DETAILED ACTION
Status of Claims
This action is in reply to the claims filed on 03 June 2025, and the election of claims filed on 17 October 2025.
Claim 21 has been canceled.
Claims 1-20 are pending and have been examined.
Election/Restriction
Applicant’s election without traverse of Invention I (claims 1-20), in the reply filed on 17 October 2025, is acknowledged.
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 .
Information Disclosure Statement
The Information Disclosure Statement filed on 31 July 2025, has been considered. An initialed copy of the Form 1449 is enclosed herewith.
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 (i.e., a law of nature, a natural phenomenon, or an abstract idea without significantly more).
Under step 1, it is determined whether the claims are directed to a statutory category of invention (see MPEP 2106.03(II)). In the instant case, claims 1-10 are directed to a system, and claims 11-20 are directed to a method.
While the claims fall within statutory categories, under revised Step 2A, Prong 1 of the eligibility analysis (MPEP 2106.04), the claimed invention recites an abstract idea of search requests and responses for a customer of a store. Specifically, representative claim 11 recites the abstract idea of:
using context information stored in at least one source, the information pertaining to one or more products listed by the store;
preparing at least one pre-configured prompt for a contextual response and associating the at least one pre-configured prompt to at least one user query;
generating an initial set of at least one prompt-query pair using the context information for each of the one or more products listed on the store, the prompt-query pair comprising the at least one pre-configured prompt and the at least one user query;
receiving the at least one prompt-query pair regarding the at least one of the one or more products, the at least one prompt-query pair being submitted by a user supported by the store, configured to populate a contextual response to the at least one prompt-query pair, displayed; and
generating, the contextual response to the at least one prompt-query pair using the pre-configured prompt and the information regarding the product stored in the at least one source.
Under revised Step 2A, Prong 1 of the eligibility analysis, it is necessary to evaluate whether the claim recites a judicial exception by referring to subject matter groupings articulated in 2106.04(a) of the MPEP. Even in consideration of the analysis, the claims recite an abstract idea. Representative claim 11 recites the abstract idea of search requests and responses for a customer in a store, as noted above. This concept is considered to be a method of organizing human activity. Certain methods of organizing human activity include “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)(II). In this case, the abstract idea recited in representative claim 11 is a certain method of organizing human activity because it relates to sale activities since the claims specifically recite the steps of a source that stores information regarding one or more products listed by a store, receiving at least one user query and further populates at least one contextual response to the user query, generating an initial set of at least one prompt-query pair using the context information for each of the one or more products listed by the store, receiving the at least one prompt-query pair regarding at least one of the one or more products, the at least one prompt-query pair being submitted by a user of the store, the user configured to populate a contextual response to the at least one prompt-query pair displayed to the user, and generating the contextual response to the at least one prompt-query pair using the pre-configured prompt and the information regarding the product stored in the at least one source, thereby making this a sales activity or behavior.
Thus, representative claim 11 recites an abstract idea.
Under Step 2A, Prong 2 of the eligibility analysis, 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. MPEP 2106.04(d). The courts have identified limitations that did not integrate a judicial exception into a practical application include limitations merely reciting the words “apply it” (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea, as discussed in MPEP 2106.05(f). MPEP 2106.04(d). In this case, representative claim 11 includes additional elements: an ecommerce store, training a large language model, a database, ecommerce store, the large language model, a user interface element, the user interface element displayed on a user device communicatively coupled with the large language model by the way of at least one server, and the database
Although reciting such 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 11 merely recites a commonplace business method (i.e., search requests and responses for a customer in a store) being applied on a general-purpose computer using general purpose computer technology. MPEP 2106.05(f). While the claims recite training a large language model, the recitations do not include details as to how the model is actually functioning beyond known functions. 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.
Under Step 2B of the eligibility analysis, 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). MPEP 2106.05. In this case, as noted above, the additional elements recited in independent claim 11 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] [v]iewed as a whole…[the] claims simply recite intermediated settlement as performed by a generic computer.” Alice Corp. Pty. Ltd. v. CLS Bank Int'l, 573 U.S. 208, 217, (2014) (citing Mayo, 566 U.S. at 79, 101 USPQ2d at 1972). Similarly, when viewed as a whole, representative claim 11 simply conveys the abstract idea itself facilitated by generic computing components. Therefore, under Step 2B of the Alice/Mayo test, there are no meaningful limitations in representative claim 11 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 11 is ineligible.
