Patents by Inventor Liangcheng WU
Liangcheng WU has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11580974Abstract: A method for exiting a voice skill, an apparatus, a device, and a storage medium are provided by embodiments of the present disclosure, wherein a user voice instruction is received; a target exit intention corresponding to the user voice instruction is identified according to the user voice instruction and a grammar rule of a preset exit intention; and a corresponding operation is executed on a current voice skill of a device according to the target exit intention. The embodiments of the present disclosure refine and expand the user's exit intention. After the target exit intention to which the user voice instruction belongs is identified, the corresponding operation is executed according to the target exit intention so as to meet the users' different exit requirements for the voice skills, enhance the fluency and convenience of user interaction with the device and improve the user's exit experience when using the voice skills.Type: GrantFiled: June 29, 2020Date of Patent: February 14, 2023Assignee: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD.Inventors: Huan Tang, Xiao Zhou, Liangcheng Wu
-
Patent number: 11468378Abstract: The present disclosure provides a method and apparatus for skill sharing. A user's first click operation on a sharing link of a first skill is received; and the page jumps to a skill development page according to the first click operation, where the skill development page includes an input box of a link and an import button, and the input box is used to input a sharing link of a skill, while the import button is used to input an import instruction of the skill; and the first skill is imported into a skill development platform according to a user operation. By generating a sharing link of the skill, the sharing link of the skill can be shared within any location in existing sharing ways. The sharing manner thus enables the user to import the first skill in a variety of ways and avoids repeated development from different developers.Type: GrantFiled: October 30, 2019Date of Patent: October 11, 2022Inventors: Yaowen Qi, Quan Liang, Liangcheng Wu, Huan Tang
-
Patent number: 11383162Abstract: Provided are a voice skill game editing method, an apparatus, a device and a readable storage medium, which involve displaying a plurality of node elements having a hierarchical relationship and a cascading element for connecting a parent node and a child node in a node editing area of a user editing interface; acquiring voice scenario information configured by a user for the node elements in an element configuration area of the node elements when the node elements are determined as in an active state; acquiring voice skill control information configured by the user for the cascading element in an element configuration area of the cascading element when the cascading element is determined as in an active state; and determining, according to the hierarchical relationship corresponding to the node elements and the voice skill control information configured for the cascading element, game logic between the voice scenario information.Type: GrantFiled: June 25, 2020Date of Patent: July 12, 2022Inventors: Kaisheng Song, Xuening Deng, Yaowen Qi, Jiale Wang, Huan Tang, Liangcheng Wu, Lei Zhong, Peng Yuan, Linlin Zhao, Sen Li
-
Publication number: 20210335357Abstract: The disclosure provides a method for controlling an intelligent speech apparatus, an electronic device and a storage medium. The method includes: receiving a play command comprising a target file identifier; determining a file permission of a target file corresponding to the target file identifier; playing a preset push information, when the file permission does not match a current user permission of a user of the intelligent speech apparatus; and playing the target file when receiving speech data associated with the push information within a preset time period.Type: ApplicationFiled: November 30, 2020Publication date: October 28, 2021Inventors: Wenyu WANG, Liangcheng WU, Lei ZHONG
-
Publication number: 20210264912Abstract: A data analysis method, an apparatus and a storage medium based on an intelligent speech device which relate to the technical field of artificial intelligence are provided. According to some embodiments, the intelligent speech device acquires feature information of the user visiting the shop; the intelligent speech device uploads user data and the identification information of the shop to the cloud based on the acquired feature information of the user visiting the shop, so that the cloud performs data analysis based on the user data and the identification information of the shop. As compared with related art, the technical solution may extend the performance of the intelligent speech device so that the intelligent speech device may constitute a business intelligence system with the cloud, achieve analysis of business data and improve an anticipation degree and a use rate of the intelligent speech device.Type: ApplicationFiled: September 14, 2020Publication date: August 26, 2021Applicant: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTDInventors: Wenyu WANG, Liangcheng WU, Lei ZHONG
-
