of three possible meals that may be compatible with at least a dietary request for a dairy free diet]).
The method of Neumann is applicable to the method of Rapaport as they share characteristics and capabilities, namely, they are both targeted to recipes and ingredients. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the substitution of ingredients in a recipe as disclosed by Rapaport to include identifying ingredients that are inconsistent with a dietary request as taught by Neumann. One of ordinary skill in the art would have been motivated to expand the method of Rapaport in order to determine relationships between elements of dietary data, in combination with or instead of alimentary labels (¶0055).
Regarding Claim 5, Rapaport in view of Neumann in view of Silvain teaches the method of claim 1, Rapaport discloses further comprising: receiving, from the user device, a selection of the user-selectable option to add one or more of the plurality of ingredients, including the alternative ingredient (Figs. 2 and 4[element 414]; ¶0019[the selected at least one text-based ingredient for substitution is automatically substituted within the GUI with the selected at least one substitute ingredient indication] in view of ¶0157[At 416, the substitute ingredient (optional text-based version) is provided, for example, transmitted over network 210 to client terminal 208. The substitute ingredient may be presented on a display (e.g. of the client terminal) optionally within the GUI, and/or automatically substituted for the selected ingredients in the text-based food-recipe. The adjusted text-based food-recipe may be transmitted to the client terminal for presentation, and/or stored as an adjusted recipe, for example, a vegan version of a meat recipe, and/or an allergy free version of an allergy prone recipe]);
identifying a plurality of items in an online catalog that correspond to each of the plurality of ingredients (¶0027[receiving by the computer system in communication with an ingredient-substitution dataset, a plurality of ingredient substitution data structures each corresponding to one of the selected at least one ingredient, each ingredient substitution data structure storing at least two ingredients that are substitutes for each other, identifying, within the selected at least one sample food-recipe data structure, at least one certain ingredient stored in the ingredient substitution data structure storing one of the selected ingredients, and providing an indication of substitution of the selected at least one ingredient with the at least one certain ingredient, for the target food-recipe data structure.]); and
sending, to the user device, a confirmation interface that includes a user-selectable option to confirm the plurality of items, wherein the user device displays the confirmation interface (Figs. 2 and 4[element 414]; ¶0157[At 416, the substitute ingredient (optional text-based version) is provided, for example, transmitted over network 210 to client terminal 208. The substitute ingredient may be presented on a display (e.g. of the client terminal) optionally within the GUI, and/or automatically substituted for the selected ingredients in the text-based food-recipe. The adjusted text-based food-recipe may be transmitted to the client terminal for presentation, and/or stored as an adjusted recipe, for example, a vegan version of a meat recipe, and/or an allergy free version of an allergy prone recipe]).
Although Rapaport discloses sending a user interface that identifies a recipe with user-selectable options to add ingredients, Rapaport does not explicitly disclose adding ingredients to an order and confirming an order for items.
However, Neumann teaches adding ingredients to an order (¶0054[User location including geographic location of a user may be utilized to generate transport request 124 that may contain orders including ingredients or selections that may be available to a user in a certain geographical location. For example, a user with an alimentary instruction set that contains a recommendation to consume dairy products may receive transport request 124 including an order for yogurts produced within a certain radius of the geolocation.]).
The method of Neumann is applicable to the method of Rapaport as they share characteristics and capabilities, namely, they are both targeted to recipes and ingredients. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the substitution of ingredients in a recipe as disclosed by Rapaport to include ordering ingredients as taught by Neumann. One of ordinary skill in the art would have been motivated to expand the method of Rapaport in order to determine relationships between elements of dietary data, in combination with or instead of alimentary labels (¶0055).
Regarding Claim 9, Rapaport discloses a computer program product comprising a non-transitory computer readable storage medium having instructions encoded thereon that, when executed by a processor of a computer system, cause the computer system to perform steps comprising (Fig. 2; ¶0071):
sending, to a user device, a user interface that identifies a recipe and lists a plurality of ingredients for the recipe, wherein the user interface includes a user-selectable option to add one or more of the plurality of ingredients (Fig. 2[elements 204 and 220], Fig. 4; ¶¶0145-0150[At 402, a text-based food-recipe is received by computing device 204. The text-based recipe may be… a user interface of client terminal 208 (e.g., via a GUI) over network 210, transmitted from server 212 over network 210, and/or from a storage device storing text-based food-recipes… At 406, a selection of one or more ingredients appearing within the set of ingredients of the target food-recipe data structure is received… The selection may be made manually, for example, by a user manually selecting (e.g., clicking, hovering a pointer over, clicking within a box near) on the ingredient via a GUI on client terminal 208.]);
receiving an instruction to identify an alternative ingredient to substitute for a particular ingredient of the plurality of ingredients of the recipe (Fig. 4[element 406]; ¶¶0148-0150[At 406, a selection of one or more ingredients appearing within the set of ingredients of the target food-recipe data structure is received… The selection may be made manually, for example, by a user manually selecting] in view of ¶0143[Reference is now made to FIG. 4, which is a flowchart of an exemplary method of computing a substitute for one or more ingredients in a text-based food-recipe by the trained neural network]);
generating a prompt for a large language model, wherein the prompt includes: a description of the recipe, a description of the particular ingredient to be substituted, and a request to suggest a different ingredient to substitute for the particular ingredient in the recipe (Figs. 1 and 4; ¶¶0146-0148[At 404, the text-based food-recipe is converted into a target food-recipe data structure storing a representation of the text-based food-recipe. The target food-recipe data structure stores a set of ingredients, and instructions for preparation of the respective food-recipe… The target food-recipe data structure may be encoded for feeding into the input layer of the trained neural network, as described herein with reference to act 104 of FIG. 1… A 406, a selection of one or more ingredients appearing within the set of ingredients of the target food-recipe data structure is received. The ingredient is selected for substitution] in view of ¶0058[The neural network enables identification of substitute ingredients by consideration of the recipe as a whole, and/or the context of the recipe, since for example, not every ingredient substitute is suitable for every recipe. Different recipes having different contexts may require a different suitable substitute ingredient.]);
providing the prompt to the large language model to obtain an output therefrom (¶0147[The target food-recipe data structure may be encoded for feeding into the input layer of the trained neural network, as described herein with reference to act 104 of FIG. 1] in view of ¶0067[the GUI presents the text-based food-recipe, and dynamically replaces each instance of a selected ingredient within the text-based food recipe with the substitute ingredient determined based on output of the neural network]);
parsing, from the output of the large language model, the alternative ingredient for the recipe (¶0151[At 408, one or more adjusted food-recipe data structures are computed. Each adjusted food-recipe data structure includes a predefined textual code that replaces one of the selected text-based ingredients for substitution] in view of ¶0067[the GUI presents the text-based food-recipe, and dynamically replaces each instance of a selected ingredient within the text-based food recipe with the substitute ingredient determined based on output of the neural network]);
updating the user interface, wherein the user interface includes the alternative ingredient (Fig. 4; ¶0157[At 416, the substitute ingredient (optional text-based version) is provided, for example, transmitted over network 210 to client terminal 208. The substitute ingredient may be presented on a display (e.g. of the client terminal) optionally within the GUI, and/or automatically substituted for the selected ingredients in the text-based food-recipe. The adjusted text-based food-recipe may be transmitted to the client terminal for presentation, and/or stored as an adjusted recipe, for example, a vegan version of a meat recipe, and/or an allergy free version of an allergy prone recipe]);
