DETAILED ACTION
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 .
Status of Claims
This first action on the merits is in response to the application filed on January 24, 2024. Claims 1-20 are pending and have been examined.
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 claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
The steps for determining eligibility under 35 U.S.C. 101 can be found in the MPEP § 2106.03-2106.05.
Under Step 1, the claims are directed to statutory categories. Specifically, the method, as claimed in claims 1-10, is directed to a process. Additionally, the computer program product, as claimed in claims 11-19, is directed to an article of manufacture. Furthermore, the system, as claimed in claim 20, is directed to a machine.
While the claims fall within statutory categories, under Step 2A, Prong 1, the claimed invention recites the abstract idea of recipe recommendations. Specifically, representative claim 1 recites the abstract idea of:
receiving a request from a user to generate a set of recipes;
retrieving a set of user data associated with the user;
generating a first prompt to generate the set of recipes based at least in part on the request and the set of user data;
providing the first prompt to obtain a first textual output, the first textual output including the set of recipes;
extracting the set of recipes from the first textual output;
displaying a set of information describing each recipe of the set of recipes and a set of options to modify a recipe and to accept the recipe;
responsive to receiving an additional request to modify the recipe, performing a recipe modification process comprising:
generating a second prompt to modify the recipe based at least in part on the additional request, the set of information describing the recipe, and the set of user data associated with the user,
providing the second prompt to obtain a second textual output, the second textual output including a set of modified recipes,
extracting the set of modified recipes from the second textual output, and
updating to include the set of information describing each modified recipe of the set of modified recipes and the set of options to modify a modified recipe and to accept the modified recipe;
repeating the recipe modification process for each additional request received until a modified recipe is accepted;
responsive to receiving a selection of an accepted recipe, predicting an availability of each item of one or more items associated with the accepted recipe at a retailer location; and
updating to include an additional option to add a set of items of the one or more items associated with the accepted recipe to a shopping list associated with the user based at least in part on the predicted availability of each item.
Under Step 2A, Prong 1, it is necessary to evaluate whether the claim recites a judicial exception by referring to subject matter groupings articulated in the guidance. When considering MPEP §2106.04(a), the claims recite an abstract idea. For example, representative claim 1 recites the abstract idea of recommending recipes, as noted above. This concept is considered to be a certain method of organizing human activity. Certain methods of organizing human activity are defined in the MPEP as including “fundamental economic principles or practices (including hedging, insurance, mitigating risk); commercial or legal interactions (including agreements in the form of contracts; legal obligations; advertising, marketing or sales activities or behaviors; business relations); managing personal behavior or relationships or interactions between people (including social activities, teaching, and following rules or instructions).” MPEP §2106.04(a)(2) subsection II. In this case, the abstract idea recited in representative claim 1 is a certain method of organizing human activity because responsive to receiving a selection of an accepted recipe, predicting an availability of each item of one or more items associated with the accepted recipe at a retailer location; and updating to include an additional option to add a set of items of the one or more items associated with the accepted recipe to a shopping list associated with the user based at least in part on the predicted availability of each item is a sales activity. Thus, representative claim 1 recites an abstract idea.
The recited limitations of representative claim 1 also recite an abstract idea because they are considered to be mental processes. As described in the MPEP, mental processes are “concepts performed in the human mind (including an observation, evaluation, judgment, opinion)”. MPEP §2106.04(a)(2) subsection III. In this case, receiving a request from a user to generate a set of recipes; is a type of observation. Additionally, retrieving a set of user data associated with the user; generating a first prompt to generate the set of recipes based at least in part on the request and the set of user data; providing the first prompt to obtain a first textual output, the first textual output including the set of recipes; extracting the set of recipes from the first textual output; displaying a set of information describing each recipe of the set of recipes and a set of options to modify a recipe and to accept the recipe; responsive to receiving an additional request to modify the recipe, performing a recipe modification process comprising: generating a second prompt to modify the recipe based at least in part on the additional request, the set of information describing the recipe, and the set of user data associated with the user, providing the second prompt to obtain a second textual output, the second textual output including a set of modified recipes, extracting the set of modified recipes from the second textual output, and updating to include the set of information describing each modified recipe of the set of modified recipes and the set of options to modify a modified recipe and to accept the modified recipe; repeating the recipe modification process for each additional request received until a modified recipe is accepted; responsive to receiving a selection of an accepted recipe, predicting an availability of each item of one or more items associated with the accepted recipe at a retailer location; and updating to include an additional option to add a set of items of the one or more items associated with the accepted recipe to a shopping list associated with the user based at least in part on the predicted availability of each item are types of judgement. Thus, representative claim 1 recites an abstract idea.
