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
Applicant's “Amendment” filed on 5/12/2026 has been considered.
Rejection to Claims 1-20 under 35 USC 101 have been overcome.
Claims 1, 11, 20 are amended.
Claims 1-20 are currently pending and have been examined.
Claim Rejections - 35 USC § 103
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 of this title, 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.
Claims 1, 3-8, 10-11, 13-18, 20 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent Application No. 2015/0058154 A1 to APPLEYARD in view of US 2018/0052913 A1 to Gaskill.
Regarding Claim 1, APPLEYARD discloses a method, performed at a computer system comprising a processor and a computer-readable medium, comprising:
receiving, at an online concierge system, a free-text query from a client device associated with a user of the online concierge system, wherein the free-text query describes one or more items included among one or more inventories of one or more retailers associated with the online concierge system and a set of constraints; ([0041] During step 310, discount engine 154 and sentiment scoring engine 156 receive a shopping list of goods to purchase at optimization server 150 from user computer 120 (e.g., optimizing interaction 210, etc.). During step 312, discount engine 154 analyzes items on the received shopping list and searches for possible discount offerings from various brands, manufacturers, or retailers to compile a list of possible discounts that may be applied to the items (e.g., optimizing interactions 212, 214, etc.). [0011] comprehensive set of real-time factors such as preferences, retailers pricing, discounts, buying patterns, rating, consumer sentiments, environmental impact, and other criteria (constraints) [0024] person 102 can enter a shopping list of goods to purchase into a text input form of the loaded optimization web page displayed by the web browser program, )
generating a prompt comprising the free-text query and a request to identify the one or more items and the set of constraints included in the free-text query; ([0024] the web browser program can transmit the shopping list of goods to purchase to optimization server 150. Subsequently, optimization server 150 can generate an optimized shopping list )
identifying a plurality of retailers based at least in part on a set of user data associated with the user; ([0009] The goods on the shopping list are accessed and analyzed by the optimization server. In particular, for each item on the shopping list, the optimization server queries all known data sources (e.g., retailers, service providers, manufactures, etc.) to retrieve available discounts for the item. The shopping list is then segmented into multiple sublists per retailer, based on the discounts, sentiment score by retailer, and product. )
for each retailer of the plurality of retailers: ([0028] one or more brick-and-mortar or online retailers)
identifying a set of items associated with each item category of the one or more item categories, wherein the set of items is included in an inventory of a corresponding retailer, identifying, based at least in part on the set of constraints, a combination of items comprising a subset of the set of items associated with each item category of the one or more item categories, and ([0041] During step 316, segment routing engine 158 groups items on the shopping list into shopping sub-lists based on discount information and sentiment scores, submits the shopping sub-lists to retailers for bidding, and receives bids (e.g., optimizing interactions 220, 222, etc.). )
generating a score for the combination of items based at least in part on the set of user data associated with the user and a set of item data associated with each item included in the combination of items, wherein the score indicates a likelihood of conversion by the user for the combination of items; ([0028] computes a sentiment score for each item and for each retailer. Segment routing engine 158 groups items on a shopping list, based on discount information (e.g., as provided by discount engine 154, etc.) and the customer sentiment scores (e.g., as provided by sentiment scoring engine 156, etc.), into shopping sub-lists and submits the shopping sub-lists to retailers for bidding (e.g., submits to retail servers 140, etc.).)
ranking a plurality of combinations of items determined for the plurality of retailers based at least in part on the score computed for each combination of items; and ([0012] the ranking can be based on cost, quantity, incentives, retailers rating, location, sentiments, or time. Each shopper can have different preferences and further refinement can be done by a ranking engine. Retailers can request the carbon footprint of the products they sell, and when the optimization server receives the retailer's bid it can use the carbon footprint to further refine the search results. Accordingly, the optimization engine can take a complex request and intelligently break it into a bundle of requests to be optimized. [0028] Each of the optimized shopping lists is optimized and ranked based on the shopper's preferences, the retailer and item sentiment scores, and the item's pricing. )
sending information describing a ranked set of the plurality of combinations of items for display to the client device associated with the user, wherein the sending causes the client device to display the ranked set of the plurality of combinations of items.. ([0041] During step 318, ranking engine 160 aggregates shopping sub-list bids, analyzes the results, generates one or more optimized shopping lists, and transmits the optimized shopping lists from optimization server 150 to user computer 120 (e.g., optimizing interactions 224, 226, etc.).)