sending, to the user device, the user interface, wherein the user device presents the user interface with the user-selectable option to add one or more of the plurality of ingredients, including the alternative ingredient (Figs. 2 and 4[element 414]; ¶0019[the selected at least one text-based ingredient for substitution is automatically substituted within the GUI with the selected at least one substitute ingredient indication] in view of ¶0157[At 416, the substitute ingredient (optional text-based version) is provided, for example, transmitted over network 210 to client terminal 208. The substitute ingredient may be presented on a display (e.g. of the client terminal) optionally within the GUI, and/or automatically substituted for the selected ingredients in the text-based food-recipe. The adjusted text-based food-recipe may be transmitted to the client terminal for presentation, and/or stored as an adjusted recipe, for example, a vegan version of a meat recipe, and/or an allergy free version of an allergy prone recipe]);
a user interaction with the user interface, the user interaction including an indication about whether the user-selectable option to add one or more of the plurality of ingredients, including the alternative ingredient, was selected (¶0013[For example, the user may dynamically select the ingredient for substitution from a visually presented target food-recipe displayed within a GUI. All instances of the selected ingredient within the food-recipe may be dynamically adjusted within the GUI. The user may select different ingredients for substitution to quickly change the recipe.]),
wherein the user interaction (Fig. 1; ¶0013); and
the large language model by providing a prompt (Figs. 1 and 4; ¶¶0146-0148[At 404, the text-based food-recipe is converted into a target food-recipe data structure storing a representation of the text-based food-recipe. The target food-recipe data structure stores a set of ingredients, and instructions for preparation of the respective food-recipe… The target food-recipe data structure may be encoded for feeding into the input layer of the trained neural network, as described herein with reference to act 104 of FIG. 1… A 406, a selection of one or more ingredients appearing within the set of ingredients of the target food-recipe data structure is received. The ingredient is selected for substitution] in view of ¶0058[The neural network enables identification of substitute ingredients by consideration of the recipe as a whole, and/or the context of the recipe, since for example, not every ingredient substitute is suitable for every recipe. Different recipes having different contexts may require a different suitable substitute ingredient.]; Examiner notes that ¶0038 of the instant specification states, “As used herein, machine-learning model is used interchangeably with "large language model."),
wherein the prompt includes the as a first portion of the prompt and the user interaction as a second portion of the prompt (Figs. 1 and 4; ¶¶0146-0148[At 404, the text-based food-recipe is converted into a target food-recipe data structure storing a representation of the text-based food-recipe. The target food-recipe data structure stores a set of ingredients, and instructions for preparation of the respective food-recipe… The target food-recipe data structure may be encoded for feeding into the input layer of the trained neural network, as described herein with reference to act 104 of FIG. 1… A 406, a selection of one or more ingredients appearing within the set of ingredients of the target food-recipe data structure is received. The ingredient is selected for substitution] in view of ¶0058[The neural network enables identification of substitute ingredients by consideration of the recipe as a whole, and/or the context of the recipe, since for example, not every ingredient substitute is suitable for every recipe. Different recipes having different contexts may require a different suitable substitute ingredient.]; Examiner notes that ¶0038 of the instant specification states, “As used herein, machine-learning model is used interchangeably with "large language model.").
Although Rapaport discloses sending a user interface that identifies a recipe with user-selectable options to add ingredients, Rapaport does not explicitly disclose adding ingredients to an order and adding alternative ingredients to an order and adding to an order.
However, Neumann teaches adding ingredients to an order (¶0054[User location including geographic location of a user may be utilized to generate transport request 124 that may contain orders including ingredients or selections that may be available to a user in a certain geographical location. For example, a user with an alimentary instruction set that contains a recommendation to consume dairy products may receive transport request 124 including an order for yogurts produced within a certain radius of the geolocation.]).
The system of Neumann is applicable to the system of Rapaport as they share characteristics and capabilities, namely, they are both targeted to recipes and ingredients. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the substitution of ingredients in a recipe as disclosed by Rapaport to include ordering ingredients as taught by Neumann. One of ordinary skill in the art would have been motivated to expand the system of Rapaport in order to determine relationships between elements of dietary data, in combination with or instead of alimentary labels (¶0055).
Although Rapaport discloses a user interaction, Rapaport in view of Neumann does not explicitly teach logging an interaction, wherein the interaction is included in additional training examples and tuning, based in part on the additional training examples and providing for re-training the large language model wherein the prompt includes the additional training examples.
However, Silvain teaches logging user interactions in order to re-train and tune a machine learning model based on the interactions (Figs. 3-4; ¶0034[Furthermore, the engine module 130 includes a training and optimization module 210 configured to enable administrators to fine-tune the large language model (LLM) based on insights generated from data analytics and to reevaluate facets and merchandizing using the updated large language model (LLM). As used herein, the term “insights” refer to the actionable findings obtained from evaluating user interactions, performance metrics, and system data. Fine-tuning involves adjusting the LLM's parameters and algorithms to improve its ability to generate relevant and contextually accurate responses based on updated information. Additionally, the training and optimization module 210 facilitates the re-evaluation of product facets and merchandising strategies by leveraging the updated LLM. Also, the term “merchandising” involves the strategies used to present and promote products. By applying the refined LLM to these elements, the training and optimization module 210 ensures that product categorizations and promotional tactics remain aligned with current customer preferences and trends. This ongoing process of training and optimization ensures that the system continuously evolves and improves, providing a more personalized and effective shopping experience.]).
The system of Silvain is applicable to the system of Rapaport in view of Neumann as they share characteristics and capabilities, namely, they are all targeted to searching for products. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the substitution of ingredients in a recipe as taught by Rapaport in view of Neumann to include logging user interactions and tuning a machine learning model as taught by Silvain. One of ordinary skill in the art would have been motivated to expand the system of Rapaport in view of Neumann in order to personalize a shopping experience in a conversational commerce platform (Abstract).
Regarding Claim 10, Rapaport in view of Neumann in view of Silvain teaches the computer program product of claim 9, Rapaport discloses wherein sending the user interface that identifies a recipe and lists a plurality of ingredients for the recipe comprises including, in the user interface, a selectable interface element to change a dietary attribute of the recipe (¶0150[the user profile may include personal preferences of the user, including ingredients that user prefers to avoid and/or ingredients that use like. Exemplary user interface parameters include one or more of: dairy free, genetically engineered free, organic, low carb, Eatwell Apple, contains nuts, vegetarian, kosher, gluten free, sugar free, vegan, and Halal. The user may manually define and/or select the user interface parameters.] in view of ¶¶0066-0067[the ingredient substitution may be according to a personal preference of the user and/or allergy profile of the user]).
Regarding Claim 11, Rapaport in view of Neumann in view of Silvain teaches the computer program product of claim 10, Rapaport discloses further comprising encoded instructions that when executed cause the computer system to perform steps comprising: receiving a selection of the selectable interface element to change a dietary attribute of the recipe (¶0150[the user profile may include personal preferences of the user, including ingredients that user prefers to avoid and/or ingredients that use like. Exemplary user interface parameters include one or more of: dairy free, genetically engineered free, organic, low carb, Eatwell Apple, contains nuts, vegetarian, kosher, gluten free, sugar free, vegan, and Halal. The user may manually define and/or select the user interface parameters.]);
wherein generating the prompt for the large language model comprises including, in the prompt, a request to suggest the different ingredient to substitute for the particular ingredient in the recipe in a way that is consistent with the request to change a dietary attribute of the recipe (Fig. 1; ¶0213[Referring now back to FIG. 1, at 112, the multi-dimensional representation of the target food-recipe data structure computed by the trained neural network is provided as input to code instructions for performing collaborative filtering. The collaborative filtering code, given past information of a population of users' preference information for a space of objects represented by a vector (i.e., ƒ(r)), outputs recommendations for objects for a user (based on the user's past preference information)] in view of ¶0066[the ingredient substitution may be according to a personal preference of the user and/or allergy profile of the user.] in view of ¶0150).
