Voice interaction based method and apparatus for generating multimedia playlist

• US 10,643,610 B2
• Filed: 12/29/2017
• Issued: 05/05/2020
• Est. Priority Date: 11/15/2017
• Status: Active Grant

• Current Assignee: Baidu Online Network Technology (Beijing) Co., Ltd (Baidu Incorporated), Shanghai Xiaodu Technology Company Limited
• Original Assignee: Baidu Online Network Technology (Beijing) Co., Ltd (Baidu Incorporated)
• Inventors: Lu, Guang, Liu, Shui, Luo, Xiajun, Ye, Shiquan, Yin, Xiangjie, Ju, Qiang, Xie, Jian
• Primary Examiner(s): Shin, Seong-Ah A
• Application Number:
  US15/858,885
• Publication Number:
  US 20190147864A1
• Time in Patent Office: 858 Days
• Field of Search: None
• CPC Class Codes: G06F 16/4387 by the use of playlists
• CPC Class Codes: G06F 16/4393 Multimedia presentations, e.g. slide shows, multimedia albums
• CPC Class Codes: G06F 16/48 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 25/54 for retrieval

Abstract

Embodiments of this disclosure disclose a voice interaction based method and apparatus for generating a multimedia playlist. An embodiment of the method comprises: acquiring first voice request information for playing multimedia resources; identifying a key tag for indicating a characteristic attribute of the multimedia resources in the first voice request information; finding the multimedia resources having the key tag in a multimedia resource library; and generating a multimedia playlist based on the found multimedia resources. The embodiment realizes automatic generation of multimedia playlists and improves the efficiency of voice service.

Claims

1. A voice interaction based method for generating a multimedia playlist, the method comprising:

acquiring first voice request information for playing multimedia resources;

identifying a key tag for indicating a characteristic attribute of the multimedia resources in the first voice request information;

finding the multimedia resources having the key tag in a multimedia resource library; and

generating a multimedia playlist based on the found multimedia resources;

wherein the generating a multimedia playlist based on the found multimedia resources comprises;

acquiring popularity data of the found multimedia resources, ordering the multimedia resources by the popularity data in a descending order;

acquiring descriptor data of a user sending the first voice request information associated with to-be-played multimedia resources, selecting multimedia resources matching the user descriptor as candidate multimedia resources; and

selecting a preset number of the candidate multimedia resources as target multimedia resources based on the order, and adding the target multimedia resources to the multimedia playlist; and

wherein before the selecting a preset number of the candidate multimedia resources as target multimedia resources based on the order, and adding the target multimedia resources to the multimedia playlist, the generating a multimedia playlist based on the found multimedia resources further comprises;

determining weights of the key tags for indicating a given characteristic attribute based on occurrence numbers of the key tags in the multimedia resource library; and

determining demand numbers of the multimedia resources having the key tags in the multimedia playlist based on the weights of the key tags and a preset length of the multimedia playlist; and

the selecting a preset number of the candidate multimedia resources as target multimedia resources based on the order, and adding the target multimedia resources to the multimedia playlist comprises;

dividing the candidate multimedia resources in groups based on the key tags; and

extracting, based on the order, the multimedia resources satisfying the corresponding demand numbers from each of the groups, and generating the multimedia playlist based on the order of the candidate multimedia resources.

2. The method according to claim 1, wherein the acquiring popularity data of the found multimedia resources comprises:

calculating the corresponding popularity data based on multimedia resource playing data and internet search data.

3. The method according to claim 2, wherein the acquiring popularity data of the found multimedia resources further comprises:

judging whether the multimedia resources are multimedia resources being played in a preset period before the acquiring first voice request information for playing multimedia resources; and

implementing attenuation operation on the popularity data of the multimedia resources by a preset attenuation factor, in response to determine that the multimedia resources are multimedia resources being played in a preset period before the acquiring first voice request information for playing multimedia resources.

4. The method according to claim 1, wherein the identifying a key tag for indicating a characteristic attribute of the multimedia resources in the first voice request information comprises:

extracting a tag matching a preset tag library in the first voice request information as the key tag.

5. The method according to claim 1, wherein the characteristic attribute comprises:

an author, an identifier for a set of the multimedia resources, a style, or a language.

6. The method according to claim 1, wherein after the generating a multimedia playlist based on the found multimedia resources, the method further comprises:

responding to received second voice request information for playing multimedia resources;

analyzing an intention of the second voice request information, and updating the multimedia playlist based on a result of the analyzing an intention.

7. The method according to claim 1, the method further comprising:

pushing the multimedia playlist to a device sending the first voice request information.

