# US 10,320,633 B1 · Insights for web service providers > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,320,633 B1 - Document ID: US10320633B1 - Status: Granted - Kind: B1 - Application number: 14/733,800 - Filed: 2015-06-08 - Granted: 2019-06-11 - Earliest claimed: 2014-11-20 - Assignees: BloomReach Inc. - Applicants: BloomReach Inc. - Inventors: Wai Hung Wong; Nishant Deshpande; Pradeep Muthukrishnan; Vaibhav Avinash Chidrewar; Charlie Luo; Rahul Bhandari; Ashutosh Garg - Web page: https://patentgrep.com/patent/US10320633B1 ## CPC - H04L 67/02: based on web technology, e.g. hypertext transfer protocol [HTTP] - H04L 43/06: Generation of reports - H04L 43/16: Threshold monitoring - H04L 67/535: {Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34)} - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract Techniques for providing insights for web service providers are disclosed. In some embodiments, a system, process, and/or computer program product for providing insights for web service providers includes monitoring user activities on a web site; generating a dashboard for displaying a summary of the monitored user activities on the web site; and generating a recommendation for improving performance of the web site for display on the dashboard. For example, the recommendation can be for improving performance of search results on the web site and/or for improving content navigation on the web site. ## Claims ### Claim 1 A system for providing insights for web service providers, comprising: a processor configured to: monitor user activities on a web site, wherein the user activities include a source entity and a target entity, the source entity relating to user activities before an event, the target entity relating to user activities after the event; generate a dashboard for displaying a summary of the monitored user activities on the web site, comprising to: calculate a co-visit association score based on the user activities on the web site, comprising to: determine the co-visit association score based on a pairwise frequency of the source entity and the target entity, global frequency of the source entity, and global frequency of the target entity; in response to a determination that the co-visit association score satisfied a co-visit association score threshold, identify a product associated with the user activities on the web site; generate, based on the identified product, a recommendation for improving performance of the web site for display on the dashboard, wherein the recommendation includes an addition of products to a web page displayed on the web site, a placement of a link on a web page displayed on the web site, a promotion of a product to a web page displayed on the web site, or any combination thereof; automatically perform at least one of the recommendations for improving performance of the web site; and display the dashboard via a web site, wherein the dashboard includes a heat map that includes visual indicators based on a plurality of metrics associated with the performance of the web site, and wherein the dashboard further includes data presented in-line with the web site and displayed using visual indicators based on the content on a web page of the web site; and a memory coupled to the processor and configured to provide the processor with instructions. ### Claim 2 (depends on 1) The system recited in claim 1, wherein the processor is further configured to: display the dashboard. ### Claim 3 (depends on 1) The system recited in claim 1, wherein the processor is further configured to: display the dashboard via a web site. ### Claim 4 A method of providing insights for web service providers, comprising: monitoring user activities on a web site, wherein the user activities include a source entity and a target entity, the source entity relating to user activities before an event, the target entity relating to user activities after the event; generating a dashboard for displaying a summary of the monitored user activities on the web site, comprising: calculating a co-visit association score based on the user activities on the web site, comprising: determining the co-visit association score based on a pairwise frequency of the source entity and the target entity, global frequency of the source entity, and global frequency of the target entity; in response to a determination that the co-visit association score satisfied a co-visit association score threshold, identify a product associated with the user activities on the web site; generating, based on the identified product, a recommendation for improving performance of the web site using a processor for display on the dashboard, wherein the recommendation includes an addition of products to a web page displayed on the web site, a placement of a link on a web page displayed on the web site, a promotion of a product to a web page displayed on the web site, or any combination thereof; automatically performing at least one of the recommendations for improving performance of the web site; and displaying the dashboard via a web site, wherein the dashboard includes a heat map that includes visual indicators based on a plurality of metrics associated with the performance of the web site, and wherein the dashboard further includes data presented in-line with the web site and displayed using visual indicators based on the content on a web page of the web site. ### Claim 5 (depends on 4) The method of claim 4, further comprising: displaying the dashboard. ### Claim 6 (depends on 4) The method of claim 4, further comprising: displaying the dashboard via a web site. ### Claim 7 A computer program product for providing insights for web service providers, the computer program product being embodied in a tangible non-transitory computer readable storage medium and comprising computer instructions for: monitoring user activities on a web site, wherein the user activities include a source entity and a target entity, the source entity relating to user activities before an event, the target