Regarding Claim 12, Rapaport in view of Neumann in view of Silvain teaches the computer program product of claim 10, Rapaport discloses further comprising encoded instructions that when executed cause the computer system to perform steps comprising: receiving a selection of the selectable interface element to change a dietary attribute of the recipe (¶0150[the user profile may include personal preferences of the user, including ingredients that user prefers to avoid and/or ingredients that use like. Exemplary user interface parameters include one or more of: dairy free, genetically engineered free, organic, low carb, Eatwell Apple, contains nuts, vegetarian, kosher, gluten free, sugar free, vegan, and Halal. The user may manually define and/or select the user interface parameters.]); and
generating an initial prompt for the large language model, wherein the initial prompt includes a description of the recipe, a list of the plurality of ingredients for the recipe, and a request to change a dietary attribute of the recipe (Figs. 1 and 4; ¶¶0146-0148[At 404, the text-based food-recipe is converted into a target food-recipe data structure storing a representation of the text-based food-recipe. The target food-recipe data structure stores a set of ingredients, and instructions for preparation of the respective food-recipe… The target food-recipe data structure may be encoded for feeding into the input layer of the trained neural network, as described herein with reference to act 104 of FIG. 1… A 406, a selection of one or more ingredients appearing within the set of ingredients of the target food-recipe data structure is received. The ingredient is selected for substitution] in view of ¶0058[The neural network enables identification of substitute ingredients by consideration of the recipe as a whole, and/or the context of the recipe, since for example, not every ingredient substitute is suitable for every recipe. Different recipes having different contexts may require a different suitable substitute ingredient.]);
wherein receiving the instruction to identify the alternative ingredient for a particular ingredient of the plurality of ingredients of the recipe comprises parsing a response of the large language model to the particular ingredient to be substituted with the alternative ingredient (¶0151[At 408, one or more adjusted food-recipe data structures are computed. Each adjusted food-recipe data structure includes a predefined textual code that replaces one of the selected text-based ingredients for substitution] in view of ¶0067[the GUI presents the text-based food-recipe, and dynamically replaces each instance of a selected ingredient within the text-based food recipe with the substitute ingredient determined based on output of the neural network]).
Although Rapaport disclose generating a prompt for a model, Rapaport does not explicitly disclose a request to identify which of the plurality of ingredients are inconsistent with the request to change an attribute of the recipe.
Although Rapaport disclose generating a prompt for a model, Rapaport does not explicitly disclose a request parsing the response of a model to the initial prompt to identify the ingredient to be substituted.
However, Neumann teaches identifying ingredients that are inconsistent with a dietary request using machine learning (Fig. 1; ¶0041[Still referring to FIG. 1, alimentary instruction label learner 114 may be designed and configured to generate at least an alimentary instruction set by creating at least a first machine-learning model 116 relating first dietary request data 106 to alimentary labels using the training set 104 and generating the at least an alimentary instruction set using the first machine-learning model 116; at least a first machine-learning model 116 may include one or more models that determine a mathematical relationship between first dietary request data 106 and alimentary labels… Alimentary instruction set may include meals, foods, food groups, ingredients, supplements and the like that may be compatible with at least a dietary request. For example, alimentary instruction set may include a list of three possible meals that may be compatible with at least a dietary request for a dairy free diet]).
The system of Neumann is applicable to the system of Rapaport as they share characteristics and capabilities, namely, they are both targeted to recipes and ingredients. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the substitution of ingredients in a recipe as disclosed by Rapaport to include identifying ingredients that are inconsistent with a dietary request as taught by Neumann. One of ordinary skill in the art would have been motivated to expand the system of Rapaport in order to determine relationships between elements of dietary data, in combination with or instead of alimentary labels (¶0055).
Regarding Claim 13, Rapaport in view of Neumann in view of Silvain teaches the computer program product of claim 9, Rapaport discloses wherein the instructions for processing output of the large language model, the output including one or more alternative ingredients cause the computer system to perform steps comprising: receiving, from the user device, a selection of the user-selectable option to add one or more of the plurality of ingredients, including the alternative ingredient (Figs. 2 and 4[element 414]; ¶0019[the selected at least one text-based ingredient for substitution is automatically substituted within the GUI with the selected at least one substitute ingredient indication] in view of ¶0157[At 416, the substitute ingredient (optional text-based version) is provided, for example, transmitted over network 210 to client terminal 208. The substitute ingredient may be presented on a display (e.g. of the client terminal) optionally within the GUI, and/or automatically substituted for the selected ingredients in the text-based food-recipe. The adjusted text-based food-recipe may be transmitted to the client terminal for presentation, and/or stored as an adjusted recipe, for example, a vegan version of a meat recipe, and/or an allergy free version of an allergy prone recipe]);
identifying a plurality of items in an online catalog that correspond to each of the plurality of ingredients (¶0027[receiving by the computer system in communication with an ingredient-substitution dataset, a plurality of ingredient substitution data structures each corresponding to one of the selected at least one ingredient, each ingredient substitution data structure storing at least two ingredients that are substitutes for each other, identifying, within the selected at least one sample food-recipe data structure, at least one certain ingredient stored in the ingredient substitution data structure storing one of the selected ingredients, and providing an indication of substitution of the selected at least one ingredient with the at least one certain ingredient, for the target food-recipe data structure.]); and
sending, to the user device, a confirmation interface that includes a user-selectable option to confirm the plurality of items, wherein the user device displays the confirmation interface (Figs. 2 and 4[element 414]; ¶0157[At 416, the substitute ingredient (optional text-based version) is provided, for example, transmitted over network 210 to client terminal 208. The substitute ingredient may be presented on a display (e.g. of the client terminal) optionally within the GUI, and/or automatically substituted for the selected ingredients in the text-based food-recipe. The adjusted text-based food-recipe may be transmitted to the client terminal for presentation, and/or stored as an adjusted recipe, for example, a vegan version of a meat recipe, and/or an allergy free version of an allergy prone recipe]).
Although Rapaport discloses sending a user interface that identifies a recipe with user-selectable options to add ingredients, Rapaport does not explicitly disclose adding ingredients to an order and confirming an order for items.
However, Neumann teaches adding ingredients to an order (¶0054[User location including geographic location of a user may be utilized to generate transport request 124 that may contain orders including ingredients or selections that may be available to a user in a certain geographical location. For example, a user with an alimentary instruction set that contains a recommendation to consume dairy products may receive transport request 124 including an order for yogurts produced within a certain radius of the geolocation.]).
The system of Neumann is applicable to the system of Rapaport as they share characteristics and capabilities, namely, they are both targeted to recipes and ingredients. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the substitution of ingredients in a recipe as disclosed by Rapaport to include ordering ingredients as taught by Neumann. One of ordinary skill in the art would have been motivated to expand the system of Rapaport in order to determine relationships between elements of dietary data, in combination with or instead of alimentary labels (¶0055).
