# US 2019/0378197 A1 · Matching customer and product behavioral traits > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0378197 A1 - Document ID: US20190378197A1 - Status: Published application - Kind: A1 - Application number: 16/547,636 - Filed: 2019-08-22 - Published: 2019-12-12 - Earliest claimed: 2016-02-03 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Alan M.E. Leong; Shaun N. Maharaj; Parnit Pooni; Chi Kam P. Yau - Web page: https://patentgrep.com/patent/US20190378197A1 ## CPC - G06Q 30/0631: {Recommending goods or services} - G06F 16/24: Querying - G06Q 10/40: Business processes related to social networking or social networking services - 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 At least one detail for at least one product in a group of products is received. At least one input for at least one customer in a group of customers is received. At least one detail for at least one product and at least one input for at least one customer is stored to a database repository. Product traits for at least one product are generated and stored to a database repository. Customer traits for at least one customer are generated and stored to a database repository. The generation of customer traits is independent from the generation of product traits. At least one recommendation for matching at least one product to at least one customer is generated. The at least one recommendation is based on the generated traits of the at least one product and the generated traits of the at least one customer. ## Claims ### Claim 1 A computer-implemented method comprising: receiving, by one or more computer processors, details for a product in a-merchandise catalog of products, the details comprising a product name, a hierarchy of the product in the merchandise catalog, a product description and a list of attributes; receiving, by one or more computer processors, input for a customer, the input comprising a purchase history of products ordered from the merchandise catalog of products; storing, by one or more computer processors, the details for the product and the input for the customer to a database repository; generating, by one or more computer processors, product traits automatically as the merchandise catalog of products is updated using Natural Language Processing to perform a linguistic analysis to infer product traits relating to the product; generating, by one or more computer processors, customer traits using the Natural Language Processing to perform a second linguistic analysis of the purchase history of products to infer personality traits of the customer, independently from generating the product traits; automated mapping, by one or more computer processors, the customer to products within the database repository by mapping product traits stored by the database repository to each identically matching customer trait stored by the database repository; and outputting, by one or more computer processors, a recommendation for a second product of the merchandise catalog of products based on the mapping of the product traits to the identically matching customer traits of the customer. ### Claim 2 (depends on 1) The method of claim 1, The method of claim 1, wherein the input for the customer further includes demographics selected from the group consisting of a location, an employment status, and a place of employment. ### Claim 3 (depends on 1) The method of claim 1, wherein the product traits and the customer traits are generated using Natural Language Processing by a Linguistic Inquiry and a Word Count psycholinguistic dictionary to identify words associated with psychologically-relevant categories. ### Claim 4 (depends on 1) The method of claim 1, wherein the step of outputting the recommendation comprises: determining a weighted average for the product traits and a weighted average for customer traits, wherein the weighted average comprises at least one product trait or at least one customer trait weighted by a number of occurrences of the at least one product trait or the at least one customer trait normalized as a percentage of all of the product traits or all of the customer traits; and matching a list of highest weighted product traits to a list of highest weighted customer traits based on a best-fit basis of the weighted averages. ### Claim 5 (depends on 1) The method of claim 1, wherein the input for the customer further includes demographics comprising social media activity and the social media activity comprises providing an image or video to a social media website. ### Claim 6 (depends on 5) The method of claim 5, further comprising wherein the Natural Language Processing using object recognition of the image or video from the social media activity to generate customer traits. ### Claim 7 A computer program product, the computer program product comprising: one or more computer readable storage media; and program instructions stored on the one or more computer readable storage media, the program instructions executing a computer-implemented method comprising: receiving, by one or more computer processors, details for a product in a merchandise catalog of products, the details comprising a product name, a hierarchy of the product in the merchandise catalog, product description and a list of attributes; receiving, by one or more computer processors, input for a customer, the input comprising a purchase history of products ordered from the merchandise catalog of products; storing, by one or more computer processors, the details for the product and the input for the customer to a database repository; generating, by one or more computer processors, product traits automatically as the merchandise catalog of products is updated using Natural Language Processing to perform a linguistic analysis to infer product traits relating to the product; generating, by one or more computer processors, customer