WO2018086427A1 - 一种控制智能设备的方法及装置 - Google Patents

一种控制智能设备的方法及装置 Download PDF

Info

Publication number
WO2018086427A1
WO2018086427A1 PCT/CN2017/104080 CN2017104080W WO2018086427A1 WO 2018086427 A1 WO2018086427 A1 WO 2018086427A1 CN 2017104080 W CN2017104080 W CN 2017104080W WO 2018086427 A1 WO2018086427 A1 WO 2018086427A1
Authority
WO
WIPO (PCT)
Prior art keywords
smart device
adjustment instruction
user
data
previous week
Prior art date
Application number
PCT/CN2017/104080
Other languages
English (en)
French (fr)
Inventor
李桂林
汪芳山
Original Assignee
华为技术有限公司
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 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2018086427A1 publication Critical patent/WO2018086427A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00—Data switching networks
    • H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
    • H04L12/2803—Home automation networks
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
    • G05B19/4185—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by the network communication
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00—Data switching networks
    • H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00—Data switching networks
    • H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
    • H04L12/2803—Home automation networks
    • H04L12/2816—Controlling appliance services of a home automation network by calling their functionalities
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/20—Pc systems
    • G05B2219/26—Pc applications
    • G05B2219/2642—Domotique, domestic, home control, automation, smart house
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Definitions