Regarding Claim 17, Rapaport discloses a computer system comprising: a processor; and a non-transitory computer readable storage medium having instructions encoded thereon that, when executed by the processor, cause the computer system to perform steps comprising (Fig. 2; ¶0071):
sending, to a user device, a user interface that identifies a recipe and lists a plurality of ingredients for the recipe, wherein the user interface includes a user-selectable option to add one or more of the plurality of ingredients (Fig. 2[elements 204 and 220], Fig. 4; ¶¶0145-0150[At 402, a text-based food-recipe is received by computing device 204. The text-based recipe may be… a user interface of client terminal 208 (e.g., via a GUI) over network 210, transmitted from server 212 over network 210, and/or from a storage device storing text-based food-recipes… At 406, a selection of one or more ingredients appearing within the set of ingredients of the target food-recipe data structure is received… The selection may be made manually, for example, by a user manually selecting (e.g., clicking, hovering a pointer over, clicking within a box near) on the ingredient via a GUI on client terminal 208.]);
receiving an instruction to identify an alternative ingredient to substitute for a particular ingredient of the plurality of ingredients of the recipe (Fig. 4[element 406]; ¶¶0148-0150[At 406, a selection of one or more ingredients appearing within the set of ingredients of the target food-recipe data structure is received… The selection may be made manually, for example, by a user manually selecting] in view of ¶0143[Reference is now made to FIG. 4, which is a flowchart of an exemplary method of computing a substitute for one or more ingredients in a text-based food-recipe by the trained neural network]);
generating a prompt for a large language model, wherein the prompt includes: a description of the recipe, a description of the particular ingredient to be substituted, and a request to suggest a different ingredient to substitute for the particular ingredient in the recipe (Figs. 1 and 4; ¶¶0146-0148[At 404, the text-based food-recipe is converted into a target food-recipe data structure storing a representation of the text-based food-recipe. The target food-recipe data structure stores a set of ingredients, and instructions for preparation of the respective food-recipe… The target food-recipe data structure may be encoded for feeding into the input layer of the trained neural network, as described herein with reference to act 104 of FIG. 1… A 406, a selection of one or more ingredients appearing within the set of ingredients of the target food-recipe data structure is received. The ingredient is selected for substitution] in view of ¶0058[The neural network enables identification of substitute ingredients by consideration of the recipe as a whole, and/or the context of the recipe, since for example, not every ingredient substitute is suitable for every recipe. Different recipes having different contexts may require a different suitable substitute ingredient.]);
providing the prompt to the large language model to obtain an output therefrom (¶0147[The target food-recipe data structure may be encoded for feeding into the input layer of the trained neural network, as described herein with reference to act 104 of FIG. 1] in view of ¶0067[the GUI presents the text-based food-recipe, and dynamically replaces each instance of a selected ingredient within the text-based food recipe with the substitute ingredient determined based on output of the neural network]);
parsing, from the output of the large language model, the alternative ingredient for the recipe (¶0151[At 408, one or more adjusted food-recipe data structures are computed. Each adjusted food-recipe data structure includes a predefined textual code that replaces one of the selected text-based ingredients for substitution] in view of ¶0067[the GUI presents the text-based food-recipe, and dynamically replaces each instance of a selected ingredient within the text-based food recipe with the substitute ingredient determined based on output of the neural network]);
updating the user interface, wherein the user interface includes the alternative ingredient (Fig. 4; ¶0157[At 416, the substitute ingredient (optional text-based version) is provided, for example, transmitted over network 210 to client terminal 208. The substitute ingredient may be presented on a display (e.g. of the client terminal) optionally within the GUI, and/or automatically substituted for the selected ingredients in the text-based food-recipe. The adjusted text-based food-recipe may be transmitted to the client terminal for presentation, and/or stored as an adjusted recipe, for example, a vegan version of a meat recipe, and/or an allergy free version of an allergy prone recipe]); and
sending, to the user device, the user interface, wherein the user device presents the user interface with the user-selectable option to add one or more of the plurality of ingredients, including the alternative ingredient (Figs. 2 and 4[element 414]; ¶0019[the selected at least one text-based ingredient for substitution is automatically substituted within the GUI with the selected at least one substitute ingredient indication] in view of ¶0157[At 416, the substitute ingredient (optional text-based version) is provided, for example, transmitted over network 210 to client terminal 208. The substitute ingredient may be presented on a display (e.g. of the client terminal) optionally within the GUI, and/or automatically substituted for the selected ingredients in the text-based food-recipe. The adjusted text-based food-recipe may be transmitted to the client terminal for presentation, and/or stored as an adjusted recipe, for example, a vegan version of a meat recipe, and/or an allergy free version of an allergy prone recipe]);
a user interaction with the user interface, the user interaction including an indication about whether the user-selectable option to add one or more of the plurality of ingredients, including the alternative ingredient was selected, wherein the user interaction (Fig. 1; ¶0013[For example, the user may dynamically select the ingredient for substitution from a visually presented target food-recipe displayed within a GUI. All instances of the selected ingredient within the food-recipe may be dynamically adjusted within the GUI. The user may select different ingredients for substitution to quickly change the recipe.]); and
the large language model by providing a prompt (Figs. 1 and 4; ¶¶0146-0148[At 404, the text-based food-recipe is converted into a target food-recipe data structure storing a representation of the text-based food-recipe. The target food-recipe data structure stores a set of ingredients, and instructions for preparation of the respective food-recipe… The target food-recipe data structure may be encoded for feeding into the input layer of the trained neural network, as described herein with reference to act 104 of FIG. 1… A 406, a selection of one or more ingredients appearing within the set of ingredients of the target food-recipe data structure is received. The ingredient is selected for substitution] in view of ¶0058[The neural network enables identification of substitute ingredients by consideration of the recipe as a whole, and/or the context of the recipe, since for example, not every ingredient substitute is suitable for every recipe. Different recipes having different contexts may require a different suitable substitute ingredient.]; Examiner notes that ¶0038 of the instant specification states, “As used herein, machine-learning model is used interchangeably with "large language model."),
wherein the prompt includes the as a first portion of the prompt and the user interaction as a second portion of the prompt (Figs. 1 and 4; ¶¶0146-0148[At 404, the text-based food-recipe is converted into a target food-recipe data structure storing a representation of the text-based food-recipe. The target food-recipe data structure stores a set of ingredients, and instructions for preparation of the respective food-recipe… The target food-recipe data structure may be encoded for feeding into the input layer of the trained neural network, as described herein with reference to act 104 of FIG. 1… A 406, a selection of one or more ingredients appearing within the set of ingredients of the target food-recipe data structure is received. The ingredient is selected for substitution] in view of ¶0058[The neural network enables identification of substitute ingredients by consideration of the recipe as a whole, and/or the context of the recipe, since for example, not every ingredient substitute is suitable for every recipe. Different recipes having different contexts may require a different suitable substitute ingredient.]; Examiner notes that ¶0038 of the instant specification states, “As used herein, machine-learning model is used interchangeably with "large language model.").
Although Rapaport discloses sending a user interface that identifies a recipe with user-selectable options to add ingredients, Rapaport does not explicitly disclose adding ingredients to an order and adding alternative ingredients to an order and adding to an order.
However, Neumann teaches adding ingredients to an order (¶0054[User location including geographic location of a user may be utilized to generate transport request 124 that may contain orders including ingredients or selections that may be available to a user in a certain geographical location. For example, a user with an alimentary instruction set that contains a recommendation to consume dairy products may receive transport request 124 including an order for yogurts produced within a certain radius of the geolocation.]).
The system of Neumann is applicable to the system of Rapaport as they share characteristics and capabilities, namely, they are both targeted to recipes and ingredients. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the substitution of ingredients in a recipe as disclosed by Rapaport to include ordering ingredients as taught by Neumann. One of ordinary skill in the art would have been motivated to expand the system of Rapaport in order to determine relationships between elements of dietary data, in combination with or instead of alimentary labels (¶0055).
Although Rapaport discloses a user interaction, Rapaport in view of Neumann does not explicitly teach logging an interaction, wherein the interaction is included in additional training examples and tuning, based in part on the additional training examples and providing for re-training the large language model wherein the prompt includes the additional training examples.
