WO2022166886A1 - 一种数据获取方法及装置 - Google Patents

一种数据获取方法及装置 Download PDF

Info

Publication number
WO2022166886A1
WO2022166886A1 PCT/CN2022/074979 CN2022074979W WO2022166886A1 WO 2022166886 A1 WO2022166886 A1 WO 2022166886A1 CN 2022074979 W CN2022074979 W CN 2022074979W WO 2022166886 A1 WO2022166886 A1 WO 2022166886A1
Authority
WO
WIPO (PCT)
Prior art keywords
configuration information
model
terminal device
data
network device
Prior art date
Application number
PCT/CN2022/074979
Other languages
English (en)
French (fr)
Inventor
陈晓宇
韩立锋
Original Assignee
展讯通信（上海）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 展讯通信（上海）有限公司 filed Critical 展讯通信（上海）有限公司
Publication of WO2022166886A1 publication Critical patent/WO2022166886A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/02—Arrangements for optimising operational condition

Definitions

  • the present application relates to the field of communication technologies, and in particular, to a data acquisition method and device.
  • AI artificial intelligence
  • the network device performs AI model training and inference based on the data reported by the terminal device.
  • the data reported by the terminal device is collected and processed based on static configuration information, which is configured in a predefined manner and will not change. Therefore, this data collection and processing method cannot well cope with changes in the communication environment or resources, and may degrade communication performance.
  • Embodiments of the present application provide a data acquisition method and apparatus, where a terminal device can perform corresponding configuration according to configuration information from a network device, which is conducive to better coping with changes in communication environment and resources and enhancing the performance of a communication network.
  • an embodiment of the present application provides a data acquisition method, the method comprising:
  • the terminal device receives the first configuration information from the network device; the first configuration information is used to indicate the data collection mode, data preprocessing mode and/or data reporting mode for the first model, where the first model is the network
  • the artificial intelligence AI model used by the device the terminal device performs corresponding configuration according to the first configuration information.
  • the terminal device may receive the first configuration information from the network device, update the configuration information of the terminal device itself according to the first configuration information, and then use the updated configuration information
  • the data collection, preprocessing and/or reporting methods in the data collection, preprocessing and/or reporting methods are used to report the collected and preprocessed data to the network device.
  • the first configuration information when used to indicate a data collection method, a preprocessing method, and a reporting method for the first model, the first configuration information, include:
  • the first indication information is used to indicate the first model
  • the second indication information is used to indicate the data collection method
  • the third indication information is used to indicate the data preprocessing method
  • the fourth indication information is used to indicate the data reporting method.
  • the method further includes:
  • the terminal device sends a configuration information acquisition request to the network device, where the configuration information acquisition request is used to request the first configuration information.
  • the configuration information acquisition request includes device capability information of the terminal device.
  • the terminal device sends a configuration information acquisition request to the network device, including:
  • the terminal device When the processing capability of the terminal device is limited, the terminal device sends a configuration information acquisition request to the network device; or,
  • the terminal device sends a configuration information acquisition request to the network device when changing the data precision requirement.
  • the method further includes:
  • the terminal device reports data to the network device according to the first configuration information.
  • the method further includes:
  • the terminal device receives an activation message sent from the network device, where the activation message is used to activate the configuration according to the first configuration information.
  • the terminal device receives the first configuration information from the network device, including:
  • the terminal device receives a radio resource control RRC message from a network device, where the RRC message includes the first configuration information.
  • the first configuration information is further used to indicate the second model; the method further includes:
  • the terminal device adjusts the AI model used by itself according to the second model.
  • the present application provides a data acquisition method, the method comprising:
  • the network device obtains first configuration information for the first model, where the first configuration information is used to indicate the data collection method, data preprocessing method and/or data reporting method for the first model, and the first model is the The artificial intelligence AI model used by the network device; the network device sends the first configuration information to the terminal device.
  • the terminal device may receive the first configuration information from the network device, update the configuration information of the terminal device itself according to the first configuration information, and then use the updated configuration information
  • the data collection, preprocessing and/or reporting methods in the data collection, preprocessing and/or reporting methods are used to report the collected and preprocessed data to the network device.
  • the first configuration information when used to indicate a data collection method, a preprocessing method, and a reporting method for the first model, the first configuration information, include:
  • the first indication information is used to indicate the first model
  • the second indication information is used to indicate the data collection method
  • the third indication information is used to indicate the data preprocessing method
  • the fourth indication information is used to indicate the data reporting method.
  • the method further includes:
  • the network device receives a configuration information acquisition request from the terminal device, where the configuration information acquisition request is used to request the first configuration information.
  • the configuration information acquisition request includes device capability information of the terminal device.
  • the network device obtains the first configuration information for the first model, including:
  • the network device When the network device detects that the air interface resource is congested, it acquires the first configuration information for the first model.
  • the method further includes:
  • the network device receives the data reported by the terminal device according to the first configuration information.
  • the method further includes:
  • the network device sends an activation message to the terminal device, where the activation message is used to activate the configuration of the terminal device according to the first configuration information.
  • the network device sends the first configuration information to the terminal device, including:
  • the network device sends a radio resource control RRC message to the terminal device, where the RRC message includes the first configuration information.
  • the first configuration information is further used to indicate a second model used by the terminal device.
  • an embodiment of the present application provides a communication device, where the communication device is configured to implement a unit of the method in the first aspect or the second aspect and any possible implementation manners thereof.
  • the present application provides a communication apparatus, the communication apparatus includes a processor, and the processor is configured to execute the method in the first aspect or the second aspect and any possible implementation manners thereof.
  • the present application provides a communication device, the communication device includes a processor and a memory, the memory is used for storing computer-executed instructions; the processor is used for calling the program code from the memory to execute the first A method of the aspect or the second aspect and any possible implementation thereof.
  • the present application provides a communication device, the communication device includes a processor and a transceiver, the transceiver is configured to receive a signal or send a signal; the processor is configured to execute the first aspect or the first aspect.
  • the communication device includes a processor and a transceiver, the transceiver is configured to receive a signal or send a signal; the processor is configured to execute the first aspect or the first aspect.
  • the second aspect and the method in any possible implementation manner thereof.
  • the present application provides a communication device, the communication device includes a processor, a memory, and a transceiver, the transceiver is used for receiving a signal or sending a signal; the memory is used for storing a program code; the The processor is configured to call the program code from the memory to execute the method in the first aspect or the second aspect and any possible implementations thereof.
  • the present application provides a chip for receiving first configuration information from a network device; the first configuration information is used to indicate a data collection method, data preprocessing method, and /or data reporting method, the first model is an artificial intelligence AI model used by the network device; the chip is further configured to perform corresponding configuration according to the first configuration information.
  • the present application provides a chip for acquiring first configuration information for a first model, where the first configuration information is used to indicate a data collection method and a data preprocessing method for the first model and/or data reporting method, the first model is an artificial intelligence AI model used by the network device; the chip is also used to output the first configuration information to the terminal device.
  • the present application provides a module device, the module device includes a communication module, a power module, a storage module and a chip module, wherein: the communication module is used for internal communication of the module device, Or used for the module device to communicate with external devices; the power module is used to provide power to the module device; the storage module is used to store data and instructions; the chip module is used to: receive data from network devices.
  • first configuration information the first configuration information is used to indicate the data collection method, data preprocessing method and/or data reporting method for the first model, and the first model is the artificial intelligence AI model used by the network device; according to the The first configuration information is configured accordingly.
  • the present application provides a module device, characterized in that the module device includes a communication module, a power module, a storage module and a chip module, wherein: the communication module is used to perform a module operation. The internal communication of the group device, or for the module device to communicate with external devices; the power module is used to provide electrical energy for the module device; the storage module is used to store data and instructions; the chip module is used for: For the first model, obtain first configuration information, where the first configuration information is used to indicate a data collection method, data preprocessing method and/or data reporting method for the first model, where the first model is a manual method used by the network device Intelligent AI model; the first configuration information output to the terminal device.
  • the module device includes a communication module, a power module, a storage module and a chip module, wherein: the communication module is used to perform a module operation. The internal communication of the group device, or for the module device to communicate with external devices; the power module is used to provide electrical energy for the module device; the storage module is used to store data
  • the present application provides a computer-readable storage medium, where computer-readable instructions are stored in the computer-readable instructions, and when the computer-readable instructions are executed on a communication device, the communication device is caused to execute the above-mentioned first A method of the aspect or the second aspect and any possible implementation thereof.
  • the present application provides a computer program or computer program product comprising code or instructions, which when run on a computer, cause the computer to perform the method of the first or second aspect.
  • FIG. 1 is a schematic diagram of a system structure of a communication system according to an embodiment of the present application
  • FIG. 2 is a schematic flowchart of a data acquisition method provided by an embodiment of the present application.
  • FIG. 3 is another schematic flowchart of a data acquisition method provided by an embodiment of the present application.
  • FIG. 4 is another schematic flowchart of a data acquisition method provided by an embodiment of the present application.
  • FIG. 5 is a schematic flowchart of an activation method provided by an embodiment of the present application.
  • FIG. 6 is a schematic flowchart of another activation manner provided by an embodiment of the present application.
  • FIG. 7 is a schematic structural diagram of a communication device according to an embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of another communication device provided by an embodiment of the present application.
  • FIG. 9 is a schematic structural diagram of another communication device provided by an embodiment of the present application.
  • FIG. 10 is a schematic structural diagram of a module device provided by an embodiment of the application.
  • FIG. 11 is a schematic structural diagram of another module device provided by an embodiment of the present application.
  • connection in the embodiments of the present application refers to various connection modes such as direct connection or indirect connection, so as to realize communication between devices, which is not limited in the embodiments of the present application.
  • FIG. 1 is a schematic diagram of the system structure of a communication system provided by an embodiment of the application.
  • the communication system may include but is not limited to a network device and a terminal device.