Under Step 2A, Prong 2, if it is determined that the claims recite a judicial exception, it is then necessary to evaluate whether the claims recite additional elements that integrate the judicial exception into a practical application of that exception. See MPEP §2106.04(d). In this case, representative claim 1 includes additional elements such as an online system, a client device associated with a user of the online system, a large language model, a user interface, wherein updating the user interface causes the client device to display the updated user interface.
Although reciting additional elements, the additional elements do not integrate the abstract idea into a practical application because they merely amount to no more than an instruction to apply the abstract idea using a generic computer or merely use a computer as a tool to perform the abstract idea. These additional elements are described at a high level in Applicant’s specification without any meaningful detail about their structure or configuration. Similar to the limitations of Alice, representative claim 1 merely recites a commonplace business method (i.e., recommending recipes) being applied on a general purpose computer. See MPEP §§2106.04(d) and 2106.05(f). Thus, the claimed additional elements are merely generic elements and the implementation of the elements merely amounts to no more than an instruction to apply the abstract idea using a generic computer. Since the additional elements merely include instructions to implement the abstract idea on a generic computer or merely use a generic computer as a tool to perform an abstract idea, the abstract idea has not been integrated into a practical application. As such, representative claim 1 is directed to an abstract idea.
Under Step 2B, if it is determined that the claims recite a judicial exception that is not integrated into a practical application of that exception, it is then necessary to evaluate the additional elements individually and in combination to determine whether they provide an inventive concept (i.e., whether the additional elements amount to significantly more than the exception itself). See MPEP §2106.05.
In this case, as noted above, the additional elements recited in independent claim 1 are recited and described in a generic manner merely amount to no more than an instruction to apply the abstract idea using a generic computer or merely use a generic computer as a tool to perform an abstract idea.
Even when considered as an ordered combination, the additional elements of representative claim 1 do not add anything that is not already present when they considered individually. In Alice, the court considered the additional elements “as an ordered combination,” and determined that “the computer components ... ‘ad[d] nothing ... that is not already present when the steps are considered separately’ and simply recite intermediated settlement as performed by a generic computer.” Alice Corp. Pty. Ltd. v. CLS Bank Int’l, 573 U.S. 208, 224, 110 USPQ2d 1976, 1983-84 (2014). (citing Mayo, 566 U.S. at 79, 101 USPQ2d at 1972). Also see MPEP §2106.05(f). Similarly, when viewed as a whole, representative claim 1 simply conveys the abstract idea itself facilitated by generic computing components. Therefore, under Step 2B, there are no meaningful limitations in representative claim 1 that transforms the judicial exception into a patent eligible application such that the claims amount to significantly more than the judicial exception itself.
As such, representative claim 1 is ineligible.
Dependent claims 2-10 do not aid in the eligibility of independent claim 1. For example, claims 5, 7, and 9-10 merely further define the abstract limitations of claim 1. Also, claims 2-4, 6, and 8 merely provide further embellishments of the abstract limitations recited in independent claim 1.
Additionally, it is noted that claims 2-8 and 10 do not include further additional elements not previously recited in claim 1. Therefore, the claims do not integrate the abstract idea into a practical application because they merely amount to an instruction to apply the abstract idea using a generic computer or merely use a generic computer as a tool to perform an abstract idea. The claims also do not amount to significantly more than the abstract idea because they merely amount to an instruction to apply the abstract idea using a generic computer or merely use a generic computer as a tool to perform an abstract idea.
