[go: up one dir, main page]

WO2025213507A1 - 基于视频识别的设备控制方法、装置与系统 - Google Patents

基于视频识别的设备控制方法、装置与系统

Info

Publication number
WO2025213507A1
WO2025213507A1 PCT/CN2024/089445 CN2024089445W WO2025213507A1 WO 2025213507 A1 WO2025213507 A1 WO 2025213507A1 CN 2024089445 W CN2024089445 W CN 2024089445W WO 2025213507 A1 WO2025213507 A1 WO 2025213507A1
Authority
WO
WIPO (PCT)
Prior art keywords
video
user
video content
controlled device
characters
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2024/089445
Other languages
English (en)
French (fr)
Inventor
黄颖
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenying Digital Shenzhen Co
Original Assignee
Shenying Digital Shenzhen Co
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenying Digital Shenzhen Co filed Critical Shenying Digital Shenzhen Co
Publication of WO2025213507A1 publication Critical patent/WO2025213507A1/zh
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/20—Movements or behaviour, e.g. gesture recognition

Definitions

  • the present invention relates to technical fields such as video processing, intelligent control, artificial intelligence, digital culture, and human-computer interaction, and in particular to a device control method, apparatus, and system based on video recognition.
  • buttons, touchscreen control, remote control, or mobile phone app can be controlled by buttons, touchscreen control, remote control, or mobile phone app.
  • these existing control methods require the user to interact with the device in order for the controlled device to trigger the corresponding state and function. For example, if the user needs the device to operate in a certain state or perform a certain function, they need to input control commands through interfaces such as buttons or apps. Therefore, the control methods of existing service-oriented smart devices are highly dependent on user operation and have a low level of intelligence. The user experience when using the device needs to be improved.
  • the present invention provides a device control method, apparatus and system based on video recognition to enhance the intelligence level of smart device control and improve the user experience of smart devices.
  • the present invention provides a device control method based on video recognition, comprising the following steps:
  • the working mode of the controlled device is automatically controlled so that the controlled device acts on the user in different working modes, and the correlation between the video character behavior, the controlled device and the user experience of the controlled device is established.
  • the present invention provides a device control method based on video recognition, comprising the following steps:
  • the control signal transmitted by the server is received, and the received control signal is sent to the controlled device, so that the controlled device acts on the user in different working modes, and the correlation between the video character behavior, the controlled device and the user experience of the controlled device is established.
  • the present invention provides a device control apparatus based on video recognition, comprising:
  • the video character behavior analysis module is used to analyze the character behavior of the video content currently watched by the user to obtain different behavior types of the video characters in the current video content;
  • the device mode automatic control module is used to automatically control the working mode of the controlled device according to the different behavior types of the video characters in the current video content, so that the controlled device acts on the user in different working modes and establishes the correlation between the video character behavior, the controlled device and the user experience of the controlled device.
  • the present invention provides a device control system based on video recognition, comprising:
  • a user selects video content to watch through the user terminal;
  • a server in communication with the user terminal, runs a computer program to implement any of the above-mentioned device control methods based on video recognition, and transmits a control signal for controlling the working mode of the controlled device to the user terminal;
  • the controlled device is connected to the user terminal for communication and receives the control signal obtained by the user terminal to perform work in the corresponding working mode.
  • the present invention has the following beneficial effects:
  • the present invention provides a device control method, device and system based on video recognition.
  • the method analyzes the behavior of characters in the video content currently watched by a user to obtain different behavior types of video characters in the current video content.
  • the working mode of the controlled device is automatically controlled so that the controlled device acts on the user in different working modes, and the correlation between the behavior of the video characters, the controlled device and the user experience of the controlled device is established, thereby improving the intelligence level of smart device control and enhancing the user experience of the smart device.
  • FIG1 is a flow chart of a device control method based on video recognition according to the present invention.
  • FIG2 is another flow chart of a device control method based on video recognition according to the present invention.
  • FIG3 is a schematic diagram of an architecture of a device control method based on video recognition according to the present invention.
  • FIG4 is a schematic diagram of an architecture of a server of the present invention.
  • FIG5 is a schematic diagram of an architecture of a user terminal of the present invention.
  • FIG6 is a schematic diagram of an architecture of a device control method system based on video recognition according to the present invention.
  • this embodiment provides a device control method based on video recognition, including steps S101 and S102.
  • Steps S101 and S102 can be executed on a server, and by analyzing the behavior of characters in the video content currently being watched by the user, different behavior types of the characters in the current video content are obtained.
  • the operating mode of the controlled device is automatically controlled, so that the controlled device acts on the user in different operating modes, and a correlation is established between the behavior of the characters in the video content, the controlled device, and the user experience of the controlled device, thereby improving the intelligence level of smart device control and enhancing the user experience of the smart device.
  • the server includes memory, processors, and network interfaces that are interconnected via a system bus.
  • a server is a device capable of automatically performing numerical calculations and/or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, and the like.
  • the server can interact with users through methods such as a keyboard, mouse, remote control, touchpad, or voice-controlled devices.
  • Memory includes at least one type of readable storage medium, including flash memory, hard disks, multimedia cards, card-type memories (e.g., SD or DX memories), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic storage, magnetic disks, optical disks, and the like.
  • the memory may be an internal storage unit of the server, such as the server's hard disk or memory.
  • the memory may also be an external storage device of the server, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash card, etc. equipped on the server.
  • the memory may also include both the internal storage unit of the server and its external storage device.
  • Step S101 Performing a character behavior analysis on the video content currently being watched by the user to obtain different behavior types of the video characters in the current video content.
  • Performing a character behavior analysis on the video content currently being watched by the user to obtain different behavior types of the video characters in the current video content may include: obtaining the video content currently being watched by the user, extracting image frames from the video content; and performing character behavior recognition on the image content of each extracted frame to obtain different behavior types of the video characters in the current video content.
  • performing character behavior recognition on the image content of each extracted frame to obtain different behavior types of the video characters in the current video content may include: inputting the image content of each extracted frame into an AI character behavior recognition model; and performing character behavior recognition on the image content of each extracted frame through the AI character behavior recognition model to obtain different behavior types of the video characters in the current video content.
  • the AI character behavior recognition model includes any one of a convolutional neural network, a recurrent neural network, a long short-term memory network, a graph convolutional network, and a spatiotemporal graph convolutional network.
  • character behavior analysis is performed on the video content currently being watched by the user to obtain different behavior types of the characters in the current video content.
  • This may include: a user on the user end selects video content to watch, and a server simultaneously performs character behavior analysis on the video content currently being watched by the user to obtain different behavior types of the characters in the current video content.
  • the user on the user end may perform a video search using a video recognition module running on the user end to search for video content provided by a video service platform for viewing.
  • the server of the video recognition module simultaneously performs character behavior analysis on the video content currently being watched by the user to obtain different behavior types of the characters in the current video content.