But does not explicitly disclose providing the prompt to a large language model to obtain a structured textual output, wherein the prompt contains instructions that cause the large language model to: extract, from the textual output, the set of constraints; and generate a structured textual output including the set of constraints and one or more item categories associated with the one or more items, wherein the structured textual output includes a first list of textual elements and a second list of textual elements, wherein each of textual elements in the first list corresponds to one of the set of constraints and each of the textual elements in the second list corresponds to one of one or more item categories; an inventory database that describes an inventory of a corresponding retailer;
Gaskill, on the other hand, teaches providing the prompt to a large language model to obtain a structured textual output, ([0077] the NLU component 214 processes a sequence of user inputs including an original query and further data provided by a user in response to machine-generated prompts from the dialog manager 216 in a multi-turn interactive dialog. [0054] A language model component uses statistical models of grammar to define how words are put together in a sentence. Such models can include n-gram-based models or Deep Neural Networks built on top of word embeddings. A speech-to-text (STT) decoder component may convert a speech utterance into a sequence of words typically leveraging features derived from a raw signal using the feature extraction component, the acoustic model component, and the language model component in a Hidden Markov Model (HMM) framework to derive word sequences from feature sequences.)
wherein the prompt contains instructions that cause the large language model to: extract, from the textual output, the set of constraints; and ([0089] The NER sub-component 810 may extract deeper information from parsed user input (e.g., brand names, size information, colors, and other descriptors) and help transform the user natural language query into a structured query comprising such parsed data elements. The NER sub-component may also tap into world knowledge to help resolve meaning for extracted terms. For example, a query for “a bordeaux” may more successfully determine from an online dictionary and encyclopedia that the query term may refer to an item category (wine), attributes (type, color, origin location), and respective corresponding attribute values (Bordeaux, red, France). )
generate a structured textual output including the set of constraints and one or more item categories associated with the one or more items, wherein the structured textual output includes a first list of textual elements and a second list of textual elements, wherein each of textual elements in the first list corresponds to one of the set of constraints and each of the textual elements in the second list corresponds to one of one or more item categories; ([0079] the artificial intelligence framework 128 may map the user request to certain primary dimensions, such as categories, attributes, and attribute values, that best characterize the available items desired. This gives the bot the ability to engage with the user to further refine the search constraints if necessary. For example, if a user asks the bot for information relating to dresses, the top attributes that need specification might be color, material, and style. Further, over time, machine learning may add deeper semantics and wider “world knowledge” to the system, to better understand the user intent. For example the input “I am looking for a dress for a wedding in June in Italy” means the dress should be appropriate for particular weather conditions at a given time and place, and should be appropriate for a formal occasion. Another example might include a user asking the bot for “gifts for my nephew”. The artificial intelligence framework 128 when trained will understand that gifting is a special type of intent, that the target recipient is male based on the meaning of “nephew”, and that attributes such as age, occasion, and hobbies/likes of the target recipient should be clarified.)
an inventory database that describes an inventory of a corresponding retailer; ([0078] an inventory of items available for purchase. [0086] a given item inventory (e.g., an eBay inventory, or database/cloud 126) to which it maps.)
It would have been obvious to one of ordinary skill in the art to include in the method, as taught by APPLEYARD, the features, as taught by Gaskill, since the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. It further would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify APPLEYARD, to include the teachings of Gaskill, in order to provide intelligent, personalized answers (Gaskill, [0006]).
Regarding Claim 3, APPLEYARD in view of Gaskill teaches the method of claim 1.
APPLEYARD discloses wherein sending the information describing the ranked set of the plurality of combinations of items comprises sending one or more of: a set of items included in each combination of items, a total price associated with each combination of items, a retailer associated with each combination of items, a set of items associated with each combination of items that is not available, or a set of replacement items. ([0037] Each of the optimized shopping lists can include one or more brick-and-mortar or online retailers and items that person 102 should purchase from each. Each of the optimized shopping lists is optimized and ranked based on the preferences of person 102, the retailer and item sentiment scores, the item pricing, and other factors. )
Regarding Claim 4, APPLEYARD in view of Gaskill teaches the method of claim 1.