  • the number and form of the devices shown in FIG. 1 are used for The examples do not constitute a limitation to the embodiments of the present application, and an actual application may include more than one network device and more than one terminal device.
  • the communication system shown in FIG. 1 is described by taking a network device 10 and a terminal device 11 as an example, and the terminal device 11 can receive the first configuration information from the network device 10 .
  • a terminal device may also be referred to as a terminal, a user equipment (User Equipment, UE), an access terminal, a subscriber unit, a subscriber station, a mobile station, a mobile station, a remote station, a remote terminal, a mobile device, a user Terminal, User Agent or User Device.
  • UE User Equipment
  • the terminal device in the embodiment of the present application may be a mobile phone (mobile phone), a tablet computer (Pad), a computer with a wireless transceiver function, a virtual reality (virtual reality, VR) terminal device, an augmented reality (augmented reality, AR) terminal equipment, wireless terminals in industrial control, wireless terminals in self driving, wireless terminals in remote medical, wireless terminals in smart grid, transportation security ( Wireless terminals in transportation safety), wireless terminals in smart cities, wireless terminals in smart homes, etc.
  • a virtual reality (virtual reality, VR) terminal device an augmented reality (augmented reality, AR) terminal equipment
  • wireless terminals in industrial control wireless terminals in self driving
  • wireless terminals in remote medical wireless terminals in remote medical
  • wireless terminals in smart grid wireless terminals in smart grid
  • transportation security Wireless terminals in transportation safety
  • wireless terminals in smart cities wireless terminals in smart homes, etc.
  • the network device 10 is an access device that the terminal device 11 wirelessly accesses to the mobile communication system, which can be a base station NodeB, an evolved NodeB (evolved NodeB, eNodeB), a transmission reception point (transmission reception point, TRP), the next generation NodeB (gNB) in the 5G mobile communication system, the base station in the future mobile communication system or the access node in the WiFi system, etc.; it can also be a module or unit that completes some functions of the base station, such as , which can be a centralized unit (central unit, CU) or a distributed unit (distributed unit, DU).
  • the embodiments of the present application do not limit the specific technology and specific device form adopted by the wireless access network device.
  • network devices may also be referred to as wireless access network devices. Unless otherwise specified, wireless access network devices refer to network devices.
  • network devices can use data reported by terminal devices to train and predict AI models.
  • the data reported by the terminal device is collected and processed based on static configuration information, which is configured in a predefined manner and will not change.
  • static configuration information which is configured in a predefined manner and will not change.
  • the terminal device still collects and processes data according to the static configuration information, and the reported data may not meet the network requirements. Therefore, this data collection and processing method cannot well cope with the communication environment or Changes in resources will reduce communication performance to a certain extent.
  • the present application proposes a data acquisition method.
  • the terminal device receives first configuration information from a network device, where the first configuration information is used to indicate a data collection method, data preprocessing method and/or data reporting method for the first model, wherein the first The model is an AI model used by the network device, and the terminal device performs corresponding configuration according to the first configuration information.
  • the terminal device can receive the first configuration information from the network device, update the configuration information of the terminal device itself according to the first configuration information, and then use the data collection, preprocessing and/or reporting methods in the updated configuration information, Report the collected and preprocessed data to the network device.
  • FIG. 2 is a schematic flowchart of a data acquisition method provided by an embodiment of the present application.
  • the obtaining method includes steps 201-203, wherein:
  • the network device acquires first configuration information for the first model.
  • the network device can train and use multiple AI models.
  • the present application takes the AI model used by the network device as the first model for explanation, and the first model is the multiple AI models used by the network device. Any of the AI models in the AI model.
  • the first configuration information is configuration information obtained by the network device according to the first model, and the first configuration information is used to indicate the data collection mode, preprocessing mode, and reporting mode of the terminal device for the first model. It should be noted that the present application takes the first model as an example for explanation.
  • the first configuration information may include one or more of four indication information.
  • the first indication information is used to indicate the first model.
  • the first indication information may include an AI model identifier (AI model index), an AI model configuration identifier, and may also include a function identifier (use case id).
  • the second indication information is used to indicate the data collection mode.
  • the second indication information may include the frequency of data collection by the terminal device, and may also include the data collection interval.
  • the third indication information is used to indicate the data preprocessing mode.
  • the third indication information may include steps of preprocessing the collected data and specific operations of each step, such as data cleaning.
  • the fourth indication information is used to indicate a data reporting manner.
  • the fourth indication information may include a period of reporting data, and may also include the number of times of reporting data.
  • the second indication information is the indication information indicating the data collection method of the first model
  • the third indication information is the indication information indicating the data preprocessing method of the first model
  • the fourth indication information is the indication information indicating the data reporting method of the first model information.
  • the acquisition method of the first configuration information may be obtained from the preset configuration information according to the accuracy requirements of the first model, the processing capability of the terminal device, the limited air interface resources, and other indicators; it may also be based on an indicator, from the It can also be obtained from the preset configuration information; it can also be the configuration information calculated based on the above one or more indicators according to a preset algorithm; it can also be the configuration information received from other devices.
  • This application does not limit the acquisition method of the first configuration information.
  • the network device after acquiring the indication information in the first configuration information, the network device sends the first configuration information to the terminal device according to a preset format.
  • the preset format can be:
  • the first indication information may include use case id.
  • use case id is a use case identifier, and this field indicates the AI function use case to which the first configuration information is applied, and the AI model identifier used by the AI function use case.
  • the use case id is 3, then the use case id indicating the first model is 3, then the second instruction information, the third instruction information and the fourth instruction information in the first configuration information are all use case id. 3 Corresponding data collection methods, preprocessing methods and reporting methods. If the first indication information is default, it may indicate that the second indication information, the third indication information, and the fourth indication information in the first configuration information can be applied to all AI function use cases.
  • the first indication information has two representations, and the first representation is the identification of the model.
  • the first representation is the identification of the model.
  • the first indication information may indicate that the first model used by the network device is model3 related to positioning.
  • the second representation is the combined identification of the function and the model.
  • the positioning use case id is 01
  • the channel estimation use case id is 02
  • the channel coding use case id is 03
  • the model id related to the positioning function is 01, 02, 03
  • the model ids related to channel estimation and channel coding are all 01, 02, 03
  • the first indication information can be 0101
  • the first indication information can indicate that the first model used by the network device is related to positioning.
  • the first indication information in the first configuration information may further indicate a second model, where the second model is a model used by the terminal device.
  • the terminal device can also use the AI model to implement network functions, and/or perform data collection and data preprocessing, and the first indication information can also instruct the terminal device to adjust the AI model used by itself according to the second model.
  • the second indication information may include sampling frequency/interval.
  • the sampling frequency/interval may be used to indicate the sampling frequency and sampling duration when the terminal device collects the data of the first model. Exemplarily, for the first model, the terminal device collects once every 10 seconds (s), and collects for 1 s each time.
  • the third indication information may include a data preprocessing step, where the data preprocessing step is used to instruct the terminal to perform a preprocessing step on the data of the first model.
  • the steps of preprocessing may include data cleaning, feature extraction, data compression, and the like.
  • the fourth indication information may include reporting data dimension, reporting data period, and reporting data times.
  • the field of the reported data dimension is used to indicate the type and quantity of indicators that the terminal device needs to collect/measure and upload for the first model.
  • the second indication information indicates that the information reported by the terminal may include the type and quantity of measurement information, such as reference signal received power, reference signal received quality, and the like.
  • the reporting data period is used to indicate the period for the terminal equipment to report data.
  • the terminal device may perform data reporting once every 5s; for another example, for the first model, the terminal device may perform data reporting once aperiodically.
  • the number of times of data reporting is used to indicate the number of times that the terminal device reports data.
  • the terminal device needs to report 100 times, and stops reporting after 100 reports. It can be understood that when the number of times of data reporting is reached, the default settings can be restored, or the times of reporting data configured by the last configuration information can be restored, or it can be negotiated with the network device to request the network device to send the configuration information. This is not limited.
  • the first configuration information further includes a configuration effective time
  • the configuration effective time can be a relative time, that is, the first configuration information is valid within the timing range of the timer (timer); the configuration effective time also It can be an absolute time, that is, before a certain moment, the first configuration information is valid. It can be understood that after the validity period expires, the terminal device can restore the default settings, or restore the data collection method, preprocessing method, and reporting method in the last configuration information, or negotiate with the network device to request the network device. Sending configuration information, which is not limited in this application.
  • the terminal device may locally extract the sampling frequency/interval corresponding to the use case id in the static configuration information.
  • the terminal device receives the first configuration information from the network device.
  • the network device may send the first configuration information to the terminal device through radio resource control (Radio Resource Control, RRC) signaling, and the terminal device may The configuration information is updated by receiving an RRC message from the network device, where the RRC message includes the above-mentioned first configuration information.
  • RRC Radio Resource Control
  • the terminal device when the terminal device is in the connected state (RRC Connected), it receives an RRC release (release) message from the network device, where the RRC release message includes the above-mentioned first configuration information. Furthermore, after receiving the RRC release message, the terminal device releases the link and switches to a disconnected state, that is, an idle state (RRC IDLE)/inactive state (RRC Inactive). Therefore, it is possible to ensure that the terminal devices in the idle state (RRC IDLE)/inactive state (RRC Inactive) participate in the training and prediction of the AI model in an orderly manner, and improve the accuracy of the AI function.
  • RRC IDLE idle state
  • RRC Inactive inactive state
  • the content of the first configuration information obtained by the network device for the terminal device in the connected state and the terminal device about to enter the idle state/inactive state may be the same or different.
  • the terminal device performs corresponding configuration according to the first configuration information.
  • the terminal device when the terminal device is in the connected state, upon receiving the first configuration information, it may return a reception message to the network device, where the reception response message instructs the terminal device to confirm receiving the first configuration information.
