# US 2021/0241774 A1 · Detecting voice grocery concepts from catalog items > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0241774 A1 - Document ID: US20210241774A1 - Status: Published application - Kind: A1 - Application number: 16/777,775 - Filed: 2020-01-30 - Published: 2021-08-05 - Earliest claimed: 2020-01-30 - Assignees: Walmart Apollo, LLC - Applicants: Walmart Apollo, LLC - Inventors: Ghodratollah Aalipour Hafshejani; Phani Ram Sayapaneni - Web page: https://patentgrep.com/patent/US20210241774A1 ## CPC - G10L 15/26: Speech to text systems (G10L15/08 takes precedence) - G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback} - G06F 16/90332: {Natural language query formulation or dialogue systems} - G06Q 30/0627: {by specifying product or service characteristics, e.g. product dimensions} - G06Q 30/0641: {utilising user interfaces specially adapted for shopping} - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR ## Abstract A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform receiving a voice command from a user to perform a virtual action intended to apply to one item of two or more items in a cart of the user; generating a concept vector representing a concept in the voice command; transforming the respective item attributes for each of the two or more items into a respective feature vector; generating a respective candidate score for the each of the two or more items; identifying the one item to which the voice command is intended to apply; and executing an action with respect to the one item based on the voice command. Other embodiments are disclosed. ## Claims ### Claim 1 A system comprising: one or more processors; and one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform: receiving a voice command from a user to perform a virtual action intended to apply to one item of two or more items in a cart of the user, the two or more items each being associated with respective item attributes; generating a concept vector representing a concept in the voice command relating to the one of the two or more items; transforming the respective item attributes for each of the two or more items into a respective feature vector for the each of the two or more items; generating a respective candidate score for the each of the two or more items based at least in part on the concept vector and the respective feature vector for the each of the two or more items; identifying the one item to which the voice command is intended to apply, wherein the one item is identified from among the two or more items, and wherein the identifying is based on which of the two or more items is associated with a highest one of the respective candidate scores for the two or more items; and executing an action with respect to the one item based on the voice command. ### Claim 2 (depends on 1) The system of claim 1, wherein executing the action with respect to the one item based on the voice command further comprises one of: removing the one item of the two or more items from the cart of the user; or modifying a quantity of the one item in the cart of the user. ### Claim 3 (depends on 1) The system of claim 1, wherein generating the concept vector further comprises: performing a search using the concept as a search query to determine a set of items associated with the concept; and generating the concept vector based on common attributes across the set of items. ### Claim 4 (depends on 1) The system of claim 1, wherein generating the respective candidate score for the each of the two or more items further comprises: generating a respective search query frequency score for the each of the two or more items; and generating a respective feature vector similarity score for the each of the two or more items. ### Claim 5 (depends on 4) The system of claim 4, wherein generating the respective candidate score for the each of the two or more items further comprises: adding the respective feature vector similarity score for the each of the two or more items to the respective search query frequency score for the each of the two or more items. ### Claim 6 (depends on 4) The system of claim 4, wherein: the respective feature vector similarity score for the each of the two or more items is generated using a Jaccard Similarity measurement between (a) the concept vector for the concept and (b) the respective feature vector for the each of the two or more items. ### Claim 7 (depends on 4) The system of claim 4, wherein: the respective feature vector similarity score for the each of the two or more items is generated using a Cosine Similarity measurement between (a) the concept vector for the concept and (b) the respective feature vector for the each of the two or more items. ### Claim 8 (depends on 4) The system of claim 4, wherein: the respective search query frequency score for the each of the two or more items is based on a search performed using a search query that is based on a concatenation of (a) a respective brand of the each of the two or more items and (b) the concept. ### Claim 9 (depends on 1) The system of claim 1, wherein transforming the respective item attributes for the each of the two or more items into the respective feature vector further comprises: generating respective embeddings for the respective item attributes for the each of the two or more items. ### Claim 10 (depends on 1) The system of claim 1, wherein: the respective item attributes for the each of the two or more items comprise a product type, a global product type, a shelf title, an aisle title, a category, and a department. ### Claim 11 The method being implemented via execution of computing instructions configured to run at one or more processors and stored at one or more non-transitory computer-readable media, the method comprising: receiving a voice command from a user to perform a virtual action intended to apply to one item of two or more items in a cart of the user, the two or more items each being associated with respective item attributes; generating a concept vector representing a concept in the voice command relating to the one of the two or more items; transforming the respective item attributes for each of the two or more items into a respective feature vector for the each of the two or more items; generating a respective candidate score for the each of the two or more items based at least in part on the concept vector and the respective feature vector for the each of the two or more items; identifying the one item to which the voice command is intended to apply, wherein the one item is identified from among the two or more items, and wherein the identifying is based on which of the two or more items is associated with a highest one of the respective candidate scores for the two or more items; and executing an action with respect to the one item based on the voice command. ### Claim 12 (depends on 11) The method of claim 11, wherein executing the action with respect to the one item based on the voice command further comprises one of: removing the one item of the two or more items from the cart of the user; or modifying a quantity of the one item in the cart of the user. ### Claim 13 (depends on 11) The method of claim 11, wherein generating the concept vector further comprises: performing a search using the concept as a search query to determine a set of items associated with the concept; and generating the concept vector based on common attributes across the set of items. ### Claim 14 (depends on 11) The method of claim 11, wherein generating the respective candidate score for the each of the two or more items further comprises: generating a respective search query frequency score for the each of the two or more items; and generating a respective feature vector similarity score for the each of the two or more items. ### Claim 15 (depends on 14) The method of claim 14, wherein generating the respective candidate score for the each of the two or more items further comprises: adding the respective feature vector similarity score for the each of the two or more items to the respective search query frequency score for the each of the two or more items. ### Claim 16 (depends on 14) The method of claim 14, wherein: the respective feature vector similarity score for the each of the two or more items is generated using a Jaccard Similarity measurement between (a) the concept vector for the concept and (b) the respective feature vector for the each of the two or more items. ### Claim 17 (depends on 14) The method of claim 14, wherein: the respective feature vector similarity score for the each of the two or more items is generated using a Cosine Similarity measurement between (a) the concept vector for the concept and (b) the respective feature vector for the each of the two or more items. ### Claim 18 (depends on 14) The method of claim 14, wherein: the respective search query frequency score for the each of the two or more items is based on a search performed using a search query that is based on a concatenation of (a) a respective brand of the each of the two or more items and (b) the concept. ### Claim 19 (depends on 11) The method of claim 11, wherein transforming the respective item attributes for the each of the two or more items into the respective feature vector further comprises: generating respective embeddings for the respective item attributes for the each of the two or more items. ### Claim 20 (depends on 11) The method of claim 11, wherein: the respective item attributes for the each of the two or more items comprise a product type, a global product type, a shelf title, an aisle title, a category, and a department.