Independent claim 1 is similar in nature to representative claim 11 and Step 2A, Prong 1 analysis is the same as above for representative claim 11. It is noted that in independent claim 1 includes the additional elements of a graphical user interface on a user device, and at least one server comprising at least one processor and memory for storing instructions executable on the processor, the at least one server communicatively coupled to the user device over a network connection. The Applicant’s specification does not provide any discussion or description of a graphical user interface on a user device, and at least one server comprising at least one processor and memory for storing instructions executable on the processor, the at least one server communicatively coupled to the user device over a network connection in claim 1, as being anything other than generic elements. Thus, the claimed additional elements of claim 1 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. As such, the additional elements of claim 1 do not integrate the judicial exception into a practical application of the abstract idea. Additionally, the additional elements of claim 1, considered individually and in combination, do not provide an inventive concept because they merely amount to no more than an instruction to apply the abstract idea using a generic computer.
As such, claim 1 is ineligible.
Dependent claims 2-10 and 12-20, depending from claims 1 and 11 respectively, do not aid in the eligibility of the representative independent claim 11. The claims of 2-10 and 12-20 merely act to provide further limitations of the abstract idea and are ineligible subject matter.
It is noted that dependent claims includes the additional elements of a webpage component, a mobile application component, and a web component displayed in the body of an email (claims 3 & 13), a caching means communicatively coupled to the server (claims 7 & 17), a retrieval unit (claim 7), blogs and online (claims 8 & 18), click rate and click-to-purchase ratio (claims 10 & 20). Applicant’s specification does not provide any discussion or description of the claimed additional elements of claims 3, 7-8, 10, 13, 17-18, and 20, as being anything other than a generic element. The claimed additional elements, individually and in combination do not integrate into a practical application and do not provide an inventive concept because they are merely being used to apply the abstract idea using a generic computer (see MPEP 2106.05(f)). Accordingly, claims 3, 7-8, 10, 13, 17-18, and 20 are directed towards an abstract idea. Additionally, the additional elements of claims 3, 7-8, 10, 13, 17-18, and 20, considered individually and in combination, do not provide an inventive concept because they merely amount to no more than an instruction to apply the abstract idea using a generic computer. It is further noted that the remaining dependent claims 2, 4-6, 9, 12, 14-16, and 19 do not recite any further additional elements to consider in the analysis, and therefore would not provide additional elements that would integrate the abstract idea into a practical application and would not provide an inventive concept.
As such, dependent claims 2-10 and 12-20 are ineligible.
Double Patenting
A rejection based on double patenting of the “same invention” type finds its support in the language of 35 U.S.C. 101 which states that “whoever invents or discovers any new and useful process... may obtain a patent therefor...” (Emphasis added). Thus, the term “same invention,” in this context, means an invention drawn to identical subject matter. See Miller v. Eagle Mfg. Co., 151 U.S. 186 (1894); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Ockert, 245 F.2d 467, 114 USPQ 330 (CCPA 1957).
A statutory type (35 U.S.C. 101) double patenting rejection can be overcome by canceling or amending the claims that are directed to the same invention so they are no longer coextensive in scope. The filing of a terminal disclaimer cannot overcome a double patenting rejection based upon 35 U.S.C. 101.
Claims 1-20 are provisionally rejected under 35 U.S.C. 101 as claiming the same invention as that of claims 1-20 of co-pending Application No. 18/589,343 (reference application). This is a provisional statutory double patenting rejection since the claims directed to the same invention have not in fact been patented.
Claim Rejections - 35 USC § 103
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.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or
nonobviousness.
Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Poliak, S., et al. (PGP No. US 2024/0420208 A1), in view of Kundel, D., et al. (PGP No. US 2024/0354321 A1).