  • the present invention relates to the field of communications, and in particular, to a method and apparatus for controlling a functional device.
  • terminal devices such as smart watches or smart phones can directly or indirectly detect physiological data such as body surface temperature, humidity, heart rate, blood pressure, etc., and can also pass Wireless-Fidelity Wi-Fi module and other devices.
  • Devices are connected, such as computers, routers, etc.
  • its built-in processing unit can also process data.
  • the terminal device can control the smart home device according to the detected physiological data of the user.
  • the adjustment is based only on the data of a single user, the adjustment effect is inevitably caused, and the needs of many people cannot be met.
  • Embodiments of the present invention provide a method and apparatus that can solve the problem of poor adjustment effect caused by adjusting a smart device according to user data of a single user.
  • a method for controlling a smart device comprising: acquiring, by a terminal device, user data of a user in a current period, and running data in a current period from a target smart device; and applying, by the terminal device, user data and running data An individual model determining a first usage probability of each smart device adjustment instruction, wherein the individual model is trained by historical user data of the user and historical operational data of the target smart device; the terminal device applies the user data and the operational data to the group a model, determining a second usage probability of each smart device adjustment instruction, wherein the population model is trained by historical user data of the plurality of users and historical operation data of the corresponding smart device; the terminal device adjusts the instruction according to each smart device The first usage probability and the second usage probability of each smart device adjustment instruction determine an adjustment instruction of the control target smart device; the terminal device sends an adjustment instruction of the control target smart device to the target smart device.
  • the terminal device determines the control target according to the first usage probability of each smart device adjustment instruction and the second usage probability of each smart device adjustment instruction
  • the adjustment instruction of the smart device includes: for each smart device adjustment instruction, the terminal device determines a weighted sum of the first usage probability and the second usage probability of the smart device adjustment instruction; the terminal device determines the maximum weight and the corresponding smart device adjustment instruction is Controls the adjustment instructions of the target smart device.
  • the terminal device determines that the adjustment value indicated by the adjustment instruction of the control target smart device is less than the preset adjustment threshold
  • the terminal device determines the degree of difference between the individual model and the group model; when the degree of difference is greater than the preset difference threshold, the terminal device updates the user data of the user in the previous week and the running data of the previous week from the target smart device. Individual model.
  • the terminal device is based on the user data of the user in the previous week, and the target smart device.
  • the individual model of the operational data update during the previous week includes: the terminal device is based on the user of the user during the previous week.
  • the data, as well as the operational data from the target smart device during the previous week, determine the feedback data of the user during the previous week; the terminal device runs according to the user data of the user during the previous week and the previous week from the target smart device.
  • the data, the user's feedback data in the previous week updates the individual model.
  • an apparatus for controlling a smart device includes: a processor, a memory, a bus, and a communication interface; a memory for storing program code, a processor and a memory connected by a bus, and when the device is running, the processor executes the memory The stored program code to cause the apparatus to perform the method of the first aspect or any of the possible implementations of the first aspect.
  • a computer readable storage medium wherein executable program code is stored, the program code being used to implement the method of any one of the possible implementations of the first aspect or the first aspect.
  • an apparatus for controlling a smart device comprising means for performing the method of the first aspect or any one of the possible implementations of the first aspect.
  • the smart device adjustment instruction suitable for multiple users is determined by combining the adjustment instruction information of the individual model and the adjustment instruction information of the group model. , improved the effect of adjusting smart devices.
  • FIG. 1 is a schematic diagram of a network architecture applied to an embodiment of the present invention
  • FIG. 2 is a schematic diagram showing the hardware structure of a computer device 200 according to an embodiment of the invention.
  • FIG. 3 is an exemplary flowchart of a method 300 of controlling a smart device according to an embodiment of the invention
  • FIG. 4 is a schematic structural diagram of an apparatus 400 for controlling a smart device according to an embodiment of the invention.
  • FIG. 1 is a schematic diagram of a network architecture 100 to which an embodiment of the present invention is applied.
  • the smart device 101 and the terminal device 102 are in the same limited space 103, for example, in the same room.
  • the user 104 using the terminal device 102 exists in the limited space 103, while other users 105 are also present.
  • the smart device 101 transmits its own operational data to the terminal device 102.
  • the terminal device 102 collects user data of the user 104, and determines an adjustment instruction for controlling the smart device 101 in conjunction with the operation data of the smart device 101.
  • the terminal device 102 transmits the determined adjustment command to the smart device 101 to adjust the operating state of the smart device 101.
  • the server 106 can provide the terminal device 102 with adjustment instruction information used by the group user to control other smart devices.
  • the terminal device 102 can simultaneously consider the adjustment instruction information provided by the server 106 to make the determined adjustment instruction more accurate.
  • the smart device 101 can be a lighting device, an electric curtain, a music system, a smart home appliance, or the like.
  • the terminal device 102 can be mobile power Words, tablets, etc.
  • FIG. 2 is a schematic diagram showing the hardware structure of a computer device 200 according to an embodiment of the invention.
  • computer device 200 includes a processor 202, a memory 204, a communication interface 206, and a bus 208.
  • the processor 202, the memory 204, and the communication interface 206 implement a communication connection with each other through the bus 208.
  • the processor 202 can be a general-purpose central processing unit (CPU), a microprocessor, an application specific integrated circuit (ASIC), or one or more integrated circuits for executing related programs.
  • CPU central processing unit
  • ASIC application specific integrated circuit
  • the memory 204 can be a read only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM).
  • the memory 204 can store an operating system 2041 and other applications 2042.
  • the program code for implementing the technical solution provided by the embodiment of the present invention is stored in the memory 204 and executed by the processor 202.
  • Communication interface 206 enables communication with other devices or communication networks using transceivers such as, but not limited to, transceivers.
  • Bus 208 can include a path for communicating information between various components (e.g., processor 202, memory 204, communication interface 206).
  • the communication interface 206 is configured to acquire user data of the user in the current period, and running data in the current period from the target smart device;
  • the processor 202 is configured to use the user data and the Applying the operational data to the individual model, determining a first usage probability of each smart device adjustment instruction, the individual model being trained by historical user data of the user and historical operational data of the target smart device;
  • the user data and the running data are applied to the group model, and the second usage probability of each smart device adjustment instruction is determined, and the group model is trained by historical user data of the plurality of users and historical operation data of the corresponding smart device.
  • the communication interface 206 is configured to target the target The smart device sends an adjustment instruction that controls the target smart device.
  • FIG. 3 is an exemplary flow diagram of a method 300 of controlling a smart device in accordance with an embodiment of the present invention.
  • the method 300 of controlling a smart device can be performed by the smart device 101, the terminal device 102, and the server 106 shown in FIG.
  • the target smart device sends the running data in the current period to the terminal device.
  • the terminal device receives the running data in the current period from the target smart device.
  • the terminal device acquires user data of the user in the current period.
  • the terminal device periodically collects user data to regulate the target smart device.
  • the user data includes physiological data of the user, such as body surface temperature, body surface humidity, heart rate, etc., and may also include temperature, humidity, and the like of the environment in which the user is located.
  • the running data sent by the target smart device is an operating parameter of the target smart device. For example, when the target smart device is an air conditioner, the running data may include a temperature value, a humidity value, a wind power, a mode, and the like.
  • the terminal device applies the user data and the running data to an individual model, and determines each The first usage probability of the smart device adjustment instruction is trained by the historical user data of the user and the historical running data of the target smart device.
  • the terminal device applies the user data and the running data to a group model, and determines a second usage probability of each smart device adjustment instruction, where the group model is composed of historical user data and corresponding by multiple users.
  • the historical running data of the smart device is trained.