  • the video recognition module is embedded in a browser, and the user-end user searches for video content provided by the video service platform through the browser for viewing. After the video recognition module recognizes the video content currently being viewed by the user, it synchronizes the currently viewed video content to the video recognition module's server to perform character behavior analysis of the video content. Furthermore, the video recognition module supports multiple methods of video search and recognition; it can search and recognize video content provided by the video service platform, as well as search and recognize the user's local videos. It is understandable that the video recognition module can support multiple video searches and video uploads by the user. For example, the video recognition module has an embedded search engine to support online video searches and locally uploaded video searches.
  • the video recognition module recognizes the video content being viewed in real time and sends the information to the server, enabling instant analysis and processing of the behavior of the characters in the video content, obtaining different behavior types of the characters in the current video content, and using this to automatically control the operating mode of the controlled device.
  • Step S102 Automatically control the working mode of the controlled device according to different behavior types of the video characters in the current video content, so that the controlled device acts on the user in different working modes, and establishes the correlation between the video character behavior, the controlled device, and the user experience of the controlled device.
  • the controlled device may act on the user in different working modes, including the force of direct physical contact with the user's body, the heat of physical contact with the user's body, and the sound waves of non-physical contact with the user's body.
  • the controlled device includes a massager; the working mode of the massager includes a reciprocating motion mode and/or a rotational motion mode.
  • the controlled device may include a massager; the working mode of the massager may include different vibration frequency modes and/or different vibration intensity modes.
  • the working mode of the massager may include a multi-frequency vibration mode, a single-frequency vibration mode, a pulse mode, a kneading mode, an air pressure mode, and a heating mode, etc.
  • automatically controlling the working mode of the controlled device according to different behavior types of the video characters in the current video content includes:
  • character behavior analysis is performed on the video content currently watched by the user to obtain different behavior types of video characters in the current video content, which may include: obtaining the video content currently watched by the user, extracting video clips from the video content; and performing character behavior recognition on the content of each extracted video clip to obtain different behavior types of video characters in the current video content.
  • the behaviors of people in video content may be continuous or repetitive. Extracting and using a single video frame will result in cumbersome data processing, which is not conducive to saving data processing and transmission resources.
  • this embodiment by extracting video clips from the video content, and performing character behavior recognition on the content of each extracted video clip, different behavior types of the video characters in the current video content are obtained, thereby saving data processing and data transmission resources.
  • character behavior analysis is performed on the video content currently being viewed by the user to obtain different behavior types of the video characters in the current video content.
  • This may include extracting and analyzing the audio from the video to obtain the different behavior types of the video characters in the current video content.
  • the analysis of the audio in the video may include analyzing parameters such as audio volume, frequency, bit rate, sampling rate, amplitude, waveform, audio format, duration, dynamic range, signal-to-noise ratio (SNR), total harmonic distortion (THD), and number of channels.
  • SNR signal-to-noise ratio
  • TDD total harmonic distortion
  • character behavior analysis is performed on the video content currently being viewed by the user to obtain different behavior types of the video characters in the current video content.
  • This may include extracting and analyzing the audio from the video while simultaneously extracting and analyzing the image frames of the video content currently being viewed by the user. This may include extracting and analyzing the audio from the video to obtain different behavior types of the video characters in the current video content. It should be noted that in this embodiment, by performing both image and audio analysis on the video content currently being viewed by the user, a more accurate identification of different behavior types of the video characters in the current video content can be obtained.
  • this embodiment provides a device control method based on video recognition, including step S201 and step S202.
  • step S201 and step S202 can be run on the user side, for example, on the user's smart phone side, by playing the video content currently selected by the user and communicating with the server and the controlled device respectively.
  • the server performs character behavior analysis on the video content currently watched by the user to obtain different behavior types of the video characters in the current video content.
  • the server transmits a control signal for controlling different working modes of the controlled device to the user side according to the different behavior types of the video characters in the current video content.
  • the received control signal is sent to the controlled device, so that the controlled device acts on the user in different working modes, establishes the correlation between the video character behavior, the controlled device and the user experience of the controlled device, thereby improving the intelligence level of smart device control and improving the user experience of smart devices.
  • the user terminal includes memory, a processor, and a network interface that are interconnected via a system bus.
  • the user terminal herein is a device capable of automatically performing numerical calculations and/or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, a microprocessor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), an embedded device, etc.
  • ASIC application-specific integrated circuit
  • FPGA field-programmable gate array
  • DSP digital signal processor
  • the user terminal can interact with the user through a keyboard, mouse, remote control, touchpad, or voice-controlled device.
  • Memory includes at least one type of readable storage medium, including flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, a magnetic disk, an optical disk, etc.
  • the memory may be an internal storage unit of the user terminal, such as the hard disk or internal memory of the user terminal.
  • the memory may also be an external storage device of the user terminal, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash card, etc. equipped on the user terminal.
  • the memory may also include both the internal storage unit of the user terminal and its external storage device.
  • performing character behavior analysis on the video content currently watched by the user to obtain different behavior types of video characters in the current video content may include: obtaining the video content currently watched by the user, extracting image frames from the video content; and performing character behavior recognition on the extracted image content of each frame to obtain different behavior types of video characters in the current video content.
  • performing character behavior recognition on the extracted image content of each frame to obtain different behavior types of video characters in the current video content may include: inputting the extracted image content of each frame into an AI character behavior recognition model; and performing character behavior recognition on the extracted image content of each frame through the AI character behavior recognition model to obtain different behavior types of video characters in the current video content.
  • the AI character behavior recognition model includes any one of the AI character behavior recognition models selected from convolutional neural networks, recurrent neural networks, long short-term memory networks, graph convolutional networks, and spatiotemporal graph convolutional networks.
  • users on the user end can perform video searches through the video recognition module running on the user end to search for video content provided by the video service platform for viewing.
  • the server of the video recognition module synchronously performs character behavior analysis on the video content currently watched by the user to obtain different behavior types of video characters in the current video content.
  • the controlled device in different operating modes, can act on the user through direct physical contact with the user's body, through the application of force, through physical contact with the user's body, or through the application of sound waves without physical contact with the user's body.
  • the controlled device comprises a massager; the massager's operating modes include a reciprocating motion mode and/or a rotational motion mode.
  • the controlled device comprises a massager; the massager's operating modes include different vibration frequency modes and/or different vibration intensity modes.
  • a browser and a video recognition module are embedded in the video recognition module, and the user-end user searches for video content provided by the video service platform through the browser for viewing.
  • the video recognition module recognizes the video content currently being watched by the user, it synchronizes the currently being watched video content to the server of the video recognition module to perform character behavior analysis of the video content.