8. A voice interaction based apparatus for generating a multimedia playlist, the apparatus comprising:

at least one processor; and

a memory storing instructions, the instructions when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising;

acquiring first voice request information for playing multimedia resources;

identifying a key tag for indicating a characteristic attribute of the multimedia resources in the first voice request information;

finding the multimedia resources having the key tag in a multimedia resource library; and

generating a multimedia playlist based on the found multimedia resources;

wherein the generating a multimedia playlist based on the found multimedia resources comprises;

acquiring popularity data of the found multimedia resources, ordering the multimedia resources by the popularity data in a descending order;

acquiring descriptor data of a user sending the first voice request information associated with to-be-played multimedia resources, selecting multimedia resources matching the user descriptor as candidate multimedia resources; and

selecting a preset number of the candidate multimedia resources as target multimedia resources based on the order, and adding the target multimedia resources to the multimedia playlist; and

wherein before the selecting a preset number of the candidate multimedia resources as target multimedia resources based on the order, and adding the target multimedia resources to the multimedia playlist, the generating a multimedia playlist based on the found multimedia resources further comprises;

determining weights of the key tags for indicating a given characteristic attribute based on occurrence numbers of the key tags in the multimedia resource library; and

determining demand numbers of the multimedia resources having the key tags in the multimedia playlist based on the weights of the key tags and a preset length of the multimedia playlist; and

the selecting a preset number of the candidate multimedia resources as target multimedia resources based on the order, and adding the target multimedia resources to the multimedia playlist comprises;

dividing the candidate multimedia resources in groups based on the key tags; and

extracting, based on the order, the multimedia resources satisfying the corresponding demand numbers from each of the groups, and generating the multimedia playlist based on the order of the candidate multimedia resources.

9. The apparatus according to claim 8, wherein the acquiring popularity data of the found multimedia resources comprises:

calculating the corresponding popularity data based on multimedia resource playing data and internet search data.

10. The apparatus according to claim 9, wherein the acquiring popularity data of the found multimedia resources further comprises:

judging whether the multimedia resources are multimedia resources being played in a preset period before the acquiring first voice request information for playing multimedia resources; and

implementing attenuation operation on the popularity data of the multimedia resources by a preset attenuation factor, in response to determine that the multimedia resources are multimedia resources being played in a preset period before the acquiring first voice request information for playing multimedia resources.

11. The apparatus according to claim 8, wherein the identifying a key tag for indicating a characteristic attribute of the multimedia resources in the first voice request information comprises:

extracting a tag matching a preset tag library in the first voice request information as the key tag.

12. The apparatus according to claim 8, wherein the characteristic attribute comprises:

an author, an identifier for a set of the multimedia resources, a style or a language.

13. The apparatus according to claim 8, wherein the operations further comprise:

responding to received second voice request information for playing multimedia resources;

analyzing an intention of the second voice request information, and updating the multimedia playlist based on a result of the analyzing an intention.

14. The apparatus according to claim 8, wherein the operations further comprise:

pushing the multimedia playlist to a device sending the first voice request information.

15. A non-transitory computer storage medium storing a computer program, the computer program when executed by one or more processors, causes the one or more processors to perform operations, the operations comprising:

acquiring first voice request information for playing multimedia resources;

identifying a key tag for indicating a characteristic attribute of the multimedia resources in the first voice request information;

finding the multimedia resources having the key tag in a multimedia resource library; and

generating a multimedia playlist based on the found multimedia resources;

wherein the generating a multimedia playlist based on the found multimedia resources comprises;

acquiring popularity data of the found multimedia resources, ordering the multimedia resources by the popularity data in a descending order;

acquiring descriptor data of a user sending the first voice request information associated with to-be-played multimedia resources, selecting multimedia resources matching the user descriptor as candidate multimedia resources; and

selecting a preset number of the candidate multimedia resources as target multimedia resources based on the order, and adding the target multimedia resources to the multimedia playlist; and

wherein before the selecting a preset number of the candidate multimedia resources as target multimedia resources based on the order, and adding the target multimedia resources to the multimedia playlist, the generating a multimedia playlist based on the found multimedia resources further comprises;

determining weights of the key tags for indicating a given characteristic attribute based on occurrence numbers of the key tags in the multimedia resource library; and

determining demand numbers of the multimedia resources having the key tags in the multimedia playlist based on the weights of the key tags and a preset length of the multimedia playlist; and

the selecting a preset number of the candidate multimedia resources as target multimedia resources based on the order, and adding the target multimedia resources to the multimedia playlist comprises;

dividing the candidate multimedia resources in groups based on the key tags; and

extracting, based on the order, the multimedia resources satisfying the corresponding demand numbers from each of the groups, and generating the multimedia playlist based on the order of the candidate multimedia resources.