  • the group model is provided by the server to the terminal device.
  • the group model reflects the control of smart devices by other terminal devices when multiple people are co-located in a limited space.
  • the individual model and the population model are multi-class probability models, which can be implemented by Softmax algorithm, Gaussian Mixture Model (GMM) or Naive Bayes algorithm.
  • GMM Gaussian Mixture Model
  • the individual model and the population model are implemented by the Softmax algorithm
  • the individual model can be expressed as
  • k is the number of adjustment instructions.
  • X1 is user data.
  • the population model can be expressed as
  • k is the number of adjustment instructions.
  • X2 is the running data.
  • represents the modulus of the vector x1
  • represents the modulus of the vector x2.
  • y 3 means that the temperature is lowered by 1 degree Celsius.
  • the terminal device determines, according to the first usage probability of each smart device adjustment command and the second usage probability of each smart device adjustment command, an adjustment instruction for controlling the target smart device.
  • the terminal device determines a weighted sum of the first usage probability and the second usage probability of the smart device adjustment instruction; the terminal device determines a maximum weighted sum corresponding smart device adjustment instruction To control an adjustment instruction of the target smart device.
  • the terminal device sends an adjustment instruction for controlling the target smart device to the target smart device.
  • the terminal device sends an adjustment command that the temperature rises by 1 degree Celsius to the smart air conditioner. Assuming that the current smart air conditioner is set to a temperature of 24 ° C, the adjusted temperature is 25 ° C.
  • the method 300 for controlling the smart device may further include the following steps:
  • the terminal device determines a difference degree between the individual model and the group model; When the difference degree is greater than the preset difference degree threshold, the terminal device updates the individual model according to the user data of the user in the previous week and the running data from the target smart device in the previous week.
  • the adjustment command indicates that the temperature is raised by 1 degree Celsius and the preset adjustment threshold is 2 degrees Celsius.
  • Terminal equipment can be based on To determine the degree of difference d between the individual model and the population model.
  • the terminal device determines, according to the user data of the user in the previous week and the running data from the target smart device in the previous week, that the user is in the previous week.
  • Feedback data the terminal device updates the user data of the user in the previous week, the operation data of the previous week from the target smart device, and the feedback data of the user during the previous week.
  • the individual model the terminal device determines, according to the user data of the user in the previous week and the running data from the target smart device in the previous week, that the user is in the previous week.
  • Feedback data the terminal device updates the user data of the user in the previous week, the operation data of the previous week from the target smart device, and the feedback data of the user during the previous week.
  • the terminal device sends the user data of the user in the previous week, the running data of the previous week from the target smart device, and the feedback data of the user in the previous week to server.
  • the server collects data sent by different terminal devices. When the collected data reaches a certain amount, the server updates the group model and sends the updated group model to the terminal device for use by the terminal device in the next cycle.
  • the smart device adjustment instruction suitable for multiple users is determined by combining the adjustment instruction information of the individual model and the adjustment instruction information of the group model. , improved the effect of adjusting smart devices.
  • FIG. 4 is a schematic structural diagram of an apparatus 400 for controlling a smart device according to an embodiment of the invention.
  • the apparatus 400 for controlling a smart device includes an acquisition module 402, a processing module 404, and a transmission module 406.
  • the device 400 that controls the smart device is the computer device 200 in FIG. 2 or the terminal device shown in FIG.
  • the obtaining module 402 can be used to execute S302, S303 in the example of FIG. 3.
  • the processing module 404 can be used to execute S304, S305, S306, and S308 in the embodiment of FIG. 3.
  • the sending module 406 can be used to execute the embodiment in FIG. 3. S307.
  • the obtaining module 402 is configured to acquire user data of the user in the current period, and running data in a current period from the target smart device.
  • a processing module 404 configured to apply the user data and the running data to an individual model, and determine a first usage probability of each smart device adjustment instruction, where the individual model is historical user data of the user and the target The historical operation data of the smart device is trained.
  • the processing module 404 is further configured to apply the user data and the running data to the group model, and determine a second usage probability of the smart device adjustment instruction, where the group model is composed of historical user data of multiple users.
  • the historical operation data of the corresponding smart device is trained.
  • the processing module 404 is further configured to determine, according to the first usage probability of each smart device adjustment instruction and the second usage probability of each smart device adjustment instruction, an adjustment instruction for controlling the target smart device.
  • the sending module 406 is configured to send, to the target smart device, an adjustment instruction that controls the target smart device.
  • the processing module 404 determines, according to the first usage probability of each smart device adjustment instruction and the second usage probability of each smart device adjustment instruction, that the adjustment instruction of the target smart device is:
  • the processing module 404 is configured to determine a weighted sum of the first usage probability and the second usage probability of the smart device adjustment instruction; determining a maximum weighted sum corresponding smart device adjustment instruction to control the target Adjustment instructions for smart devices.
  • the processing module 404 determines that the adjustment value indicated by the adjustment instruction for controlling the target smart device is less than a preset adjustment threshold
  • the processing module 404 is further configured to determine the individual model and the group model.
  • the processing module 404 is configured to: according to the user data of the user in the previous week, and the operation of the previous week from the target smart device, when the difference is greater than the preset difference threshold. The data updates the individual model.
  • the processing module 404 according to the user data of the user in the previous week, and the running data from the target smart device in the previous week, updating the individual model includes:
  • the processing module 404 is configured to determine feedback of the user during the previous week according to the user data of the user in the previous week and the operation data of the previous week from the target smart device.
  • the processing module 404 updates the user data of the user in the previous week, the running data of the previous week from the target smart device, and the feedback data of the user during the previous week.
  • the individual model is configured to determine feedback of the user during the previous week according to the user data of the user in the previous week and the operation data of the previous week from the target smart device.
  • the processing module 404 updates the user data of the user in the previous week, the running data of the previous week from the target smart device, and the feedback data of the user during the previous week.
  • the individual model is configured to determine feedback of the user during the previous week according to the user data of the user in the previous week and the operation data of the previous week from the target smart device.
  • the smart device adjustment instruction suitable for multiple users is determined by combining the adjustment instruction information of the individual model and the adjustment instruction information of the group model. , improved the effect of adjusting smart devices.
  • the "module" in the embodiment of FIG. 4 may be an Application Specific Integrated Circuit (ASIC), an electronic circuit, a processor and a memory that executes one or more software or firmware programs, a combination logic circuit, and others.
  • ASIC Application Specific Integrated Circuit
  • the foregoing device for controlling the smart device is implemented by using a computer device.
  • the acquiring module and the sending module may be implemented by using a processor, a memory, and a communication interface of the computer device, where the processing module may pass through a processor of the computer device and Memory is implemented.
  • the computer device 200 shown in FIG. 2 only shows the processor 202, the memory 204, the communication interface 206, and the bus 208, in a specific implementation process, those skilled in the art should understand that the above-described control smart device is The device also contains other devices necessary to achieve proper operation.
  • the above device for controlling the smart device may further comprise hardware devices for implementing other additional functions.
  • the above-described means for controlling the smart device may also only include the devices necessary to implement the embodiments of the present invention, and do not necessarily include all of the devices shown in FIG.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium.
  • the technical solution of the present invention which is essential or contributes to the prior art, or all or part of the technical solution, may be embodied in the form of a software product stored in a storage medium.
  • a number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) or a processor to perform all or part of the steps of the methods described in various embodiments of the present invention.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • General Engineering & Computer Science (AREA)
  • Manufacturing & Machinery (AREA)
  • Quality & Reliability (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Selective Calling Equipment (AREA)
  • Telephone Function (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