However, Silvain teaches logging user interactions in order to re-train and tune a machine learning model based on the interactions (Figs. 3-4; ¶0034[Furthermore, the engine module 130 includes a training and optimization module 210 configured to enable administrators to fine-tune the large language model (LLM) based on insights generated from data analytics and to reevaluate facets and merchandizing using the updated large language model (LLM). As used herein, the term “insights” refer to the actionable findings obtained from evaluating user interactions, performance metrics, and system data. Fine-tuning involves adjusting the LLM's parameters and algorithms to improve its ability to generate relevant and contextually accurate responses based on updated information. Additionally, the training and optimization module 210 facilitates the re-evaluation of product facets and merchandising strategies by leveraging the updated LLM. Also, the term “merchandising” involves the strategies used to present and promote products. By applying the refined LLM to these elements, the training and optimization module 210 ensures that product categorizations and promotional tactics remain aligned with current customer preferences and trends. This ongoing process of training and optimization ensures that the system continuously evolves and improves, providing a more personalized and effective shopping experience.]).
The system of Silvain is applicable to the system of Rapaport in view of Neumann as they share characteristics and capabilities, namely, they are all targeted to searching for products. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the substitution of ingredients in a recipe as taught by Rapaport in view of Neumann to include logging user interactions and tuning a machine learning model as taught by Silvain. One of ordinary skill in the art would have been motivated to expand the system of Rapaport in view of Neumann in order to personalize a shopping experience in a conversational commerce platform (Abstract).
Regarding Claim 18, Rapaport in view of Neumann in view of Silvain teaches the computer system of claim 17, Rapaport discloses wherein sending the user interface that identifies a recipe and lists a plurality of ingredients for the recipe comprises including, in the user interface, a selectable interface element to change a dietary attribute of the recipe (¶0150[the user profile may include personal preferences of the user, including ingredients that user prefers to avoid and/or ingredients that use like. Exemplary user interface parameters include one or more of: dairy free, genetically engineered free, organic, low carb, Eatwell Apple, contains nuts, vegetarian, kosher, gluten free, sugar free, vegan, and Halal. The user may manually define and/or select the user interface parameters.] in view of ¶¶0066-0067[the ingredient substitution may be according to a personal preference of the user and/or allergy profile of the user]).
Regarding Claim 19, Rapaport in view of Neumann in view of Silvain teaches the computer system of claim 18, Rapaport discloses further comprising encoded instructions on the non-transitory computer readable storage medium that when executed cause the computer system to perform steps comprising: receiving a selection of the selectable interface element to change a dietary attribute of the recipe (¶0150[the user profile may include personal preferences of the user, including ingredients that user prefers to avoid and/or ingredients that use like. Exemplary user interface parameters include one or more of: dairy free, genetically engineered free, organic, low carb, Eatwell Apple, contains nuts, vegetarian, kosher, gluten free, sugar free, vegan, and Halal. The user may manually define and/or select the user interface parameters.]);
wherein generating the prompt for the large language model comprises including, in the prompt, a request to suggest the different ingredient to substitute for the particular ingredient in the recipe in a way that is consistent with the request to change a dietary attribute of the recipe (Fig. 1; ¶0213[Referring now back to FIG. 1, at 112, the multi-dimensional representation of the target food-recipe data structure computed by the trained neural network is provided as input to code instructions for performing collaborative filtering. The collaborative filtering code, given past information of a population of users' preference information for a space of objects represented by a vector (i.e., ƒ(r)), outputs recommendations for objects for a user (based on the user's past preference information)] in view of ¶0066[the ingredient substitution may be according to a personal preference of the user and/or allergy profile of the user.] in view of ¶0150).
Regarding Claim 20, Rapaport in view of Neumann in view of Silvain teaches the computer system of claim 18, further comprising encoded instructions on the non-transitory computer readable storage medium that when executed cause the computer system to perform steps comprising: receiving a selection of the selectable interface element to change a dietary attribute of the recipe (¶0150[the user profile may include personal preferences of the user, including ingredients that user prefers to avoid and/or ingredients that use like. Exemplary user interface parameters include one or more of: dairy free, genetically engineered free, organic, low carb, Eatwell Apple, contains nuts, vegetarian, kosher, gluten free, sugar free, vegan, and Halal. The user may manually define and/or select the user interface parameters.]); and
generating an initial prompt for the large language model, wherein the initial prompt includes a description of the recipe, a list of the plurality of ingredients for the recipe, and a request to change a dietary attribute of the recipe (Figs. 1 and 4; ¶¶0146-0148[At 404, the text-based food-recipe is converted into a target food-recipe data structure storing a representation of the text-based food-recipe. The target food-recipe data structure stores a set of ingredients, and instructions for preparation of the respective food-recipe… The target food-recipe data structure may be encoded for feeding into the input layer of the trained neural network, as described herein with reference to act 104 of FIG. 1… A 406, a selection of one or more ingredients appearing within the set of ingredients of the target food-recipe data structure is received. The ingredient is selected for substitution] in view of ¶0058[The neural network enables identification of substitute ingredients by consideration of the recipe as a whole, and/or the context of the recipe, since for example, not every ingredient substitute is suitable for every recipe. Different recipes having different contexts may require a different suitable substitute ingredient.]);
wherein receiving the instruction to identify the alternative ingredient for a particular ingredient of the plurality of ingredients of the recipe comprises parsing a response of the large language model to the particular ingredient to be substituted with the alternative ingredient (¶0151[At 408, one or more adjusted food-recipe data structures are computed. Each adjusted food-recipe data structure includes a predefined textual code that replaces one of the selected text-based ingredients for substitution] in view of ¶0067[the GUI presents the text-based food-recipe, and dynamically replaces each instance of a selected ingredient within the text-based food recipe with the substitute ingredient determined based on output of the neural network]).
Although Rapaport disclose generating a prompt for a model, Rapaport does not explicitly disclose a request to identify which of the plurality of ingredients are inconsistent with the request to change an attribute of the recipe.
Although Rapaport disclose generating a prompt for a model, Rapaport does not explicitly disclose a request parsing the response of a model to the initial prompt to identify the ingredient to be substituted.
However, Neumann teaches identifying ingredients that are inconsistent with a dietary request using machine learning (Fig. 1; ¶0041[Still referring to FIG. 1, alimentary instruction label learner 114 may be designed and configured to generate at least an alimentary instruction set by creating at least a first machine-learning model 116 relating first dietary request data 106 to alimentary labels using the training set 104 and generating the at least an alimentary instruction set using the first machine-learning model 116; at least a first machine-learning model 116 may include one or more models that determine a mathematical relationship between first dietary request data 106 and alimentary labels… Alimentary instruction set may include meals, foods, food groups, ingredients, supplements and the like that may be compatible with at least a dietary request. For example, alimentary instruction set may include a list of three possible meals that may be compatible with at least a dietary request for a dairy free diet]).
The system of Neumann is applicable to the system of Rapaport as they share characteristics and capabilities, namely, they are both targeted to recipes and ingredients. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the substitution of ingredients in a recipe as disclosed by Rapaport to include identifying ingredients that are inconsistent with a dietary request as taught by Neumann. One of ordinary skill in the art would have been motivated to expand the system of Rapaport in order to determine relationships between elements of dietary data, in combination with or instead of alimentary labels (¶0055).
Claim(s) 6, 7, 14, and 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Rapaport in view of Neumann in view of Silvain in view of Neumann et al., hereinafter, Neumann II (US 2023/0207136 A1 [previously cited]).
