Beijing Didi Infinity Technology and Development Co., Ltd.

Conghui Fu

Dong Li

Jing Chen

Xin Chen

Zihan Yi

Zetian Ni

Techniques for automatically detecting when a ride requester has requested a ride-share ride on behalf of a guest rider using some or all of the communications between the driver and ride requester are described herein. For example, a server can obtain chat logs between a ride requester and a driver and process the chat logs to identify whether the ride requester has requested a ride on behalf of a guest rider. In particular, the server can train an artificial intelligence model (e.g., a machine learning model) to predict potential guest rider behavior. Once trained, the server can obtain chat logs comprising chat messages sent between a driver and a ride requester, and apply a representation of the chat logs as an input to the trained artificial intelligence model to determine whether guest rider behavior is detected.

Machine learning-based real-time guest rider identification

Mismatched drivers may be identified based on passenger evaluations. A set of evaluations may be obtained. Each evaluation in the set of evaluations may be based on whether a current driver matches a registered driver. A convergence point number may be obtained. The convergence point number may be a number of evaluations required for accurate identification. An identification rate may be computed based on the set of evaluations and the convergence point number. The current driver may be verified based on a comparison of the identification rate to a threshold match rate. If the identification rate is greater than a threshold match rate, it may be determined that the identity of the current driver is valid. If the identification rate is not greater than a threshold match rate, the current driver may be identified as a mismatched driver.

Growing community of inventors

Santa Clara, CA, United States of America

Conghui Fu