Patents by Inventor Nengjun Ouyang
Nengjun Ouyang 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: 11844121Abstract: The present disclosure discloses a wireless connection establishment method, an apparatus, a device and a storage media, which is applied to artificial intelligence, Internet of Vehicles and intelligent transportation technologies in the field of computer technology.Type: GrantFiled: June 21, 2021Date of Patent: December 12, 2023Assignee: Apollo Intelligent Connectivity (Beijing) Technology Co., Ltd.Inventors: Qing Wang, Nengjun Ouyang, Xinxue Lei
-
Publication number: 20230216912Abstract: Provided are a page display method and an electronic device. The present invention relates to the technical field of computers, and in particular, to the automatic driving technology, the Internet of Vehicles technology, and the field of smart cabins. The specific implementation solution is: a remote server corresponding to an in-vehicle device is determined, wherein the content displayed on a page by the remote server is authorized by default to be displayed on the in-vehicle device; first page data of a remote server is acquired, wherein the first page data corresponds to a first page displayed on the remote server; and the first page is displayed on the in-vehicle device according to the first page data.Type: ApplicationFiled: September 13, 2022Publication date: July 6, 2023Applicant: Apollo Intelligent Connectivity (Beijing) Technology Co., Ltd.Inventors: Qili HUANG, Nengjun OUYANG
-
Patent number: 11587550Abstract: A method and an apparatus for outputting information are provided. The method includes acquiring voice information received within a preset time period before a device is awakened, where the device is provided with a wake-up model for outputting preset response information when a preset wake-up word is received; performing speech recognition on the voice information to obtain a recognition result; extracting feature information of the voice information in response to determining that the recognition result does not include a preset wake-up word; generating a counterexample training sample according to the feature information; and training the wake-up model using a counter-example training sample, and outputting the trained wake-up model.Type: GrantFiled: December 10, 2020Date of Patent: February 21, 2023Assignee: Apollo Intelligent Connectivity (Beijing) Technology Co., Ltd.Inventors: Nengjun Ouyang, Ke Zhao, Rong Liu
-
Publication number: 20230004379Abstract: A service method for head unit software includes: obtaining operations related to the HU software; determining service interfaces of operation services comprised in HU system software corresponding to the operations, in which the HU system software is connected to the HU software; and calling the service interfaces to obtain results of executing the operations by the operation services.Type: ApplicationFiled: September 9, 2022Publication date: January 5, 2023Applicant: APOLLO INTELLIGENT CONNECTIVITY (BEIJING) TECHNOLOGY CO., LTD.Inventors: Wenhuan Zhou, Qili Huang, Nengjun Ouyang
-
Patent number: 11531463Abstract: A method for processing a touch instruction, an electronic device and a storage medium, related to the fields of Internet of Things, intelligent transportation, and the like, are provided. The method includes: detecting a type of a received touch event; in a case where the type of the touch event is a predetermined type, acquiring a number of fingers which execute the touch event of the predetermined type each time; and determining a touch instruction by utilizing a change situation of the number of fingers which execute two adjacent touch events of the predetermined type. According to the solution, the number of fingers which execute the touch event can be determined by utilizing the change situation of the number of fingers corresponding to two adjacent touch events conforming to the predetermined type.Type: GrantFiled: July 2, 2021Date of Patent: December 20, 2022Inventors: Qili Huang, Nengjun Ouyang, Qing Wang
-
Publication number: 20220287118Abstract: The present disclosure provides a method and apparatus for interconnecting a vehicle and a machine, and relates to the field of communication technology, and specifically to the field of vehicle networking technology. A specific implementation comprises: acquiring device information used for a wireless direct connection first; then sending the device information to a vehicle-mounted terminal based on a short-range wireless communication protocol; and finally, receiving a connection request based on the device information, and establishing a wireless direct connection with the vehicle-mounted terminal sending the connection request. A vehicle-machine interconnection is implemented through the data transmission based on the short-range wireless communication protocol, without the need to continuously scan surrounding devices like a Bluetooth module, thereby saving the device energy consumption and improving the pertinence of the vehicle-machine interconnection.Type: ApplicationFiled: May 24, 2022Publication date: September 8, 2022Inventors: Shubin Liu, Nengjun Ouyang, Qilli Huang