Regarding Claim 6, Rapaport in view of Neumann in view of Silvain teaches the method of claim 1, Rapaport discloses wherein generating the prompt for the large language model comprises: including, in the prompt, a request for a textual different ingredient is a suitable substitute for the particular ingredient in the recipe (Fig. 1; ¶0058[The neural network enables identification of substitute ingredients by consideration of the recipe as a whole, and/or the context of the recipe, since for example, not every ingredient substitute is suitable for every recipe. Different recipes having different contexts may require a different suitable substitute ingredient.] in view of ¶0131[General substitution ingredient-substitution data structures that store substitutes that are suitable for one recipe but not suitable for another recipe are not necessarily selected. For example, the ingredients {A,B} may be substitutes for a dairy based recipe, but unsuitable for a meat based recipe. The ingredients {B,C} may be substitutes for the meat based recipe, but not for the dairy based recipe.]).
Although Rapaport discloses a prompt for a model, Rapaport in view of Neumann in view of Silvain does not explicitly teach an explanation about why the different ingredient is suitable.
However, Neumann II teaches generating and displaying an explanation about why a combination of ingredients is suitable (¶0064[With continued reference to FIG. 1, at least a server 104 is configured to generate at least a vibrant compatibility plan 192 containing a sequencing instruction set wherein the sequencing instruction set contains at least an optimal combination of at least a first compatible food element and at least a second compatible food element as a function of the at least a desired dietary state. Sequencing instruction set may include information and/or data describing optimal combinations of foods and ingredients that a user may combine to create meals or that when combined together may optimize the nutrition of each other as a function of a user's desired dietary state. For instance and without limitation, sequencing instruction set may include information describing optimal combinations of a first compatible food element such as red kidney beans and a second compatible food element such as brown rice for a user with a desired dietary state of vegan diet.] in view of Claim 1[display the vibrant compatibility plan through a graphical user interface (GUI) of the user client device of the comparison]).
The method of Neumann II is applicable to the method of Rapaport in view of Neumann in view of Silvain as they share characteristics and capabilities, namely, they are all targeted to ordering products. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the substitution of ingredients in a recipe as taught by Rapaport in view of Neumann in view of Silvain to include an explanation about why an ingredient makes a suitable combination as taught by Neumann II. One of ordinary skill in the art would have been motivated to expand the method of Rapaport in view of Neumann in view of Silvain in order to output at least a compatible food element (Abstract).
Regarding Claim 7, Rapaport in view of Neumann in view of Silvain in view of Neumann II teaches the method of claim 6, Rapaport discloses wherein updating the user interface comprises: parsing, from the output of the large language model, the different ingredient is a suitable substitute for the particular ingredient in the recipe (¶0067[the GUI presents the text-based food-recipe, and dynamically replaces each instance of a selected ingredient within the text-based food recipe with the substitute ingredient determined based on output of the neural network]); and
including, in the user interface, the different ingredient is a suitable substitute for the particular ingredient in the recipe (Fig. 4; ¶0157[At 416, the substitute ingredient (optional text-based version) is provided, for example, transmitted over network 210 to client terminal 208. The substitute ingredient may be presented on a display (e.g. of the client terminal) optionally within the GUI, and/or automatically substituted for the selected ingredients in the text-based food-recipe. The adjusted text-based food-recipe may be transmitted to the client terminal for presentation, and/or stored as an adjusted recipe, for example, a vegan version of a meat recipe, and/or an allergy free version of an allergy prone recipe]).
Although Rapaport discloses parsing input from the model, Rapaport in view of Neumann in view of Silvain does not explicitly teach the textual explanation about why the different ingredient is a suitable substitute for a particular ingredient in a recipe.
Although Rapaport discloses updating a user interface, Rapaport in view of Neumann in view of Silvain does not explicitly teach including in the user interface, the textual explanation about why the different ingredient is a suitable substitute for a particular ingredient in a recipe.
However, Neumann II teaches generating and displaying an explanation about why a combination of ingredients is suitable (¶0064[With continued reference to FIG. 1, at least a server 104 is configured to generate at least a vibrant compatibility plan 192 containing a sequencing instruction set wherein the sequencing instruction set contains at least an optimal combination of at least a first compatible food element and at least a second compatible food element as a function of the at least a desired dietary state. Sequencing instruction set may include information and/or data describing optimal combinations of foods and ingredients that a user may combine to create meals or that when combined together may optimize the nutrition of each other as a function of a user's desired dietary state. For instance and without limitation, sequencing instruction set may include information describing optimal combinations of a first compatible food element such as red kidney beans and a second compatible food element such as brown rice for a user with a desired dietary state of vegan diet.] in view of Claim 1[display the vibrant compatibility plan through a graphical user interface (GUI) of the user client device of the comparison]).
The method of Neumann II is applicable to the method of Rapaport in view of Neumann in view of Silvain as they share characteristics and capabilities, namely, they are all targeted to ordering products. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the substitution of ingredients in a recipe as taught by Rapaport in view of Neumann in view of Silvain to include an explanation about why an ingredient makes a suitable combination as taught by Neumann II. One of ordinary skill in the art would have been motivated to expand the method of Rapaport in view of Neumann in view of Silvain in order to output at least a compatible food element (Abstract).
Regarding Claim 14, Rapaport in view of Neumann in view of Silvain teaches the computer program product of claim 9, Rapaport discloses wherein generating the prompt for the large language model comprises: including, in the prompt, a request for a textual different ingredient is a suitable substitute for the particular ingredient in the recipe (Fig. 1; ¶0058[The neural network enables identification of substitute ingredients by consideration of the recipe as a whole, and/or the context of the recipe, since for example, not every ingredient substitute is suitable for every recipe. Different recipes having different contexts may require a different suitable substitute ingredient.] in view of ¶0131[General substitution ingredient-substitution data structures that store substitutes that are suitable for one recipe but not suitable for another recipe are not necessarily selected. For example, the ingredients {A,B} may be substitutes for a dairy based recipe, but unsuitable for a meat based recipe. The ingredients {B,C} may be substitutes for the meat based recipe, but not for the dairy based recipe.]).
Although Rapaport discloses a prompt for a model, Rapaport in view of Neumann in view of Silvain does not explicitly teach an explanation about why the different ingredient is suitable.
However, Neumann II teaches generating and displaying an explanation about why a combination of ingredients is suitable (¶0064[With continued reference to FIG. 1, at least a server 104 is configured to generate at least a vibrant compatibility plan 192 containing a sequencing instruction set wherein the sequencing instruction set contains at least an optimal combination of at least a first compatible food element and at least a second compatible food element as a function of the at least a desired dietary state. Sequencing instruction set may include information and/or data describing optimal combinations of foods and ingredients that a user may combine to create meals or that when combined together may optimize the nutrition of each other as a function of a user's desired dietary state. For instance and without limitation, sequencing instruction set may include information describing optimal combinations of a first compatible food element such as red kidney beans and a second compatible food element such as brown rice for a user with a desired dietary state of vegan diet.] in view of Claim 1[display the vibrant compatibility plan through a graphical user interface (GUI) of the user client device of the comparison]).
The system of Neumann II is applicable to the system of Rapaport in view of Neumann in view of Silvain as they share characteristics and capabilities, namely, they are all targeted to ordering products. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the substitution of ingredients in a recipe as taught by Rapaport in view of Neumann in view of Silvain to include an explanation about why an ingredient makes a suitable combination as taught by Neumann II. One of ordinary skill in the art would have been motivated to expand the system of Rapaport in view of Neumann in view of Silvain in order to output at least a compatible food element (Abstract).