  • the video recognition module recognizes the video content being viewed in real time and sends the information to the server, enabling instant analysis and processing of the behavior of the characters in the video content, obtaining different behavior types of the characters in the current video content, and using this to automatically control the operating mode of the controlled device.
  • character behavior analysis is performed on the video content currently watched by the user to obtain different behavior types of video characters in the current video content, which may include: obtaining the video content currently watched by the user, extracting video clips from the video content; and performing character behavior recognition on the content of each extracted video clip to obtain different behavior types of video characters in the current video content.
  • the behaviors of people in video content may be continuous or repetitive. Extracting and using a single video frame will result in cumbersome data processing, which is not conducive to saving data processing and transmission resources.
  • this embodiment by extracting video clips from the video content, and performing character behavior recognition on the content of each extracted video clip, different behavior types of the video characters in the current video content are obtained, thereby saving data processing and data transmission resources.
  • the video player embedded in the user end video recognition module supports local files and network streaming videos.
  • the browser embedded in the user end video recognition module supports searching for web pages that play HTML5 videos, such as YouTube, Vimeo, and other videos.
  • the user end video recognition module can integrate third-party video SDKs and provide rich functions through these SDKs, such as on-demand, live broadcast, advertising preview, etc.
  • the video recognition module can also support live streaming video.
  • the video recognition module can also support continuing to watch the video in picture-in-picture mode while the video is playing.
  • the video recognition module can support video playback methods such as screen casting, DLNA projection, and video file sharing.
  • this embodiment provides a device control apparatus based on video recognition, including:
  • the video character behavior analysis module is used to analyze the character behavior of the video content currently watched by the user to obtain different behavior types of the video characters in the current video content;
  • the device mode automatic control module is used to automatically control the working mode of the controlled device according to the different behavior types of the video characters in the current video content, so that the controlled device acts on the user in different working modes and establishes the correlation between the video character behavior, the controlled device and the user experience of the controlled device.
  • the working mode of the controlled device is automatically controlled so that the controlled device acts on the user in different working modes, and the correlation between the video character behavior, the controlled device and the usage experience of the controlled device is established, thereby improving the intelligence level of smart device control and improving the user experience of the smart device.
  • performing character behavior analysis on the video content currently watched by the user to obtain different behavior types of video characters in the current video content may include: obtaining the video content currently watched by the user, extracting image frames from the video content; and performing character behavior recognition on the extracted image content of each frame to obtain different behavior types of video characters in the current video content.
  • performing character behavior recognition on the extracted image content of each frame to obtain different behavior types of video characters in the current video content may include: inputting the extracted image content of each frame into an AI character behavior recognition model; and performing character behavior recognition on the extracted image content of each frame through the AI character behavior recognition model to obtain different behavior types of video characters in the current video content.
  • the AI character behavior recognition model includes any one of the AI character behavior recognition models selected from convolutional neural networks, recurrent neural networks, long short-term memory networks, graph convolutional networks, and spatiotemporal graph convolutional networks.
  • the user at the user end can search for the video through the video recognition module running on the user end.
  • the server of the video recognition module synchronously analyzes the character behavior of the video content currently watched by the user to obtain different behavior types of the video characters in the current video content.
  • the controlled device in different operating modes, can act on the user through direct physical contact with the user's body, through the application of force, through physical contact with the user's body, or through the application of sound waves without physical contact with the user's body.
  • the controlled device comprises a massager; the massager's operating modes include a reciprocating motion mode and/or a rotational motion mode.
  • the controlled device comprises a massager; the massager's operating modes include different vibration frequency modes and/or different vibration intensity modes.
  • this embodiment provides a device control system based on video recognition, including:
  • a user selects video content to watch through the user terminal;
  • a server in communication with the user terminal, runs a computer program to implement the device control method based on video recognition described in any one of the first embodiments, and transmits a control signal for controlling the working mode of the controlled device to the user terminal;
  • the controlled device is connected to the user terminal for communication and receives the control signal obtained by the user terminal to perform work in the corresponding working mode.
  • the server runs a computer program to implement the device control method based on video recognition described in any one of the first embodiments, and can transmit a control signal to the user terminal to control the operating mode of the controlled device.
  • the server can perform a character behavior analysis on the video content currently being viewed by the user to obtain different behavior types of the video characters in the current video content.
  • the server Based on the different behavior types of the video characters in the current video content, the server automatically controls the operating mode of the controlled device, so that the controlled device acts on the user in different operating modes, establishes a correlation between the video character behavior, the controlled device, and the user experience of the controlled device, thereby improving the intelligence level of smart device control and enhancing the user experience of the smart device.
  • performing character behavior analysis on the video content currently watched by the user to obtain different behavior types of video characters in the current video content may include: obtaining the video content currently watched by the user, extracting image frames from the video content; and performing character behavior recognition on the extracted image content of each frame to obtain different behavior types of video characters in the current video content.
  • performing character behavior recognition on the extracted image content of each frame to obtain different behavior types of video characters in the current video content may include: inputting the extracted image content of each frame into an AI character behavior recognition model; and performing character behavior recognition on the extracted image content of each frame through the AI character behavior recognition model to obtain different behavior types of video characters in the current video content.
  • the AI character behavior recognition model includes any one of the AI character behavior recognition models selected from convolutional neural networks, recurrent neural networks, long short-term memory networks, graph convolutional networks, and spatiotemporal graph convolutional networks.
  • the user at the user end can search for the video through the video recognition module running on the user end.
  • the server of the video recognition module synchronously analyzes the character behavior of the video content currently watched by the user to obtain different behavior types of the video characters in the current video content.
  • the controlled device in different operating modes, can act on the user through direct physical contact with the user's body, through the application of force, through physical contact with the user's body, or through the application of sound waves without physical contact with the user's body.
  • the controlled device comprises a massager; the massager's operating modes include a reciprocating motion mode and/or a rotational motion mode.
  • the controlled device comprises a massager; the massager's operating modes include different vibration frequency modes and/or different vibration intensity modes.
  • the video player embedded in the client's video recognition module supports local files and network streaming videos.
  • the browser embedded in the client's video recognition module supports searching for web pages that play HTML5 videos, such as YouTube, Vimeo, and other videos.
  • the client's video recognition module can integrate third-party video SDKs, which provide rich features such as on-demand, live broadcast, and ad previews.
  • the video recognition module can also support live streaming videos.
  • the video recognition module can also support continued viewing of the video in picture-in-picture mode while the video is playing.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • Psychiatry (AREA)
  • Social Psychology (AREA)
  • Computational Linguistics (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