Furthermore, it is noted that claim 9 includes additional elements of accessing a machine-learning model trained, wherein the machine-learning model is trained by: training the machine-learning model based at least in part on the recipe data, the user data, and the label for each recipe of the first plurality of recipes; and applying the machine-learning model. However, these additional elements do not integrate the abstract idea into a practical application because they merely amount to an instruction to apply the abstract idea using a generic computer or merely use a generic computer as a tool to perform an abstract idea. These additional elements are merely generic elements and are likewise described in a generic manner in Applicant’s specification. Additionally, the additional elements do not amount to significantly more because they merely amount to an instruction to apply the abstract idea using a generic computer or merely use a generic computer as a tool to perform an abstract idea.
Thus, dependent claims 2-10 are also ineligible.
Lastly, the analysis above applies to all statutory categories of invention. Although literally invoking a computer program product and system, respectively, claims 11-19 and 20 remain only broadly and generally defined, with the claimed functionality paralleling that of claims 1-9 and 1, respectively. It is noted that claim 11 includes further additional elements of a computer program product comprising a non-transitory computer-readable storage medium having instructions encoded thereon that, when executed by a processor, cause the processor to perform steps, and claim 20 includes further additional elements of computer system comprising: a processor; and a non-transitory computer-readable storage medium storing instructions that, when executed by the processor, perform actions. However, these additional elements do not integrate the abstract idea into a practical application because they merely amount to an instruction to apply the abstract idea using a generic computer or merely use a generic computer as a tool to perform an abstract idea. These additional elements are merely generic elements and are likewise described in a generic manner in Applicant’s specification. Additionally, the additional elements do not amount to significantly more because they merely amount to an instruction to apply the abstract idea using a generic computer or merely use a generic computer as a tool to perform an abstract idea. As such, claims 11-19 and 20 are rejected for at least similar rationale as discussed above.
Subject Matter Overcoming Prior Art
The following is an examiner’s statement of reasons for indicating the claims overcome the prior art:
Claims 1-20 overcome the prior art due to the combination of features. Specifically, a large language model in combination with a system for recommending recipes based on a user’s preferences, purchase history, and ingredient availability at a retail store is novel and non-obvious over the cited prior art. The cited prior art utilizes each of these features, but the cited prior art fails to obviously teach this specific combination.
The most relevant prior art includes Argue et. al. (US 20170076355 A1, herein referred to as Argue), Beauchamp (US 20240256762 A1, herein referred to as Beauchamp), Leifer et. al. (US 11587140 B2), Zaragoza et. al. (US 20140249966 A1), Takeuchi et. al. (US 20240242297 A1), Padmavathi et. al. (2023 NPL), and Friedman et. al. (2023 NPL).
Argue discloses a computer system and computer-readable medium for performing a suggested recipe method (Argue: [0082], [0087]). A customer using an application on their computing device can request one or more suggested recipes, and the system uses the customer’s purchase history to suggest recipes to the customer (Argue: [0082]). The customer can also add preferences for the system to consider in the recipe recommendation (Argue: [0070]). The output module of the system presents the recommended recipes to the user, which can include the name and listing of required ingredients (Argue: [0072], [0017]). The customer can scroll, swipe, pan, or otherwise progress through the relevant recipes, which are presented one at a time based on relevance via the user interface (Argue: [0072], [0083]). The customer can also choose to save the recipe by bookmarking the recipe or modify the recipe by establishing preferred ingredients or nutritional characteristics (Argue: [0084], [0067]).
If the customer wants to see different recipes, they can press a “Try Something New” or “Surprise Me” button and use a scale for the preferences (Argue: [0069]). Once the customer saves a recipe, the customer can ask the system to convert the recipe into a shopping list based on commercially-available products corresponding to the recipe’s ingredients (Argue: [0073], [0085]). Once the recipe is converted to a shopping list, the list is presented to the user on the user interface (Argue: [0085]). The system can learn from the user selections and modify future recipe suggestions (Argue: [0086]).
