# US 2017/0255652 A1 · Method for dynamically matching images with content items based on keywords in response to search queries > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2017/0255652 A1 - Document ID: US20170255652A1 - Status: Published application - Kind: A1 - Application number: 15/057,992 - Filed: 2016-03-01 - Published: 2017-09-07 - Earliest claimed: 2016-03-01 - Assignees: Baidu USA LLC - Applicants: Baidu USA LLC - Inventors: Qi Kong; Fan Zhu; Dong Li; Yifei Jiang; Shuang Wu; Youling Zou; Guang Yang; Jingao Wang - Web page: https://patentgrep.com/patent/US20170255652A1 ## CPC - G06F 16/538: Presentation of query results - G06F 16/5866: {using information manually generated, e.g. tags, keywords, comments, manually generated location and time information} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract According to one embodiment, in response to a search query received from a client device for searching content, one or more first keywords are determined from the search query. A lookup operation is performed in an image-to-keyword (image/keyword) mapping table based on the first keywords. The image/keyword mapping table includes a plurality of entries, each entry mapping an image identifier (ID) identifying an image to one or more second keywords. For each of images identified in the image/keyword mapping table, a matching degree is determined between the first keywords and the second keywords. A ranking process is performed based on matching degrees on a plurality of images identified in the image/keyword mapping table whose second keywords match at least a portion of the first keywords. ## Claims ### Claim 1 A computer-implemented method for matching images with content items based on keywords, the method comprising: in response to a search query received from a client device for searching content, determining, by a query analysis module executed by a processor, one or more first keywords from the search query; performing by a matching module a lookup operation in an image-to-keyword (image/keyword) mapping table based on the first keywords, the image/keyword mapping table including a plurality of entries, each entry mapping an image identifier (ID) identifying an image to one or more second keywords; for each of images identified in the image/keyword mapping table, determining by a ranking module a matching degree between the first keywords and the second keywords; and ranking by the ranking module based on matching degrees a plurality of images identified in the image/keyword mapping table whose second keywords match at least a portion of the first keywords. ### Claim 2 (depends on 1) The method of claim 1, further comprising: performing a search in a content store based on the search query to identifying a list of content items; and associating at least a portion of the ranked images with at least a portion of the content items based on ranking. ### Claim 3 (depends on 2) The method of claim 2, further comprising: integrating the at least a portion of the ranked images with the at least a portion of the content items to generate a search result; and transmitting the search result to the client device, wherein the ranked images are used as background images for the content items. ### Claim 4 (depends on 1) The method of claim 1, wherein determining a matching degree between the first keywords and the second keywords comprises: determining whether a first entry of the image/keyword mapping table contains third keywords that include all the first keywords of the search query; and assigning a first predetermined score to a first image associated with the first entry, in response to determining that the third keywords exactly match the first keywords. ### Claim 5 (depends on 1) The method of claim 1, wherein determining a matching degree between the first keywords and the second keywords comprises: determining whether a second entry of the image/keyword mapping table contains one or more fourth keywords that include a portion of the first keywords of the search query; and assigning a second predetermined score to a second image associated with the second entry, in response to determining that one or more fourth keywords that match a portion of the first keywords. ### Claim 6 (depends on 1) The method of claim 1, wherein determining a matching degree between the first keywords and the second keywords comprises: determining whether a third entry of the image/keyword mapping table contains one or more fifth keywords that are semantically similar to at least a portion of the first keywords of the search query; and assigning a third predetermined score to a third image associated with the third entry, in response to determining that one or more fifth keywords that are semantically similar to at least a portion of the first keywords, wherein the images are ranked based on corresponding scores of the images. ### Claim 7 (depends on 1) The method of claim 1, wherein determining a matching degree between the first keywords and the second keywords comprises: determining a first number of keywords matched between the first keywords and the second keywords of a first entry in the image/keyword mapping table; determining a second number of keywords included in the query; and calculating a matching score representing the matching degree based on the first number of keywords and the second number of keywords. ### Claim 8 (depends on 7) The method of claim 7, further comprising determining a third number of keywords included in the first entry of the image/keyword mapping table, wherein the matching score is calculated further based on the third number of keywords. ### Claim 9 A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations of matching images with content items based on keywords, the operations comprising: in response to a search query received from a client device for searching content, determining one or more first keywords from the search query; performing a lookup operation in an image-to-keyword (image/keyword) mapping table based on the first keywords, the image/keyword mapping table including a plurality of entries, each entry mapping an image identifier (ID) identifying an image to one or more second keywords; for each of images identified in the image/keyword mapping table, determining a matching degree between the first keywords and the second keywords; and ranking based on matching degrees a plurality of images identified in the image/keyword mapping table whose second keywords match at least a portion of the first keywords. ### Claim 10 (depends on 9) The non-transitory machine-readable medium of claim 9, wherein the operations further comprise: performing a search in a content store based on the search query to identifying a list of content items; and associating at least a portion of the ranked images with at least a portion of the content items based on ranking. ### Claim 11 (depends on 10) The non-transitory