本发明涉及视频处理、智能控制、人工智能、数字文化、人机交互等技术领域，提供一种基于视频识别的设备控制方法、装置与系统，通过对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型，根据所述当前视频内容中视频人物的不同行为类型，自动控制受控设备的工作模式，以使所述受控设备以不同的工作模式作用于用户，建立视频人物行为、受控设备以及受控设备使用体验的关联度，从而提升智能设备控制的智能化程度，提升智能设备的用户使用体验。

Description

基于视频识别的设备控制方法、装置与系统 技术领域
本发明涉及视频处理、智能控制、人工智能、数字文化、人机交互等技术领域，尤其涉及一种基于视频识别的设备控制方法、装置与系统。
 背景技术
随着信息技术的发展，很多服务类智能设备能够通过一定的控制方式作用于用户身体，给用户带来不同作用的使用体验。通常，这些控制方式主要包括按键控制、触屏控制、遥控器控制，手机APP控制等。例如，按摩器可以通过按键控制其振动频率，也可以通过触屏控制其振动频率，还可以通过遥控器控制其振动频率，还可以通过手机APP控制其振动频率。总体而言，现有的这些控制方式都需要用户对设备进行操作交互，受控设备才能触发对应状态和功能。例如，用户需要设备工作在某一状态下，实现某一功能时，需要通过按键或APP等接口输入控制指令。因此，现有的服务类智能设备的控制方式对用户操作的依赖程度较高，智能化程度偏低，用户对设备进行使用时，使用体验有待提升。
综上所述，现有服务类智能设备的控制技术中，存在智能化程度有待提升，用户使用体验有待提升等技术问题。
 发明内容
针对上述现有技术存在的不足，本发明提供一种基于视频识别的设备控制方法、装置与系统，以提升智能设备控制的智能化程度，提升智能设备的用户使用体验。
第一方面，本发明提供一种基于视频识别的设备控制方法，包括以下步骤：
对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型；
根据所述当前视频内容中视频人物的不同行为类型，自动控制受控设备的工作模式，以使所述受控设备以不同的工作模式作用于用户，建立视频人物行为、受控设备以及受控设备使用体验的关联度。
第二方面，本发明提供一种基于视频识别的设备控制方法，包括以下步骤：
根据用户当前选择的视频内容进行播放，并与服务器和受控设备分别通信连接；所述服务器对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型；所述服务器根据所述当前视频内容中视频人物的不同行为类型，向用户端传输控制受控设备不同的工作模式的控制信号；
接收所述服务器传输的所述控制信号，将接收到的所述控制信号发送给所述受控设备，以使所述受控设备以不同的工作模式作用于用户，建立视频人物行为、受控设备以及受控设备使用体验的关联度。
第三方面，本发明提供一种基于视频识别的设备控制装置，包括：
视频人物行为分析模块，用于对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型；
设备模式自动控制模块，用于根据所述当前视频内容中视频人物的不同行为类型，自动控制受控设备的工作模式，以使所述受控设备以不同的工作模式作用于用户，建立视频人物行为、受控设备以及受控设备使用体验的关联度。
第四方面，本发明提供一种基于视频识别的设备控制系统，包括：
用户端；用户通过所述用户端选择视频内容进行观看；
服务器，与所述用户端通信连接，运行计算机程序以实现上述任一项所述基于视频识别的设备控制方法，向用户端传输控制所述受控设备的工作模式的控制信号；
受控设备，与所述用户端通信连接，接收用户端获取到的所述控制信号，以进行对应工作模式的工作。
本发明与现有技术相比，其有益效果如下：
本发明提供一种基于视频识别的设备控制方法、装置与系统，通过对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型，根据所述当前视频内容中视频人物的不同行为类型，自动控制受控设备的工作模式，以使所述受控设备以不同的工作模式作用于用户，建立视频人物行为、受控设备以及受控设备使用体验的关联度，从而提升智能设备控制的智能化程度，提升智能设备的用户使用体验。
 附图说明
此处所说明的附图用来提供对本发明的进一步理解，构成本发明的一部分，本发明的示意性实施例及其说明用于解释本发明，并不构成对本发明的不当限定。后文将参照附图以示例性而非限制性的方式详细描述本发明的一些具体实施例。附图中相同的附图标记标示了相同或类似的部件或部分，本领域技术人员应该理解的是，这些附图未必是按比例绘制的，在附图中：
图1是本发明基于视频识别的设备控制方法的一种流程示意图；
图2是本发明基于视频识别的设备控制方法的另一种流程示意图；
图3是本发明基于视频识别的设备控制方法装置的一种架构示意图；
图4是本发明服务器的一种架构示意图；
图5是本发明用户端的一种架构示意图；
图6是本发明基于视频识别的设备控制方法系统的一种架构示意图。
 具体实施方式
为了使本技术领域的人员更好地理解本发明方案，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述。显然，所描述的实施例仅仅是本发明一部分的实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都应当属于本发明保护的范围。
实施例一
参见图1和图4，本实施例提供一种基于视频识别的设备控制方法，包括步骤S101和步骤S102。其中，步骤S101和步骤S102可以在服务器运行，通过对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型，根据所述当前视频内容中视频人物的不同行为类型，自动控制受控设备的工作模式，以使所述受控设备以不同的工作模式作用于用户，建立视频人物行为、受控设备以及受控设备使用体验的关联度，从而提升智能设备控制的智能化程度，提升智能设备的用户使用体验。
需要说明的是，服务器包括通过系统总线相互通信连接存储器、处理器、网络接口。其中，本技术领域技术人员可以理解，这里的服务器是一种能够按照事先设定或存储的指令，自动进行数值计算和/或信息处理的设备，其硬件包括但不限于微处理器、专用集成电路(Application Specific Integrated Circuit，ASIC)、可编程门阵列(Field－Programmable Gate Array，FPGA)、数字处理器 (Digital Signal Processor，DSP)、嵌入式设备等。服务器可以与用户通过键盘、鼠标、遥控器、触摸板或声控设备等方式进行人机交互。存储器至少包括一种类型的可读存储介质，可读存储介质包括闪存、硬盘、多媒体卡、卡型存储器（例如，SD或DX存储器等）、随机访问存储器（RAM）、静态随机访问存储器（SRAM）、只读存储器（ROM）、电可擦除可编程只读存储器（EEPROM）、可编程只读存储器（PROM）、磁性存储器、磁盘、光盘等。在一些实施例中，存储器可以是服务器的内部存储单元，例如该服务器的硬盘或内存。在另一些实施例中，存储器也可以是服务器的外部存储设备，例如该服务器上配备的插接式硬盘，智能存储卡（Smart Media Card, SMC），安全数字（Secure Digital, SD）卡，闪存卡（Flash Card）等。当然，存储器还可以既包括服务器的内部存储单元也包括其外部存储设备。
步骤S101、对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型。其中，对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型，可以包括：获取用户当前观看的视频内容，对所述视频内容进行图像帧提取；对提取到的每一帧的图像内容进行人物行为识别，以得到当前视频内容中视频人物的不同行为类型。进一步，对提取到的每一帧的图像内容进行人物行为识别，以得到当前视频内容中视频人物的不同行为类型，可以包括：将提取到的每一帧的图像内容输入AI人物行为识别模型；通过所述AI人物行为识别模型对提取到的每一帧的图像内容进行人物行为识别，以得到当前视频内容中视频人物的不同行为类型。进一步，所述AI人物行为识别模型包括卷积神经网络、循环神经网络、长短期记忆网络、图卷积网络以及时空图卷积网络中任意一种AI人物行为识别模型。