  • the terminal device correspondingly updates the data collection manner, data preprocessing manner and/or data reporting manner of the first model based on the received first configuration information.
  • what the terminal device currently stores may be the data collection method, data preprocessing method and/or data reporting method of the first model in the static configuration information; it may also be the first configuration information update sent by the network device last time.
  • the data collection method in the first configuration information is used to update the data collection method corresponding to the first model in the static configuration information; the data preprocessing method in the first configuration information is used to update the data collection method corresponding to the first model in the static configuration information.
  • the data preprocessing method is used; the data reporting method corresponding to the first model in the static configuration information is updated by using the data reporting method in the first configuration information. If a certain field of the first configuration information is default, the default value of the default field in the static configuration information is retained.
  • the terminal device reports data to the network device according to the first configuration information.
  • the terminal device collects and preprocesses data according to the updated configuration information of the first model, and reports the data to the network device.
  • the terminal device may determine the first model according to the first indication information in the first configuration information; and then perform data collection on the data of the first model according to the data collection mode indicated by the second indication information in the first configuration information; Preprocess the collected data according to the data preprocessing mode indicated by the third indication information in the first configuration information; The data is reported to the network device.
  • the terminal device needs to report 500 times of data as training data.
  • the first configuration information sent by the network device may be:
  • the data to be reported by the terminal device is the signal strength information of model3; the data preprocessing method is data cleaning and feature extraction; the data collection method is once every 10s, and each collection is 1s; The reporting method is to report 500 times. Then the network device can complete the training of model3 according to the received data reported by the terminal device.
  • the first indication information in the first configuration information may further indicate a second model, where the second model is a model used by the terminal device.
  • the terminal device may use the second model as the model corresponding to the use case id.
  • the terminal device in the inactive state can initiate small data transmission (SDT), and report the preprocessed data to the network device.
  • SDT small data transmission
  • the terminal device may receive the first configuration information from the network device, update the configuration information of the terminal device itself according to the first configuration information, and then use the data collection, preprocessing and / or reporting method, reporting the collected and preprocessed data to the network device.
  • FIG. 3 is another schematic flowchart of a data acquisition method provided by an embodiment of the present application.
  • the above data acquisition method includes steps 301 to 304 . in:
  • a terminal device sends a configuration information acquisition request to a network device.
  • the terminal device may send a configuration information update request to the network device, where the configuration information update request is used to request to acquire the first configuration information.
  • the first configuration information is used to indicate a data collection method, data preprocessing method and/or data reporting method for the first model, where the first model is an AI model used by the network device.
  • the configuration information acquisition request may include device capability information of the terminal device, the configuration information acquisition request may also include data accuracy requirement information, and may also include other information, which is not limited in this application.
  • the device capability information of the terminal device may be used to indicate the current processing capability of the terminal device.
  • the device processing capability information may include storage space information, and may also include computing capability information of a central processing unit (CPU), thermal assistance information of terminal devices, and the like.
  • the terminal device may send a configuration information acquisition request to the network device.
  • the device capability information of the terminal device may be thermal assistance information, and the thermal assistance information may indicate that the current temperature of the terminal device is higher than a preset temperature threshold, that is, an overheating problem occurs;
  • the device capability information may also be current storage space information, and the storage space information may indicate that the current available storage space of the terminal device is less than a preset storage space threshold.
  • the device capability information of the terminal device may also be CPU computing capability information, and the CPU computing capability information may indicate that the current CPU computing rate is lower than a preset computing rate threshold. This application does not limit this.
  • the device processing capability information may further include information on changing the accuracy of the AI model of the first model suggested by the terminal device, information on reducing the amount of inference computation suggested by the terminal device, and reducing transmit power suggested by the terminal device information, etc.
  • the network device may acquire the first configuration information based on information such as device capability information sent by the terminal device, and send the first configuration information to the terminal device, so that the terminal device performs corresponding configuration according to the first configuration information.
  • the network device can adjust the data reporting manner of the terminal device for the first model according to the thermal assistance information, and the network device can reduce the amount of data reported by the terminal device, thereby reducing the transmit power of the terminal device.
  • the network device can also reconfigure the AI model used by the terminal device, so that the terminal device can replace the currently used AI model, thereby reducing the overheating problem of the terminal device and reducing the impact on the user experience of the terminal device.
  • the terminal device when it changes the data precision requirement, it can send a configuration information acquisition request to the network device.
  • the terminal device considering the privacy of the terminal device, it is necessary to improve the degree of data preprocessing, so that data irrelevant to the terminal device can be extracted and reported to the network device. Therefore, the terminal device can send the current device capability information.
  • the device capability information can include the data preprocessing method suggested by the terminal device, the information on the accuracy of the AI model, etc., and then the network device can obtain the information based on the device capability information sent by the terminal device. first configuration information, and send the first configuration information to the terminal device. Therefore, the risk of user privacy exposure can be reduced, the security of the terminal device can be enhanced, and the user experience of the terminal device can be guaranteed.
  • a configuration information acquisition request may be sent to the network device.
  • the configuration information acquisition request including the device capability information can also be sent to the network device, and the network device can acquire the first configuration information according to the device capability information sent by the terminal device, and obtain the The first configuration information is sent to the terminal device, so that the terminal device performs corresponding configuration according to the first configuration information.
  • the network device acquires first configuration information for the first model.
  • the terminal device receives the first configuration information from the network device.
  • the terminal device performs corresponding configuration according to the first configuration information.
  • steps 302 to 304 are the same as the specific implementation manners of the above-mentioned steps 201 to 203, which are not repeated here.
  • the terminal device may receive the first configuration information from the network device, update the configuration information of the terminal device itself according to the first configuration information, and then use the data collection, preprocessing and / or reporting method, reporting the collected and preprocessed data to the network device.
  • FIG. 4 is another schematic flowchart of a data acquisition method provided by an embodiment of the present application.
  • the above data acquisition method includes steps 401 to 403 . in:
  • the network device When detecting that the air interface resource is congested, the network device obtains first configuration information for the first model.
  • step 401 is the same as the specific implementation manner of the foregoing step 201, and details are not described herein again.
  • the network device may actively acquire the first configuration information for the first model, and send it to the terminal device.
  • the network device may acquire the first configuration information for the first model when detecting that the air interface resources are limited, such as when the air interface resources are congested.
  • the air interface resource congestion may be detected by a radio resource management (radio resource management, RRM) module of the network device.
  • RRM radio resource management
  • the network device may acquire the first configuration information of the first model according to the currently available number of air interface resources. For example, the network device can use the first configuration information to improve the degree of terminal device preprocessing, and adjust the terminal device data preprocessing method to increase the data compression rate, reduce the amount of data that the terminal device needs to report, and reduce air interface pressure.
  • the network device when the network device detects that the problem of air interface resource congestion is alleviated or recovered, it can obtain the first configuration information for the first model again, and deliver the obtained first configuration information to the terminal device.
  • the terminal device receives the first configuration information from the network device.
  • the terminal device performs corresponding configuration according to the first configuration information.
  • steps 402 to 403 are the same as the specific implementation manners of the foregoing steps 202 to 203 , and details are not described herein again.
  • the terminal device may receive the first configuration information from the network device, update the configuration information of the terminal device itself according to the first configuration information, and then use the data collection, preprocessing and / or reporting method, reporting the collected and preprocessed data to the network device.
  • FIG. 5 and FIG. 6 are schematic flowcharts of an activation method provided by an embodiment of the present application.
  • the terminal device directly activates after receiving the first configuration information.
  • the terminal device performs corresponding configuration for the first model according to the first configuration information, and collects and preprocesses data according to the updated configuration information of the first model, and sends the data to the network device.
  • the direct activation method may be applicable to scenarios in which the terminal device is in a connected state or a non-connected state.
  • the terminal device may store the first configuration information locally and wait for the network device to send an activation message.
  • the network device may issue an activation message within the effective time range of the configuration of the first configuration information, so that after receiving the activation message, the terminal device performs corresponding configuration according to the first configuration information. And the data is reported to the network device according to the updated data collection method, data preprocessing method and/or data reporting method of the first model.
  • the activation message may be a medium access control-control element (MAC CE) message, or the activation message may also be sent to the terminal device as a part of the MAC CE message.
  • MAC CE medium access control-control element
  • the activation method using the activation message is more flexible, and at the same time, when the first configuration information has been stored in the terminal, the activation method using the activation message has faster execution and response speed.
  • the network device may also send a deactivation message to the terminal device, and the deactivation message may also be carried in a MAC CE message, for deactivating the Activate the first configuration information.
  • step 602 and step 603 shown in FIG. 6 may be performed simultaneously, or may be performed sequentially, which is not limited in this application. That is, when the network device sends the first configuration information to the terminal, it can simultaneously deliver the MAC CE message, or it can first send the first configuration information to the terminal device, and then send the MAC CE message for the first model to the terminal device.
  • the foregoing direct activation manner may be combined with the activation manner of issuing an activation message.
  • the terminal device when the terminal device is in the connected state, it may receive an RRC message sent by the network device, and directly activate the terminal to perform configuration according to the first configuration information. It is also possible to receive the MAC CE message for the third configuration information used by the network device sent by the network device, and activate the terminal device to configure according to the third configuration information stored, and the third configuration information is the configuration information of the third model used by the network device,
  • the third configuration information may include a data collection method, a data preprocessing method and/or a data reporting method for the third model.
  • the specific activation method can be determined based on the requirements of the actual application scenario, which is not limited in this application.
  • the terminal device may receive the first configuration information from the network device, update the configuration information of the terminal device itself according to the first configuration information, and then use the data collection, preprocessing and / or reporting method, reporting the collected and preprocessed data to the network device.
  • FIG. 7 shows a schematic structural diagram of a communication apparatus according to an embodiment of the present application.
  • the device may be a terminal device, or a device in the terminal device, or a device that can be used in combination with the terminal device.