entity relating to user activities after the event; generating a dashboard for displaying a summary of the monitored user activities on the web site, comprising: calculating a co-visit association score based on the user activities on the web site, comprising: determining the co-visit association score based on a pairwise frequency of the source entity and the target entity, global frequency of the source entity, and global frequency of the target entity; in response to a determination that the co-visit association score satisfied a co-visit association score threshold, identifying a product associated with the user activities on the web site; generating, based on the identified product, a recommendation for improving performance of the web site for display on the dashboard, wherein the recommendation includes an addition of products to a web page displayed on the web site, a placement of a link on a web page displayed on the web site, a promotion of a product to a web page displayed on the web site, or any combination thereof; automatically performing at least one of the recommendations for improving performance of the web site; and displaying the dashboard via a web site, wherein the dashboard includes a heat map that includes visual indicators based on a plurality of metrics associated with the performance of the web site, and wherein the dashboard further includes data presented in-line with the web site and displayed using visual indicators based on the content on a web page of the web site. ### Claim 8 (depends on 7) The computer program product recited in claim 7, further comprising computer instructions for: displaying the dashboard. ### Claim 9 (depends on 7) The computer program product recited in claim 7, further comprising computer instructions for: displaying the dashboard via a web site. ### Claim 10 A system for providing insights for web service providers, comprising: a processor configured to: monitor user activities on a web site prior to a user event on the web site, wherein the user event includes a search on the web site based on a user query, a view of a category page on the web site, an add to cart of a product on the web site, and/or a view of a product page on the web site; monitor user activities on the web site before and after the event on the web site, wherein the user activities include a source entity and a target entity, the source entity relating to user activities before the user event, the target entity relating to user activities after the user event; generate a recommendation for improving performance of the web site based on the monitored user activities prior to the event on the web site and after the event on the web site, comprising to: calculate a co-visit association score based on the user activities on the web site, comprising to: determine the co-visit association score based on a pairwise frequency of the source entity and the target entity, global frequency of the source entity, and global frequency of the target entity; in response to a determination that the co-visit association score satisfied a co-visit association score threshold, generate the recommendation based on a product associated with the user activities on the web site, wherein the recommendation includes an addition of products to a web page displayed on the web site, a placement of a link on a web page displayed on the web site, a promotion of a product to a web page displayed on the web site, or any combination thereof; automatically perform at least one of the recommendations for improving performance of the web site; and display a dashboard via a web site, wherein the dashboard includes a heat map that includes visual indicators based on a plurality of metrics associated with the performance of the web site, and wherein the dashboard further includes data presented in-line with the web site and displayed using visual indicators based on the content on a web page of the web site; and a memory coupled to the processor and configured to provide the processor with instructions. ### Claim 11 (depends on 10) The system recited in claim 10, wherein the processor is further configured to: determine a user intent based on the monitored user activities prior to the search on the web site and after the search on the web site; and associate the user intent based on the monitored user activities prior to the search on the web site and after the search on the web site with the user query. ### Claim 12 (depends on 10) The system recited in claim 10, wherein the processor is further configured to: determine a user intent based on the monitored user activities prior to the search on the web site and after the search on the web site; associate the user intent based on the monitored user activities prior to the search on the web site and after the search on the web site with the user query; and determine a search result that is not relevant to the user intent based on the monitored user activities prior to the search on the web site and after the search on the web site. ### Claim 13 (depends on 1) The system of claim 1, wherein the recommendation further includes an identification of low performing categories displayed on the web site and an identification of poor performing products displayed on the web site. ### Claim 14 (depends on 4) The method of claim 4, wherein the recommendation further includes an identification of low performing categories displayed on the web site and an identification of poor performing products displayed on the web site. ### Claim 15 (depends on 7) The computer program product of claim 7, wherein the recommendation further includes an identification of low performing categories displayed on the web site and an identification of poor performing products displayed on the web site. ### Claim 16 (depends on 10) The system of claim 10, wherein the recommendation further includes an identification of low performing categories displayed on the web site and an identification of poor performing products displayed on the web site.