在一些优选实施例中，对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型，可以包括：用户端用户选择视频内容进行观看，服务器同步对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型。进一步，用户端用户可以通过运行在用户端的视频识别模块进行视频搜索，以搜索视频服务平台提供的视频内容进行观看，所述视频识别模块的服务器同步对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型。
在进一步的一些优选实施例中，所述视频识别模块内嵌入浏览器，用户端用户通过所述浏览器搜索视频服务平台提供的视频内容进行观看，所述视频识别模块识别到用户当前观看的视频内容后将当前观看的视频内容同步到视频识别模块的服务器，以进行视频内容的人物行为分析。进一步，所述视频识别模块支持多种方式的视频搜索与识别；可以搜索和识别视频服务平台提供的视频内容，也可以搜索和识别用户本地视频。可以理解的是，视频识别模块可以支持用户多种视频搜索及视频上传，例如，视频识别模块内嵌搜索引擎以支持在线视频搜索和本地上传视频搜索。
需要说明的是，本实施例中，用户可以直接在视频识别模块中浏览和观看视频，无需切换到其他平台或应用程序，从而提高用户体验和操作便捷性。通过视频识别模块实时识别观看的视频内容，并将信息发送到服务器，可以实现对视频内容的人物行为进行即时分析和处理，得到当前视频内容中视频人物的不同行为类型，以用于自动控制受控设备的工作模式。
步骤S102、根据所述当前视频内容中视频人物的不同行为类型，自动控制受控设备的工作模式，以使所述受控设备以不同的工作模式作用于用户，建立视频人物行为、受控设备以及受控设备使用体验的关联度。
需要说明的是，受控设备以不同的工作模式作用于用户可以包括直接的物理接触方式接触用户身体的力的作用，也可以包括物理接触方式接触用户身体的热量的作用，也可以包括非物理接触用户身体的的声波的作用。在一些优选实施例中，所述受控设备包括按摩器；所述按摩器的工作模式包括往复运动模式和/或旋转运动模式。在另外一些优选实施例中，所述受控设备可以包括按摩器；所述按摩器的工作模式可以包括不同的振动频率模式和/或不同的振动强度模式。需要说明的是，所述按摩器的工作模式可以包括多频振动模式、单频振动模式、脉冲模式、揉捏模式、气压模式以及发热模式等。
在进一步的一些优选实施例中，根据所述当前视频内容中视频人物的不同行为类型，自动控制受控设备的工作模式，包括：
创建受控设备的不同工作模式和视频人物的不同行为的数据库；所述视频人物的不同行为与所述受控设备的不同工作模式进行对应关联；
在分析识别到所述当前视频内容中视频人物的不同行为类型后，查询所述视频人物的不同行为所对应关联的所述受控设备的不同工作模式，根据查询到的所述不同工作模式，发出对应的控制信号自动控制受控设备的工作模式。
需要说明的是，本实施例中，通过视频内容与用户实际环境中的设备行为进行同步，从而可以增强用户的沉浸感和互动体验。自动识别视频内容并调整设备工作模式，减少用户手动操作，提升设备控制的智能化水平。
在进一步的一些优选实施例中，对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型，可以包括：获取用户当前观看的视频内容，对所述视频内容进行视频片段提取；对提取到的每一视频片段的内容进行人物行为识别，以得到当前视频内容中视频人物的不同行为类型。
需要说明的是，视频内容中人物行为可能存在持续性或重复性，单一的视频帧提取使用，会造成数据处理冗繁，不利于数据处理资源和传输资源的节约。本实施例中，通过对所述视频内容进行视频片段提取，对提取到的每一视频片段的内容进行人物行为识别，以得到当前视频内容中视频人物的不同行为类型，从而节约数据处理资源和数据传输资源。
在进一步的一些优选实施例中，对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型，可以包括提取视频中音频进行分析，以得到当前视频内容中视频人物的不同行为类型。优选地，视频中音频的分析可以包括音频的音量、频率、比特率、采样率、振幅、波形、音频格式、持续时间、动态范围、信噪比(SNR)、总谐波失真 (THD)以及声道数等参数的分析。进一步，对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型，可以包括在对用户当前观看的视频内容进行图像帧提取分析的同时，提取视频中音频进行分析，以得到当前视频内容中视频人物的不同行为类型。需要说明的是，本实施例中，通过对用户当前观看的视频内容进行图像和音频分析，从而可以得到更为精准的当前视频内容中视频人物的不同行为类型。
实施例二
参见图2和图5，本实施例提供一种基于视频识别的设备控制方法，包括步骤S201和步骤S202。其中，步骤S201和步骤S202可以在用户端运行，例如，在用户的智能手机端运行，通过根据用户当前选择的视频内容进行播放，并与服务器和受控设备分别通信连接，所述服务器对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型，所述服务器根据所述当前视频内容中视频人物的不同行为类型，向用户端传输控制受控设备不同的工作模式的控制信号，再通过接收所述服务器传输的所述控制信号，将接收到的所述控制信号发送给所述受控设备，以使所述受控设备以不同的工作模式作用于用户，建立视频人物行为、受控设备以及受控设备使用体验的关联度，从而提升智能设备控制的智能化程度，提升智能设备的用户使用体验。
需要说明的是，用户端包括通过系统总线相互通信连接存储器、处理器、网络接口。其中，本技术领域技术人员可以理解，这里的用户端是一种能够按照事先设定或存储的指令，自动进行数值计算和/或信息处理的设备，其硬件包括但不限于微处理器、专用集成电路(Application Specific Integrated Circuit，ASIC)、可编程门阵列(Field－Programmable Gate Array，FPGA)、数字处理器 (Digital Signal Processor，DSP)、嵌入式设备等。用户端可以与用户通过键盘、鼠标、遥控器、触摸板或声控设备等方式进行人机交互。存储器至少包括一种类型的可读存储介质，可读存储介质包括闪存、硬盘、多媒体卡、卡型存储器（例如，SD或DX存储器等）、随机访问存储器（RAM）、静态随机访问存储器（SRAM）、只读存储器（ROM）、电可擦除可编程只读存储器（EEPROM）、可编程只读存储器（PROM）、磁性存储器、磁盘、光盘等。在一些实施例中，存储器可以是用户端的内部存储单元，例如该用户端的硬盘或内存。在另一些实施例中，存储器也可以是用户端的外部存储设备，例如该用户端上配备的插接式硬盘，智能存储卡（Smart Media Card, SMC），安全数字（Secure Digital, SD）卡，闪存卡（Flash Card）等。当然，存储器还可以既包括用户端的内部存储单元也包括其外部存储设备。
需要说明的是，对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型，可以包括：获取用户当前观看的视频内容，对所述视频内容进行图像帧提取；对提取到的每一帧的图像内容进行人物行为识别，以得到当前视频内容中视频人物的不同行为类型。进一步，对提取到的每一帧的图像内容进行人物行为识别，以得到当前视频内容中视频人物的不同行为类型，可以包括：将提取到的每一帧的图像内容输入AI人物行为识别模型；通过所述AI人物行为识别模型对提取到的每一帧的图像内容进行人物行为识别，以得到当前视频内容中视频人物的不同行为类型。进一步，所述AI人物行为识别模型包括卷积神经网络、循环神经网络、长短期记忆网络、图卷积网络以及时空图卷积网络中任意一种AI人物行为识别模型。
需要说明的是，用户端用户可以通过运行在用户端的视频识别模块进行视频搜索，以搜索视频服务平台提供的视频内容进行观看，所述视频识别模块的服务器同步对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型。
