Intelligent playing method and apparatus based on preference feedback

Patent metadata

Field	Value
Publication number	US-11017010-B2
Application number	US-201715856704-A
Country	US
Kind code	B2
Filing date	Dec 28, 2017
Priority date	Nov 16, 2017
Publication date	May 25, 2021
Grant date	May 25, 2021

Abstract

The embodiments of the disclosure disclose an intelligent playing method and apparatus based on preference feedback. An embodiment of the method comprises: receiving voice feedback on currently played multimedia from a user; analyzing a user intention based on the voice feedback; calculating, in response to the user intention indicating updating a currently played multimedia list, a similarity between multimedia in a multimedia database and the current multimedia; and updating the currently played multimedia list based on the voice feedback and the similarity. The embodiment improves the quality and pertinence in playing multimedia.

First claim

What is claimed is:

1. An intelligent playing method based on preference feedback, the method comprising:
receiving voice feedback on currently played multimedia from a user;
obtaining a precondition for the voice feedback, wherein the voice feedback comprises positive feedback and negative feedback, and the precondition refers to a playing instruction for triggering playing of current multimedia, and comprises random-based play, multimedia-based on-demand play, leading-author-based on-demand play, tag-based on-demand play, and list-based on-demand play;
analyzing a user intention based on the voice feedback and the precondition comprising the random-based play, multimedia-based on-demand play, leading-author-based on-demand play, tag-based on-demand play, and list-based on-demand play;
calculating, in response to the user intention indicating updating a currently played multimedia list, a similarity between multimedia in a multimedia database and the currently played multimedia; and
updating the currently played multimedia list based on the voice feedback and the similarity;
wherein the method is performed by at least one processor; and
wherein the updating the currently played multimedia list based on the voice feedback and the similarity comprises: updating the currently played multimedia list based on the voice feedback, the similarity, and the precondition comprising the random-based play, multimedia-based on-demand play, leading-author-based on demand play, tag-based on-demand play, and list-based on-demand play;
wherein the method further comprises:
modifying, in response to the user intention indicating modifying the currently played multimedia list, the currently played multimedia list based on the voice feedback and the precondition; and/or switching, in response to the user intention indicating deleting the current multimedia, to next multimedia and deleting multimedia hit by the negative feedback from the currently played multimedia list;
wherein the modifying, in response to the user intention indicating modifying the currently played multimedia list, the currently played multimedia list comprises:
modifying, in response to the negative feedback being negative feedback on a leading author of multimedia and the precondition being the multimedia-based on-demand play, current multimedia and follow-up multimedia in the currently played multimedia list using a preset number of popular multimedia by another leading author and of the same name as the multimedia hit by the negative feedback in the multimedia database, and deleting the multimedia hit by the negative feedback from the currently played multimedia list;
modifying, in response to the negative feedback being negative feedback on a leading author of multimedia and the precondition being the random-based play or the leading-author-based on-demand play, the current multimedia and the follow-up multimedia in the currently played multimedia list using a preset number of popular multimedia by a leading author other than the leading author involved in the negative feedback in the multimedia database, and deleting multimedia hit by the leading author involved in the negative feedback from the currently played multimedia list; and
modifying, in response to the negative feedback being negative feedback on a multimedia tag and the precondition being the leading-author-based on-demand play, the current multimedia and the follow-up multimedia in the currently played multimedia list using a preset number of popular multimedia having a tag of a current leading author and different from the multimedia tag involved in the negative feedback in the multimedia database, and deleting the multimedia hit by the multimedia tag involved in the negative feedback from the currently played multimedia list.

2. The method according to claim 1 , wherein the updating the currently played multimedia list based on the voice feedback and the similarity comprises:
ordering, in response to the voice feedback being the positive feedback, the multimedia in the multimedia database in a descending order based on the similarity to obtain a positive ranking list, and updating the currently played multimedia list using a preset number of popular multimedia in the positive ranking list based on the positive feedback; and
ordering, in response to the voice feedback being the negative feedback, the multimedia in the multimedia database in an ascending order based on the similarity to obtain a negative ranking list, and updating the currently played multimedia list using a preset number of popular multimedia in the negative ranking list based on the negative feedback.

3. The method according to claim 1 , wherein the updating the currently played multimedia list based on the voice feedback, the precondition and the similarity comprises:
ordering, in response to the voice feedback being the positive feedback, the multimedia in the multimedia database in a descending order based on the similarity to obtain a positive ranking list, and updating the currently played multimedia list using a preset number of popular multimedia in the positive ranking list based on the positive feedback and the precondition; and
ordering, in response to the voice feedback being the negative feedback, the multimedia in the multimedia database in an ascending order based on the similarity to obtain a negative ranking list, and updating the currently played multimedia list using a preset number of popular multimedia in the negative ranking list based on the negative feedback and the precondition.

4. The method according to claim 3 , wherein the updating the currently played multimedia list using a preset number of popular multimedia in the positive ranking list based on the positive feedback and the precondition comprises:
updating, in response to the positive feedback being positive feedback on multimedia or a leading author of multimedia and the precondition being the random-based play, the follow-up multimedia in the currently played multimedia list using the preset number of popular multimedia in the positive ranking list;
updating, in response to the positive feedback being positive feedback on a multimedia tag and the precondition being the random-based play, the follow-up multimedia in the currently played multimedia list using a preset number of popular multimedia having a tag identical to a positive feedback tag in the positive ranking list; and
updating, in response to the positive feedback being positive feedback on the multimedia tag and the precondition being the leading-author-based on-demand play, the follow-up multimedia in the currently played multimedia list preferentially using a preset number of popular multimedia by a current leading author and having a tag identical to the positive feedback tag in the positive ranking list.

5. The method according to claim 3 , wherein the updating the currently played multimedia list using a preset number of popular multimedia in the negative ranking list based on the negative feedback and the precondition comprises:
updating, in response to the negative feedback being negative feedback on multimedia and the precondition being the random-based play or the multimedia-based on-demand play, the current multimedia and the follow-up multimedia in the currently played multimedia list using the preset number of popular multimedia in the negative ranking list, and deleting the multimedia hit by the negative feedback from the currently played multimedia list; and
updating, in response to the negative feedback being negative feedback on a multimedia tag and the precondition being the random-based play or the tag-based on-demand play, the current multimedia and the follow-up multimedia in the currently played multimedia list using a preset number of popular multimedia ha

Assignees

• Baidu online network technology beijing co ltd

Inventors

• Lu Guang
• Liu Shui
• Luo Xiajun
• Ye Shiquan
• Ju Qiang
• Xie Jian

Classifications

• G06F3/167 Primary

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title

• G06F16/635

  Filtering based on additional data, e.g. user or group profiles · CPC title

• G06F16/637

  Administration of user profiles, e.g. generation, initialization, adaptation or distribution · CPC title

• G06F16/4387 Primary

  by the use of playlists · CPC title

• G06F16/436

  using biological or physiological data of a human being, e.g. blood pressure, facial expression, gestures · CPC title