本发明的实施例提供一种控制智能设备的方法，包括：终端设备获取当前周期内用户的用户数据，以及来自目标智能设备的当前周期内的运行数据；将所述用户数据和所述运行数据应用于个体模型，确定每个智能设备调整指令的第一使用概率；将所述用户数据和所述运行数据应用于群体模型，确定所述每个智能设备调整指令的第二使用概率；所述终端设备根据所述每个智能设备调整指令的第一使用概率和所述每个智能设备调整指令的第二使用概率确定控制所述目标智能设备的调整指令；所述终端设备向所述目标智能设备发送控制所述目标智能设备的调整指令。提高了调整智能设备的效果。

Description

一种控制智能设备的方法及装置
本申请要求于2016年11月8日提交中国专利局、申请号为201610980787.1，发明名称为“一种控制智能设备的方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及通信领域，尤其涉及一种控制职能设备的方法及装置。
背景技术
目前，如智能手表或智能手机等终端设备，能直接或间接地检测用户的体表温度、湿度、心率、血压等生理数据，还能通过无线保真(Wireless-Fidelity Wi-Fi)模块与其它设备相连，如电脑、路由器等。同时其内置的处理单元还可以对数据进行处理。目前，终端设备可以根据检测到的用户的生理数据来对智能家居设备进行控制。然而，当用户处于多人环境时，如果只根据单个用户的数据进行调节，势必会导致调节效果差，不能满足多人的需求。
发明内容
本发明的实施例提供一种方法和装置，能够解决根据单个用户的用户数据调节智能设备导致的调节效果差的问题。
第一方面，提供了一种控制智能设备的方法，包括：终端设备获取当前周期内用户的用户数据，以及来自目标智能设备的当前周期内的运行数据；终端设备将用户数据和运行数据应用于个体模型，确定每个智能设备调整指令的第一使用概率，其中，个体模型由该用户的历史用户数据和目标智能设备的历史运行数据所训练得到；终端设备将用户数据和运行数据应用于群体模型，确定每个智能设备调整指令的第二使用概率，其中，群体模型由多个用户的历史用户数据和对应的智能设备的历史运行数据所训练得到；终端设备根据每个智能设备调整指令的第一使用概率和每个智能设备调整指令的第二使用概率确定控制目标智能设备的调整指令；终端设备向目标智能设备发送控制目标智能设备的调整指令。
结合第一方面的实现方式，在第一方面第一种可能的实现方式中，终端设备根据每个智能设备调整指令的第一使用概率和每个智能设备调整指令的第二使用概率确定控制目标智能设备的调整指令包括：对于每个智能设备调整指令，终端设备确定该智能设备调整指令的第一使用概率和第二使用概率的加权和；终端设备确定最大加权和对应的智能设备调整指令为控制目标智能设备的调整指令。
结合第一方面或第一方面的第一种可能的实现方式，在第二种可能实现的方式中，当终端设备确定控制目标智能设备的调整指令所指示的调整值小于预设调整阈值时，终端设备确定个体模型和群体模型的差异度；当差异度大于预设差异度阈值时，终端设备根据上一周期内该用户的用户数据，以及来自目标智能设备的上一周期内的运行数据更新个体模型。
结合第一方面或第一方面的第一种或第二种可能的实现方式，在第三种可能实现的方式中，终端设备根据上一周期内该用户的用户数据，以及来自目标智能设备的上一周期内的运行数据更新个体模型包括：终端设备根据上一周期内用户的用户 数据，以及来自目标智能设备的上一周期内的运行数据，确定用户在上一周期内的反馈数据；终端设备根据上一周期内用户的用户数据、来自目标智能设备的上一周期内的运行数据、用户在上一周期内的反馈数据更新个体模型。
第二方面，提供了一种控制智能设备的装置，包括：处理器、存储器、总线和通信接口；存储器用于存储程序代码，处理器与存储器通过总线连接，当装置运行时，处理器执行存储器存储的程序代码，以使装置执行第一方面或第一方面的任一可能的实现方式所述的方法。
第三方面，提供了一种计算机可读存储介质，其中存储有可执行的程序代码，该程序代码用以实现第一方面或第一方面的任意一种可能的实现方式所述的方法。
第四方面，提供了一种控制智能设备的装置，包含用于执行第一方面或第一方面的任意一种可能的实现方式中的方法的模块。
根据本发明实施例提供的技术方案，在多个用户共处一个有限空间内时，通过将个体模型的调整指令信息和群体模型的调整指令信息相结合，确定出适合多个用户的智能设备调整指令，提高了调整智能设备的效果。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本发明实施例应用的网络架构的示意图；
图2是依据本发明一实施例的计算机设备200的硬件结构示意图；
图3是依据本发明一实施例的控制智能设备的方法300的示范性流程图；
图4是依据本发明一实施例的控制智能设备的装置400的结构示意图。
具体实施方式
以下描述中，为了说明而不是为了限定，提出了诸如特定系统结构、接口、技术之类的具体细节，以便透彻理解本发明。然而，本领域的技术人员应当清楚，在没有这些具体细节的其它实施例中也可以实现本发明。在其它情况中，省略对众所周知的装置、电路以及方法的详细说明，以免不必要的细节妨碍本发明的描述。
图1是本发明实施例应用的网络架构100的示意图。其中，智能设备101与终端设备102处于同一有限空间103中，例如处于同一房间中。有限空间103中存在使用终端设备102的用户104，同时还存在其他用户105。智能设备101将自身的运行数据发送到终端设备102。终端设备102收集用户104的用户数据，结合智能设备101的运行数据来确定对智能设备101进行控制的调整指令。终端设备102将确定出的调整指令发送到智能设备101，以调整智能设备101的运行状态。服务器106可以为终端设备102提供群体用户对其他智能设备进行控制时所使用的调整指令信息。终端设备102在确定对智能设备101的调整指令时，可以同时考虑服务器106提供的调整指令信息，以使确定出的调整指令更加准确。其中，智能设备101可以为灯光设备、电动窗帘、音乐系统、智能家电等。终端设备102可以为移动电 话、平板电脑等。