  • the communication apparatus shown in FIG. 7 may include a processing unit 701 and a communication unit 702 .
  • the processing unit 701 is used for data processing.
  • the communication unit 702 integrates a receiving unit and a transmitting unit.
  • the communication unit 702 may also be referred to as a transceiving unit. Alternatively, the communication unit 702 can also be divided into a receiving unit and a sending unit.
  • the above-mentioned communication unit 702 is used to receive the first configuration information from the network device; the above-mentioned first configuration information is used to indicate the data collection method, data preprocessing method and/or data reporting method for the first model, and the above-mentioned first model is The artificial intelligence AI model used by the above-mentioned network device; the above-mentioned processing unit 701 is configured to perform corresponding configuration according to the above-mentioned first configuration information.
  • the above-mentioned first configuration information when used to indicate the data collection method, pre-processing method and reporting method for the above-mentioned first model, the above-mentioned first configuration information includes: first indication information, first The second indication information, the third indication information, and the fourth indication information, the first indication information is used to indicate the first model, the second indication information is used to indicate the data collection method, and the third indication information is used to indicate the data preprocessing mode, the above-mentioned fourth indication information is used to indicate the data reporting mode.
  • the communication unit 702 is further configured to send a configuration information acquisition request to the network device, where the configuration information acquisition request is used to request the first configuration information.
  • the configuration information acquisition request includes device capability information of the terminal device.
  • the above-mentioned communication unit 702 sends a configuration information acquisition request to the above-mentioned network device, which is specifically used for: when the processing capability of the device is limited, to send a configuration information acquisition request to the above-mentioned network device; or, when changing data When the accuracy is required, a configuration information acquisition request is sent to the above-mentioned network device.
  • the foregoing processing unit 701 is further configured to report data to the foregoing network device according to the foregoing first configuration information.
  • the above-mentioned communication unit 702 is further configured to receive an activation message sent from the above-mentioned network device, where the above-mentioned activation message is used to activate the configuration according to the above-mentioned first configuration information.
  • the communication unit 702 receives the first configuration information from the network device, and is specifically configured to: receive a radio resource control RRC message from the network device, where the RRC message includes the first configuration information.
  • the above-mentioned first configuration information is further used to indicate the second model; the above-mentioned processing unit 701 is further used to adjust the AI model used by itself according to the above-mentioned second model.
  • the terminal device may receive the first configuration information from the network device, update the configuration information of the terminal device itself according to the first configuration information, and then use the data collection, preprocessing and / or reporting method, reporting the collected and preprocessed data to the network device.
  • the above communication device may be, for example, a chip or a chip module.
  • the modules included in the devices and products described in the above embodiments they may be software modules or hardware modules, or may be partly software modules and partly hardware modules.
  • each module contained therein may be implemented by hardware such as circuits, or at least some modules may be implemented by a software program that runs inside the chip
  • the remaining (if any) modules can be implemented by hardware such as circuits; for each device and product applied to or integrated in the chip module, each module contained therein can be implemented by hardware such as circuits.
  • different modules may be located in the same component (such as a chip, circuit module, etc.) or in different components of the chip module, or at least some modules may be implemented by a software program that runs on the processing integrated inside the chip module
  • the remaining (if any) modules can be implemented by hardware such as circuits; for each device and product applied to or integrated in the terminal, each module included can be implemented by hardware such as circuits, and different modules can be It is located in the same component (for example, chip, circuit module, etc.) or in different components in the terminal, or at least some of the modules can be implemented in the form of software programs.
  • the software program runs on the processor integrated inside the terminal, and the rest (if any) Some modules can be implemented in hardware such as circuits.
  • FIG. 8 shows a schematic structural diagram of another communication apparatus according to an embodiment of the present application.
  • the device may be a network device, or a device in a network device, or a device that can be matched and used with the network device.
  • the communication apparatus shown in FIG. 8 may include a processing unit 801 and a communication unit 802 .
  • the processing unit 801 is used for data processing.
  • the communication unit 802 integrates a receiving unit and a transmitting unit.
  • the communication unit 802 may also be referred to as a transceiving unit.
  • the communication unit 802 can also be divided into a receiving unit and a sending unit.
  • the processing unit 801 is configured to obtain first configuration information for the first model, where the first configuration information is used to indicate a data collection method, data preprocessing method and/or data reporting method for the first model.
  • An artificial intelligence AI model used by the above-mentioned network device; the above-mentioned communication unit 802 is configured to send the first configuration information to the terminal device.
  • the terminal device may receive the first configuration information from the network device, update the configuration information of the terminal device itself according to the first configuration information, and then use the data collection, preprocessing and / or reporting method, reporting the collected and preprocessed data to the network device.
  • the above-mentioned first configuration information when used to indicate the data collection method, pre-processing method and reporting method for the above-mentioned first model, the above-mentioned first configuration information includes: first indication information, first The second indication information, the third indication information, and the fourth indication information, the first indication information is used to indicate the first model, the second indication information is used to indicate the data collection method, and the third indication information is used to indicate the data preprocessing mode, the above-mentioned fourth indication information is used to indicate the data reporting mode.
  • the above-mentioned communication unit 802 is further configured to receive a configuration information acquisition request from the above-mentioned terminal device, where the above-mentioned configuration information acquisition request is used to request the above-mentioned first configuration information.
  • the configuration information acquisition request includes device capability information of the terminal device.
  • the above-mentioned processing unit 801 obtains the first configuration information for the first model, and is specifically configured to obtain the first configuration information for the first model when air interface resource congestion is detected.
  • the above-mentioned communication unit 802 is further configured to receive the data reported by the above-mentioned terminal device according to the above-mentioned first configuration information.
  • the communication unit 802 is further configured to send an activation message to the terminal device, where the activation message is used to activate the configuration of the terminal device according to the first configuration information.
  • the communication unit 802 sends the first configuration information to the terminal device, and is specifically configured to: send a radio resource control RRC message to the terminal device, where the RRC message includes the first configuration information.
  • the above-mentioned first configuration information is further used to indicate the second model used by the above-mentioned terminal device.
  • the above communication device may be, for example, a chip or a chip module.
  • the modules included in the devices and products described in the above embodiments they may be software modules or hardware modules, or may be partly software modules and partly hardware modules.
  • each module contained therein may be implemented by hardware such as circuits, or at least some of the modules may be implemented by a software program that runs inside the chip
  • the remaining (if any) modules can be implemented by hardware such as circuits; for each device and product applied to or integrated in the chip module, each module contained therein can be implemented by hardware such as circuits.
  • different modules may be located in the same component (such as a chip, circuit module, etc.) or different components of the chip module, or at least some modules may be implemented in the form of software programs that run on the processing integrated inside the chip module.
  • the remaining (if any) modules can be implemented by hardware such as circuits; for each device and product applied to or integrated in the terminal, each module included can be implemented by hardware such as circuits, and different modules can be It is located in the same component (for example, chip, circuit module, etc.) or in different components in the terminal, or at least some of the modules can be implemented in the form of software programs.
  • the software program runs on the processor integrated inside the terminal, and the rest (if any) Some modules can be implemented in hardware such as circuits.
  • FIG. 9 is another communication apparatus 90 provided by an embodiment of the present application, which is used to implement the functions of the terminal device in the foregoing FIG. 2 and FIG. 6 .
  • the apparatus may be a terminal device or an apparatus for a terminal device.
  • the means for the terminal device may be a system-on-a-chip or a chip within the terminal device. Wherein, the chip system may be composed of chips, and may also include chips and other discrete devices.
  • the communication apparatus 90 is configured to implement the functions of the network device in the above-mentioned FIG. 2 and FIG. 6 .
  • the apparatus 90 may be a network device or an apparatus for a network device.
  • the means for the network device may be a system-on-a-chip or a chip within the network device.
  • the communication apparatus 90 includes at least one processor 920, configured to implement the data processing function of the terminal device in the method provided in the embodiment of the present application.
  • the apparatus 90 may further include a communication interface 910, configured to implement the sending and receiving operations of the terminal device in the method provided in the embodiment of the present application.
  • the communication interface may be a transceiver, a circuit, a bus, a module or other types of communication interfaces, which are used to communicate with other devices through a transmission medium.
  • the communication interface 910 is used by the apparatus in the apparatus 90 to communicate with other devices.
  • the processor 920 uses the communication interface 910 to send and receive data, and is used to implement the method described above in FIG. 2 in the foregoing method embodiment.
  • Apparatus 90 may also include at least one memory 930 for storing program instructions and/or data.
  • Memory 930 is coupled to processor 920 .
  • the coupling in the embodiments of the present application is an indirect coupling or communication connection between devices, units or modules, which may be in electrical, mechanical or other forms, and is used for information exchange between devices, units or modules.
  • Processor 920 may cooperate with memory 930 .
  • Processor 920 may execute program instructions stored in memory 930 . At least one of the at least one memory described above may be included in the processor.
  • the processor 920 can read the software program in the memory 930, interpret and execute the instructions of the software program, and process the data of the software program.
  • the processor 920 performs baseband processing on the data to be sent, and outputs a baseband signal to a radio frequency circuit (not shown in the figure).
  • the radio frequency circuit performs radio frequency processing on the baseband signal and sends the radio frequency signal through the antenna in the form of electromagnetic waves Send out.
  • the radio frequency circuit receives the radio frequency signal through the antenna, converts the radio frequency signal into a baseband signal, and outputs the baseband signal to the processor 920, and the processor 920 converts the baseband signal into data and processes the data. deal with.
  • the above-mentioned radio frequency circuits and antennas may be provided independently of the processor 920 that performs baseband processing.
  • the radio frequency circuits and antennas may be arranged remotely from the communication device. .
  • connection medium between the communication interface 910 , the processor 920 , and the memory 930 is not limited in the embodiments of the present application.
  • the memory 930, the processor 920, and the communication interface 910 are connected through a bus 940 in FIG. 9.
