Method and device for recommending content

Abstract

Embodiments of the present invention provide a content recommendation method and device, the method comprising: acquiring voice request data of a target user, and extracting corresponding interactive recommendation features in the voice request data; The corresponding recommended content is obtained from the recommendation knowledge base corresponding to the target user and sent to the target user; wherein, the recommendation knowledge base includes a plurality of corresponding relationship models; and each corresponding relationship model is based on each The interactive recommendation features extracted from the sample voice request data of historical users and the recommended content corresponding to each historical user are established. The method greatly facilitates the user's use, and at the same time combines the acoustics, semantics, user attributes and speaker information requested by the target user, thereby further improving the accuracy of content recommendation.

Description

technical field [0001] The present invention relates to the technical field of speech signal processing and natural language processing, and more specifically, to a content recommendation method and device. Background technique [0002] With the advent of the wave of "artificial intelligence", more and more smart devices have entered the field of vision of ordinary users, and users are increasingly relying on using smart devices to achieve their needs, such as Amazon's Echo, Google Home's smart speakers, Baidu's smart robots, smart TVs used in homes, etc., when these smart devices are in use, multiple users generally share the same smart device. For example, family members use the same smart TV to watch TV, and the same robot serves multiple different users. customers, etc.; smart recommendation can undoubtedly greatly improve users’ stickiness to smart devices and retain users for smart devices. The existing smart recommendation methods on smart devices generally require us...

AI Technical Summary

Problems solved by technology

[0002] With the advent of the wave of "artificial intelligence", more and more smart devices have entered the field of vision of ordinary users, and users are increasingly relying on using smart devices to achieve their needs, such as Amazon's Echo, Google Home's smart speakers, Baidu's smart robots, smart TVs used in homes, etc., when these smart devices are in use, multiple users generally share the same smart device. For example, family members use the same smart TV to watch TV, and the same robot serves multiple different users. customers, etc.; smart recommendation can undoubtedly greatly improve users’ stickiness to smart devices and retain users for smart devices. The existing smart recommendation methods on smart devices generally require users to pre-register an account when recommending content for users. Smart devices will The data of the same user is put together, and some content that the user is interested in is recommended based on the user's historical information each time; however, for unregistered users, the recommended content cannot be provided, and the user experience is not good

Images