APPLEYARD discloses wherein identifying a plurality of retailers based at least in part on a set of user data comprises identifying a plurality of retailers based at least in part on one or more of: a preference of the user for each retailer of the plurality of retailers, a preference of the user for an attribute of an item, an order history associated with the user, or a location associated with the user.. ([0037] Each of the optimized shopping lists can include one or more brick-and-mortar or online retailers and items that person 102 should purchase from each. Each of the optimized shopping lists is optimized and ranked based on the preferences of person 102, the retailer and item sentiment scores, the item pricing, and other factors. )
Regarding Claim 5, APPLEYARD in view of Gaskill teaches the method of claim 1.
APPLEYARD discloses wherein extracting the set of constraints comprises extracting a budget.. ([0037] Each of the optimized shopping lists can include one or more brick-and-mortar or online retailers and items that person 102 should purchase from each. Each of the optimized shopping lists is optimized and ranked based on the preferences of person 102, the retailer and item sentiment scores, the item pricing, and other factors. [claim 3] wherein the user preference includes one or more of an environmental impact preference, a price preference, [claim 6] a dynamic price condition,)
Regarding Claim 6, APPLEYARD in view of Gaskill teaches the method of claim 1.
APPLEYARD discloses wherein generating the score for the combination of items comprises: generating a total price associated with the combination of items based at least in part on the set of item data associated with each item included in the combination of items; and generating the score for the combination of items based at least in part on the total price associated with the combination of items. ([0036] a bid is a simple total price for the entire shopping sub-list,,)
Regarding Claim 7, APPLEYARD in view of Gaskill teaches the method of claim 6.
APPLEYARD discloses wherein the total price associated with the combination of items is further based at least in part on a delivery fee associated with an order including the combination of items.. ([0012] Carbon footprint can be calculated and used as factor for analysis and optimization. Further, the carbon footprint is not limited to just a given product's carbon footprint, but also relates to the carbon footprint generated by the shopper and the retailer (e.g., the carbon footprint involved with shipping, transportation, and customer pickup, etc.). Generally, the optimization engine can generate an optimized shopping list based on the proximity of a brick-and-mortar retailer to a shopper, to offset a carbon footprint by directing the shopper to the brick-and-mortar retailer. )
Regarding Claim 8, APPLEYARD in view of Gaskill teaches the method of claim 1.
APPLEYARD discloses wherein generating the score for the combination of items comprises: predicting an availability of each item included in the combination of items at a retailer location associated with a corresponding retailer based at least in part on the set of item data associated with each item included in the combination of items; and generating the score for the combination of items based at least in part on the predicted availability of each item.. ([0025] Data servers 130 include one or more servers hosting reviews, feedback, or other sentiment data about goods available for purchase, about retailers, or both. For example, data servers 130 can include recall databases, service bulletin databases, product comment web pages, social media platforms, and other structured or unstructured data repositories about goods available for purchase and retailers. [0037] Each of the optimized shopping lists can include one or more brick-and-mortar or online retailers and items that person 102 should purchase from each. Each of the optimized shopping lists is optimized and ranked based on the preferences of person 102, the retailer and item sentiment scores, the item pricing, and other factors. ,)
Regarding Claim 10, APPLEYARD in view of Gaskill teaches the method of claim 1.