  • the bus is represented by a thick line in FIG. 9.
  • the connection between other components is only for schematic illustration. , is not limited.
  • the above-mentioned bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of presentation, only one thick line is used in Figure 9, but it does not mean that there is only one bus or one type of bus.
  • the communication interface 910 may output or receive a baseband signal.
  • the output or reception of the communication interface 910 may be a radio frequency signal.
  • the processor may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, which can implement or The methods, operations, and logic block diagrams disclosed in the embodiments of the present application are executed.
  • a general purpose processor may be a microprocessor or any conventional processor or the like. The operations of the methods disclosed in combination with the embodiments of the present application may be directly embodied as being executed by a hardware processor, or executed by a combination of hardware and software modules in the processor.
  • the communication apparatus 90 may execute the relevant steps of the terminal device or the network device in the foregoing method embodiments. For details, reference may be made to the implementation manners provided by the foregoing steps, which will not be repeated here.
  • each module contained therein may be implemented in hardware such as circuits, and different modules may be located in the same component (eg, chip, circuit module, etc.) or different components in the terminal Alternatively, at least some of the modules can be implemented by means of a software program that runs on a processor integrated inside the terminal, and the remaining (if any) partial modules can be implemented by means of hardware such as circuits.
  • Embodiments of the present application further provide a chip, where the chip can execute the relevant steps of the terminal device in the foregoing method embodiments.
  • the above-mentioned chip is used for: receiving the first configuration information from the network device; the above-mentioned first configuration information is used to indicate the data collection method, data preprocessing method and/or data reporting method for the first model, and the above-mentioned first model is the above-mentioned network
  • the artificial intelligence AI model used by the device perform corresponding configuration according to the above first configuration information.
  • the above-mentioned first configuration information when used to indicate the data collection method, pre-processing method and reporting method for the above-mentioned first model, the above-mentioned first configuration information includes: first indication information, first The second indication information, the third indication information, and the fourth indication information, the first indication information is used to indicate the first model, the second indication information is used to indicate the data collection method, and the third indication information is used to indicate the data preprocessing mode, the above-mentioned fourth indication information is used to indicate the data reporting mode.
  • the chip is further configured to: output a configuration information acquisition request to the network device, where the configuration information acquisition request is used to request the first configuration information.
  • the configuration information acquisition request includes device capability information of the terminal device.
  • the above-mentioned chip is used to send a configuration information acquisition request to the above-mentioned network device, and is specifically used for:
  • a configuration information acquisition request is sent to the above-mentioned network device; or, when the data precision requirement is changed, a configuration information acquisition request is output to the above-mentioned network device.
  • the chip is further configured to: the terminal device reports data to the network device according to the first configuration information.
  • the chip is further configured to: receive an activation message sent from the network device, where the activation message is used to activate the configuration according to the first configuration information.
  • the chip is configured to receive first configuration information from a network device, and is specifically configured to: receive a radio resource control RRC message from the network device, where the RRC message includes the first configuration information.
  • the above-mentioned first configuration information is further used to indicate the second model; the above-mentioned chip is further used to adjust the AI model used by itself according to the above-mentioned second model.
  • An embodiment of the present application further provides a chip, where the chip can execute the relevant steps of the network device in the foregoing method embodiments.
  • the chip is used to obtain first configuration information for a first model, where the first configuration information is used to indicate a data collection method, data preprocessing method and/or data reporting method for the first model, and the first model is the above
  • the artificial intelligence AI model used by the network device the first configuration information output to the terminal device.
  • the above-mentioned first configuration information when used to indicate the data collection method, pre-processing method and reporting method for the above-mentioned first model, the above-mentioned first configuration information includes: first indication information, first The second indication information, the third indication information, and the fourth indication information, the first indication information is used to indicate the first model, the second indication information is used to indicate the data collection method, and the third indication information is used to indicate the data preprocessing mode, the above-mentioned fourth indication information is used to indicate the data reporting mode.
  • the chip is further configured to: receive a configuration information acquisition request from the terminal device, where the configuration information acquisition request is used to request the first configuration information.
  • the configuration information acquisition request includes device capability information of the terminal device.
  • the above chip is configured to obtain the first configuration information for the first model, and is specifically configured to obtain the first configuration information for the first model when air interface resource congestion is detected.
  • the chip is further configured to receive data reported by the terminal device according to the first configuration information.
  • the chip is further configured to send an activation message to the terminal device, where the activation message is used to activate the configuration of the terminal device according to the first configuration information.
  • the chip is configured to send the first configuration information to the terminal device, and is specifically configured to: output a radio resource control RRC message to the terminal device, where the RRC message includes the first configuration information.
  • the above-mentioned first configuration information is further used to indicate the second model used by the above-mentioned terminal device.
  • the chip includes at least one processor, at least one first memory, and at least one second memory; wherein, the at least one first memory and the at least one processor are interconnected through a line, and the first memory Instructions are stored in the memory; the at least one second memory and the at least one processor are interconnected through a line, and the data to be stored in the foregoing method embodiments are stored in the second memory.
  • each module contained therein may be implemented by hardware such as circuits, or at least some of the modules may be implemented by a software program that runs on the integrated circuit inside the chip.
  • the processor and the remaining (if any) modules can be implemented in hardware such as circuits.
  • FIG. 10 is a schematic structural diagram of a module device provided by an embodiment of the present application.
  • the module device 100 can perform the relevant steps of the terminal device in the foregoing method embodiments, and the module device 100 includes: a communication module 1001 , a power module 1002 , a storage module 1003 and a chip module 1004 .
  • the above-mentioned communication module 1001 is used for internal communication of the module equipment, or used for the above-mentioned module equipment to communicate with external equipment;
  • the above-mentioned power module 1002 is used to provide power for the above-mentioned module equipment;
  • the above-mentioned storage module 1003 is used for For storing data and instructions;
  • the above-mentioned chip module 1004 is used for:
  • the above-mentioned first configuration information is used to indicate the data collection method, data preprocessing method and/or data reporting method for the first model, and the above-mentioned first model is the artificial intelligence used by the above-mentioned network equipment.
  • AI model perform corresponding configuration according to the above-mentioned first configuration information.
  • the above-mentioned first configuration information when used to indicate the data collection method, pre-processing method and reporting method for the above-mentioned first model, the above-mentioned first configuration information includes: first indication information, first The second indication information, the third indication information, and the fourth indication information, the first indication information is used to indicate the first model, the second indication information is used to indicate the data collection method, and the third indication information is used to indicate the data preprocessing mode, the above-mentioned fourth indication information is used to indicate the data reporting mode.
  • the chip module 1004 is further configured to: output a configuration information acquisition request to the network device, where the configuration information acquisition request is used to request the first configuration information.
  • the configuration information acquisition request includes device capability information of the terminal device.
  • the above-mentioned chip module 1004 is configured to send a configuration information acquisition request to the above-mentioned network device, and is specifically configured to: when the processing capability of the device is limited, send a configuration information acquisition request to the above-mentioned network device; or, When the data precision requirement is changed, a configuration information acquisition request is output to the above-mentioned network device.
  • the chip module 1004 is further configured to: the terminal device reports data to the network device according to the first configuration information.
  • the above-mentioned chip module 1004 is further configured to: receive an activation message sent from the above-mentioned network device, and the above-mentioned activation message is used to activate the configuration according to the above-mentioned first configuration information.
  • the chip module 1004 is configured to receive the first configuration information from the network device, and is specifically configured to: receive a radio resource control RRC message from the network device, where the RRC message includes the first configuration information.
  • the above-mentioned first configuration information is further used to indicate the second model; the above-mentioned chip is further used to adjust the AI model used by itself according to the above-mentioned second model.
  • each module contained therein can be implemented by hardware such as circuits, and different modules can be located in the same component of the chip module (such as a chip, a circuit module, etc.) or In different components, or at least some of the modules can be implemented by means of a software program, the software program runs on the processor integrated inside the chip module, and the remaining (if any) part of the modules can be implemented by means of hardware such as circuits.
  • FIG. 11 is a schematic structural diagram of another module device provided by an embodiment of the present application.
  • the module device 110 can perform the steps related to the access network device in the foregoing method embodiments.
  • the module device 110 includes a communication module 1101 , a power module 1102 , a storage module 1103 and a chip module 1104 .
  • the above-mentioned communication module 1101 is used for internal communication of the module equipment, or used for the above-mentioned module equipment to communicate with external equipment;
  • the above-mentioned power module 1102 is used for providing power for the above-mentioned module equipment;
  • the above-mentioned storage module 1103 is used for For storing data and instructions;
  • the above-mentioned chip module 1104 is used for:
  • first configuration information For the first model, obtain first configuration information, where the first configuration information is used to indicate a data collection method, a data preprocessing method and/or a data reporting method for the first model, and the first model is a manual method used by the network device. Intelligent AI model; the first configuration information output to the terminal device.
  • the above-mentioned first configuration information when used to indicate the data collection method, pre-processing method and reporting method for the above-mentioned first model, the above-mentioned first configuration information includes: first indication information, first The second indication information, the third indication information, and the fourth indication information, the first indication information is used to indicate the first model, the second indication information is used to indicate the data collection method, and the third indication information is used to indicate the data preprocessing mode, the above-mentioned fourth indication information is used to indicate the data reporting mode.
  • the above-mentioned chip module 1104 is further configured to: receive a configuration information acquisition request from the above-mentioned terminal device, where the above-mentioned configuration information acquisition request is used to request the above-mentioned first configuration information.
  • the configuration information acquisition request includes device capability information of the terminal device.
  • the chip module 1104 is configured to obtain the first configuration information for the first model, and is specifically configured to obtain the first configuration information for the first model when air interface resource congestion is detected.
  • the above-mentioned chip module 1104 is further configured to receive the data reported by the above-mentioned terminal device according to the above-mentioned first configuration information.