需要说明的是，受控设备以不同的工作模式作用于用户可以包括直接的物理接触方式接触用户身体的力的作用，也可以包括物理接触方式接触用户身体的热量的作用，也可以包括非物理接触用户身体的的声波的作用。在一些优选实施例中，所述受控设备包括按摩器；所述按摩器的工作模式包括往复运动模式和/或旋转运动模式。在另外一些优选实施例中，所述受控设备可以包括按摩器；所述按摩器的工作模式可以包括不同的振动频率模式和/或不同的振动强度模式。
在进一步的一些优选实施例中，所述视频识别模块内嵌入浏览器和视频识别模块，用户端用户通过所述浏览器搜索视频服务平台提供的视频内容进行观看，所述视频识别模块识别到用户当前观看的视频内容后将当前观看的视频内容同步到视频识别模块的服务器，以进行视频内容的人物行为分析。
需要说明的是，本实施例中，用户可以直接在视频识别模块中浏览和观看视频，无需切换到其他平台或应用程序，从而提高用户体验和操作便捷性。通过视频识别模块实时识别观看的视频内容，并将信息发送到服务器，可以实现对视频内容的人物行为进行即时分析和处理，得到当前视频内容中视频人物的不同行为类型，以用于自动控制受控设备的工作模式。
在进一步的一些优选实施例中，对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型，可以包括：获取用户当前观看的视频内容，对所述视频内容进行视频片段提取；对提取到的每一视频片段的内容进行人物行为识别，以得到当前视频内容中视频人物的不同行为类型。
需要说明的是，视频内容中人物行为可能存在持续性或重复性，单一的视频帧提取使用，会造成数据处理冗繁，不利于数据处理资源和传输资源的节约。本实施例中，通过对所述视频内容进行视频片段提取，对提取到的每一视频片段的内容进行人物行为识别，以得到当前视频内容中视频人物的不同行为类型，从而节约数据处理资源和数据传输资源。
需要说明的是，用户在用户端内有多种视频内容选择方式。例如，用户端视频识别模块内嵌入视频播放器支持本地文件和网络流媒体视频。例如，用户端视频识别模块内嵌入浏览器，支持搜索HTML5播放视频的网页，如YouTube、Vimeo等各种视频。例如，用户端视频识别模块可以集成第三方视频SDK，通过这些SDK提供丰富的功能,如点播、直播、广告预览等。例如，视频识别模块还可以支持直播流媒体视频。例如，视频识别模块还可以在视频播放时,支持画中画模式下继续观看视频。此外，视频识别模块可以支持如投屏播放、DLNA投射、视频文件分享等视频播放方式。
实施例三
参见图3，本实施例提供一种基于视频识别的设备控制装置，包括：
视频人物行为分析模块，用于对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型；
设备模式自动控制模块，用于根据所述当前视频内容中视频人物的不同行为类型，自动控制受控设备的工作模式，以使所述受控设备以不同的工作模式作用于用户，建立视频人物行为、受控设备以及受控设备使用体验的关联度。
需要说明的是，本实施例中，通过对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型，根据所述当前视频内容中视频人物的不同行为类型，自动控制受控设备的工作模式，以使所述受控设备以不同的工作模式作用于用户，建立视频人物行为、受控设备以及受控设备使用体验的关联度，从而提升智能设备控制的智能化程度，提升智能设备的用户使用体验。
需要说明的是，对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型，可以包括：获取用户当前观看的视频内容，对所述视频内容进行图像帧提取；对提取到的每一帧的图像内容进行人物行为识别，以得到当前视频内容中视频人物的不同行为类型。进一步，对提取到的每一帧的图像内容进行人物行为识别，以得到当前视频内容中视频人物的不同行为类型，可以包括：将提取到的每一帧的图像内容输入AI人物行为识别模型；通过所述AI人物行为识别模型对提取到的每一帧的图像内容进行人物行为识别，以得到当前视频内容中视频人物的不同行为类型。进一步，所述AI人物行为识别模型包括卷积神经网络、循环神经网络、长短期记忆网络、图卷积网络以及时空图卷积网络中任意一种AI人物行为识别模型。
需要说明的是，对于用户当前观看的视频内容，用户端用户可以通过运行在用户端的视频识别模块进行视频搜索得到。所述视频识别模块的服务器同步对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型。
需要说明的是，受控设备以不同的工作模式作用于用户可以包括直接的物理接触方式接触用户身体的力的作用，也可以包括物理接触方式接触用户身体的热量的作用，也可以包括非物理接触用户身体的的声波的作用。在一些优选实施例中，所述受控设备包括按摩器；所述按摩器的工作模式包括往复运动模式和/或旋转运动模式。在另外一些优选实施例中，所述受控设备可以包括按摩器；所述按摩器的工作模式可以包括不同的振动频率模式和/或不同的振动强度模式。
实施例四
参见图6，本实施例提供一种基于视频识别的设备控制系统，包括：
用户端；用户通过所述用户端选择视频内容进行观看；
服务器，与所述用户端通信连接，运行计算机程序以实现实施例一中任一项所述基于视频识别的设备控制方法，向用户端传输控制所述受控设备的工作模式的控制信号；
受控设备，与所述用户端通信连接，接收用户端获取到的所述控制信号，以进行对应工作模式的工作。
需要说明的是，本实施例中，服务器运行计算机程序以实现实施例一中任一项所述基于视频识别的设备控制方法，可以向用户端传输控制所述受控设备的工作模式的控制信号。其中，服务器可以对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型，根据所述当前视频内容中视频人物的不同行为类型，自动控制受控设备的工作模式，以使所述受控设备以不同的工作模式作用于用户，建立视频人物行为、受控设备以及受控设备使用体验的关联度，从而提升智能设备控制的智能化程度，提升智能设备的用户使用体验。
需要说明的是，对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型，可以包括：获取用户当前观看的视频内容，对所述视频内容进行图像帧提取；对提取到的每一帧的图像内容进行人物行为识别，以得到当前视频内容中视频人物的不同行为类型。进一步，对提取到的每一帧的图像内容进行人物行为识别，以得到当前视频内容中视频人物的不同行为类型，可以包括：将提取到的每一帧的图像内容输入AI人物行为识别模型；通过所述AI人物行为识别模型对提取到的每一帧的图像内容进行人物行为识别，以得到当前视频内容中视频人物的不同行为类型。进一步，所述AI人物行为识别模型包括卷积神经网络、循环神经网络、长短期记忆网络、图卷积网络以及时空图卷积网络中任意一种AI人物行为识别模型。
需要说明的是，对于用户当前观看的视频内容，用户端用户可以通过运行在用户端的视频识别模块进行视频搜索得到。所述视频识别模块的服务器同步对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型。
需要说明的是，受控设备以不同的工作模式作用于用户可以包括直接的物理接触方式接触用户身体的力的作用，也可以包括物理接触方式接触用户身体的热量的作用，也可以包括非物理接触用户身体的的声波的作用。在一些优选实施例中，所述受控设备包括按摩器；所述按摩器的工作模式包括往复运动模式和/或旋转运动模式。在另外一些优选实施例中，所述受控设备可以包括按摩器；所述按摩器的工作模式可以包括不同的振动频率模式和/或不同的振动强度模式。
需要说明的是，用户在用户端内有多种视频内容选择方式。例如，用户端视频识别模块内嵌入视频播放器支持本地文件和网络流媒体视频。例如，用户端视频识别模块内嵌入浏览器，支持搜索HTML5播放视频的网页，如YouTube、Vimeo等各种视频。例如，用户端视频识别模块可以集成第三方视频SDK，通过这些SDK提供丰富的功能,如点播、直播、广告预览等。例如，视频识别模块还可以支持直播流媒体视频。例如，视频识别模块还可以在视频播放时,支持画中画模式下继续观看视频。
最后应说明的是：以上各实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述各实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分或者全部技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的范围。

