# US 2017/0255647 A1 · Method for selecting images for matching with content based on metadata of images and content in real-time 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 2017/0255647 A1 - Document ID: US20170255647A1 - Status: Published application - Kind: A1 - Application number: 15/058,020 - Filed: 2016-03-01 - Published: 2017-09-07 - Earliest claimed: 2016-03-01 - Assignees: Baidu USA LLC - Applicants: Baidu USA LLC - Inventors: Fan Zhu; Qi Kong; Dong Li; Yifei Jiang; Shuang Wu; Youling Zou; Guang Yang; Jingao Wang - Web page: https://patentgrep.com/patent/US20170255647A1 ## CPC - G06F 16/583: using metadata automatically derived from the content - G06F 16/24578: {using ranking} - G06F 16/285: {Clustering or classification} - G06F 16/5866: {using information manually generated, e.g. tags, keywords, comments, manually generated location and time information} - G06F 16/951: Indexing; Web crawling techniques - G06F 16/9538: Presentation of query results - 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 at a server from a client device for searching content, a search is performed in a content database or via a content server based on one or more search terms of the search query to identify a first list of one or more content items. A search is performed in an image store based on the one or more search terms to identify a list of one or more images. Each content item of the first list is associated with one of the images. A second list of one or more content items having at least a portion of the images integrated therein is generated. The second list of content items is transmitted to the client device, such that each content item of the first list is presented with one of the images. ## Claims ### Claim 1 A computer-implemented method of selecting images for content items in response to search queries, the method comprising: in response to a search query received at a server from a client device for searching content, searching in a content database or via a content server by a search engine hosted by the server based on one or more search terms of the search query to identify a first list of one or more content items; searching by an image selection module hosted by the server in an image store based on the one or more search terms to identify a list of one or more images; integrating by the search engine each content item of the first list with one of the images, generating a second list of one or more content items having at least a portion of the images integrated therein; and transmitting by the search engine the second list of content items to the client device, such that each content item of the first list is presented with one of the images. ### Claim 2 (depends on 1) The method of claim 1, wherein integrating each content item of the first list with one of the images comprises superimposing each content item onto a selected one of the images, such that the content item is on foreground while the selected image serves as a background image. ### Claim 3 (depends on 1) The method of claim 1, further comprising: for each of the images, calculating a matching score between the image and a first content item of the first list based on a context of the first content item and metadata associated with the image; ranking each of the images based on a respective matching score between the image and the first content item; and selecting one of the images having a matching score greater than a predetermined threshold, wherein the selected image is to be integrated with the first content item. ### Claim 4 (depends on 3) The method of claim 3, further comprising, for each of the content items in the first list, iteratively performing calculating a matching score, ranking each of the images based on matching scores, and selecting one of the images based on the matching scores. ### Claim 5 (depends on 4) The method of claim 4, further comprising: determining whether an identical image has been selected for more than one content item of the first list; and applying a predetermined tie-breaking formula to matching scores of the images associated with the more than one content item to select different images for different content items of the first list. ### Claim 6 (depends on 3) The method of claim 3, wherein a matching score between each image and the first content item is calculated based on a similarity between the first content item and each image, including determining whether the first content item describes image content represented by the image. ### Claim 7 (depends on 3) The method of claim 3, wherein a matching score between each image and the first content item is calculated based on a prior user access pattern of the image. ### Claim 8 (depends on 3) The method of claim 3, wherein a matching score between each image and the first content item is calculated based on a prior user access pattern of a combination of the image and the first content item presented together. ### Claim 9 (depends on 3) The method of claim 3, wherein a matching score between each image and the first content item is calculated based on an image quality or a style of the image. ### Claim 10 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, the operations comprising: in response to a search query received from a client device for searching content, searching in a content database or via a content server by a search engine based on one or more search terms of the search query to identify a first list of one or more content items; searching by an image selection module in an image store based on the one or more search terms to identify a list of one or more images; integrating by the search engine each content item of the first list with one of the images, generating a second list of one or more content items having at least a portion of the images integrated therein; and transmitting by the search engine the second list of content items to the client device, such that each content item of the first list is presented with one of the images. ### Claim 11 (depends on 10) The non-transitory machine-readable