Argue does not disclose generating a first prompt to generate the set of recipes based at least in part on the request and the set of user data; providing the first prompt to a large language model to obtain a first textual output; nor extracting the set of recipes from the first textual output. Argue also does not disclose providing the second prompt to the large language model to obtain a second textual output; extracting the set of modified recipes from the second textual output; nor updating the user interface to include the set of information describing each modified recipe. Argue further does not disclose repeating the recipe modification process for each additional request received from the client device until a modified recipe is accepted, nor that the shopping list is generated based on the availability of products at a retailer.
Beauchamp discloses a large language model that produces textualized outputs based on user prompts (Beauchamp: [0072]). The system displays text to the user, and the user can select portions of the text to annotate with modifications (Beauchamp: [0085]). The system then generates a prompt for the model to process the annotations and output the modifications entered by the user (Beauchamp: [0089]-[0090]). The prompt is created by the model extracting and parsing the user inputs (Beauchamp: [0081]). This process can be repeated until the user is satisfied with the final text output (Beauchamp: [0155]-[0156]).
Beauchamp does not disclose that the large language model produces recipe recommendations responsive to user input. Beauchamp also does not disclose extracting the set of recipes from the textual outputs of the model, nor that a shopping list is generated based on the availability of products at a retailer location.
Leifer discloses a machine learning model that receives user food preferences and historical data for creating a food plan that is tailored to the user (Leifer: [Col. 6, ln. 58-67; Col. 7, ln. 1-2]). The system keeps a database for potential ingredient substitutions based on the user preferences and availability of the ingredients (Leifer: [Col. 3, ln. 21-34]). The availability of ingredients can be based on fulfillment parameters such as grocer data including inventory and location data (Leifer: [Col. 10, ln. 48-67; Col. 11, ln. 1-2]).
Leifer does not disclose generating a first prompt to generate the set of recipes based at least in part on the request and the set of user data; providing the first prompt to a large language model to obtain a first textual output; nor extracting the set of recipes from the first textual output. Leifer also does not disclose providing the second prompt to the large language model to obtain a second textual output; extracting the set of modified recipes from the second textual output; nor updating the user interface to include the set of information describing each modified recipe. Leifer further does not disclose updating a user interface to reflect user-made modifications to the recipes nor repeating the recipe modification process for each additional request received from the client device until a modified recipe is accepted.
Takeuchi discloses a machine learning method for suggesting recipes to a user (Takeuchi: [0051]). The machine learning method employs a word vector algorithm to predict which recipes to recommend and which ingredients to substitute (Takeuchi: [0052]). Such an algorithm extracts text from the recipes to match to available ingredients (Takeuchi: [0055], [0058]). The system also tracks a customer’s browsing session to predict which recipes to suggest (Takeuchi: [0058]).
Takeuchi does not disclose generating a first prompt to generate the set of recipes based at least in part on the request and the set of user data nor providing the first prompt to a large language model to obtain a first textual output. Takeuchi also does not disclose providing the second prompt to the large language model to obtain a second textual output; nor updating the user interface to include the set of information describing each modified recipe. Takeuchi further does not disclose updating a user interface to reflect user-made modifications to the recipes; repeating the recipe modification process for each additional request received from the client device until a modified recipe is accepted; nor that a shopping list is generated based on the availability of products at a retailer location.
Zaragoza discloses a software method for converting recipes on a website to a shopping list (Zaragoza: [0038]). A user can request to view recipes, and the system recommends recipes that are available online to the user (Zaragoza: [0063]). The system can take into account user preferences and purchase history to make the recommendation (Zaragoza: [0042]-[0043]). Upon a user requesting to create a shopping list from the recipe, the system creates the list based on items available at a particular store (Zaragoza: [0052]).