APPLEYARD discloses wherein sending the information describing the ranked set of the plurality of combinations of items further causes the client device to display an option to add each combination of items to a shopping list associated with the user. ([0041] During step 320, customer data 162 receives the selected optimized shopping list as modified (if applicable) at optimization server 150 (e.g., optimizing interaction 228, etc.). (user selection of an optimized shopping list is interpreted as adding the combination of items to a shopping list))
Regarding Claim 11, APPLEYARD discloses 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 comprising:
receiving, at an online concierge system, a free-text query from a client device associated with a user of the online concierge system, wherein the free-text query describes one or more items included among one or more inventories of one or more retailers associated with the online concierge system and a set of constraints; ([0041] During step 310, discount engine 154 and sentiment scoring engine 156 receive a shopping list of goods to purchase at optimization server 150 from user computer 120 (e.g., optimizing interaction 210, etc.). During step 312, discount engine 154 analyzes items on the received shopping list and searches for possible discount offerings from various brands, manufacturers, or retailers to compile a list of possible discounts that may be applied to the items (e.g., optimizing interactions 212, 214, etc.). [0011] comprehensive set of real-time factors such as preferences, retailers pricing, discounts, buying patterns, rating, consumer sentiments, environmental impact, and other criteria (constraints) [0024] person 102 can enter a shopping list of goods to purchase into a text input form of the loaded optimization web page displayed by the web browser program, )
generating a prompt comprising the free-text query and a request to identify the one or more items and the set of constraints included in the free-text query; ([0024] the web browser program can transmit the shopping list of goods to purchase to optimization server 150. Subsequently, optimization server 150 can generate an optimized shopping list )
identifying a plurality of retailers based at least in part on a set of user data associated with the user; ([0009] The goods on the shopping list are accessed and analyzed by the optimization server. In particular, for each item on the shopping list, the optimization server queries all known data sources (e.g., retailers, service providers, manufactures, etc.) to retrieve available discounts for the item. The shopping list is then segmented into multiple sublists per retailer, based on the discounts, sentiment score by retailer, and product. )
for each retailer of the plurality of retailers: ([0028] one or more brick-and-mortar or online retailers)
identifying a set of items associated with each item category of the one or more item categories, wherein the set of items is included among an inventory of a corresponding retailer, identifying, based at least in part on the set of constraints, a combination of items comprising a subset of the set of items associated with each item category of the one or more item categories, and ([0041] During step 316, segment routing engine 158 groups items on the shopping list into shopping sub-lists based on discount information and sentiment scores, submits the shopping sub-lists to retailers for bidding, and receives bids (e.g., optimizing interactions 220, 222, etc.). )
generating a score for the combination of items based at least in part on the set of user data associated with the user and a set of item data associated with each item included in the combination of items, wherein the score indicates a likelihood of conversion by the user for the combination of items; ([0028] computes a sentiment score for each item and for each retailer. Segment routing engine 158 groups items on a shopping list, based on discount information (e.g., as provided by discount engine 154, etc.) and the customer sentiment scores (e.g., as provided by sentiment scoring engine 156, etc.), into shopping sub-lists and submits the shopping sub-lists to retailers for bidding (e.g., submits to retail servers 140, etc.).)
ranking a plurality of combinations of items determined for the plurality of retailers based at least in part on the score computed for each combination of items; and ([0012] the ranking can be based on cost, quantity, incentives, retailers rating, location, sentiments, or time. Each shopper can have different preferences and further refinement can be done by a ranking engine. Retailers can request the carbon footprint of the products they sell, and when the optimization server receives the retailer's bid it can use the carbon footprint to further refine the search results. Accordingly, the optimization engine can take a complex request and intelligently break it into a bundle of requests to be optimized. [0028] Each of the optimized shopping lists is optimized and ranked based on the shopper's preferences, the retailer and item sentiment scores, and the item's pricing. )
sending information describing a ranked set of the plurality of combinations of items for display to the client device associated with the user, wherein the sending causes the client device to display the ranked set of the plurality of combinations of items.. ([0041] During step 318, ranking engine 160 aggregates shopping sub-list bids, analyzes the results, generates one or more optimized shopping lists, and transmits the optimized shopping lists from optimization server 150 to user computer 120 (e.g., optimizing interactions 224, 226, etc.).)
But does not explicitly disclose providing the prompt to a large language model to obtain a structured textual output, wherein the prompt contains instructions that cause the large language model to: extract, from the textual output, the set of constraints; and generate a structured textual output including the set of constraints and one or more item categories associated with the one or more items, wherein the structured textual output includes a first list of textual elements and a second list of textual elements, wherein each of textual elements in the first list corresponds to one of the set of constraints and each of the textual elements in the second list corresponds to one of one or more item categories; an inventory database that describes an inventory of a corresponding retailer;
Gaskill, on the other hand, teaches providing the prompt to a large language model to obtain a structured textual output, providing the prompt to a large language model to obtain a textual output; ([0077] the NLU component 214 processes a sequence of user inputs including an original query and further data provided by a user in response to machine-generated prompts from the dialog manager 216 in a multi-turn interactive dialog. [0054] A language model component uses statistical models of grammar to define how words are put together in a sentence. Such models can include n-gram-based models or Deep Neural Networks built on top of word embeddings. A speech-to-text (STT) decoder component may convert a speech utterance into a sequence of words typically leveraging features derived from a raw signal using the feature extraction component, the acoustic model component, and the language model component in a Hidden Markov Model (HMM) framework to derive word sequences from feature sequences.)