Publication number: 20210005193Abstract: A method for exiting a voice skill, an apparatus, a device, and a storage medium are provided by embodiments of the present disclosure, wherein a user voice instruction is received; a target exit intention corresponding to the user voice instruction is identified according to the user voice instruction and a grammar rule of a preset exit intention; and a corresponding operation is executed on a current voice skill of a device according to the target exit intention. The embodiments of the present disclosure refine and expand the user's exit intention. After the target exit intention to which the user voice instruction belongs is identified, the corresponding operation is executed according to the target exit intention so as to meet the users' different exit requirements for the voice skills, enhance the fluency and convenience of user interaction with the device and improve the user's exit experience when using the voice skills.Type: ApplicationFiled: June 29, 2020Publication date: January 7, 2021Applicant: Baidu Online Network Technology (Beijing) Co., Ltd.Inventors: Huan Tang, Xiao Zhou, Liangcheng Wu
-
Publication number: 20200406137Abstract: Provided are a voice skill game editing method, an apparatus, a device and a readable storage medium, which involve displaying a plurality of node elements having a hierarchical relationship and a cascading element for connecting a parent node and a child node in a node editing area of a user editing interface; acquiring voice scenario information configured by a user for the node elements in an element configuration area of the node elements when the node elements are determined as in an active state; acquiring voice skill control information configured by the user for the cascading element in an element configuration area of the cascading element when the cascading element is determined as in an active state; and determining, according to the hierarchical relationship corresponding to the node elements and the voice skill control information configured for the cascading element, game logic between the voice scenario information.Type: ApplicationFiled: June 25, 2020Publication date: December 31, 2020Inventors: Kaisheng SONG, Xuening DENG, Yaowen QI, Jiale WANG, Huan TANG, Liangcheng WU, Lei ZHONG, Peng YUAN, Linlin ZHAO, Sen LI
-
Publication number: 20200409693Abstract: A file generation method, device and apparatus, as well as a storage medium are provided. The method includes: receiving attribute information of a feature; editing a business logic of the feature; and generating a description file for the feature according to the attribute information and the business logic. In the embodiments of the present disclosure, the description file for the feature can be generated using the attribute information and the business logic of the feature. The description file can be directly converted into feature service codes, thus contributing to a rapid service generation and reducing the programming difficulty of the service development.Type: ApplicationFiled: November 26, 2019Publication date: December 31, 2020Inventors: Kaisheng Song, Xuening Deng, Yaowen Qi, Huan Tang, Liangcheng Wu, Jiale Wang, Lei Zhong, Peng Yuan, Linlin Zhao, Sen Li
-
Publication number: 20200242537Abstract: The present disclosure provides a method and apparatus for skill sharing. A user's first click operation on a sharing link of a first skill is received; and the page jumps to a skill development page according to the first click operation, where the skill development page includes an input box of a link and an import button, and the input box is used to input a sharing link of a skill, while the import button is used to input an import instruction of the skill; and the first skill is imported into a skill development platform according to a user operation. By generating a sharing link of the skill, the sharing link of the skill can be shared within any location in existing sharing ways. The sharing manner thus enables the user to import the first skill in a variety of ways and avoids repeated development from different developers.Type: ApplicationFiled: October 30, 2019Publication date: July 30, 2020Inventors: Yaowen QI, Quan LIANG, Liangcheng WU, Huan TANG
-
Publication number: 20200007926Abstract: Embodiments of the present disclosure disclose a method and apparatus for playing a video. A specific embodiment of the method includes: in response to detecting a target video is played to an image frame associated with a time node, pausing the playing of the target video, the target video being acquired from a server by a smart device in response to receiving a video playing voice command in a form of voice; sending to the server a request for acquiring voice interactive content corresponding to the time node; receiving the voice interactive content returned by the server; and playing the received voice interactive content. According to the embodiment, the interactive interaction with the user performed through a dialogue is implemented during the playing of the video.Type: ApplicationFiled: March 12, 2019Publication date: January 2, 2020Inventors: Huan Tang, Peng Yuan, Haiguang Yuan, Liangcheng Wu
-
Publication number: 20190147104Abstract: A method and apparatus for constructing an artificial intelligence application are provided. A specific embodiment of the method includes: acquiring a content description document corresponding to a piece of content provided by a content supplier and a hierarchical relationship between content categories; analyzing the content description document to obtain a content attribute, and constructing an operation description template based on the hierarchical relationship between the content categories, or the content attribute; binding the operation description template to a preset interface of an operation type of an operation described by the operation description template; and constructing an artificial intelligence application using the operation description template and the preset interface bound to the operation description template.Type: ApplicationFiled: September 17, 2018Publication date: May 16, 2019Inventors: Liangcheng WU, Xiaoli TIAN, Jingya WANG, Tao YANG, Zhenchao JIA, Tian WANG, Huan TANG, Peng YUAN, Lei ZHONG