Claims (10)

  1. 一种基于视频识别的设备控制方法，其特征在于，包括以下步骤：
    对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型；
    根据所述当前视频内容中视频人物的不同行为类型，自动控制受控设备的工作模式，以使所述受控设备以不同的工作模式作用于用户，建立视频人物行为、受控设备以及受控设备使用体验的关联度。
  2. 如权利要求1所述的基于视频识别的设备控制方法，其特征在于，对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型，包括：
    获取用户当前观看的视频内容，对所述视频内容进行图像帧提取；
    对提取到的每一帧的图像内容进行人物行为识别，以得到当前视频内容中视频人物的不同行为类型。
  3. 如权利要求2所述的基于视频识别的设备控制方法，其特征在于，对提取到的每一帧的图像内容进行人物行为识别，以得到当前视频内容中视频人物的不同行为类型，包括：
    将提取到的每一帧的图像内容输入AI人物行为识别模型；
    通过所述AI人物行为识别模型对提取到的每一帧的图像内容进行人物行为识别，以得到当前视频内容中视频人物的不同行为类型。
  4. 如权利要求3所述的基于视频识别的设备控制方法，其特征在于，所述AI人物行为识别模型包括卷积神经网络、循环神经网络、长短期记忆网络、图卷积网络以及时空图卷积网络中任意一种AI人物行为识别模型。
  5. 如权利要求1所述的基于视频识别的设备控制方法，其特征在于，所述受控设备包括按摩器；所述按摩器的工作模式包括往复运动模式和/或旋转运动模式。
  6. 如权利要求1所述的基于视频识别的设备控制方法，其特征在于，所述受控设备包括按摩器；所述按摩器的工作模式包括不同的振动频率模式和/或不同的振动强度模式。
  7. 如权利要求1-6任一项所述的基于视频识别的设备控制方法，其特征在于，对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型，包括：
    用户端用户选择视频内容进行观看，服务器同步对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型。
  8. 一种基于视频识别的设备控制方法，其特征在于，包括：
    根据用户当前选择的视频内容进行播放，并与服务器和受控设备分别通信连接；所述服务器对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型；所述服务器根据所述当前视频内容中视频人物的不同行为类型，向用户端传输控制受控设备不同的工作模式的控制信号；
    接收所述服务器传输的所述控制信号，将接收到的所述控制信号发送给所述受控设备，以使所述受控设备以不同的工作模式作用于用户，建立视频人物行为、受控设备以及受控设备使用体验的关联度。
  9. 一种基于视频识别的设备控制装置，其特征在于，包括：
    视频人物行为分析模块，用于对用户当前观看的视频内容进行人物行为分析，以得到当前视频内容中视频人物的不同行为类型；
    设备模式自动控制模块，用于根据所述当前视频内容中视频人物的不同行为类型，自动控制受控设备的工作模式，以使所述受控设备以不同的工作模式作用于用户，建立视频人物行为、受控设备以及受控设备使用体验的关联度。
  10. 一种基于视频识别的设备控制系统，其特征在于，包括：
    用户端；用户通过所述用户端选择视频内容进行观看；
    服务器，与所述用户端通信连接，运行计算机程序以实现如权利要求1-7任一项所述基于视频识别的设备控制方法，向用户端传输控制所述受控设备的工作模式的控制信号；
    受控设备，与所述用户端通信连接，接收用户端获取到的所述控制信号，以进行对应工作模式的工作。
PCT/CN2024/089445 2024-04-11 2024-04-24 基于视频识别的设备控制方法、装置与系统 Pending WO2025213507A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202410434510.3 2024-04-11
CN202410434510.3A CN118226963A (zh) 2024-04-11 2024-04-11 基于视频识别的设备控制方法、装置与系统