wherein the prompt contains instructions that cause the large language model to: extract, from the textual output, the set of constraints; and extracting, from the textual output, the set of constraints and one or more item categories associated with the one or more items; ([0089] The NER sub-component 810 may extract deeper information from parsed user input (e.g., brand names, size information, colors, and other descriptors) and help transform the user natural language query into a structured query comprising such parsed data elements. The NER sub-component may also tap into world knowledge to help resolve meaning for extracted terms. For example, a query for “a bordeaux” may more successfully determine from an online dictionary and encyclopedia that the query term may refer to an item category (wine), attributes (type, color, origin location), and respective corresponding attribute values (Bordeaux, red, France). )
generate a structured textual output including the set of constraints and one or more item categories associated with the one or more items, wherein the structured textual output includes a first list of textual elements and a second list of textual elements, wherein each of textual elements in the first list corresponds to one of the set of constraints and each of the textual elements in the second list corresponds to one of one or more item categories; ([0079] the artificial intelligence framework 128 may map the user request to certain primary dimensions, such as categories, attributes, and attribute values, that best characterize the available items desired. This gives the bot the ability to engage with the user to further refine the search constraints if necessary. For example, if a user asks the bot for information relating to dresses, the top attributes that need specification might be color, material, and style. Further, over time, machine learning may add deeper semantics and wider “world knowledge” to the system, to better understand the user intent. For example the input “I am looking for a dress for a wedding in June in Italy” means the dress should be appropriate for particular weather conditions at a given time and place, and should be appropriate for a formal occasion. Another example might include a user asking the bot for “gifts for my nephew”. The artificial intelligence framework 128 when trained will understand that gifting is a special type of intent, that the target recipient is male based on the meaning of “nephew”, and that attributes such as age, occasion, and hobbies/likes of the target recipient should be clarified.)
an inventory database that describes an inventory of a corresponding retailer; ([0078] an inventory of items available for purchase. [0086] a given item inventory (e.g., an eBay inventory, or database/cloud 126) to which it maps.)
It would have been obvious to one of ordinary skill in the art to include in the method, as taught by APPLEYARD, the features, as taught by Gaskill, since the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. It further would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify APPLEYARD, to include the teachings of Gaskill, in order to provide intelligent, personalized answers (Gaskill, [0006]).
Claim 13 recites a system comprising substantially similar limitations as claim 3. The claim is rejected under substantially similar grounds as claim 3.
Claim 14 recites a system comprising substantially similar limitations as claim 4. The claim is rejected under substantially similar grounds as claim 4.
Claim 15 recites a system comprising substantially similar limitations as claim 5. The claim is rejected under substantially similar grounds as claim 5.
Claim 16 recites a system comprising substantially similar limitations as claim 6. The claim is rejected under substantially similar grounds as claim 6.
Claim 17 recites a system comprising substantially similar limitations as claim 7. The claim is rejected under substantially similar grounds as claim 7.
Claim 18 recites a system comprising substantially similar limitations as claim 8. The claim is rejected under substantially similar grounds as claim 8.