machine-readable medium of claim 10, wherein the operations further comprise: integrating the at least a portion of the ranked images with the at least a portion of the content items to generate a search result; and transmitting the search result to the client device, wherein the ranked images are used as background images for the content items. ### Claim 12 (depends on 9) The non-transitory machine-readable medium of claim 9, wherein determining a matching degree between the first keywords and the second keywords comprises: determining whether a first entry of the image/keyword mapping table contains third keywords that include all the first keywords of the search query; and assigning a first predetermined score to a first image associated with the first entry, in response to determining that the third keywords exactly match the first keywords. ### Claim 13 (depends on 9) The non-transitory machine-readable medium of claim 9, wherein determining a matching degree between the first keywords and the second keywords comprises: determining whether a second entry of the image/keyword mapping table contains one or more fourth keywords that include a portion of the first keywords of the search query; and assigning a second predetermined score to a second image associated with the second entry, in response to determining that one or more fourth keywords that match a portion of the first keywords. ### Claim 14 (depends on 9) The non-transitory machine-readable medium of claim 9, wherein determining a matching degree between the first keywords and the second keywords comprises: determining whether a third entry of the image/keyword mapping table contains one or more fifth keywords that are semantically similar to at least a portion of the first keywords of the search query; and assigning a third predetermined score to a third image associated with the third entry, in response to determining that one or more fifth keywords that are semantically similar to at least a portion of the first keywords, wherein the images are ranked based on corresponding scores of the images. ### Claim 15 (depends on 9) The non-transitory machine-readable medium of claim 9, wherein determining a matching degree between the first keywords and the second keywords comprises: determining a first number of keywords matched between the first keywords and the second keywords of a first entry in the image/keyword mapping table; determining a second number of keywords included in the query; and calculating a matching score representing the matching degree based on the first number of keywords and the second number of keywords. ### Claim 16 (depends on 15) The non-transitory machine-readable medium of claim 15, wherein the operations further comprise determining a third number of keywords included in the first entry of the image/keyword mapping table, wherein the matching score is calculated further based on the third number of keywords. ### Claim 17 A data processing system, comprising: a processor; a memory coupled to the processor; a query analysis module, in response to a search query received from a client device for searching content, to determine one or more first keywords from the search query; a matching module to perform a lookup operation in an image-to-keyword (image/keyword) mapping table based on the first keywords, the image/keyword mapping table including a plurality of entries, each entry mapping an image identifier (ID) identifying an image to one or more second keywords; and a ranking module, for each of images identified in the image/keyword mapping table, to determine a matching degree between the first keywords and the second keywords, and to rank based on matching degrees a plurality of images identified in the image/keyword mapping table whose second keywords match at least a portion of the first keywords. ### Claim 18 (depends on 17) The system of claim 17, wherein a search engine to: perform a search in a content store based on the search query to identifying a list of content items, and associate at least a portion of the ranked images with at least a portion of the content items based on ranking. ### Claim 19 (depends on 18) The system of claim 18, wherein the search engine is further to: integrate the at least a portion of the ranked images with the at least a portion of the content items to generate a search result, and transmit the search result to the client device, wherein the ranked images are used as background images for the content items. ### Claim 20 (depends on 17) The system of claim 17, wherein determining a matching degree between the first keywords and the second keywords comprises: determining whether a first entry of the image/keyword mapping table contains third keywords that include all the first keywords of the search query; and assigning a first predetermined score to a first image associated with the first entry, in response to determining that the third keywords exactly match the first keywords. ### Claim 21 (depends on 17) The system of claim 17, wherein determining a matching degree between the first keywords and the second keywords comprises: determine whether a second entry of the image/keyword mapping table contains one or more fourth keywords that include a portion of the first keywords of the search query, and assign a second predetermined score to a second image associated with the second entry, in response to determining that one or more fourth keywords that match a portion of the first keywords. ### Claim 22 (depends on 17) The system of claim 17, wherein determining a matching degree between the first keywords and the second keywords comprises: determine whether a third entry of the image/keyword mapping table contains one or more fifth keywords that are semantically similar to at least a portion of the first keywords of the search query, and assign a third predetermined score to a third image associated with the third entry, in response to determining that one or more fifth keywords that are semantically similar to at least a portion of the first keywords, wherein the images are ranked based on corresponding scores of the images. ### Claim 23 (depends on 17) The system of claim 17, wherein determining a matching degree between the first keywords and the second keywords comprises: determining a first number of keywords matched between the first keywords and the second keywords of a first entry in the image/keyword mapping table; determining a second number of keywords included in the query; and calculating a matching score representing the matching degree based on the first number of keywords and the second number of keywords. ### Claim 24 (depends on 23) The system of claim 23, wherein the wherein the ranking module is further to determine a third number of keywords included in the first entry of the image/keyword mapping table, wherein the matching score is calculated further based on the third number of keywords.