Claim 1-
Poliak discloses a system for generating dynamic search requests and responses for a customer of an ecommerce store (Poliak, see: paragraphs [0050] disclosing “interface for e-commerce” and [0053] disclosing “system for customer engagement 100”; and see paragraph [0057]), the system comprising:
at least one source database storing context information regarding one or more products listed on the ecommerce store (Poliak, see: paragraph [0051] disclosing “can receive (e.g., from an e-commerce server associated with an e-commerce business, e.g., retailer), a product catalog”; and see: [0059] disclosing “memory comprises…a product catalog database (PCD) 144” and “at least one list of products”);
at least one user interface element supported by the ecommerce store, the user interface element displayable on a graphical user interface on a user device and configured to receive at least one user query and further configured to populate at least one contextual response to the user query (Poliak, see: paragraph [0065] disclosing “user input (e.g., a query) is received” and “an end user input is received, such as by new prompt API endpoint 140” and “new input is passed to LLM 184 to generate a response to the end user that includes product information”; and paragraph [0070] disclosing ‘end user may input one or more prompts 402…may be typed or otherwise input into the window 402”; and paragraph [0077] disclosing “end user interface may be generated and displayed on display 780”);
at least one server comprising at least one processor and memory for storing instructions executable on the processor, the at least one server communicatively coupled to the user device over a network connection (Poliak, see: paragraph [0053] disclosing “central server 104 is configured to communicate with the end user devices…via networks”; and paragraph [0055] disclosing “end user devices…comprise a Central Processing Unit” and “memory 116 comprises an operating system 118”); and
at least one large language model communicatively coupled to the at least one source database and the at least one server, the at least one large language model using data stored in the at least one source database, the at least one large language model being configured to (Poliak, see: paragraph [0053] disclosing “central server 104…and a plurality of LLMs 108”; and paragraph [0059] disclosing “configured to perform on the product catalog” and “feed the transforms into the LLM” and “receiving the embeddings for each product description from the LLM…associated with each product in the product catalog, and store the vectors in the PCD 144” and paragraph [0070] disclosing “information in the responses to the end user…depend on the artificial intelligence algorithms and learning of the LLMs 108”):
generate an initial set of at least one prompt-query pair using the context information for each of the one or more products listed on the ecommerce store (Poliak, see: paragraph [0071] disclosing “generate a reverse text index of products in the product catalog 160…may include meta data of the information associated with a plurality of products”; and see: paragraph [0072] disclosing “text search engine 604 may convert text in text prompts into one or more text queries to query the reverse text index stored in PCD 144”);
receive the at least one user query from the user device, the user query comprising a user selection of a query, the query being associated with at least one pre-configured prompt for the at least one large language model (Poliak, see: paragraph [0087] disclosing “may include at least one of a chronologically ordered list of any preceding end user inputs or responses to preceding end user inputs 906, one or more lists of products that were previously presented to the end user 908, one or more lists of products selected by the end user 910” and “end user input of ‘How much does the most expensive blue ring cost?’”; and paragraph [0088] disclosing “may include passing context and end user input (e.g., the query) to an action sequence module” and “The action sequence module 916 may use a Large Language Model to understand the need described in the end user input 902 and context 904 related to the end user input, and output a sequence of actions and parameters…associated with the actions that will fulfill the need.”; and paragraph [0089] disclosing “each action in the sequence of actions 916 is selected by the LLM from a library of available action types [i.e., pre-configured prompt]”; and see: FIG. 9 and FIG. 10);
generate and display the contextual response to the prompt-query pair using the pre-configured prompt, the at least one user query, and the information regarding the product stored in the at least one source database (Poliak, see: paragraph [0089] disclosing “may include an action type for retrieving at least one list of products and information about those products based on a search query”; and paragraph [0097] disclosing “generating a response to the end user that answers the questions by including information about the referenced products; and outputting the response to the end user” and “a response ‘The ring costs $100’”; Also see: FIG. 24).
Although Poliak discloses at least one large language model that uses data stored in a database, such as the product catalog databases, the large language models that are recited in Poliak do not specifically suggest that they are being trained by the stored data. Poliak does not disclose:
the at least one large language model being trained using data;
Kundel, however, does teach:
the at least one large language model being trained using data (Kundel, see: paragraph [0036] teaching “automated identification and retrieval of relevant contextual information for quick and accurate processing of user queries by generative artificial intelligence models” and “may be an NL model, an LLM model” and “may be trained using various user queries as training inputs and responses of GM 120 to those queries as ground truth”).
This step of Kundel is applicable to the system of Poliak, as they both share characteristics and capabilities, namely, they are directed to natural language queries and responses. 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 system of Poliak, to include the features of the at least one large language model being trained using data, as taught by Kundel. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify the reference of Poliak to improve meaningful responses and follow-up questions to queries, which also increases overall user satisfaction (Kundel, see: paragraph [0013]).
