Townsend Street Labs, Inc.

Okta, Inc.

Rajhans Samdani

Pratyus Patnaik

Nathaniel Ackerman Rook

Suchit Agarwal

Jay Srinivasan

David Colby Kaneda

Marissa Mary Montgomery

Ankit Goyal

William Stone Potter

Pierre Rappolt

Emily Wang

Roopak Venkatakrishnan

Systems for processing queries may first determine correspondence between the parameters of the query and a set of existing data entries, a set of previous queries that have been received, or both the existing data entries and the previous queries. If the query parameters do not correspond to the data entries or pervious queries, correspondence is determined between the query parameters and group data that associates at least a subset the query parameters with a particular group that may generate a response to the query. The same group or the generated response may be used when similar queries are received. If the group transmits the query to a different group or if negative user feedback is received, the group data may be modified to indicate the different group or to remove the association with the initial group that received the query.

System for routing of requests

A system creates and searches knowledge base (KB) articles inside an organization while supporting operation as a SaaS (Software as-a-Service) across a plurality of organizations. The system implements a real-time online learning-to-rank (L2R) algorithm for learning relevance scoring that is customized to each organization. This algorithm incorporates rich lexical features using a query similarity kernel. A scoring function includes a pairwise static module, which may be trained off-line using training data, and a lexical adaptive module, which is trained on-line based on user feedback. The scoring function makes the system easy to deploy, modify, and suitable for handling events that naturally happen over the lifecycle of any KB deployment, without manual training.

System for handling workplace queries using online learning to rank

A system stores resources such as text articles, videos, and so forth for an organization. During operation, the system receives a query and provides a response. During initial use of the system, there is little or no historical data available to help determine which resource is most relevant to a particular query. In this 'cold-start' situation, the system determines attributes associated with a user account of the user making the query. The query is used to search a data store and retrieve a set of resources based on a term match with the query and to find the resources which correspond to the attributes of the user account. This allows the system to provide simplified output that is more likely to be relevant to that particular user in the 'cold-start' situation.

Personalized search based on account attributes

Systems and methods for determining whether a data entry has deprecated may receive a query from a user device and provide a data entry responsive to the query. If user feedback associated with the response indicates that the response resolved the query, confirmation data that associates the data entry with the query parameters is generated. If the user feedback indicates that the response did not resolve the query, existing confirmation data is accessed to determine whether a previous association between the data entry and the parameters of the query was generated. If correspondence between the confirmation data and the query and response is determined, a notification indicating the deprecation of the data entry is generated and the data entry may be suppressed from future output.

System for determining and modifying deprecated data entries

A system dynamically routes queries from an organization for processing. An incoming query is classified using a base model to determine a canonical group. The query is routed based on the canonical group. Responsive to the query, response data is then provided to the user device. Event data about the query, the routing, and the response data is used to train a first model that is used to determine subsequent routing. When a threshold is reached with respect to the available event data, a second model is trained using the event data. Processing of subsequent queries using the second model results in reduced demand for computer resources and reduces response times. The second model may be retrained on a schedule, or upon occurrence of a trigger event, such as an addition or removal of a canonical group.

Dynamic query routing system

A system for processing queries from a user device may first generate an augmented query by determining weight values and synonyms for at least a portion of the parameters in the query, and adding or removing one or more query parameters. Correspondence between the augmented query and an existing set of data entries may be used to determine a subset of data entries that may be responsive to the query. Correspondence may then be determined between the augmented query and previous queries that were addressed by the subset of data entries, to determine a particular previous query having the greatest correspondence with the augmented query. The data entry associated with the particular previous query may be used to generate a response to the query received from the user device.

Growing community of inventors

San Francisco, CA, United States of America

Rajhans Samdani