# US 2019/0318406 A1 · System for Bidding on Multi-Modal Sub-Spaces for E-Commerce Searches > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0318406 A1 - Document ID: US20190318406A1 - Status: Published application - Kind: A1 - Application number: 15/954,925 - Filed: 2018-04-17 - Published: 2019-10-17 - Earliest claimed: 2018-04-17 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Priyanka Agrawal; Ayushi Dalmia; Jaikrishnan Hari; Sachindra Joshi; Vikas C. Raykar; Raghavendra Singh - Web page: https://patentgrep.com/patent/US20190318406A1 ## CPC - G06Q 30/0625: {by formulating product or service queries, e.g. using keywords or predefined options} - G06F 16/334: Query execution (filtering based on additional data G06F16/335) - G06F 16/50: of still image data - G06F 16/90335: {Query processing} - G06F 16/9532: Query formulation - 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, systems, and computer program products in connection with a system for bidding on multi-modal sub-spaces for e-commerce searches is provided herein. A computer-implemented method includes representing, in an embedding space affiliated with at least one electronic commerce website: (i) images related to one or more bids and (ii) items of text related to the one or more bids, the images and the items of text both coming from one or more bidding entities. Such a method also includes mapping a query to the embedding space based on a comparison of features of the query to (i) the images and (ii) the items of text. Further, such a method additionally includes selecting at least one of the one or more bidding entities based on the mapping, and outputting, to at least one user in response to the query, search results associated with the at least one selected bidding entity. ## Claims ### Claim 1 A computer-implemented method, the method comprising steps of: representing, in an embedding space affiliated with at least one electronic commerce website: (i) one or more images related to one or more bids and (ii) one or more items of text related to the one or more bids, said one or more images and said one or more items of text both coming from one or more bidding entities; mapping a query to the embedding space based on a comparison of one or more features of the query to (i) the one or more images and (ii) the one or more items of text; selecting at least one of the one or more bidding entities based on said mapping; and outputting, to at least one user in response to the query, search results associated with the at least one selected bidding entity; wherein the steps are carried out by at least one computing device. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, wherein said representing comprises representing, at one or more particular sub-spaces within the embedding space, and based on bid information submitted by the one or more bidding entities, (i) the one or more images related to the one or more bids and (ii) the one or more items of text related to the one or more bids. ### Claim 3 (depends on 1) The computer-implemented method of claim 1, wherein the one or more images comprise one or more images of one or more products offered for sale by the one or more bidding entities. ### Claim 4 (depends on 1) The computer-implemented method of claim 1, wherein the one or more items of text describe one or more products offered for sale by the one or more bidding entities. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, wherein the query comprises an image query. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, wherein the query comprises a text query. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, wherein said selecting comprises selecting the at least one bidding entity based on a weighted similarity score between (i) the one or more features of the query and (ii) revenue generated, for each of the one or more bidding entities. ### Claim 8 (depends on 1) The computer-implemented method of claim 1, wherein said outputting comprises deriving the search results from one or more catalogues associated with the at least one selected bidding entity. ### Claim 9 A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computing device to cause the computing device to: represent, in an embedding space affiliated with at least one electronic commerce website: (i) one or more images related to one or more bids and (ii) one or more items of text related to the one or more bids, said one or more images and said one or more items of text both coming from one or more bidding entities; map a query to the embedding space based on a comparison of one or more features of the query to (i) the one or more images and (ii) the one or more items of text; select at least one of the one or more bidding entities based on said mapping; and output, to at least one user in response to the query, search results associated with the at least one selected bidding entity. ### Claim 10 (depends on 9) The computer program product of claim 9, wherein said representing comprises representing, at one or more particular sub-spaces within the embedding space, and based on bid information submitted by the one or more bidding entities, (i) the one or more images related to the one or more bids and (ii) the one or more items of text related to the one or more bids. ### Claim 11 (depends on 9) The computer program product of claim 9, wherein the one or more images comprise one or more images of one or more products offered for sale by the one or more bidding entities, and wherein the one or more items of text comprise one or more items of text describing one or more products offered for sale by the one or more bidding entities. ### Claim 12 (depends on 9) The computer program product of claim 9, wherein the query comprises at least one of an image query and a text query. ### Claim 13 (depends on 9) The computer program product of claim 9, wherein said selecting comprises selecting the at least one bidding entity based on a weighted similarity score between the one or more features of the query and revenue generated from each of the one or more bidding entities. ### Claim 14 (depends on 9) The computer program product of claim 9, wherein said outputting comprises deriving the search results from one or more catalogues associated with the at least one selected bidding entity. ### Claim 15 A system comprising: a memory; and at least one processor operably coupled to the memory and configured for: representing, in an embedding space affiliated with at least one electronic commerce website: (i) one or more images related to one or more bids and (ii) one or more items of text related to the one or more bids, said one or more images and said one or more items of text both coming from one or more bidding entities; mapping a query to the embedding space based on a comparison of one or more features of the query to (i) the one or more images and (ii) the one or more items of text; selecting at least one of the one or more bidding entities based on said mapping; and outputting, to at least one user in response to the query, search results associated with the at least one selected bidding entity. ### Claim 16 (depends on 15) The system of claim 15, wherein said representing comprises representing, at one or more particular sub-spaces within the embedding space, and based on bid information submitted by the one or more bidding entities, (i) the one or more images related to the one or more bids and (ii) the one or more items of text related to the one or more bids. ### Claim 17 A computer-implemented method, the method comprising steps of: generating an embedding space associated with at least one electronic commerce website, wherein the embedding space comprises multiple sub-spaces associated with multiple types of commercial offerings of the at least one electronic commerce website; displaying the multiple sub-spaces via a user interface; processing one or more bids, submitted by one or more bidding entities, for coupling one or more offerings to one or more of the multiple sub-spaces, wherein said processing comprises processing one or more interactions between the one or more bidding entities and the user interface; assigning one or more offerings from one or more of the bidding entities to one or more of the multiple sub-spaces based on said processing; and outputting, to at least one user in response to a query associated with a given one of the multiple types of commercial offerings of the at least one electronic commerce website, search results associated with the bidding entity assigned to the sub-space associated with the given type of commercial offering; wherein the steps are carried out by at least one computing device. ### Claim 18 (depends on 17) The computer-implemented method of claim 17, wherein the query comprises an image query. ### Claim 19 (depends on 17) The computer-implemented method of claim 17, wherein the query comprises a text query. ### Claim 20 (depends on 17) The computer-implemented method of claim 17, wherein said outputting comprises deriving the search results from one or more catalogues associated with the at least one selected bidding entity.