-
Patent number: 11257497Abstract: The present disclosure provides a voice wake-up processing method, an apparatus and a storage medium. After acquiring voice wake-up signals collected by audio input devices in at least two audio zones, an electronic device may correct, based on to-be-woken-up audio zones obtained from amplitudes of the voice wake-up signals collected by the audio input devices in the at least two audio zones, a to-be-woken-up audio zone identified using a voice engine, avoiding that audio zones in which a plurality of audio input devices collecting voice wake-up signals produced from a same user are located are all woken up, therefore, it is possible to improve accuracy of a voice wake-up result obtained by the electronic device. Therefore, the present disclosure can solve the technical problem that a vehicle-mounted terminal has low voice wake-up accuracy due to an insufficient degree of sound isolation between audio zones of the vehicle-mounted terminal.Type: GrantFiled: December 23, 2019Date of Patent: February 22, 2022Assignee: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD.Inventors: Hanying Peng, Nengjun Ouyang
-
Publication number: 20210390947Abstract: A method and an apparatus for outputting information are provided. The method includes acquiring voice information received within a preset time period before a device is awakened, where the device is provided with a wake-up model for outputting preset response information when a preset wake-up word is received; performing speech recognition on the voice information to obtain a recognition result; extracting feature information of the voice information in response to determining that the recognition result does not include a preset wake-up word; generating a counterexample training sample according to the feature information; and training the wake-up model using a counter-example training sample, and outputting the trained wake-up model.Type: ApplicationFiled: December 10, 2020Publication date: December 16, 2021Inventors: Nengjun OUYANG, Ke ZHAO, Rong LIU
-
Publication number: 20210333963Abstract: A method for processing a touch instruction, an electronic device and a storage medium, related to the fields of Internet of Things, intelligent transportation, and the like, are provided. The method includes: detecting a type of a received touch event; in a case where the type of the touch event is a predetermined type, acquiring a number of fingers which execute the touch event of the predetermined type each time; and determining a touch instruction by utilizing a change situation of the number of fingers which execute two adjacent touch events of the predetermined type. According to the solution, the number of fingers which execute the touch event can be determined by utilizing the change situation of the number of fingers corresponding to two adjacent touch events conforming to the predetermined type.Type: ApplicationFiled: July 2, 2021Publication date: October 28, 2021Inventors: Qili Huang, Nengjun Ouyang, Qing Wang
-
Publication number: 20210315034Abstract: The present disclosure discloses a wireless connection establishment method, an apparatus, a device and a storage media, which is applied to artificial intelligence, Internet of Vehicles and intelligent transportation technologies in the field of computer technology.Type: ApplicationFiled: June 21, 2021Publication date: October 7, 2021Inventors: Qing Wang, Nengjun Ouyang, Xinxue Lei
-
Publication number: 20210295857Abstract: This application discloses a voice recognition method, a voice recognition apparatus, an electronic device and a computer readable storage medium, and relates to the field of voice recognition technology. A specific implementation is: performing a latency estimation according to a first microphone signal and a first reference signal in a preset time period to obtain a latency value; acquiring a system audio signal, and processing the system audio signal by using the latency value to obtain a second reference signal; performing de-noising processing on a collected second microphone signal according to the second reference signal, to obtain a to-be-recognized voice signal; and performing recognition on the to-be-recognized voice signal.Type: ApplicationFiled: September 28, 2020Publication date: September 23, 2021Applicant: Beijing Baidu Netcom Science and Technology Co., LtdInventors: Nengjun OUYANG, Junhua XU, Zhengbin SONG, Danqing YANG, Gang XU
-