Claim 2-
Poliak in view of Kundel teach the system of claim 1, as described above.
Poliak discloses the dynamic search requests comprising any of the following: frequently asked questions; product comparisons; summaries of customer reviews; suggested co-purchases; and lists of best-selling products (Poliak, see: paragraph [0097] disclosing “the user input is a query ‘How much does it cost?’ and in FIG. 25, the user input is a request to ‘Compare these rings.’ At block 2304, the method 2300 may include receiving context related to the end user input that includes a chronologically ordered list of any preceding end user inputs or responses to preceding end user inputs, and one or more lists of products that were previously presented to the end user, viewed by the end user, added to a shopping cart by the end user, or selected by the end user”).
Claim 3-
Poliak in view of Kundel teach the system of claim 1, as described above.
Poliak discloses the user interface element comprising any of the following:
a webpage component, a mobile application component, and a web component displayed in the body of an email (Poliak, see: paragraph [0070] disclosing “a window 402 of a web browser 120 on an end user device 102”).
Claim 4-
Poliak in view of Kundel teach the system of claim 1, as described above.
Poliak discloses the at least one prompt-query pair being submitted as a clickable link having the text of the at least one product-related query (Poliak, see: paragraph [0075] disclosing “The response may include a selectable link to product information of products of the at least one list of products”)
Claim 5-
Poliak in view of Kundel teach the system of claim 1, as described above.
Poliak discloses further comprising a conversation agent configured to record a customer's browse behavior on an ecommerce store and the customer (Poliak, see: paragraph [0070] disclosing “using chat service 142” and paragraph [0097] disclosing “the user input is a query ‘How much does it cost?’” and “At block 2304, the method 2300 may include receiving context related to the end user input that includes a chronologically ordered list of any preceding end user inputs or responses to preceding end user inputs, and one or more lists of products that were previously presented to the end user”).
Poliak does not disclose:
an identifier of the customer;
Kundel, however, does teach:
an identifier of the customer (Kundel, see: paragraph [0021] teaching “user data 112 may include (for a particular user) a user identification”).
This step of Kundel is applicable to the system of Poliak, as they both share characteristics and capabilities, namely, they are directed to natural language queries and responses. 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 system of Poliak, to include the feature of an identifier of the customer, as taught by Kundel. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify the reference of Poliak to improve meaningful responses and follow-up questions to queries, which also increases overall user satisfaction (Kundel, see: paragraph [0013]).
Claim 6-
Poliak in view of Kundel teach the system of claim 5, as described above.
Poliak discloses the large language model further configured to generate the contextual response to the at least one prompt-query pair based on the customer's browse behavior and the identifier as recorded by the conversation agent (Poliak, see: paragraph [0097] disclosing “At block 2304, the method 2300 may include receiving context related to the end user input that includes a chronologically ordered list of any preceding end user inputs or responses to preceding end user inputs, and one or more lists of products that were previously presented to the end user, viewed by the end user” and “response to the end user that answers the questions by including information about the referenced products; and outputting the response to the end user. For example, in FIG. 24, the method outputs a response ‘The ring costs $100’”).
Claim 7-
Poliak in view of Kundel teach the system of claim 1, as described above.
Poliak discloses further comprising: A caching means communicatively coupled to the server, the caching means configured to cache the plurality of prompt-query pairs and the contextual responses associated with each of the prompt-query pairs; and a retrieval unit configured to fetch cached contextual responses and display the cached contextual responses without invoking the large language model (Poliak, see: paragraph [0099] disclosing “At block 2622, the method 2600 may include retrieving one or more retrieved content files from the content vector database” and paragraph [0100] disclosing “include outputting the response to the end user”) (Examiner’s note: It is noted that the Examiner is interpreting that the method includes retrieving content of the prompts and queries of the user along with the displayed responses to the end user, which is occurring via the content vector database, not occurring because of the large language model.).
Claim 8-
Poliak in view of Kundel teach the system of claim 1, as described above.