Regarding Claim 20, APPLEYARD discloses A computer system comprising: a processor; and a non-transitory computer-readable storage medium storing instructions that, when executed by the processor, perform actions comprising:
receiving, at an online concierge system, a free-text query from a client device associated with a user of the online concierge system, wherein the free-text query describes one or more items included among one or more inventories of one or more retailers associated with the online concierge system and a set of constraints; ([0041] During step 310, discount engine 154 and sentiment scoring engine 156 receive a shopping list of goods to purchase at optimization server 150 from user computer 120 (e.g., optimizing interaction 210, etc.). During step 312, discount engine 154 analyzes items on the received shopping list and searches for possible discount offerings from various brands, manufacturers, or retailers to compile a list of possible discounts that may be applied to the items (e.g., optimizing interactions 212, 214, etc.). [0011] comprehensive set of real-time factors such as preferences, retailers pricing, discounts, buying patterns, rating, consumer sentiments, environmental impact, and other criteria (constraints) [0024] person 102 can enter a shopping list of goods to purchase into a text input form of the loaded optimization web page displayed by the web browser program, )
generating a prompt comprising the free-text query and a request to identify the one or more items and the set of constraints included in the free-text query; ([0024] the web browser program can transmit the shopping list of goods to purchase to optimization server 150. Subsequently, optimization server 150 can generate an optimized shopping list )
extracting, from the textual output, the set of constraints and one or more item categories associated with the one or more items; ([0010] Further, the ability to learn from shopper buying decisions to enhance the future shopping experiences (i.e., self-learning) further enhances the shopping experience. )
identifying a plurality of retailers based at least in part on a set of user data associated with the user; ([0009] The goods on the shopping list are accessed and analyzed by the optimization server. In particular, for each item on the shopping list, the optimization server queries all known data sources (e.g., retailers, service providers, manufactures, etc.) to retrieve available discounts for the item. The shopping list is then segmented into multiple sublists per retailer, based on the discounts, sentiment score by retailer, and product. )
for each retailer of the plurality of retailers: ([0028] one or more brick-and-mortar or online retailers)
identifying a set of items associated with each item category of the one or more item categories, wherein the set of items is included in an inventory of a corresponding retailer, identifying, based at least in part on the set of constraints, a combination of items comprising a subset of the set of items associated with each item category of the one or more item categories, and ([0041] During step 316, segment routing engine 158 groups items on the shopping list into shopping sub-lists based on discount information and sentiment scores, submits the shopping sub-lists to retailers for bidding, and receives bids (e.g., optimizing interactions 220, 222, etc.). )
generating a score for the combination of items based at least in part on the set of user data associated with the user and a set of item data associated with each item included in the combination of items, wherein the score indicates a likelihood of conversion by the user for the combination of items; ([0028] computes a sentiment score for each item and for each retailer. Segment routing engine 158 groups items on a shopping list, based on discount information (e.g., as provided by discount engine 154, etc.) and the customer sentiment scores (e.g., as provided by sentiment scoring engine 156, etc.), into shopping sub-lists and submits the shopping sub-lists to retailers for bidding (e.g., submits to retail servers 140, etc.).)
ranking a plurality of combinations of items determined for the plurality of retailers based at least in part on the score computed for each combination of items; and ([0012] the ranking can be based on cost, quantity, incentives, retailers rating, location, sentiments, or time. Each shopper can have different preferences and further refinement can be done by a ranking engine. Retailers can request the carbon footprint of the products they sell, and when the optimization server receives the retailer's bid it can use the carbon footprint to further refine the search results. Accordingly, the optimization engine can take a complex request and intelligently break it into a bundle of requests to be optimized. [0028] Each of the optimized shopping lists is optimized and ranked based on the shopper's preferences, the retailer and item sentiment scores, and the item's pricing. )
sending information describing a ranked set of the plurality of combinations of items for display to the client device associated with the user, wherein the sending causes the client device to display the ranked set of the plurality of combinations of items.. ([0041] During step 318, ranking engine 160 aggregates shopping sub-list bids, analyzes the results, generates one or more optimized shopping lists, and transmits the optimized shopping lists from optimization server 150 to user computer 120 (e.g., optimizing interactions 224, 226, etc.).)