终端设备102可以通过计算机设备的形式实现。图2是依据本发明一实施例的计算机设备200的硬件结构示意图。如图2所示，计算机设备200包括处理器202、存储器204、通信接口206和总线208。其中，处理器202、存储器204和通信接口206通过总线208实现彼此之间的通信连接。
处理器202可以采用通用的中央处理器(Central Processing Unit，CPU)，微处理器，应用专用集成电路(Application Specific Integrated Circuit，ASIC)，或者一个或多个集成电路，用于执行相关程序，以实现本发明实施例所提供的技术方案。
存储器204可以是只读存储器(Read Only Memory，ROM)，静态存储设备，动态存储设备或者随机存取存储器(Random Access Memory，RAM)。存储器204可以存储操作系统2041和其他应用程序2042。在通过软件或者固件来实现本发明实施例提供的技术方案时，用于实现本发明实施例提供的技术方案的程序代码保存在存储器204中，并由处理器202来执行。
通信接口206使用例如但不限于收发器一类的收发装置，来实现与其他设备或通信网络之间的通信。
总线208可包括一通路，在各个部件(例如处理器202、存储器204、通信接口206)之间传送信息。
当终端设备102通过计算机设备200实现时，通信接口206用于获取当前周期内用户的用户数据，以及来自目标智能设备的当前周期内的运行数据；处理器202用于将所述用户数据和所述运行数据应用于个体模型，确定每个智能设备调整指令的第一使用概率，所述个体模型由所述用户的历史用户数据和所述目标智能设备的历史运行数据所训练得到；将所述用户数据和所述运行数据应用于群体模型，确定所述每个智能设备调整指令的第二使用概率，所述群体模型由多个用户的历史用户数据和对应的智能设备的历史运行数据所训练得到；根据所述每个智能设备调整指令的第一使用概率和所述每个智能设备调整指令的第二使用概率确定控制所述目标智能设备的调整指令；通信接口206用于向所述目标智能设备发送控制所述目标智能设备的调整指令。
图3是依据本发明一实施例的控制智能设备的方法300的示范性流程图。在具体实现过程中，控制智能设备的方法300可以由图1所示的智能设备101、终端设备102和服务器106来执行。
S301，目标智能设备向终端设备发送当前周期内的运行数据。
S302，终端设备接收来自目标智能设备的当前周期内的运行数据。
S303，终端设备获取当前周期内用户的用户数据。
终端设备周期性的收集用户数据来对目标智能设备进行调控。用户数据包括用户的生理数据，如体表温度，体表湿度，心率等，还可以包括用户所处环境的温度、湿度等。目标智能设备发送的运行数据为目标智能设备的运行参数，例如，当目标智能设备为空调时，运行数据可以包括温度值、湿度值、风力、模式等。
S304，所述终端设备将所述用户数据和所述运行数据应用于个体模型，确定每 个智能设备调整指令的第一使用概率，所述个体模型由所述用户的历史用户数据和所述目标智能设备的历史运行数据所训练得到。
S305，所述终端设备将所述用户数据和所述运行数据应用于群体模型，确定所述每个智能设备调整指令的第二使用概率，所述群体模型由多个用户的历史用户数据和对应的智能设备的历史运行数据所训练得到。
群体模型由服务器提供给终端设备。群体模型反映了在多人共处一个有限空间中时，其他终端设备对智能设备所进行的控制。
个体模型和群体模型为多分类概率模型，可以通过Softmax算法、高斯混合模型(Gaussian Mixture Model,GMM)或朴素贝叶斯算法等来实现。
例如，当个体模型和群体模型通过Softmax算法实现时，个体模型可以表示为
Figure PCTCN2017104080-appb-000001
其中，
Figure PCTCN2017104080-appb-000002
k为调整指令的个数。x1为用户数据。θj(j＝1,2,…,k)为M维向量。
群体模型可以表示为
Figure PCTCN2017104080-appb-000003
其中，
Figure PCTCN2017104080-appb-000004
k为调整指令的个数。x2为运行数据。λj(j＝1,2,…,k)为M维向量。
M的确定方法可以为M＝||x1||+||x2||。其中||x1||表示向量x1的模，||x2||表示向量x2的模。
当目标智能设备为智能空调时，x1可以表示为x1＝{体表温度，体表湿度，心率，环境温度，环境湿度}。x2可以表示为x2＝{温度值，湿度值，风力，制冷}。
当将用户数据与运行数据应用于上述个体模型和群体模型时，可以得到每种调整指令的使用概率。可以用P1(y＝j|x1,x2,θ)表示通过个体模型得到的使用第j种调整指令的概率，用P2(y＝j|x1,x2,λ)表示通过群体模型得到的使用第j种调整指令的概率。
例如，当取k＝3时，通过个体模型得到的使用第j种调整指令的概率为P1(y＝1)＝0.2，P1(y＝2)＝0.6和P1(y＝3)＝0.2。通过群体模型得到的使用第j种调整指令的概率为P2(y＝1)＝0.5，P2(y＝2)＝0.2和P2(y＝3)＝0.3。其中，y＝1表示温度升高1摄氏度，y＝2表示温度保持不变，y＝3表示温度降低1摄氏度。
S306，所述终端设备根据所述每个智能设备调整指令的第一使用概率和所述每个智能设备调整指令的第二使用概率确定控制所述目标智能设备的调整指令。
可选的，对于每个智能设备调整指令，所述终端设备确定该智能设备调整指令的第一使用概率和第二使用概率的加权和；所述终端设备确定最大加权和对应的智能设备调整指令为控制所述目标智能设备的调整指令。
例如，对于S304和S305中的例子，终端设备可以根据
Figure PCTCN2017104080-appb-000005
来确定最大加权和对应的调整指令。取w1＝0.4，w2＝0.6，得到
Figure PCTCN2017104080-appb-000006
即调整指令指示智能空调将当前的温度升高1摄氏度。
