# US 11,308,542 B2 · Systems and methods for using keywords extracted from reviews > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,308,542 B2 - Document ID: US11308542B2 - Status: Granted - Kind: B2 - Application number: 16/674,590 - Filed: 2019-11-05 - Published: 2021-05-06 - Granted: 2022-04-19 - Earliest claimed: 2019-11-05 - Assignees: Shopify Inc. - Applicants: Shopify Inc. - Inventors: Siavash Ghorbani; Carl Johan Gustavsson - Web page: https://patentgrep.com/patent/US11308542B2 ## CPC - G06Q 30/0631: {Recommending goods or services} - G06F 16/9536: Search customisation based on social or collaborative filtering - 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 - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Methods and systems for generating recommendations to supplement a listing of a merchant offering are disclosed. In some examples one or more keywords are extracted from one or more stored reviews associated with a first category of merchant offering. An association is stored between at least a first one of the extracted keywords and the first category. A recommendation is generated, to a merchant electronic device, to include the first keyword in a listing of a first merchant offering belonging to the first category. ## Claims ### Claim 1 A system comprising: a processor in communication with a storage, the processor configured to execute instructions to cause the system to: extract one or more keywords from one or more stored reviews associated with a first category of merchant offering; store an association between at least a first one of the extracted keywords and the first category; receive a partial entry of a merchant-submitted listing of the first merchant offering; generate a recommendation as an autocompletion text, based on the partial entry, to a merchant electronic device, to include the first keyword in a listing of a first merchant offering belonging to the first category, the autocompletion text including the first keyword; and update the merchant-submitted listing to append the recommendation including the first keyword to the merchant-submitted listing. ### Claim 2 (depends on 1) The system of claim 1, wherein the instructions further cause the system to: identify a set of positive reviews from the one or more stored reviews; wherein the first keyword associated with the first category is selected from keywords extracted from the set of positive reviews. ### Claim 3 (depends on 1) The system of claim 1, wherein each stored review is associated with a reviewer profile, wherein the instructions further cause the system to: identify, from one or more reviewer profiles associated respectively with the one or more stored reviews, at least one attribute; and further store an association between the at least one attribute and the first keyword. ### Claim 4 (depends on 3) The system of claim 3, wherein the at least one attribute includes a geographical attribute, and wherein the recommendation is generated for a geographically-targeted listing. ### Claim 5 (depends on 1) The system of claim 1, wherein the instructions further cause the system to: receive a merchant-submitted listing for the first merchant offering; and when the first keyword is absent from the merchant-submitted listing, generate the recommendation to add the first keyword into the merchant-submitted listing. ### Claim 6 (depends on 1) The system of claim 1, wherein the instructions further cause the system to: identify the first merchant offering as belonging to the first category based on a partial entry of a merchant-submitted listing for the first merchant offering; and generate the recommendation as a product description for the first merchant offering, including the first keyword. ### Claim 7 A computer-implemented method comprising: extract one or more keywords from one or more stored reviews associated with a first category of merchant offering; storing an association between at least a first one of the extracted keywords and the first category; receiving a partial entry of a merchant-submitted listing of the first merchant offering; generating a recommendation as an autocompletion text, based on the partial entry, to a merchant electronic device, to include the first keyword in a listing of a first merchant offering belonging to the first category, the autocompletion text including the first keyword; and updating the merchant-submitted listing to append the recommendation including the first keyword to the merchant-submitted listing. ### Claim 8 (depends on 7) The computer-implemented method of claim 7, further comprising: identifying a set of positive reviews from the one or more stored reviews; wherein the first keyword associated with the first category is selected from keywords extracted from the set of positive reviews. ### Claim 9 (depends on 7) The computer-implemented method of claim 7, wherein each stored review is associated with a reviewer profile, the method further comprising: identifying, from one or more reviewer profiles associated respectively with the one or more stored reviews, at least one attribute; and further storing an association between the at least one attribute and the first keyword. ### Claim 10 (depends on 9) The computer-implemented method of claim 9, wherein the at least one attribute includes a geographical attribute, and wherein the recommendation is generated for a geographically-targeted listing. ### Claim 11 (depends on 7) The computer-implemented method of claim 7, further comprising: receiving a merchant-submitted listing for the first merchant offering; and when the first keyword is absent from the merchant-submitted listing, generating the recommendation to add the first keyword into the merchant-submitted listing. ### Claim 12 (depends on 7) The computer-implemented method of claim 7, further comprising: identifying the first merchant offering as belonging to the first category based on a partial entry of a merchant-submitted listing for the first merchant offering; and generating the recommendation as a product description for the first merchant offering, including the first keyword. ### Claim 13 A non-transitory computer readable medium having instructions stored tangibly thereon, wherein the instructions, when executed, cause a system to: extract one or more keywords from one or more stored reviews associated with a first category of merchant offering; store an association between at least a first one of the extracted keywords and the first category; receive a partial entry of a merchant-submitted listing of the first merchant offering; generate a recommendation as an autocompletion text, based on the partial entry, to a merchant electronic device, to include the first keyword in a listing of a first merchant offering belonging to the first category, the autocompletion text including the first keyword; and update the merchant-submitted listing to append the recommendation including the first keyword to the merchant-submitted listing. ### Claim 14 (depends on 13) The non-transitory computer readable medium of claim 13, wherein the instructions further cause the system to: identify a set of positive reviews from the one or more stored reviews; wherein the first keyword associated with the first category is selected from keywords extracted from the set of positive reviews. ### Claim 15 (depends on 13) The non-transitory computer readable medium of claim 13, wherein each stored review is associated with a reviewer profile, wherein the instructions further cause the system to: identify, from one or more reviewer profiles associated respectively with the one or more stored reviews, at least one attribute; and further store an association between the at least one attribute and the first keyword. ### Claim 16 (depends on 13) The non-transitory computer readable medium of claim 13 wherein the instructions further cause the system to: receive a merchant-submitted listing for the first merchant offering; and when the first keyword is absent from the merchant-submitted listing, generate the recommendation to add the first keyword into the merchant-submitted listing. ### Claim 17 (depends on 13) The non-transitory computer readable medium of claim 13, wherein the instructions further cause the system to: identify the first merchant offering as belonging to the first category based on a partial entry of a merchant-submitted listing for the first merchant offering; and generate the recommendation as a product description for the first merchant offering, including the first keyword. ### Claim 18 (depends on 13) The non-transitory computer readable medium of claim 13, wherein the at least one attribute includes a geographical attribute, and wherein the recommendation is generated for a geographically-targeted listing. ### Claim 19 (depends on 3) The system of claim 3, wherein the merchant-submitted listing, after updating to include the first keyword associated with the at least one attribute, is also associated with the at least one attribute. ### Claim 20 (depends on 9) The method of claim 9, wherein the merchant-submitted listing, after updating to include the first keyword associated with the at least one attribute, is also associated with the at least one attribute.