traits using the Natural Language Processing to perform a second linguistic analysis of the purchase history of products to infer personality traits of the customer, independently from generating the product traits; automated mapping, by one or more computer processors, the customer to products within the database repository by mapping product traits stored by the database repository to each identically matching customer trait stored by the database repository; and outputting, by one or more computer processors, a recommendation for a second product of the merchandise catalog of products based on the mapping of the product traits to the identically matching customer traits of the customer. ### Claim 8 (depends on 7) The computer program product of claim 7, wherein the input for the customer further includes demographics selected from the group consisting of a location, an employment status, and a place of employment. ### Claim 9 (depends on 7) The computer program product of claim 7, wherein the product traits and the customer traits are generated using Natural Language Processing by a Linguistic Inquiry and a Word Count psycholinguistic dictionary to identify words associated with psychologically-relevant categories. ### Claim 10 (depends on 7) The computer program product of claim 7, wherein the step of outputting the recommendation comprises: determining a weighted average for the product traits and a weighted average for customer traits, wherein the weighted average comprises at least one product trait or at least one customer trait weighted by a number of occurrences of the at least one product trait or the at least one customer trait normalized as a percentage of all of the product traits or all of the customer traits; and matching a list of highest weighted product traits to a list of highest weighted customer traits based on a best-fit basis of the weighted averages. ### Claim 11 (depends on 7) The computer program product of claim 7, wherein the input for the customer further includes demographics comprising social media activity and the social media activity comprises providing an image or video to a social media website. ### Claim 12 (depends on 11) The computer program product of claim 11 further comprising wherein the Natural Language Processing is using object recognition of the image or video from the social media activity to generate customer traits. ### Claim 13 A computer system comprising: at least one processor; and a computer-readable storage media coupled to the at least one processor, wherein the computer-readable storage media contains program instructions executing a computer-implemented method comprising: receiving, by one or more computer processors, details for a product in a merchandise catalog of products, the details comprising a product name, a hierarchy of the product in the merchandise catalog, product description and a list of attributes; receiving, by one or more computer processors, input for a customer, the input comprising a purchase history of products ordered from the merchandise catalog of products; storing, by one or more computer processors, the details for the product and the input for the customer to a database repository; generating, by one or more computer processors, product traits automatically as the merchandise catalog of products is updated using Natural Language Processing to perform a linguistic analysis to infer product traits relating to the product; generating, by one or more computer processors, customer traits using the Natural Language Processing to perform a second linguistic analysis of the purchase history of products to infer personality traits of the customer, independently from generating the product traits; automated mapping, by one or more computer processors, the customer to products within the database repository by mapping product traits stored by the database repository to each identically matching customer trait stored by the database repository; and outputting, by one or more computer processors, a recommendation for a second product of the merchandise catalog of products based on the mapping of the product traits to the identically matching customer traits of the customer. ### Claim 14 (depends on 13) The computer system of claim 13, wherein the input for the customer further includes demographics selected from the group consisting of a location, an employment status, and a place of employment. ### Claim 15 (depends on 13) The computer system of claim 13, wherein the product traits and the customer traits are generated using Natural Language Processing by a Linguistic Inquiry and a Word Count psycholinguistic dictionary to identify words associated with psychologically-relevant categories. ### Claim 16 (depends on 13) The computer system of claim 13, wherein the step of outputting the recommendation comprises: determining a weighted average for the product traits and a weighted average for customer traits, wherein the weighted average comprises at least one product trait or at least one customer trait weighted by a number of occurrences of the at least one product trait or the at least one customer trait normalized as a percentage of all of the product traits or all of the customer traits; and matching a list of highest weighted product traits to a list of highest weighted customer traits based on a best-fit basis of the weighted averages. ### Claim 17 (depends on 13) The computer system of claim 13, wherein the input for the customer further includes demographics comprising social media activity and the social media activity comprises providing an image or video to a social media website. ### Claim 18 (depends on 17) The computer system of claim 17, further comprising wherein the Natural Language Processing is using object recognition of the image or video from the social media activity to generate customer traits.