  • the chip module 1104 is further configured to send an activation message to the terminal device, where the activation message is used to activate the configuration of the terminal device according to the first configuration information.
  • the above-mentioned chip module 1104 is configured to send the first configuration information to the terminal device, and is specifically configured to: output a radio resource control RRC message to the above-mentioned terminal device, where the above-mentioned RRC message includes the above-mentioned first configuration information .
  • the above-mentioned first configuration information is further used to indicate the second model used by the above-mentioned terminal device.
  • each module contained therein can be implemented by hardware such as circuits, and different modules can be located in the same component of the chip module (such as a chip, a circuit module, etc.) or In different components, or at least some of the modules can be implemented by means of a software program, the software program runs on the processor integrated inside the chip module, and the remaining (if any) part of the modules can be implemented by means of hardware such as circuits.
  • Embodiments of the present application further provide a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the computer-readable storage medium is executed on a processor, the method flow of the foregoing method embodiment is implemented.
  • the embodiments of the present application further provide a computer program product, and when the computer program product is executed on a processor, the method process of the above method embodiment can be realized.

Abstract

本申请实施例公开了一种数据获取方法及装置，该数据获取方法包括：终端设备接收来自网络设备的第一配置信息；所述第一配置信息用于指示针对第一模型的数据采集方式、数据预处理方式和/或数据上报方式，所述第一模型为所述网络设备使用的人工智能AI模型；所述终端设备根据所述第一配置信息，进行相应的配置。采用本申请所提出的方法，有利于更好的应对通信环境和资源的变化，增强通信网络的性能。

Description

一种数据获取方法及装置 技术领域
本申请涉及通信技术领域，具体涉及一种数据获取方法及装置。
背景技术
人工智能(artificial intelligence，AI)技术的发展，促进了通信网络的自动化和智能化。现有技术中，网络设备基于终端设备上报的数据进行AI模型的训练和推理。但是，终端设备上报的数据是基于静态配置信息采集和处理得到的，这种静态配置信息采用预定义方式配置，不会发生变化。因此，这种数据采集和处理方式不能很好的应对通信环境或资源的变化，有可能会降低通信性能。
发明内容
本申请实施例提供一种数据获取方法及装置，终端设备可以根据来自网络设备的配置信息进行相应的配置，有利于更好的应对通信环境和资源的变化，增强通信网络的性能。
第一方面，本申请实施例提供了一种数据获取方法，该方法包括：
终端设备接收来自网络设备的第一配置信息；所述第一配置信息用于指示针对第一模型的数据采集方式、数据预处理方式和/或数据上报方式，所述第一模型为所述网络设备使用的人工智能AI模型；所述终端设备根据所述第一配置信息，进行相应的配置。
基于第一方面描述的方法，在本申请实施例中，终端设备可以接收来自网络设备的第一配置信息，并根据该第一配置信息更新终端设备自身的配置信息，进而使用更新后的配置信息中的数据采集、预处理和/或上报方式，将经过采集并预处理后的数据上报至网络设备。通过网络设备动态配置终端设备的配置信息，可以更好的应对通信环境或者资源的变化，有利于增强通信网络的性能。
结合第一方面，在一种可能的实现方式中，当所述第一配置信息用于指示针对所述第一模型的数据采集方式、预处理方式和上报方式时，所述第一配置信息，包括：
第一指示信息、第二指示信息、第三指示信息、第四指示信息，所述第一指示信息用于指示所述第一模型，所述第二指示信息用于指示数据采集方式，所述第三指示信息用于指示数据预处理方式，所述第四指示信息用于指示数据上报方式。
结合第一方面，在一种可能的实现方式中，其特征在于，所述方法还包括：
所述终端设备向所述网络设备发送配置信息获取请求，所述配置信息获取请求用于请求所述第一配置信息。
结合第一方面，在一种可能的实现方式中，所述配置信息获取请求包括所述终端设备的设备能力信息。
结合第一方面，在一种可能的实现方式中，所述终端设备向所述网络设备发送配置信息获取请求，包括：
所述终端设备当设备处理能力受限时，向所述网络设备发送配置信息获取请求；或者，
所述终端设备当变更数据精度要求时，向所述网络设备发送配置信息获取请求。
结合第一方面，在一种可能的实现方式中，所述方法还包括：
所述终端设备根据所述第一配置信息，向所述网络设备上报数据。
结合第一方面，在一种可能的实现方式中，所述方法还包括：
所述终端设备接收来自所述网络设备发送激活消息，所述激活消息用于激活根据所述第一配置信息的配置。
结合第一方面，在一种可能的实现方式中，所述终端设备接收来自网络设备的第一配置信息，包括：
所述终端设备接收来自网络设备无线资源控制RRC消息，所述RRC消息包括所述第一配置信息。
结合第一方面，在一种可能的实现方式中，所述第一配置信息还用于指示第二模型；所述方法还包括：
所终端设备根据所述第二模型，调整自身使用的AI模型。
第二方面，本申请提供了一种数据获取方法，该方法包括：
网络设备针对第一模型，获取第一配置信息，所述第一配置信息用于指示针对第一模型的数据采集方式、数据预处理方式和/或数据上报方式，所述第一模型为所述网络设备使用的人工智能AI模型；所述网络设备向终端设备发送第一配置信息。
基于第二方面描述的方法，在本申请实施例中，终端设备可以接收来自网络设备的第一配置信息，并根据该第一配置信息更新终端设备自身的配置信息，进而使用更新后的配置信息中的数据采集、预处理和/或上报方式，将经过采集并预处理后的数据上报至网络设备。通过网络设备动态配置终端设备的配置信息，可以更好的应对通信环境或者资源的变化，有利于增强通信网络的性能。
结合第二方面，在一种可能的实现方式中，当所述第一配置信息用于指示针对所述第一模型的数据采集方式、预处理方式和上报方式时，所述第一配置信息，包括：
第一指示信息、第二指示信息、第三指示信息、第四指示信息，所述第一指示信息用于指示所述第一模型，所述第二指示信息用于指示数据采集方式，所述第三指示信息用于指示数据预处理方式，所述第四指示信息用于指示数据上报方式。
结合第二方面，在一种可能的实现方式中，所述方法还包括：
所述网络设备接收到来自所述终端设备的配置信息获取请求，所述配置信息获取请求用于请求所述第一配置信息。
结合第二方面，在一种可能的实现方式中，所述配置信息获取请求包括所述终端设备的设备能力信息。
结合第二方面，在一种可能的实现方式中，所述网络设备针对第一模型，获取第一配置信息，包括：
所述网络设备检测到空口资源拥塞时，针对第一模型，获取第一配置信息。
结合第二方面，在一种可能的实现方式中，所述方法还包括：
所述网络设备接收所述终端设备根据所述第一配置信息上报的数据。
结合第二方面，在一种可能的实现方式中，所述方法还包括：
所述网络设备向所述终端设备发送激活消息，所述激活消息用于激活所述终端设备根据所述第一配置信息的配置。
结合第二方面，在一种可能的实现方式中，所述网络设备向终端设备发送第一配置信息，包括：
所述网络设备向所述终端设备发送无线资源控制RRC消息，所述RRC消息包括所述第一配置信息。
结合第二方面，在一种可能的实现方式中，所述第一配置信息还用于指示所述终端设备使用的第二模型。
第三方面，本申请实施例提供一种通信装置，该通信装置用于实现上述第一方面或第二方面及其任一种可能的实现方式中的方法的单元。
第四方面，本申请提供了一种通信装置，所述通信装置包括处理器，所述处理器用于执行第一方面或第二方面及其任一种可能的实现方式中的方法。
第五方面，本申请提供了一种通信装置，所述通信装置包括处理器和存储器，所述存储器用于存储计算机执行指令；所述处理器用于从所述存储器调用所述程序代码执行第一方面或第二方面及其任一种可能的实现方式中的方法。
第六方面，本申请提供了一种通信装置，所述通信装置包括处理器和收发器，所述收发器，用于接收信号或者发送信号；所述处理器，用于执行第一方面或第二方面及其任一种可能的实现方式中的方法。
第七方面，本申请提供了一种通信装置，所述通信装置包括处理器、存储器和收发器，所述收发器，用于接收信号或者发送信号；所述存储器，用于存储程序代码；所述处理器，用于从所述存储器调用所述程序代码执行如第一方面或第二方面及其任一种可能的实现方式中的方法。