Poliak does not disclose:
the configuring of the large language model including training the large language model, at least in part, by:
collecting training data comprising one or more of:
product details posted on a page on the ecommerce store, including but not limited to the product page itself; articles, blogs, and content available online regarding the product; purchasing guides with information regarding specifications, such as sizing, dimensions, and customization options; product image information; customer reviews and feedback, including written reviews and ratings; and customer-posted questions and answers to the customer-posted questions from other customers or from online sellers; processing the training data to create training prompts simulating real-world scenarios where a hypothetical customer seeks product-related information based on the hypothetical customer's history and context; training the large language model using the training prompts to predict most likely queries the hypothetical customer might have about a product; and refining the large language model's predictions using feedback received from actual customer interactions on the ecommerce store.
Kundel, however, does teach:
the configuring of the large language model including training the large language model, at least in part, by: collecting training data (Kundel, see: paragraph [0036] teaching “automated identification and retrieval of relevant contextual information for quick and accurate processing of user queries by generative artificial intelligence models” and “may be an NL model, an LLM model” and “may be trained using various user queries as training inputs and responses of GM 120 to those queries as ground truth”) comprising one or more of:
product details posted on a page on the ecommerce store, including but not limited to the product page itself; articles, blogs, and content available online regarding the product; purchasing guides with information regarding specifications, such as sizing, dimensions, and customization options; product image information; customer reviews and feedback, including written reviews and ratings; and customer-posted questions and answers to the customer-posted questions from other customers or from online sellers; processing the training data to create training prompts simulating real-world scenarios where a hypothetical customer seeks product-related information based on the hypothetical customer's history and context; training the large language model using the training prompts to predict most likely queries the hypothetical customer might have about a product; and refining the large language model's predictions using feedback received from actual customer interactions on the ecommerce store (Kundel, see: paragraph [0013] teaching “the relevant contextual information may include the user's address, restaurants previously visited by the user, review grades given by the user to those restaurants, and/or the like”; and paragraph [0015] teaching “request that includes a representation (e.g., a summary, a list of titles, a digest of available data, etc.) of the data received from the data store (e.g., “what information in the user query would be useful for future customer interactions?”)”; and paragraph [0021] teaching “history of user queries, browsing history, and/or any other information associated with the user”; Also see paragraph [0029]).
This step of Kundel is applicable to the system of Poliak, as they both share characteristics and capabilities, namely, they are directed to natural language queries and responses. 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 system of Poliak, to include the features of the configuring of the large language model including training the large language model, at least in part, by: collecting training data comprising one or more of: product details posted on a page on the ecommerce store, including but not limited to the product page itself; articles, blogs, and content available online regarding the product; purchasing guides with information regarding specifications, such as sizing, dimensions, and customization options; product image information; customer reviews and feedback, including written reviews and ratings; and customer-posted questions and answers to the customer-posted questions from other customers or from online sellers; processing the training data to create training prompts simulating real-world scenarios where a hypothetical customer seeks product-related information based on the hypothetical customer's history and context; training the large language model using the training prompts to predict most likely queries the hypothetical customer might have about a product; and refining the large language model's predictions using feedback received from actual customer interactions on the ecommerce store, as taught by Kundel. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify the reference of Poliak to improve meaningful responses and follow-up questions to queries, which also increases overall user satisfaction (Kundel, see: paragraph [0013]).
Claim 9-
Poliak in view of Kundel teach the system of claim 8, as described above.
Poliak does not disclose:
the training data further comprising customer browse behavior, customer context information, and customer queries related to one or more of the products.
Kundel, however, does teach:
the training data further comprising customer browse behavior, customer context information, and customer queries related to one or more of the products (Kundel, see: paragraph [0013] teaching “the relevant contextual information may include the user's address, restaurants previously visited by the user, review grades given by the user to those restaurants, and/or the like”; and paragraph [0015] teaching “request that includes a representation (e.g., a summary, a list of titles, a digest of available data, etc.) of the data received from the data store (e.g., “what information in the user query would be useful for future customer interactions?”)”; and paragraph [0021] teaching “history of user queries, browsing history, and/or any other information associated with the user”; Also see paragraph [0029]).
This step of Kundel is applicable to the system of Poliak, as they both share characteristics and capabilities, namely, they are directed to natural language queries and responses. 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 system of Poliak, to include the features of the training data further comprising customer browse behavior, customer context information, and customer queries related to one or more of the products, as taught by Kundel. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify the reference of Poliak to improve meaningful responses and follow-up questions to queries, which also increases overall user satisfaction (Kundel, see: paragraph [0013]).