Zaragoza does not disclose generating a first prompt to generate the set of recipes based at least in part on the request and the set of user data; providing the first prompt to a large language model to obtain a first textual output; nor extracting the set of recipes from the first textual output. Zaragoza also does not disclose providing the second prompt to the large language model to obtain a second textual output; extracting the set of modified recipes from the second textual output; nor updating the user interface to include the set of information describing each modified recipe. Zaragoza further does not disclose updating a user interface to reflect user-made modifications to the recipes; nor repeating the recipe modification process for each additional request received from the client device until a modified recipe is accepted.
Padmavathi discloses a recipe recommendation system named RecipeMate that employs natural language processing and machine learning techniques to suggest recipes based on the user’s input ingredients, cuisine, and takes into account of user’s dietary preferences (Padmavathi, p.2). The system uses natural language processing techniques to preprocess the recipe dataset, including removing punctuations, converting everything to lowercase, and removing stop words (Padmavathi, p.2). The machine learning model then vectorizes the remaining words and calculates cosine similarity of the recipes to recommend the best possible match to the user’s input ingredients and cuisine while excluding any non-preferred ingredients (Padmavathi, p.2).
Padmavathi does not disclose providing the first prompt to a large language model to obtain a first textual output; nor extracting the set of recipes from the first textual output. Padmavathi also does not disclose providing the second prompt to the large language model to obtain a second textual output; nor extracting the set of modified recipes from the second textual output. Padmavathi further does not disclose updating the user interface to include the set of information describing each modified recipe; nor repeating the recipe modification process for each additional request received from the client device until a modified recipe is accepted.
Friedman discloses methods for improving large language models in conversational recommender systems. The proposed model, called RecLLM, utilizes large language models at various points in the system to improve the system’s recommendations (Friedman, p.2). At the conversation step, an LLM uses the dialog from the user with the user’s profile to create a recommendation request (Friedman, p.2). The dialog LLM can extract the user’s preferences from the dialog to tailor the recommendation request (Friedman, p.4). The recommendation request then goes to a recommendation LLM, which creates a candidate set of recommendations (Friedman, p.2). The candidate set is then sent to a ranker LLM, which ranks the recommendations in order of relevance for the user (Friedman, p.2). The user’s repeated interactions with the dialog LLM improve the recommendations made to the user ((Friedman, p.6-7).
Friedman does not disclose that the large language model produces recipe recommendations responsive to user input. Friedman also does not disclose extracting the set of recipes from the textual outputs of the model, nor that a shopping list is generated based on the availability of products at a retailer location.
Although individually the references teach the individual claimed features, none of the cited references anticipate or render obvious the combination of features. While these references arguably may teach the claimed limitations using a piecemeal analysis, these references would only be combined and deemed obvious based on knowledge gleaned from the applicant's disclosure. Such a reconstruction is improper (i.e., hindsight reasoning). See In re McLaughlin, 443 F.2d 1392, 170 USPQ 209 (CCPA 1971). Accordingly, claims 1-20 taken as a whole, are indicated to overcome the cited prior art. The Examiner emphasizes that it is the interrelationship of the limitations that overcomes the prior art/additional art.
Therefore, it is hereby asserted by the Examiner that, in light of the above and in further deliberation over all the evidence at hand, that the claims overcome the prior art as the evidence at hand does not anticipate the claims and does not render obvious any further modification of the references to a person of ordinary skill in art.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Ashraf et. al. (2022 NPL) describes the limitations of food recommender systems and offers insight to potential routes that could overcome these limitations by implementing refined machine learning technology.
Maschmeyer et. al. (US 20240256792 A1) was used to understand other methods for employing LLMs in recommendation systems.
Sawaf et. al. (US 20220318683 A1) was used to understand other methods for employing machine learning model combinations, including neural networks and LLMs, in recommendation contexts.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KATHERINE A BARLOW whose telephone number is (571)272-5820. The examiner can normally be reached Monday-Tuesday 11am-7pm EST.
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.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Marissa Thein, can be reached at (571) 272-6764. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
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/apply/patent-center for more information about Patent Center and 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.
/KATHERINE A BARLOW/Examiner, Art Unit 3689 02/18/2026
/VICTORIA E. FRUNZI/Primary Examiner, Art Unit 3689 2/18/2026