But does not explicitly disclose providing the prompt to a large language model to obtain a structured textual output, wherein the prompt contains instructions that cause the large language model to: extract, from the textual output, the set of constraints; and generate a structured textual output including the set of constraints and one or more item categories associated with the one or more items, wherein the structured textual output includes a first list of textual elements and a second list of textual elements, wherein each of textual elements in the first list corresponds to one of the set of constraints and each of the textual elements in the second list corresponds to one of one or more item categories; an inventory database that describes an inventory of a corresponding retailer;
Gaskill, on the other hand, teaches providing the prompt to a large language model to obtain a structured textual output, providing the prompt to a large language model to obtain a textual output; ([0077] the NLU component 214 processes a sequence of user inputs including an original query and further data provided by a user in response to machine-generated prompts from the dialog manager 216 in a multi-turn interactive dialog. [0054] A language model component uses statistical models of grammar to define how words are put together in a sentence. Such models can include n-gram-based models or Deep Neural Networks built on top of word embeddings. A speech-to-text (STT) decoder component may convert a speech utterance into a sequence of words typically leveraging features derived from a raw signal using the feature extraction component, the acoustic model component, and the language model component in a Hidden Markov Model (HMM) framework to derive word sequences from feature sequences.)
wherein the prompt contains instructions that cause the large language model to: extract, from the textual output, the set of constraints; and extracting, from the textual output, the set of constraints and one or more item categories associated with the one or more items; ([0089] The NER sub-component 810 may extract deeper information from parsed user input (e.g., brand names, size information, colors, and other descriptors) and help transform the user natural language query into a structured query comprising such parsed data elements. The NER sub-component may also tap into world knowledge to help resolve meaning for extracted terms. For example, a query for “a bordeaux” may more successfully determine from an online dictionary and encyclopedia that the query term may refer to an item category (wine), attributes (type, color, origin location), and respective corresponding attribute values (Bordeaux, red, France). )
generate a structured textual output including the set of constraints and one or more item categories associated with the one or more items, wherein the structured textual output includes a first list of textual elements and a second list of textual elements, wherein each of textual elements in the first list corresponds to one of the set of constraints and each of the textual elements in the second list corresponds to one of one or more item categories; ([0079] the artificial intelligence framework 128 may map the user request to certain primary dimensions, such as categories, attributes, and attribute values, that best characterize the available items desired. This gives the bot the ability to engage with the user to further refine the search constraints if necessary. For example, if a user asks the bot for information relating to dresses, the top attributes that need specification might be color, material, and style. Further, over time, machine learning may add deeper semantics and wider “world knowledge” to the system, to better understand the user intent. For example the input “I am looking for a dress for a wedding in June in Italy” means the dress should be appropriate for particular weather conditions at a given time and place, and should be appropriate for a formal occasion. Another example might include a user asking the bot for “gifts for my nephew”. The artificial intelligence framework 128 when trained will understand that gifting is a special type of intent, that the target recipient is male based on the meaning of “nephew”, and that attributes such as age, occasion, and hobbies/likes of the target recipient should be clarified.)
an inventory database that describes an inventory of a corresponding retailer; ([0078] an inventory of items available for purchase. [0086] a given item inventory (e.g., an eBay inventory, or database/cloud 126) to which it maps.)
It would have been obvious to one of ordinary skill in the art to include in the method, as taught by APPLEYARD, the features, as taught by Gaskill, since the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. It further would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify APPLEYARD, to include the teachings of Gaskill, in order to provide intelligent, personalized answers (Gaskill, [0006]).
Claims 2, 12 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent Application No. 2015/0058154 A1 to APPLEYARD in view of US 2018/0052913 A1 to Gaskill in view of U.S. Patent Application No. 2025/0094898 A1 to Saurav.
Regarding Claim 2, APPLEYARD in view of Gaskill teaches the method of claim 1.
However the combination of APPLEYARD and Gaskill does not explicitly teach generating a user embedding for the user based at least in part on the set of user data associated with the user; generating an item embedding for each item included in the combination of items based at least in part on the set of item data associated with a corresponding item; generating a dot product of the user embedding and the item embedding for each item included in the combination of items; aggregating the dot product of the user embedding and the item embedding for each item included in the combination of items; and generating the score for the combination of items based at least in part on the aggregated dot product of the user embedding and the item embedding for each item included in the combination of items..