第八方面，本申请提供了一种芯片，该芯片，用于接收来自网络设备的第一配置信息；所述第一配置信息用于指示针对第一模型的数据采集方式、数据预处理方式和/或数据上报方式，所述第一模型为所述网络设备使用的人工智能AI模型；该芯片，还用于根据所述第一配置信息，进行相应的配置。
第九方面，本申请提供了一种芯片，该芯片，用于针对第一模型，获取第一配置信息，所述第一配置信息用于指示针对第一模型的数据采集方式、数据预处理方式和/或数据上报方式，所述第一模型为所述网络设备使用的人工智能AI模型；该芯片，还用于向终端设备输出的第一配置信息。
第十方面，本申请提供了一种模组设备，该模组设备包括通信模组、电源模组、存储模组以及芯片模组，其中：该通信模组用于进行模组设备内部通信，或者用于该模组设备与外部设备进行通信；该电源模组用于为该模组设备提供电能；该存储模组用于存储数据 和指令；该芯片模组用于：接收来自网络设备的第一配置信息；该第一配置信息用于指示针对第一模型的数据采集方式、数据预处理方式和/或数据上报方式，该第一模型为该网络设备使用的人工智能AI模型；根据该第一配置信息，进行相应的配置。
第十一方面，本申请提供了一种模组设备，其特征在于，该模组设备包括通信模组、电源模组、存储模组以及芯片模组，其中：该通信模组用于进行模组设备内部通信，或者用于该模组设备与外部设备进行通信；该电源模组用于为该模组设备提供电能；该存储模组用于存储数据和指令；该芯片模组用于：针对第一模型，获取第一配置信息，该第一配置信息用于指示针对第一模型的数据采集方式、数据预处理方式和/或数据上报方式，该第一模型为该网络设备使用的人工智能AI模型；向终端设备输出的第一配置信息。
第十二方面，本申请提供了一种计算机可读存储介质，该计算机存储介质中存储有计算机可读指令，当该计算机可读指令在通信装置上运行时，使得该通信装置执行上述第一方面或第二方面及其任一种可能的实现方式中的方法。
第十三方面，本申请提供一种计算机程序或计算机程序产品，包括代码或指令，当代码或指令在计算机上运行时，使得计算机执行如第一方面或第二方面的方法。
附图说明
为了更清楚地说明本申请实施例技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图是本申请的一些实施例，对于本普通技术人员来讲，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为本申请实施例提供的一种通信系统的系统结构示意图；
图2为本申请实施例提供的一种数据获取方法的流程示意图；
图3为本申请实施例提供的一种数据获取方法的另一流程示意图；
图4为本申请实施例提供的一种数据获取方法的又一流程示意图；
图5为本申请实施例提供的一种激活方式的流程示意图；
图6为本申请实施例提供的另一种激活方式的流程示意图；
图7为本申请实施例提供的一种通信装置的结构示意图；
图8为本申请实施例提供的另一种通信装置的结构示意图；
图9为本申请实施例提供的又一种通信装置的结构示意图；
图10为本申请实施例提供的一种模组设备的结构示意图；
图11为本申请实施例提供的另一种模组设备的结构示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，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，都属于本申请保护的范围。
应理解，本文中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本文中字符“/”，表示前后关联对象是一种“或”的关系。
本申请实施例中出现的“多个”是指两个或两个以上。
本申请实施例中出现的第一、第二等描述，仅作示意与区分描述对象之用，没有次序之分，也不表示本申请实施例中对设备个数的特别限定，不能构成对本申请实施例的任何限制。
本申请实施例中出现的“连接”是指直接连接或者间接连接等各种连接方式，以实现设备间的通信，本申请实施例对此不做任何限定。
请参阅图1，图1为本申请实施例提供的一种通信系统的系统结构示意图，该通信系统可以包括但不限于一个网络设备和一个终端设备，图1所示的设备数量和形态用于举例并不构成对本申请实施例的限定，实际应用中可以包括一个以上的网络设备，一个以上的终端设备。图1所示的通信系统以一个网络设备10和一个终端设备11为例进行阐述，终端设备11可以接收来自网络设备10的第一配置信息。
在本申请实施例中，终端设备也可以称为终端、用户设备(User Equipment，UE)、接入终端、用户单元、用户站、移动站、移动台、远方站、远程终端、移动设备、用户终端、用户代理或用户装置。本申请的实施例中的终端设备可以是手机(mobile phone)、平板电脑(Pad)、带无线收发功能的电脑、虚拟现实(virtual reality，VR)终端设备、增强现实(augmented reality，AR)终端设备、工业控制(industrial control)中的无线终端、无人驾驶(self driving)中的无线终端、远程医疗(remote medical)中的无线终端、智能电网(smart grid)中的无线终端、运输安全(transportation safety)中的无线终端、智慧城市(smart city)中的无线终端、智慧家庭(smart home)中的无线终端等。
本申请中，网络设备10是终端设备11通过无线方式接入到该移动通信系统中的接入设备，可以是基站NodeB、演进型基站(evolved NodeB，eNodeB)、发送接收点(transmission reception point，TRP)、5G移动通信系统中的下一代基站(next generation NodeB，gNB)、未来移动通信系统中的基站或WiFi系统中的接入节点等；也可以是完成基站部分功能的模块或单元，例如，可以是集中式单元(central unit，CU)，也可以是分布式单元(distributed unit，DU)。本申请的实施例对无线接入网设备所采用的具体技术和具体设备形态不做限定。在本申请中，网络设备还可以称为无线接入网设备，如果无特殊说明，无线接入网设备均指网络设备。
随着AI技术的发展，在通信系统中应用AI技术可以增强通信网络的性能，促进通信网络的自动化和智能化。例如，网络设备可以使用终端设备上报的数据对AI模型进行训练和预测。目前，终端设备上报的数据是基于静态配置信息采集和处理得到的，这种静态配置信息是预定义方式配置的，不会发生变化。当通信环境或者资源发生变化时，终端设备仍然根据静态配置信息对数据进行采集和处理，上报的数据有可能无法满足网络需求，因此，这种数据采集和处理方式无法很好的应对通信环境或资源的变化，在一定程度上会导 致通信性能降低。
本申请提出一种数据获取方法。该数据获取方法中，终端设备接收来自网络设备的第一配置信息，该第一配置信息用于指示针对第一模型的数据采集方式、数据预处理方式和/或数据上报方式，其中，第一模型为网络设备使用的AI模型，终端设备根据该第一配置信息，进行相应的配置。可见，终端设备可以接收来自网络设备的第一配置信息，并根据该第一配置信息更新终端设备自身的配置信息，进而使用更新后的配置信息中的数据采集、预处理和/或上报方式，将经过采集并预处理后的数据上报至网络设备。通过网络设备动态配置终端设备的配置信息，可以更好的应对通信环境或者资源的变化，有利于增强通信网络的性能。
下面基于上述内容中介绍的通信系统及设备，对本申请实施例提供一种数据获取方法进行介绍，请参阅图2，图2为本申请实施例提供的一种数据获取方法的流程示意图，该数据获取方法包括步骤201-步骤203，其中：
201、网络设备针对第一模型，获取第一配置信息。
本申请实施例中，网络设备可以训练和使用多个AI模型，需要说明的是，本申请以网络设备使用的AI模型为第一模型为例进行讲解，第一模型为网络设备使用的多个AI模型中的任一AI模型。第一配置信息为网络设备根据第一模型获取的配置信息，第一配置信息用于指示终端设备针对第一模型的数据采集方式、预处理方式和上报方式。需要说明的是，本申请以第一模型为例进行讲解。
第一配置信息可以包括四个指示信息中的一项或多项。第一指示信息，用于指示第一模型。示例性的，第一指示信息可以包括AI模型的标识(AI model index)、AI模型配置标识，也可以包括功能标识(use case id)。
第二指示信息，用于指示数据采集方式。示例性的，第二指示信息可以包括终端设备采集数据的频率，也可以包括数据的采集间隔。
第三指示信息，用于指示数据预处理方式。示例性的，第三指示信息可以包括对采集到的数据进行预处理的步骤和每个步骤的具体操作，如数据清洗。
第四指示信息，用于指示数据的上报方式，示例性的，第四指示信息可以包括上报数据周期，也可以包括上报数据次数。
需要说明的是，若第一指示信息指示了第一模型，则第二指示信息、第三指示信息、第四指示信息均为针对该第一模型的指示信息。即第二指示信息为指示第一模型的数据采集方式的指示信息，第三指示信息为指示第一模型数据预处理方式的指示信息，第四指示信息为指示第一模型的数据上报方式的指示信息。
第一配置信息的获取方式可以是根据第一模型的精度要求、终端设备的处理能力、空口资源受限情况等指标，从预设的配置信息中得到的；也可以是基于一种指标，从预设的配置信息中得到的；还可以是根据预设的算法，基于上述一种或多种指标，计算出的配置信息；还可以是从其他设备接收到的配置信息。本申请对第一配置信息的获取方式不做限 定。
在一种可能的实现方式中，网络设备获取第一配置信息中的指示信息后，按照预设的格式向终端设备发送该第一配置信息。其中，预设的格式可以为：
Figure PCTCN2022074979-appb-000001
其中，第一指示信息，可以包括use case id。use case id为用例标识符，该字段指示了应用该第一配置信息的AI功能用例，以及该AI功能用例所使用的AI模型标识。示例性的，use case id为3，则指示第一模型的use case id为3，则该第一配置信息中的第二指示信息、第三指示信息以及第四指示信息均为use case id为3对应的数据采集方式、预处理方式以及上报方式。若第一指示信息缺省，则可以表示该第一配置信息中的第二指示信息、第三指示信息、第四指示信息可应用于所有AI功能用例。
在一种可能的实现方式中，第一指示信息有两种表示方式，第一种表示方式为模型的标识。示例性的，与定位相关的模型有三种：model1、model2和model3。在接收到第一指示信息中的use case id为3时，第一指示信息可以指示网络设备使用的第一模型为与定位相关的model3。第二种表示方式为功能和模型的组合标识，示例性的，定位use case id为01，信道估计use case id为02，信道编码use case id为03，与定位功能相关的模型id有01，02，03；与信道估计和信道编码相关的模型id均有01，02，03；则第一指示信息可以为0101，则第一指示信息可以指示网络设备使用的第一模型为与定位相关的模型01。