medium of claim 10, wherein integrating each content item of the first list with one of the images comprises superimposing each content item onto a selected one of the images, such that the content item is on foreground while the selected image serves as a background image. ### Claim 12 (depends on 10) The non-transitory machine-readable medium of claim 10, wherein the operations further comprise: for each of the images, calculating a matching score between the image and a first content item of the first list based on a context of the first content item and metadata associated with the image; ranking each of the images based on a respective matching score between the image and the first content item; and selecting one of the images having a matching score greater than a predetermined threshold, wherein the selected image is to be integrated with the first content item. ### Claim 13 (depends on 12) The non-transitory machine-readable medium of claim 12, wherein the operations further comprise, for each of the content items in the first list, iteratively performing calculating a matching score, ranking each of the images based on matching scores, and selecting one of the images based on the matching scores. ### Claim 14 (depends on 13) The non-transitory machine-readable medium of claim 13, wherein the operations further comprise: determining whether an identical image has been selected for more than one content item of the first list; and applying a predetermined tie-breaking formula to matching scores of the images associated with the more than one content item to select different images for different content items of the first list. ### Claim 15 (depends on 12) The non-transitory machine-readable medium of claim 12, wherein a matching score between each image and the first content item is calculated based on a similarity between the first content item and each image, including determining whether the first content item describes image content represented by the image. ### Claim 16 (depends on 12) The non-transitory machine-readable medium of claim 12, wherein a matching score between each image and the first content item is calculated based on a prior user access pattern of the image. ### Claim 17 (depends on 12) The non-transitory machine-readable medium of claim 12, wherein a matching score between each image and the first content item is calculated based on a prior user access pattern of a combination of the image and the first content item presented together. ### Claim 18 (depends on 12) The non-transitory machine-readable medium of claim 12, wherein a matching score between each image and the first content item is calculated based on an image quality or a style of the image. ### Claim 19 A data processing system, comprising: a processor; a search engine, in response to a search query received from a client device for searching content, to search in a content database or via a content server based on one or more search terms of the search query to identify a first list of one or more content items; and an image selection module to search in an image store based on the one or more search terms to identify a list of one or more images, wherein the search engine is to integrate each content item of the first list with one of the images, generating a second list of one or more content items having at least a portion of the images integrated therein, and transmit the second list of content items to the client device, such that each content item of the first list is presented with one of the images. ### Claim 20 (depends on 19) The system of claim 19, wherein integrating each content item of the first list with one of the images comprises superimposing each content item onto a selected one of the images, such that the content item is on foreground while the selected image serves as a background image. ### Claim 21 (depends on 19) The system of claim 19, wherein the image selection module comprises a ranking module to for each of the images, calculate a matching score between the image and a first content item of the first list based on a context of the first content item and metadata associated with the image, rank each of the images based on a respective matching score between the image and the first content item, and select one of the images having a matching score greater than a predetermined threshold, wherein the selected image is to be integrated with the first content item. ### Claim 22 (depends on 21) The system of claim 21, wherein the ranking module is further to, for each of the content items in the first list, iteratively perform calculating a matching score, ranking each of the images based on matching scores, and selecting one of the images based on the matching scores. ### Claim 23 (depends on 22) The system of claim 22, wherein the ranking module is further to: determine whether an identical image has been selected for more than one content item of the first list, and apply a predetermined tie-breaking formula to matching scores of the images associated with the more than one content item to select different images for different content items of the first list. ### Claim 24 (depends on 21) The system of claim 21, wherein a matching score between each image and the first content item is calculated based on a similarity between the first content item and each image, including determining whether the first content item describes image content represented by the image. ### Claim 25 (depends on 21) The system of claim 21, wherein a matching score between each image and the first content item is calculated based on a prior user access pattern of the image. ### Claim 26 (depends on 21) The system of claim 21, wherein a matching score between each image and the first content item is calculated based on a prior user access pattern of a combination of the image and the first content item presented together. ### Claim 27 (depends on 21) The system of claim 21, wherein a matching score between each image and the first content item is calculated based on an image quality or a style of the image.