S307，所述终端设备向所述目标智能设备发送控制所述目标智能设备的调整指令。
在上面的例子中，终端设备发送温度升高1摄氏度的调整指令给智能空调。假设当前智能空调设置的温度为24℃，则调整后的温度为25℃。
可选的，控制智能设备的方法300还可以包括以下步骤：
S308，当所述终端设备确定所述控制所述目标智能设备的调整指令所指示的调整值小于预设调整阈值时，所述终端设备确定所述个体模型和所述群体模型的差异度；当所述差异度大于预设差异度阈值时，所述终端设备根据上一周期内所述用户的用户数据，以及来自所述目标智能设备的上一周期内的运行数据更新所述个体模型。
例如，调整指令指示将温度升高1摄氏度，而预设调整阈值为2摄氏度。
终端设备可以根据
Figure PCTCN2017104080-appb-000007
来确定个体模型和群体模型的差异度d。
可选的，所述终端设备根据所述上一周期内所述用户的用户数据，以及所述来自所述目标智能设备的上一周期内的运行数据，确定所述用户在上一周期内的反馈数据；所述终端设备根据所述上一周期内所述用户的用户数据、所述来自所述目标智能设备的上一周期内的运行数据、所述用户在上一周期内的反馈数据更新所述个体模型。
进一步，可选的，终端设备将上一周期内所述用户的用户数据、所述来自所述目标智能设备的上一周期内的运行数据、所述用户在上一周期内的反馈数据发送给服务器。服务器收集不同终端设备发送的数据。当收集到的数据达到一定数量，服务器更新群体模型，并将更新后的群体模型发送给终端设备，供终端设备在下一周期内使用。
根据本发明实施例提供的技术方案，在多个用户共处一个有限空间内时，通过将个体模型的调整指令信息和群体模型的调整指令信息相结合，确定出适合多个用户的智能设备调整指令，提高了调整智能设备的效果。
图4是依据本发明一实施例的控制智能设备的装置400的结构示意图。控制智能设备的装置400包括获取模块402，处理模块404和发送模块406。控制智能设备的装置400为图2中的计算机设备200或图3中所示的终端设备。获取模块402可以用来执行图3实例中的S302、S303，处理模块404可以用来执行图3实施例中的S304、S305、S306、S308，发送模块406可以用来执行图3实施例中的S307。
获取模块402，用于获取当前周期内用户的用户数据，以及来自目标智能设备的当前周期内的运行数据。
处理模块404，用于将所述用户数据和所述运行数据应用于个体模型，确定每个智能设备调整指令的第一使用概率，所述个体模型由所述用户的历史用户数据和所述目标智能设备的历史运行数据所训练得到。
处理模块404，还用于将所述用户数据和所述运行数据应用于群体模型，确定所述每个智能设备调整指令的第二使用概率，所述群体模型由多个用户的历史用户数据和对应的智能设备的历史运行数据所训练得到。
处理模块404，还用于根据所述每个智能设备调整指令的第一使用概率和所述每个智能设备调整指令的第二使用概率确定控制所述目标智能设备的调整指令。
发送模块406，用于向所述目标智能设备发送控制所述目标智能设备的调整指令。
可选的，处理模块404根据所述每个智能设备调整指令的第一使用概率和所述每个智能设备调整指令的第二使用概率确定控制所述目标智能设备的调整指令包括：
对于每个智能设备调整指令，所述处理模块404用于确定该智能设备调整指令的第一使用概率和第二使用概率的加权和；确定最大加权和对应的智能设备调整指令为控制所述目标智能设备的调整指令。
可选的，当处理模块404确定所述控制所述目标智能设备的调整指令所指示的调整值小于预设调整阈值时，所述处理模块404还用于确定所述个体模型和所述群体模型的差异度；当所述差异度大于预设差异度阈值时，所述处理模块404用于根据上一周期内所述用户的用户数据，以及来自所述目标智能设备的上一周期内的运行数据更新所述个体模型。
可选的，处理模块404根据上一周期内所述用户的用户数据，以及来自所述目标智能设备的上一周期内的运行数据更新所述个体模型包括：
所述处理模块404用于根据所述上一周期内所述用户的用户数据，以及所述来自所述目标智能设备的上一周期内的运行数据，确定所述用户在上一周期内的反馈数据；所述处理模块404根据所述上一周期内所述用户的用户数据、所述来自所述目标智能设备的上一周期内的运行数据、所述用户在上一周期内的反馈数据更新所述个体模型。
根据本发明实施例提供的技术方案，在多个用户共处一个有限空间内时，通过将个体模型的调整指令信息和群体模型的调整指令信息相结合，确定出适合多个用户的智能设备调整指令，提高了调整智能设备的效果。
其中，图4实施例中的“模块”可以为专用集成电路(Application Specific Integrated Circuit，ASIC)、电子线路、执行一个或多个软件或固件程序的处理器和存储器、组合逻辑电路和其他提供上述功能的组件。可选的，上述控制智能设备的装置通过计算机设备的形式来实现，上述获取模块、发送模块可以通过计算机设备的处理器、存储器和通信接口来实现，上述处理模块可以通过计算机设备的处理器和存储器来实现。
应注意，尽管图2所示的计算机设备200仅仅示出了处理器202、存储器204、通信接口206和总线208，但是在具体实现过程中，本领域的技术人员应当明白，上述控制智能设备的装置还包含实现正常运行所必须的其他器件。同时，根据具体需要，本领域的技术人员应当明白，上述控制智能设备的装置还可包含实现其他附加功能的硬件器件。此外，本领域的技术人员应当明白，上述控制智能设备的装置也可仅仅包含实现本发明实施例所必须的器件，而不必包含图2中所示的全部器件。
另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)或处理器(processor)执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本发明的具体实施方式，但本发明的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本发明的保护范围之内。因此，本发明的保护范围应以所述权利要求的保护范围为准。

