Baidu Online Network Technology (beijing) Co., Ltd.

Shanghai Xiaodu Technology Co. Ltd.

Xiajun Luo

Guang Lu

Shiquan Ye

Qiang Ju

Jian Xie

Shui Liu

Xiangjie Yin

Hao Yang

Wenbo Zhang

Ran Zhao

Chenxi Gao

Wenjuan Zhou

Jue Huang

Yajuan Feng

Miaochang Zhang

A method and an apparatus for generating information are provided. The method includes: determining, in response to receiving a first user sentence, whether a keyword of a preset first category is included in the first user sentence, the first category including at least one subcategory; determining, in response to determining the first category keyword being included in the first user sentence, the first category keyword included in the first user sentence as a first keyword, and determining a subcategory to which the first keyword belongs, to generate a first keyword set and a subcategory set; and selecting, based on the first keyword set and the subcategory set, a song list from a pre-generated song list set as a to-be-played song list, to generate a to-be-played song list set, the song list including at least one piece of audio and song list category information.

Method and apparatus for generating information

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.

Intelligent playing method and apparatus based on preference feedback

The embodiments of the disclosure disclose a method and apparatus for generating to-be-played multimedia content. An embodiment of the method includes: receiving a third-party multimedia playlist, the third-party multimedia playlist being from a third-party multimedia playing platform; analyzing the third-party multimedia playlist to obtain identifier information of multimedia contents in the third-party multimedia playlist, the identifier information including name information of the multimedia content and name information of the leading author; determining to-be-played multimedia content matching the multimedia contents in the third-party multimedia playlist from a multimedia content database based on the identifier information of the multimedia contents in the third-party multimedia playlist to generate a to-be-played multimedia content list; and sending the to-be-played multimedia content list to a terminal playing device. The embodiment may integrate multimedia resources from different third-party multimedia platforms, and improve the consistency in playing multimedia resources.

Method and apparatus for generating to-be-played multimedia content

Embodiments of the disclosure disclose a method and apparatus for updating a multimedia playlist. An embodiment of the method comprises: sending a current multimedia content playlist to a playing terminal; analyzing, in response to receiving a voice updating request from a user to update currently played multimedia content in the current multimedia content playlist, the voice updating request to obtain an updating instruction corresponding to the currently played multimedia content; searching in a preset multimedia content database based on the updating instruction to generate an optimized multimedia playlist; and sending the optimized multimedia playlist to the playing terminal. With the embodiment, a matching degree between the obtained optimized multimedia playlist and the user's updating instruction is higher, the search operation is simpler, and then the search consumes less hardware resources.

Method and apparatus for updating multimedia playlist

Embodiments of this disclosure disclose a method and apparatus for providing a voice service. An embodiment of the method comprises: analyzing, in response to receiving first voice request information sent by an intelligent voice device containing a display, the first voice request information to determine a user demand; determining an alternative operation associated with the user demand based on a configured optional operation set; generating prompt information for guiding a user to execute the alternative operation; and pushing the prompt information to the intelligent voice device containing the display to enable the intelligent voice device to show the prompt information on the display. The embodiment realizes a user demand based differential operation prompt, and improves the efficiency of the voice service.

Method and apparatus for providing voice service

A searching method and system based on multi-round inputs and a terminal are provided. The method comprises: acquiring search conditions input by a user in multiple searches; determining a multi-round property between at least two searches of the multiple searches; determining a search purpose of one of the search conditions, and determining that the search purpose of the one of the search conditions is a multi-round search purpose; generating search results based on the multi-round search purpose and search conditions input by the user; and ranking the generated search results, and determining and outputting an optimal search result. According to the searching method provided by the present application, a machine can understand a user's purpose under a continuous multi-round interactions by understanding the context, so that the use initiative of the user is improved.

Searching method and system based on multi-round inputs, and terminal

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.

Growing community of inventors

Beijing, China

Xiajun Luo