Regarding Claim 15, Rapaport in view of Neumann in view of Silvain in view of Neumann II teaches the computer program product of claim 14, Rapaport discloses wherein updating the user interface comprises:
parsing, from the output of the large language model, the different ingredient is a suitable substitute for the particular ingredient in the recipe (¶0067[the GUI presents the text-based food-recipe, and dynamically replaces each instance of a selected ingredient within the text-based food recipe with the substitute ingredient determined based on output of the neural network]); and
including, in the user interface, the different ingredient is a suitable substitute for the particular ingredient in the recipe (Fig. 4; ¶0157[At 416, the substitute ingredient (optional text-based version) is provided, for example, transmitted over network 210 to client terminal 208. The substitute ingredient may be presented on a display (e.g. of the client terminal) optionally within the GUI, and/or automatically substituted for the selected ingredients in the text-based food-recipe. The adjusted text-based food-recipe may be transmitted to the client terminal for presentation, and/or stored as an adjusted recipe, for example, a vegan version of a meat recipe, and/or an allergy free version of an allergy prone recipe]).
Although Rapaport discloses parsing input from the model, Rapaport in view of Neumann in view of Silvain does not explicitly teach the textual explanation about why the different ingredient is a suitable substitute for a particular ingredient in a recipe.
Although Rapaport discloses updating a user interface, Rapaport in view of Neumann in view of Silvain does not explicitly teach including in the user interface, the textual explanation about why the different ingredient is a suitable substitute for a particular ingredient in a recipe.
However, Neumann II teaches generating and displaying an explanation about why a combination of ingredients is suitable (¶0064[With continued reference to FIG. 1, at least a server 104 is configured to generate at least a vibrant compatibility plan 192 containing a sequencing instruction set wherein the sequencing instruction set contains at least an optimal combination of at least a first compatible food element and at least a second compatible food element as a function of the at least a desired dietary state. Sequencing instruction set may include information and/or data describing optimal combinations of foods and ingredients that a user may combine to create meals or that when combined together may optimize the nutrition of each other as a function of a user's desired dietary state. For instance and without limitation, sequencing instruction set may include information describing optimal combinations of a first compatible food element such as red kidney beans and a second compatible food element such as brown rice for a user with a desired dietary state of vegan diet.] in view of Claim 1[display the vibrant compatibility plan through a graphical user interface (GUI) of the user client device of the comparison]).
The system of Neumann II is applicable to the system of Rapaport in view of Neumann in view of Silvain as they share characteristics and capabilities, namely, they are all targeted to ordering products. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the substitution of ingredients in a recipe as taught by Rapaport in view of Neumann in view of Silvain to include an explanation about why an ingredient makes a suitable combination as taught by Neumann II. One of ordinary skill in the art would have been motivated to expand the system of Rapaport in view of Neumann in view of Silvain in order to output at least a compatible food element (Abstract).
Claim(s) 8 and 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Rapaport in view of Neumann in view of Silvain in view of Yip et al. (US 2025/0111290 A1 [previously cited]).
Regarding Claim 8, Rapaport in view of Neumann in view of Silvain teaches the method of claim 1, Rapaport discloses further comprising: a user interaction with the user interface, the user interaction including an indication about whether the user-selectable option to add one or more of the plurality of ingredients, including the alternative ingredient, was selected (Figs. 2 and 4[element 414]; ¶0019[the selected at least one text-based ingredient for substitution is automatically substituted within the GUI with the selected at least one substitute ingredient indication] in view of ¶0157[At 416, the substitute ingredient (optional text-based version) is provided, for example, transmitted over network 210 to client terminal 208. The substitute ingredient may be presented on a display (e.g. of the client terminal) optionally within the GUI, and/or automatically substituted for the selected ingredients in the text-based food-recipe. The adjusted text-based food-recipe may be transmitted to the client terminal for presentation, and/or stored as an adjusted recipe, for example, a vegan version of a meat recipe, and/or an allergy free version of an allergy prone recipe]);
adding a set of training examples (Figs. 1-3; ¶0116[At 104, a neural network is trained according to the food-recipe data structures, the ingredient data structures, and the ingredient substitution data structures. The neural network is trained to compute coordinates of a target food-recipe point within a multi-dimensional food-recipe space for an input of a target text-based food-recipe. The trained neural network 206B may be stored in storage device 206 and/or data repository 214.] in view of ¶0096[At 102, one or more datasets 214A-C (e.g., stored as databases, and/or a cluster of records) are accessed and/or created.]); and
the large language model using the set of training examples (Figs. 1-3; ¶0116[At 104, a neural network is trained according to the food-recipe data structures, the ingredient data structures, and the ingredient substitution data structures. The neural network is trained to compute coordinates of a target food-recipe point within a multi-dimensional food-recipe space for an input of a target text-based food-recipe. The trained neural network 206B may be stored in storage device 206 and/or data repository 214.] in view of ¶0096[At 102, one or more datasets 214A-C (e.g., stored as databases, and/or a cluster of records) are accessed and/or created.]).
Although Rapaport discloses a user interaction, Rapaport in view of Neumann in view of Silvain does not explicitly teach logging a user interaction and an indication to an order that was selected.
However, Yip et al., hereinafter, Yip, teaches logging user interactions including an order (Figs. 3-4; ¶0029[the user may provide user data, via the graphical user interface, indicating the ingredients they have used since they last purchased additional ingredients, the ingredients they have available to use, or indicate the meals they have made with the ingredients.] in view of ¶0093[The meal recommendation system 320 may correlate compiled data, analyze the compiled data, arrange the compiled data, generate derived data based on the compiled data, and store the compiled and derived data in a database such as the database 416.]).
Although Rapaport discloses a user interaction, Rapaport in view of Neumann in view of Silvain does not explicitly teach adding the user interaction to a set of training examples.
However, Yip teaches adding user interaction data to a set of training examples (¶0043[The fourth machine learning model may be trained by past user selections, from the user or other users. The fourth machine learning model may be trained to produce similar recommendations to what the user was looking to cook.])
Although Rapaport discloses a user interaction, Rapaport in view of Neumann in view of Silvain does not explicitly teach tuning a model.
However, Yip teaches tuning a model (¶0016[As the user selects recipes and meals, the machine learning models may be iteratively trained by the user's choices and behavior, and therefore, modify the user's food profile and other user data. This may be used to iteratively change the suggested outputs of the one or more machine learning models, and influence the recipes suggested to the user and other users] in view of ¶0026[The food profile of a user may evolve over time or change iteratively as more data is received regarding the user's tastes or the user's tastes change]).
The method of Yip is applicable to the method of Rapaport in view of Neumann in view of Silvain as they share characteristics and capabilities, namely, they are all targeted to ordering products. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the substitution of ingredients in a recipe as taught by Rapaport in view of Neumann in view of Silvain to include logging user interactions to train and tune a machine learning model as taught by Yip. One of ordinary skill in the art would have been motivated to expand the method of Rapaport in view of Neumann in view of Silvain in order to customize meals to individual user needs, palates, or based on ingredients a user has (¶0002).