Claim 10-
Poliak in view of Kundel teach the system of claim 1, as described above.
Poliak discloses further comprising determination of an optimal subset of prompts to feature within the user interface element, the determination being based at least in part on input comprising at least one of: sales trends, browse rate, click rate, add-to-cart rate, remove-from-cart rate, browse-to-purchase ratio, and click-to-purchase ratio (Poliak, see: paragraph [0092] disclosing “the method 1400 may include generating an appropriate question to ask the end user to guide them to provide more such information about what kind of products they are looking for” and paragraph [0093] disclosing “receiving context related to the end user input that includes a chronologically ordered list of any preceding end user inputs or responses to preceding end user inputs” and “products that were previously presented to the end user, viewed by the end user, added to a shopping cart by the end user”).
Poliak does not disclose:
a scoring means for prompts;
Kundel, however, does teach:
a scoring means for prompts (Kundel, see: paragraph [0033] teaching “instances where the response to intermediate query 214 ranked the available traits by the level of usefulness, the context-based query may list a certain number of top traits (including user activities), e.g., 3 or 4 most useful traits, or traits that have been ranked with at least a minimum usefulness score, e.g., at least 3 on the usefulness scale of 1-5”).
This step of Kundel is applicable to the system of Poliak, as they both share characteristics and capabilities, namely, they are directed to natural language queries and responses. 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 system of Poliak, to include the features of a scoring means for prompts, as taught by Kundel. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify the reference of Poliak to improve meaningful responses and follow-up questions to queries, which also increases overall user satisfaction (Kundel, see: paragraph [0013]).
Claim 11-
Poliak discloses a method for generating dynamic search requests and responses for a customer of an ecommerce store (Poliak, see: paragraphs [0050] disclosing “interface for e-commerce” and [0053] disclosing “customer engagement 100”; and see paragraph [0057]), the method comprising:
a large language model using context information stored in at least one source database, the information pertaining to one or more products listed by the ecommerce store (Poliak, see: paragraph [0053] disclosing “central server 104…and a plurality of LLMs 108”; and paragraph [0059] disclosing “configured to perform on the product catalog” and “feed the transforms into the LLM” and “receiving the embeddings for each product description from the LLM…associated with each product in the product catalog, and store the vectors in the PCD 144” and paragraph [0070] disclosing “information in the responses to the end user…depend on the artificial intelligence algorithms and learning of the LLMs 108”);
preparing at least one pre-configured prompt for a contextual response and associating the at least one pre-configured prompt to at least one user query by the large language model (Poliak, see: paragraph [0071] disclosing “generate a reverse text index of products in the product catalog 160…may include meta data of the information associated with a plurality of products”);
generating an initial set of at least one prompt-query pair using the context information for each of the one or more products listed on the ecommerce store, the prompt-query pair comprising the at least one pre-configured prompt and the at least one user query (Poliak, see: paragraph [0071] disclosing “generate a reverse text index of products in the product catalog 160…may include meta data of the information associated with a plurality of products”; and see: paragraph [0072] disclosing “text search engine 604 may convert text in text prompts into one or more text queries to query the reverse text index stored in PCD 144”);
receiving the at least one prompt-query pair regarding at least one of the one or more products, the at least one prompt-query pair being submitted by a user interface element supported by the ecommerce store, the user interface element configured to populate a contextual response to the at least one prompt-query pair, the user interface element displayed on a user device communicatively coupled with the large language model by way of at least one server (Poliak, see: paragraph [0087] disclosing “may include at least one of a chronologically ordered list of any preceding end user inputs or responses to preceding end user inputs 906, one or more lists of products that were previously presented to the end user 908, one or more lists of products selected by the end user 910” and “end user input of ‘How much does the most expensive blue ring cost?’”; and paragraph [0088] disclosing “may include passing context and end user input (e.g., the query) to an action sequence module” and “The action sequence module 916 may use a Large Language Model to understand the need described in the end user input 902 and context 904 related to the end user input, and output a sequence of actions and parameters…associated with the actions that will fulfill the need.”; and paragraph [0089] disclosing “each action in the sequence of actions 916 is selected by the LLM from a library of available action types [i.e., pre-configured prompt]”; and see: FIG. 9 and FIG. 10); and
generating, by the large language model, the contextual response to the at least one prompt-query pair using the pre-configured prompt and the information regarding the product stored in the at least one source database (Poliak, see: paragraph [0089] disclosing “may include an action type for retrieving at least one list of products and information about those products based on a search query”; and paragraph [0097] disclosing “generating a response to the end user that answers the questions by including information about the referenced products; and outputting the response to the end user” and “a response ‘The ring costs $100’”; Also see: FIG. 24).