Patent number: 10811031Abstract: Embodiments of the present disclosure disclose a method and a device for obtaining an amplitude for a sound zone, a related electronic device and a storage medium. The method includes the following. Speech data of a target sound zone is obtained in real time. The speech data includes audio signals corresponding to a plurality of sampling points. The audio signals are stored by comparing an amplitude of a current audio signal to be stored with an amplitude of each stored audio signal to determine whether to store the current audio signal according to a comparison result. A current amplitude for the target sound zone is calculated according to amplitudes of all stored audio signals.Type: GrantFiled: December 26, 2019Date of Patent: October 20, 2020Assignee: Baidu Online NetworkTechnology (Beijing) Co., Ltd.Inventors: Hanying Peng, Nengjun Ouyang
-
Publication number: 20200211582Abstract: Embodiments of the present disclosure disclose a method and a device for obtaining an amplitude for a sound zone, a related electronic device and a storage medium. The method includes the following. Speech data of a target sound zone is obtained in real time. The speech data includes audio signals corresponding to a plurality of sampling points. The audio signals are stored by comparing an amplitude of a current audio signal to be stored with an amplitude of each stored audio signal to determine whether to store the current audio signal according to a comparison result. A current amplitude for the target sound zone is calculated according to amplitudes of all stored audio signals.Type: ApplicationFiled: December 26, 2019Publication date: July 2, 2020Inventors: Hanying PENG, Nengjun OUYANG
-
Publication number: 20200202857Abstract: The present disclosure provides a voice wake-up processing method, an apparatus and a storage medium. After acquiring voice wake-up signals collected by audio input devices in at least two audio zones, an electronic device may correct, based on to-be-woken-up audio zones obtained from amplitudes of the voice wake-up signals collected by the audio input devices in the at least two audio zones, a to-be-woken-up audio zone identified using a voice engine, avoiding that audio zones in which a plurality of audio input devices collecting voice wake-up signals produced from a same user are located are all woken up, therefore, it is possible to improve accuracy of a voice wake-up result obtained by the electronic device. Therefore, the present disclosure can solve the technical problem that a vehicle-mounted terminal has low voice wake-up accuracy due to an insufficient degree of sound isolation between audio zones of the vehicle-mounted terminal.Type: ApplicationFiled: December 23, 2019Publication date: June 25, 2020Inventors: HANYING PENG, Nengjun Ouyang
-
Patent number: 10446150Abstract: An in-vehicle voice command recognition method and apparatus, and a storage medium. The method includes: acquiring a voice command inputted by a user; determining basic information of the user according to a pre-trained deep neural network (DNN) model; identifying contents of the voice command according to the basic information of the user, and determining at least one potential user intention according to the identified contents and a scenario page context at the time when the user inputs the voice command; determining a confidence level of the potential user intention according to the DNN model; determining a real user intention from the potential user intention according to the confidence level; and executing a corresponding action according to the real user intention. The embodiments of the present disclosure can effectively improve the correct recognition rate of voice commands.Type: GrantFiled: November 23, 2015Date of Patent: October 15, 2019Assignee: Baidu Online Network Technology (Beijing) Co. Ltd.Inventors: Lihui Xun, Nengjun Ouyang, Xiangyu Mu
-
Publication number: 20180190283Abstract: An embodiment of the present disclosure discloses an in-vehicle voice command recognition method and apparatus, and a storage medium. The method comprises: acquiring a voice command inputted by a user; determining basic information of the user according to a pre-trained deep neural network (DNN) model; identifying contents of the voice command according to the basic information of the user, and determining at least one potential user intention according to the identified contents and a scenario page context at the time when the user inputs the voice command; determining a confidence level of the potential user intention according to the DNN model; determining a real user intention from the potential user intention according to the confidence level; and executing a corresponding action according to the real user intention.Type: ApplicationFiled: November 23, 2015Publication date: July 5, 2018Inventors: Lihui Xun, Nengjun Ouyang, Xiangyu Mu