Claims (9)

  1. 一种控制智能设备的方法，其特征在于，包括以下步骤：
    终端设备获取当前周期内用户的用户数据，以及来自目标智能设备的当前周期内的运行数据；
    所述终端设备将所述用户数据和所述运行数据应用于个体模型，确定每个智能设备调整指令的第一使用概率，所述个体模型由所述用户的历史用户数据和所述目标智能设备的历史运行数据所训练得到；
    所述终端设备将所述用户数据和所述运行数据应用于群体模型，确定所述每个智能设备调整指令的第二使用概率，所述群体模型由多个用户的历史用户数据和对应的智能设备的历史运行数据所训练得到；
    所述终端设备根据所述每个智能设备调整指令的第一使用概率和所述每个智能设备调整指令的第二使用概率确定控制所述目标智能设备的调整指令；
    所述终端设备向所述目标智能设备发送控制所述目标智能设备的调整指令。
  2. 根据权利要求1所述的方法，其特征在于，所述终端设备根据所述每个智能设备调整指令的第一使用概率和所述每个智能设备调整指令的第二使用概率确定控制所述目标智能设备的调整指令包括：
    对于每个智能设备调整指令，所述终端设备确定该智能设备调整指令的第一使用概率和第二使用概率的加权和；
    所述终端设备确定最大加权和对应的智能设备调整指令为控制所述目标智能设备的调整指令。
  3. 根据权利要求1或2所述的方法，其特征在于，所述方法还包括：
    当所述终端设备确定所述控制所述目标智能设备的调整指令所指示的调整值小于预设调整阈值时，所述终端设备确定所述个体模型和所述群体模型的差异度；
    当所述差异度大于预设差异度阈值时，所述终端设备根据上一周期内所述用户的用户数据，以及来自所述目标智能设备的上一周期内的运行数据更新所述个体模型。
  4. 根据权利要求3所述的方法，其特征在于，所述终端设备根据上一周期内所述用户的用户数据，以及来自所述目标智能设备的上一周期内的运行数据更新所述个体模型包括：
    所述终端设备根据所述上一周期内所述用户的用户数据，以及所述来自所述目标智能设备的上一周期内的运行数据，确定所述用户在上一周期内的反馈数据；
    所述终端设备根据所述上一周期内所述用户的用户数据、所述来自所述目标智能设备的上一周期内的运行数据、所述用户在上一周期内的反馈数据更新所述个体模型。
  5. 一种控制智能设备的装置，其特征在于，包括获取模块，处理模块和发送模块：
    所述获取模块，用于获取当前周期内用户的用户数据，以及来自目标智能设备的当前周期内的运行数据；
    所述处理模块，用于将所述用户数据和所述运行数据应用于个体模型，确定每个智能设备调整指令的第一使用概率，所述个体模型由所述用户的历史用户数据和 所述目标智能设备的历史运行数据所训练得到；
    所述处理模块，还用于将所述用户数据和所述运行数据应用于群体模型，确定所述每个智能设备调整指令的第二使用概率，所述群体模型由多个用户的历史用户数据和对应的智能设备的历史运行数据所训练得到；
    所述处理模块，还用于根据所述每个智能设备调整指令的第一使用概率和所述每个智能设备调整指令的第二使用概率确定控制所述目标智能设备的调整指令；
    所述发送模块，用于向所述目标智能设备发送控制所述目标智能设备的调整指令。
  6. 根据权利要求5所述的装置，其特征在于，所述处理模块根据所述每个智能设备调整指令的第一使用概率和所述每个智能设备调整指令的第二使用概率确定控制所述目标智能设备的调整指令包括：
    对于每个智能设备调整指令，所述处理模块用于确定该智能设备调整指令的第一使用概率和第二使用概率的加权和；
    确定最大加权和对应的智能设备调整指令为控制所述目标智能设备的调整指令。
  7. 根据权利要求5或6所述的装置，其特征在于，当所述处理模块确定所述控制所述目标智能设备的调整指令所指示的调整值小于预设调整阈值时，所述处理模块还用于确定所述个体模型和所述群体模型的差异度；
    当所述差异度大于预设差异度阈值时，所述处理模块用于根据上一周期内所述用户的用户数据，以及来自所述目标智能设备的上一周期内的运行数据更新所述个体模型。
  8. 根据权利要求7所述的装置，其特征在于，所述处理模块根据上一周期内所述用户的用户数据，以及来自所述目标智能设备的上一周期内的运行数据更新所述个体模型包括：
    所述处理模块用于根据所述上一周期内所述用户的用户数据，以及所述来自所述目标智能设备的上一周期内的运行数据，确定所述用户在上一周期内的反馈数据；
    所述处理模块根据所述上一周期内所述用户的用户数据、所述来自所述目标智能设备的上一周期内的运行数据、所述用户在上一周期内的反馈数据更新所述个体模型。
  9. 一种控制智能设备的装置，其特征在于，包括：处理器、存储器、总线和通信接口；所述存储器用于存储程序代码，所述处理器与所述存储器通过所述总线连接，当所述装置运行时，所述处理器执行所述存储器存储的所述程序代码，以使所述装置执行权利要求1至4任意一项所述的方法。
PCT/CN2017/104080 2016-11-08 2017-09-28 一种控制智能设备的方法及装置 WO2018086427A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610980787.1 2016-11-08
CN201610980787.1A CN108063701B (zh) 2016-11-08 2016-11-08 一种控制智能设备的方法及装置