Publications (1)

Publication Number Publication Date
WO2025213507A1 true WO2025213507A1 (zh) 2025-10-16

Family

ID=91506540

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2024/089445 Pending WO2025213507A1 (zh) 2024-04-11 2024-04-24 基于视频识别的设备控制方法、装置与系统

Country Status (2)

Country Link
CN (1) CN118226963A (zh)
WO (1) WO2025213507A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105763984A (zh) * 2016-03-02 2016-07-13 宇龙计算机通信科技(深圳)有限公司 一种功能耳机、按摩器控制系统及方法
KR101645928B1 (ko) * 2016-06-08 2016-08-05 홍정택 웨어러블 스마트 마사지기
CN107616896A (zh) * 2016-07-14 2018-01-23 幸福在线（北京）网络技术有限公司 一种智能按摩系统及智能按摩方法
CN108210286A (zh) * 2017-09-26 2018-06-29 深圳市超级人生科技有限公司 一种按摩器的运动控制方法、装置及系统
CN115376207A (zh) * 2022-08-08 2022-11-22 深圳市雷鸟网络传媒有限公司 健身互动方法、装置、电子设备及计算机可读存储介质

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111752389B (zh) * 2020-06-24 2023-03-10 京东方科技集团股份有限公司 交互系统、交互方法和机器可读存储介质
JP2024004325A (ja) * 2022-06-28 2024-01-16 株式会社東亜産業 マッサージ装置制御システム、マッサージ装置制御プログラム及びマッサージ装置
CN115457657B (zh) * 2022-09-06 2025-10-21 厦门大学 基于bert模型的通道特征交互时间建模行为识别方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105763984A (zh) * 2016-03-02 2016-07-13 宇龙计算机通信科技(深圳)有限公司 一种功能耳机、按摩器控制系统及方法
KR101645928B1 (ko) * 2016-06-08 2016-08-05 홍정택 웨어러블 스마트 마사지기
CN107616896A (zh) * 2016-07-14 2018-01-23 幸福在线（北京）网络技术有限公司 一种智能按摩系统及智能按摩方法
CN108210286A (zh) * 2017-09-26 2018-06-29 深圳市超级人生科技有限公司 一种按摩器的运动控制方法、装置及系统
CN115376207A (zh) * 2022-08-08 2022-11-22 深圳市雷鸟网络传媒有限公司 健身互动方法、装置、电子设备及计算机可读存储介质

Also Published As

Publication number Publication date
CN118226963A (zh) 2024-06-21

Similar Documents

Publication Publication Date Title
CN104935980A (zh) 互动信息处理方法、客户端及服务平台
CN104091423B (zh) 一种信号传输方法及家庭点歌系统
JP2013013092A (ja) 双方向ストリーミングコンテンツ処理方法、装置、及びシステム
CN104091596B (zh) 一种乐曲识别方法、系统和装置
CN107801096A (zh) 视频播放的控制方法、装置、终端设备及存储介质
CN106488311B (zh) 音效调整方法及用户终端
WO2020135161A1 (zh) 视频播放跳转方法、系统及计算机可读存储介质
CN105551498A (zh) 一种语音识别的方法及装置
CN103731707A (zh) 移动终端设备控制智能电视端语音输入的方法及系统
CN112423081B (zh) 一种视频数据处理方法、装置、设备及可读存储介质
CN108882101B (zh) 一种智能音箱的播放控制方法、装置、设备及存储介质
JP2023522092A (ja) インタラクション記録生成方法、装置、デバイス及び媒体
WO2019101099A1 (zh) 视频节目识别方法、设备、终端、系统和存储介质
CN110659006B (zh) 跨屏显示的方法、装置、电子设备及可读存储介质
CN111274449B (zh) 视频播放方法、装置、电子设备和存储介质
CN106993211A (zh) 基于人工智能的网络电视控制方法及装置
CN117809659A (zh) 一种服务器、终端设备及语音交互方法
CN115396709B (zh) 显示设备、服务器及免唤醒语音控制方法
CN112258232A (zh) 一种基于直播画面的推广内容展示方法及装置
WO2025213507A1 (zh) 基于视频识别的设备控制方法、装置与系统
WO2024036979A9 (zh) 一种多媒体资源播放方法及相关装置
CN113703711A (zh) 播放音效控制方法、装置、电子设备和计算机存储介质
CN114968164A (zh) 语音处理方法、系统、装置和终端设备
CN119316643B (zh) 一种显示设备、控制设备及设备唤醒方法
CN113946712B (zh) 片段推荐方法、片段推荐装置、电子设备和可读存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 24934583

Country of ref document: EP

Kind code of ref document: A1