SAURAV, on the other hand, teaches generating a user embedding for the user based at least in part on the set of user data associated with the user; generating an item embedding for each item included in the combination of items based at least in part on the set of item data associated with a corresponding item; generating a dot product of the user embedding and the item embedding for each item included in the combination of items; aggregating the dot product of the user embedding and the item embedding for each item included in the combination of items; and generating the score for the combination of items based at least in part on the aggregated dot product of the user embedding and the item embedding for each item included in the combination of items. ([0071] In some embodiments, the combined model 396 may be used to combine the seller embeddings generated by the seller model 392 and the item embeddings generated by the item model 394, to form item-seller combinations each with an associated affinity score. In some examples, for each item-seller pair or combination, the combined model 396 may perform a dot product operation based on the embeddings of the item and the seller in the pair or combination, to compute an affinity score representing a degree of affinity between the item and the seller. A higher affinity score represents a higher degree of affinity between the item and the seller. An affinity indicates how close the embedding of the seller is to the embeddings of the items present in the marketplace, by considering the catalog of the seller. [0104] the retrieval model 601 may generate a list of items each of which has a higher-than-threshold affinity score when being paired with the query seller. )
It would have been obvious to one of ordinary skill in the art to include in the method, as taught by APPLEYARD and Gaskill, the features as taught by SAURAV, since the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. It further would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination, to include the teachings of SAURAV, in order to generate a recommendation list (SAURAV, [0001]).
Claim 12 recites a system comprising substantially similar limitations as claim 2. The claim is rejected under substantially similar grounds as claim 2.
Claims 9, 19 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent Application No. 2015/0058154 A1 to APPLEYARD in view of US 2018/0052913 A1 to Gaskill in view of U.S. Patent Application No. 2024/0037863 A1 to Cocchiarella.
Regarding Claim 9, APPLEYARD in view of Gaskill teaches the method of claim 8.
However the combination of APPLEYARD and Gaskill does not explicitly teach further comprising: determining a percentage of items included in the combination of items associated with at least a threshold predicted availability at the retailer location; and selecting the ranked set of the plurality of combinations of items based at least in part on the percentage of items included in the combination of items associated with at least the threshold predicted availability at the retailer location..
Cocchiarella, on the other hand, teaches further comprising: determining a percentage of items included in the combination of items associated with at least a threshold predicted availability at the retailer location; and selecting the ranked set of the plurality of combinations of items based at least in part on the percentage of items included in the combination of items associated with at least the threshold predicted availability at the retailer location.. ([0051] The confidence score may be the error or uncertainty score of the probability of availability and may be calculated using any standard statistical error measurement. In some embodiments, the confidence score is based in part on whether the item-warehouse pair availability prediction was accurate for previous delivery orders (e.g., if an item was predicted to be available at a warehouse 210 and was not found by a shopper 208 or was predicted to be unavailable but was found by the shopper 208).)
It would have been obvious to one of ordinary skill in the art to include in the method, as taught by APPLEYARD and Gaskill, the features as taught by Cocchiarella, since the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. It further would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination, to include the teachings of Cocchiarella, in order to provide their customers with options to suit their personal needs and tastes (Cocchiarella, [0002]).
Claim 19 recites a system comprising substantially similar limitations as claim 9. The claim is rejected under substantially similar grounds as claim 9.
Response to Arguments
Applicant’s arguments filed with respect to the rejection of claims under 35 USC 101 have been fully considered and are persuasive.
Applicant argues that the inability of computing systems to natively query multiple retailer inventory databases using free-text natural language is a well-recognized technical limitation. The claims address this technical problem by employing a specific technical pipeline that transforms unstructured free-text into structured, machine-actionable data by generating a prompt comprising the free-text query and a request to identify the one or more items and the set of constraints included in the free-text query, providing the prompt to a large language model to obtain a structured textual output, the prompt containing instructions that cause the large language model to generate the structured textual output that includes a first list of textual elements and a second list of textual elements corresponding to the set of constraints and one or more item categories. This pipeline converts an inherently unstructured input into two distinct structured lists that can be used to search across multiple retailer inventory databases. The claims provide an practical application that integrates the abstract idea into a particular practical application.
Applicant’s arguments with respect to rejection of the claim under 35 USC 103 have been considered but are moot in view of new grounds of rejection, necessitated by Applicant’s amendment.
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 nonprovisional extension fee (37 CFR 1.17(a)) 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 mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Michelle T. Kringen whose telephone number is (571)270-0159. The examiner can normally be reached M-F: 11am-7pm.
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.
/MICHELLE T KRINGEN/Primary Examiner, Art Unit 3689
Prosecution Insights