Publications (1)

Publication Number Publication Date
WO2018086427A1 true WO2018086427A1 (zh) 2018-05-17

Family

ID=62109385

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/104080 WO2018086427A1 (zh) 2016-11-08 2017-09-28 一种控制智能设备的方法及装置

Country Status (2)

Country Link
CN (1) CN108063701B (zh)
WO (1) WO2018086427A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116095804A (zh) * 2023-01-13 2023-05-09 惠州市源医科技有限公司 一种5g智能路由器及其功率调节方法

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109901408A (zh) * 2019-03-08 2019-06-18 阿里巴巴集团控股有限公司 一种智能设备的控制方法、装置和系统
CN110471303A (zh) * 2019-08-30 2019-11-19 北京青岳科技有限公司 一种基于计算机视觉的家居智能控制方法
CN114815645A (zh) * 2022-04-19 2022-07-29 青岛海尔科技有限公司 物联网设备的控制方法和装置、存储介质和电子装置
CN114885016A (zh) * 2022-04-29 2022-08-09 青岛海尔科技有限公司 服务推送的方法和装置、存储介质及电子装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160048142A1 (en) * 2014-08-15 2016-02-18 Delta Electronics, Inc. Intelligent air-conditioning controlling system and intelligent controlling method for the same
CN105376649A (zh) * 2015-11-24 2016-03-02 江苏有线技术研究院有限公司 实现精准组合推荐的机顶盒盲操作方法和系统
CN105371425A (zh) * 2015-10-12 2016-03-02 美的集团股份有限公司 空调器
US9473321B1 (en) * 2015-11-23 2016-10-18 International Business Machines Corporation Dynamic control of smart home using wearable device

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9978260B2 (en) * 2012-12-18 2018-05-22 Samsung Electronics Co., Ltd. Method and apparatus for controlling a home device remotely in a home network system
CN105760141B (zh) * 2016-04-05 2023-05-09 中兴通讯股份有限公司 一种实现多维控制的方法、智能终端及控制器
CN105910232B (zh) * 2016-04-29 2018-10-19 广东美的制冷设备有限公司 基于邻近空调设定学习的空调控制方法、系统及空调

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160048142A1 (en) * 2014-08-15 2016-02-18 Delta Electronics, Inc. Intelligent air-conditioning controlling system and intelligent controlling method for the same
CN105371425A (zh) * 2015-10-12 2016-03-02 美的集团股份有限公司 空调器
US9473321B1 (en) * 2015-11-23 2016-10-18 International Business Machines Corporation Dynamic control of smart home using wearable device
CN105376649A (zh) * 2015-11-24 2016-03-02 江苏有线技术研究院有限公司 实现精准组合推荐的机顶盒盲操作方法和系统

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116095804A (zh) * 2023-01-13 2023-05-09 惠州市源医科技有限公司 一种5g智能路由器及其功率调节方法
CN116095804B (zh) * 2023-01-13 2023-08-08 惠州市源医科技有限公司 一种5g智能路由器及其功率调节方法

Also Published As

Publication number Publication date
CN108063701A (zh) 2018-05-22
CN108063701B (zh) 2020-12-08

Similar Documents

Publication Publication Date Title
WO2018086427A1 (zh) 一种控制智能设备的方法及装置
EP3452954B1 (en) Dynamic classifier selection based on class skew
CN108304758B (zh) 人脸特征点跟踪方法及装置
US10697661B2 (en) Thermal control apparatus and method
CN108027952B (zh) 用于提供内容的方法和电子设备
US10917552B2 (en) Photographing method using external electronic device and electronic device supporting the same
EP3316123B1 (en) Electronic device and controlling method thereof
EP2990907A2 (en) Device for controlling the performance level of the device based on fluctuations in internal temperature and method thereof
US11449790B2 (en) Artificial intelligence device and method for executing an operation based on predicted biometric state of a user
US10681711B2 (en) Method for data scheduling and power control and electronic device thereof
KR102632254B1 (ko) 심볼 검출기 선택 방법 및 시스템
US11380131B2 (en) Method and device for face recognition, storage medium, and electronic device
US20160179070A1 (en) Electronic device for controlling another electronic device and control method thereof
WO2019080685A1 (zh) 视频图像分割方法及装置、存储介质、电子设备
US20160150582A1 (en) Electronic device for establishing communication by electronic device
EP3635533B1 (en) Electronic apparatus for processing user utterance for controlling an external electronic apparatus and controlling method thereof
TW202139625A (zh) 由通訊網路中的電子裝置進行的方法、以及用於通訊網路中的電子裝置
CN107852546A (zh) 电子设备及其输入/输出方法
US20160103150A1 (en) Method and apparatus for measuring the speed of an electronic device
US11171701B2 (en) Electronic device for controlling communications and method for operating same
US20230106213A1 (en) Machine learning model compression using weighted low-rank factorization
TWI842877B (zh) 用於選擇符碼偵測器的系統及方法
CN111835461B (zh) 提供多输入多输出检测器选择的系统和方法
CN117579201A (zh) 模型匹配方法、装置、通信设备及可读存储介质

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: 17869045

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17869045

Country of ref document: EP

Kind code of ref document: A1