Although Poliak discloses at least one large language model that uses data stored in a database, such as the product catalog databases, the large language models that are recited in Poliak do not specifically suggest that they are being trained by the stored data. Poliak does not disclose:.
training a large language model;
Kundel, however, does teach:
training a large language model (Kundel, see: paragraph [0036] teaching “automated identification and retrieval of relevant contextual information for quick and accurate processing of user queries by generative artificial intelligence models” and “may be an NL model, an LLM model” and “may be trained using various user queries as training inputs and responses of GM 120 to those queries as ground truth”).
This step of Kundel is applicable to the method of Poliak, as they both share characteristics and capabilities, namely, they are directed to natural language queries and responses. 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 method of Poliak, to include the features of training a large language model, as taught by Kundel. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify the reference of Poliak to improve meaningful responses and follow-up questions to queries, which also increases overall user satisfaction (Kundel, see: paragraph [0013]).
Regarding claim 12, claim 12 is directed to a method. Claim 12 recites limitations that are parallel in nature to those addressed above for claim 2 which is directed towards a system. Claim 12 is therefore rejected for the same reasons as set forth above for claim 2.
Regarding claim 13, claim 13 is directed to a method. Claim 13 recites limitations that are parallel in nature to those addressed above for claim 3 which is directed towards a system. Claim 13 is therefore rejected for the same reasons as set forth above for claim 3.
Regarding claim 14, claim 14 is directed to a method. Claim 14 recites limitations that are parallel in nature to those addressed above for claim 4 which is directed towards a system. Claim 14 is therefore rejected for the same reasons as set forth above for claim 4.
Regarding claim 15, claim 15 is directed to a method. Claim 15 recites limitations that are parallel in nature to those addressed above for claim 5 which is directed towards a system. Claim 15 is therefore rejected for the same reasons as set forth above for claim 5.
Regarding claim 16, claim 16 is directed to a method. Claim 16 recites limitations that are parallel in nature to those addressed above for claim 6 which is directed towards a system. Claim 16 is therefore rejected for the same reasons as set forth above for claim 6.
Regarding claim 17, claim 17 is directed to a method. Claim 17 recites limitations that are parallel in nature to those addressed above for claim 7 which is directed towards a system. Claim 17 is therefore rejected for the same reasons as set forth above for claim 7.
Regarding claim 18, claim 18 is directed to a method. Claim 18 recites limitations that are parallel in nature to those addressed above for claim 8 which is directed towards a system. Claim 18 is therefore rejected for the same reasons as set forth above for claim 8.
Regarding claim 19, claim 19 is directed to a method. Claim 19 recites limitations that are parallel in nature to those addressed above for claim 9 which is directed towards a system. Claim 19 is therefore rejected for the same reasons as set forth above for claim 9.
Regarding claim 20, claim 20 is directed to a method. Claim 20 recites limitations that are parallel in nature to those addressed above for claim 10 which is directed towards a system. Claim 20 is therefore rejected for the same reasons as set forth above for claim 10.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Baldua, M., et al. (PGP No. US 2025/0110957 A1) describes receiving a first query including at least one first query term and configuring at least one prompt to cause a large language model to translate the at least one first query term into a set of functions that can be executed to obtain at least one second query term and generate output of a plan that is a modified version of the first query based at least on one second query term.
Non-patent literature (NPL) document, Generative AI in E-commerce: Use Cases, solutions and implementation, published by LeewayHertz (2023), provides a web page that describes uses of generative AI, such as chat bot services, in e-commerce environments and describes the benefits for retailers of using AI to improve retail experience for the customer as well as for the retailer in terms of improved sales.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ASHLEY PRESTON whose telephone number is (571)272-4399. The examiner can normally be reached M-F 8-4.
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, Jeffrey Smith can be reached at 571-272-6763. 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.
/ASHLEY D PRESTON/Examiner, Art Unit 3688