US 12,248,524 B2
System, method, and computer program for monitoring and optimizing enterprise knowledge management platform using non-personally-identifiable information in logs
Sumeet Sobti, Palo Alto, CA (US); Piyush Prahladka, Palo Alto, CA (US); Eddie Zhou, Palo Alto, CA (US); Rui Wu, Palo Alto, CA (US); Arjun Landes, Palo Alto, CA (US); Debarghya Das, Palo Alto, CA (US); Neil Rajesh Dhruva, Palo Alto, CA (US); Shivaal Roy, Palo Alto, CA (US); Mrinal Mohit, Palo Alto, CA (US); and Calvin Qi, Palo Alto, CA (US)
Assigned to Glean Technologies, Inc., Palo Alto, CA (US)
Filed by Glean Technologies, Inc., Palo Alto, CA (US)
Filed on Apr. 21, 2022, as Appl. No. 17/725,739.
Prior Publication US 2023/0342405 A1, Oct. 26, 2023
Int. Cl. G06F 16/953 (2019.01)
CPC G06F 16/953 (2019.01) 20 Claims
OG exemplary drawing
 
1. A system for monitoring and optimizing work assistant search engines that are implemented within secured enterprise user computing systems, comprising:
a storage device; and
one or more processing devices, communicatively connected to the storage device, to:
receive diagnostic data of a work assistant search engine from a secured enterprise user computing system, the diagnostic data comprising feature values and scores, wherein the secured enterprise user computing system is safe from transmitting non-diagnostic data to the system, wherein the feature values are an abstract layer calculated based on a query, an identifier of a user requesting the query, and data objects representing documents identified by the work assistant search engine responsive to the query, and the abstract layer is devoid of personal information of the user or content of the documents identified by the work assistant search engine, and wherein the scores are calculated by applying a score model to the feature values;
determine, by analyzing the diagnostic data, a search quality metric value associated with the feature values and the scores;
responsive to determining that the search quality metric value differs from a target search quality metric value by a predetermined threshold value, determine an updated score model; and
provide the updated score model to the secured enterprise user computing system to update the work assistant search engine.