Regarding Claim 16, Rapaport in view of Neumann in view of Silvain teaches the computer program product of claim 9, Rapaport discloses wherein the instructions for processing output of the large language model, the output including one or more alternative ingredients cause the computer system to perform steps comprising: a user interaction with the user interface, the user interaction including an indication about whether the user-selectable option to add one or more of the plurality of ingredients, including the alternative ingredient, was selected (Figs. 2 and 4[element 414]; ¶0019[the selected at least one text-based ingredient for substitution is automatically substituted within the GUI with the selected at least one substitute ingredient indication] in view of ¶0157[At 416, the substitute ingredient (optional text-based version) is provided, for example, transmitted over network 210 to client terminal 208. The substitute ingredient may be presented on a display (e.g. of the client terminal) optionally within the GUI, and/or automatically substituted for the selected ingredients in the text-based food-recipe. The adjusted text-based food-recipe may be transmitted to the client terminal for presentation, and/or stored as an adjusted recipe, for example, a vegan version of a meat recipe, and/or an allergy free version of an allergy prone recipe]);
adding a set of training examples (Figs. 1-3; ¶0116[At 104, a neural network is trained according to the food-recipe data structures, the ingredient data structures, and the ingredient substitution data structures. The neural network is trained to compute coordinates of a target food-recipe point within a multi-dimensional food-recipe space for an input of a target text-based food-recipe. The trained neural network 206B may be stored in storage device 206 and/or data repository 214.] in view of ¶0096[At 102, one or more datasets 214A-C (e.g., stored as databases, and/or a cluster of records) are accessed and/or created.]); and
the large language model using the set of training examples (Figs. 1-3; ¶0116[At 104, a neural network is trained according to the food-recipe data structures, the ingredient data structures, and the ingredient substitution data structures. The neural network is trained to compute coordinates of a target food-recipe point within a multi-dimensional food-recipe space for an input of a target text-based food-recipe. The trained neural network 206B may be stored in storage device 206 and/or data repository 214.] in view of ¶0096[At 102, one or more datasets 214A-C (e.g., stored as databases, and/or a cluster of records) are accessed and/or created.]).
Although Rapaport discloses a user interaction, Rapaport in view of Neumann in view of Silvain does not explicitly teach logging a user interaction and an indication to an order that was selected.
However, Yip teaches logging user interactions including an order (Figs. 3-4; ¶0029[the user may provide user data, via the graphical user interface, indicating the ingredients they have used since they last purchased additional ingredients, the ingredients they have available to use, or indicate the meals they have made with the ingredients.] in view of ¶0093[The meal recommendation system 320 may correlate compiled data, analyze the compiled data, arrange the compiled data, generate derived data based on the compiled data, and store the compiled and derived data in a database such as the database 416.]).
Although Rapaport discloses a user interaction, Rapaport in view of Neumann in view of Silvain does not explicitly teach adding the user interaction to a set of training examples.
However, Yip teaches adding user interaction data to a set of training examples (¶0043[The fourth machine learning model may be trained by past user selections, from the user or other users. The fourth machine learning model may be trained to produce similar recommendations to what the user was looking to cook.])
Although Rapaport discloses a user interaction, Rapaport in view of Neumann in view of Silvain does not explicitly teach tuning a model.
However, Yip teaches tuning a model (¶0016[As the user selects recipes and meals, the machine learning models may be iteratively trained by the user's choices and behavior, and therefore, modify the user's food profile and other user data. This may be used to iteratively change the suggested outputs of the one or more machine learning models, and influence the recipes suggested to the user and other users] in view of ¶0026[The food profile of a user may evolve over time or change iteratively as more data is received regarding the user's tastes or the user's tastes change]).
The system of Yip is applicable to the system of Rapaport in view of Neumann in view of Silvain as they share characteristics and capabilities, namely, they are all targeted to ordering products. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the substitution of ingredients in a recipe as taught by Rapaport in view of Neumann in view of Silvain to include logging user interactions to train and tune a machine learning model as taught by Yip. One of ordinary skill in the art would have been motivated to expand the system of Rapaport in view of Neumann in view of Silvain in order to customize meals to individual user needs, palates, or based on ingredients a user has (¶0002).
Response to Arguments
Applicant’s arguments on pages 13 and 14 of the remarks filed 05/08/2026, with respect to the previous 35 USC § 101 rejections have been fully considered but are not persuasive.
Applicant argues on pages 13 and 14 of the remarks that the amended claims provide a technical improvement and cites to ¶¶0081-0082 and ¶0112 for support. Examiner respectfully disagrees. The MPEP provides guidance on how to evaluate whether claims recite an improvement in the functioning of a computer or an improvement to other technology or technical field. For example, the MPEP states "the specification should be evaluated to determine if the disclosure provides sufficient details such that one of ordinary skill in the art would recognize the claimed invention as providing an improvement." The MPEP further states that "[t]he specification need not explicitly set forth the improvement, but it must describe the invention such that the improvement would be apparent to one of ordinary skill in the art," and that, "conversely, if the specification explicitly sets forth an improvement but in a conclusory manner the examiner should not determine the claim improves technology" (see MPEP 2106.04). That is, the claim includes the components or steps of the invention that provide the improvement described in the specification.
While the examiner acknowledges that improvements to the functioning of a computer or to any other technology or technical field may constitute integration into a practical application (see MPEP 2106.05(a)), the instant claims do not provide a technical improvement. Rather, the claims provide an improvement to the abstract idea of purchasing alternative ingredients of a recipe. This is also illustrated in Paragraph [0001] of the instant specification which discusses that the invention might provide improvements to ordering ingredients of a recipe. Furthermore, a method, performed, the method comprising: sending, to a user, a user interface that identifies a recipe and lists a plurality of ingredients for the recipe, wherein the user interface includes a user-selectable option to add one or more of the plurality of ingredients to an order; receiving an instruction to identify an alternative ingredient to substitute for a particular ingredient of the plurality of ingredients of the recipe; generating a prompt, wherein the prompt includes: a description of the recipe, a description of the particular ingredient to be substituted, and a request to suggest a different ingredient to substitute for the particular ingredient in the recipe; providing the prompt to obtain an output therefrom; parsing, from the output, the alternative ingredient for the recipe; updating the user interface, wherein the user interface includes the alternative ingredient; sending, to the user, the user interface, wherein the user device presents the user interface with the user-selectable option to add one or more of the plurality of ingredients, including the alternative ingredient, to an order; logging a user interaction with the user interface, the user interaction including an indication about whether the user-selectable option to add one or more of the plurality of ingredients, including the alternative ingredient, to an order was selected, wherein the user interaction is included in additional training examples; and tuning, based in part on the additional training examples, by providing a prompt, wherein the prompt includes the additional training examples as a first portion of the prompt and the user interaction as a second portion of the prompt as recited in amended claim 1 are encompassed by the abstract idea and the mere execution of the abstract idea on generic components which are recited at a high level of generality does not integrate the abstract idea into a practical application or provide a technical improvement. The additional elements of a user “device,” a “large language model,” and “re-training the large language model” are generic and high-level components and are described as such in the instant specification Fig. 1 and ¶¶0114-0117.
Accordingly, Examiner maintains that the invention is directed to a judicial exception without
significantly more. The claims recite an abstract idea. This judicial exception is not integrated into a practical application. The claim(s) do not include additional elements that are sufficient to amount to significantly more than the judicial exception. Thus the 35 USC §101 rejections are maintained.
Applicant’s arguments on pages 14 and 15 of the remarks filed 05/08/2026, with respect to the previous 35 USC § 103 rejections have been fully considered but are moot in view of the new 103 rejection of the amended claims.
Accordingly, references Rapaport, Neumann, Silvain, Neumann II, and Yip have been maintained and reference Silvain has been added in view of the claim amendments.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AHOORA LADONI whose email is Ahoora.Ladoni@uspto.gov and telephone number is (703) 756-5617. The examiner can normally be reached M-F 0900–1700 ET.
Examiner interviews are available via telephone, in-person and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/AHOORA LADONI/Examiner, Art Unit 3689
/KELLY S. CAMPEN/Primary Examiner, Art Unit 3691
Prosecution Insights