在一种可能的实现方式中，第一配置信息中的第一指示信息还可以指示第二模型，该第二模型为终端设备使用的模型。可以理解的是，终端设备也可以使用AI模型实现网络功能，和/或进行数据的采集和数据的预处理，则第一指示信息还可以指示终端设备根据第二模型调整自身使用的AI模型。
第二指示信息，可以包括采样频率/间隔。采样频率/间隔可以用于指示终端设备对第一模型的数据进行采集时的采样频率和采样时长。示例性的，针对第一模型，终端设备每10秒(s)采集一次，每次采集1s。
第三指示信息，可以包括数据预处理步骤，数据预处理步骤用于指示终端对于第一模型的数据进行预处理的步骤。示例性的，预处理的步骤可以包括数据清洗、特征提取、数据压缩等等。
第四指示信息，可以包括上报数据维度、上报数据周期、上报数据次数。上报数据维度的字段用于指示终端设备针对第一模型，需要采集/测量和上传的指标种类和数量。示例性的，以第一模型为定位功能的模型为例，则第二指示信息指示终端上报的信息可以包括测量信息的种类和数量，如参考信号接收功率、参考信号接收质量等等。上报数据周期用于指示终端设备进行数据上报的周期。示例性的，针对第一模型，终端设备可以每5s执行一次数据上报；再例如，针对第一模型，终端设备可以非周期性的执行一次数据上报。上报数据次数用于指示终端设备进行数据上报的次数。示例性的，针对第一模型，终端设备需上报100次，在上报100次后停止继续上报。可以理解的是，当达到上报数据次数时，可以恢复默认设置，也可以是恢复为上一次配置信息配置的上报数据次数，还可以是与网络设备协商，请求网络设备发送配置信息，本申请在此不作限定。
在一种可能的实现方式中，第一配置信息还包括配置生效时间，配置生效时间可以为相对时间，即在定时器(timer)的定时时长范围内该第一配置信息有效；配置生效时间也可以为绝对时间，即在某个时刻之前，该第一配置信息有效。可以理解的是，在有效期过期后，终端设备可以恢复默认设置，也可以是恢复为上一次配置信息中的数据采集方式、预处理方式和上报方式，还可以是与网络设备协商，请求网络设备发送配置信息，本申请在这里不做限定。
其中，optional表示该字段可以缺省，若某一个字段缺省，则代表该字段应用静态配置信息的默认指示信息。示例性的，若该第一配置信息中采样相关{采样频率/间隔}的字段缺省，则终端设备可以从本地提取静态配置信息中use case id对应的采样频率/间隔。
202、终端设备接收来自网络设备的第一配置信息。
在一种可能的实现方式中，终端设备在处于连接态(RRC Connected)时，网络设备可以通过无线资源控制(Radio Resource Control，RRC)信令将第一配置信息发送至终端设备，终端设备可以通过接收来自网络设备的RRC消息来更新配置信息，该RRC消息中包括上述第一配置信息。
在一种可能的实现方式中，终端设备在处于连接态(RRC Connected)时，接收来自网络设备的RRC释放(release)消息，该RRC release消息中包括上述第一配置信息。进而，终端设备在接收到RRC release消息后，释放链路，切换至非连接态，即空闲态(RRC IDLE)/非激活态(RRC Inactive)。从而能够保证空闲态(RRC IDLE)/非激活态(RRC Inactive)的终端设备有序的参与AI模型的训练和预测，提高AI功能的精度。
可以理解的是，网络设备针对连接态的终端设备，和即将进入空闲态/非激活态的终端 设备获取到的第一配置信息的内容可以相同，也可以不同。
203、终端设备根据第一配置信息，进行相应的配置。
在一种可能的实现方式中，终端设备处于连接态时，接收到第一配置信息，可以向网络设备返回接收消息，该接收响应消息指示终端设备确认接第一配置信息。
在一种可能的实现方式中，终端设备基于接收到的第一配置信息，对第一模型的数据采集方式、数据预处理方式和/或数据上报方式进行对应的更新。其中，终端设备当前存储的可以是静态配置信息中的第一模型的数据采集方式、数据预处理方式和/或数据上报方式；也可以是上一次网络设备发送第一配置信息更新后，针对第一模型的数据采集方式、数据预处理方式和/或数据上报方式。
示例性的，使用第一配置信息中的数据采集方式，更新静态配置信息中第一模型对应的数据采集方式；使用第一配置信息中的数据预处理方式，更新静态配置信息中第一模型对应的数据预处理方式；使用第一配置信息中的数据上报方式，更新静态配置信息中第一模型对应的数据上报方式。若第一配置信息某一个字段缺省，则保留静态配置信息中该缺省字段的默认值。
进一步的，终端设备根据第一配置信息，向网络设备上报数据。以第一模型为例，终端设备根据更新后的第一模型的配置信息，进行数据的采集、预处理，并上报至网络设备。
具体的，终端设备可以根据第一配置信息中的第一指示信息确定第一模型；进而根据第一配置信息中的第二指示信息指示的数据采集方式，对第一模型的数据进行数据采集；根据第一配置信息中的第三指示信息指示的数据预处理方式，对采集到的数据进行预处理；进而根据第一配置信息中的第四指示信息指示的数据上报方式，将预处理后的数据上报至网络设备。
示例性的，以网络设备为了训练model3，需要终端设备上报500次数据作为训练数据。则网络设备发送的第一配置信息可以为：
{
数据相关{
3，
信号强度信息，
数据清洗，特征提取，
}
采样相关{
每10s采集一次，
每次采集1s，
}
上报相关{
每5s执行一次上报，
上报500次，
}
配置生效时间(定时器，超期丢弃配置)
…
}
则终端设备在定时器的定时时长范围内，需要上报的数据为model3的信号强度信息；数据预处理的方式为数据清洗、特征提取；数据采集方式为每10s采集一次，每次采集1s；数据上报方式为上报500次。则网络设备可以根据接收到的终端设备上报的数据完成对model3的训练。
在一种可能的实现方式中，第一配置信息中的第一指示信息还可以指示第二模型，该第二模型为终端设备使用的模型。示例性的，终端设备可以将第二模型作为该use case id对应的模型。
可选的，非激活态的终端设备可以发起小数据传输(small data transmission，SDT)，将预处理后的数据上报至网络设备。
在本申请实施例中，终端设备可以接收来自网络设备的第一配置信息，并根据该第一配置信息更新终端设备自身的配置信息，进而使用更新后的配置信息中的数据采集、预处理和/或上报方式，将经过采集并预处理后的数据上报至网络设备。通过网络设备动态配置终端设备的配置信息，可以更好的应对通信环境或者资源的变化，有利于增强通信网络的性能。
请参阅图3，图3为本申请实施例提供的一种数据获取方法的另一流程示意图。上述数据获取方法包括步骤301-步骤304。其中：
301、终端设备向网络设备发送配置信息获取请求。
在一种可能的实现方式中，终端设备可以向网络设备发送配置信息更新请求，该配置信息更新请求用于请求获取第一配置信息。第一配置信息用于指示针对第一模型的数据采集方式、数据预处理方式和/或数据上报方式，第一模型为网络设备使用的AI模型。
其中，配置信息获取请求可以包括终端设备的设备能力信息，配置信息获取请求也可以包括数据精度要求信息，还可以包括其他信息，本申请对此不做限定。
具体的，终端设备的设备能力信息可以用于指示当前终端设备的处理能力。其中，设备处理能力信息可以包括存储空间信息，也可以包括中央处理器(central processing unit，CPU)的运算能力信息、终端设备的热辅助信息等等。
在一种可能的实现方式中，终端设备当设备处理能力受限时，可以向网络设备发送配置信息获取请求。其中，终端设备当设备处理能力受限时，终端设备的设备能力信息可以是热辅助信息，该热辅助信息可以指示当前终端设备温度高于预设的温度阈值，即出现过热问题；终端设备的设备能力信息还可以是当前的存储空间信息，该存储空间信息可以指示当前终端设备可用的存储空间小于预设存储空间阈值。终端设备的设备能力信息还可以是CPU运算能力信息，该CPU运算能力信息可以指示当前CPU运算速率低于预设的运算 速率阈值。本申请对此不作限定。
在一种可能的实现方式中，设备处理能力信息还可以包括终端设备建议的第一模型的变更AI模型的精度的信息、终端设备建议的降低推理计算量的信息、终端设备建议的降低发射功率的信息等等。则网络设备可以基于终端设备发送的设备能力信息等信息，获取第一配置信息，并将第一配置信息发送至终端设备，以使终端设备根据第一配置信息进行相应的配置。
例如，网络设备可以根据热辅助信息调整终端设备针对第一模型的数据上报方式，网络设备可以降低终端设备上报的数据量，从而降低终端设备的发射功率。再例如，网络设备也可以重新配置终端设备使用的AI模型，以使终端设备更换当前使用的AI模型，从而减轻终端设备的过热问题，降低对终端设备用户体验的影响。
在一种可能的实现方式中，终端设备当变更数据精度要求时，可以向网络设备发送配置信息获取请求。示例性的，终端设备处于隐私性考虑，需要提高数据预处理的程度，从而能够提取出与终端设备无关的数据上报至网络设备。从而终端设备可以发送当前的设备能力信息，该设备能力信息可以包括终端设备建议的数据预处理方式，对AI模型精度要求信息等等信息，进而网络设备可以基于终端设备发送的设备能力信息，获取第一配置信息，并将第一配置信息发送至终端设备。从而能够降低用户隐私暴露风险，增强终端设备安全性，保障终端设备的用户体验。
在一种可能的实现方式中，终端设备能力不受限时，可以向网络设备发送配置信息获取请求。同理，当终端能力不受限时，也可以将包含设备能力信息的配置信息获取请求发送至网络设备，网络设备可以根据终端设备发送的设备能力信息，获取第一配置信息，并将获取到的第一配置信息发送至终端设备，以使终端设备根据第一配置信息，进行相应的配置。
302、网络设备针对第一模型，获取第一配置信息。
303、终端设备接收来自网络设备的第一配置信息。
304、终端设备根据第一配置信息，进行相应的配置。
其中，步骤302-步骤304的具体实现方式与上述步骤201-步骤203的具体实现方式相同，在此不再赘述。
在本申请实施例中，终端设备可以接收来自网络设备的第一配置信息，并根据该第一配置信息更新终端设备自身的配置信息，进而使用更新后的配置信息中的数据采集、预处理和/或上报方式，将经过采集并预处理后的数据上报至网络设备。通过网络设备动态配置终端设备的配置信息，可以更好的应对通信环境或者资源的变化，有利于增强通信网络的性能。
请参阅图4，图4是本申请实施例提供的一种数据获取方法的又一流程示意图。上述数据获取方法包括步骤401-步骤403。其中：
401、网络设备检测到空口资源拥塞时，针对第一模型，获取第一配置信息。
其中，步骤401的具体实现方式与上述步骤201的具体实现方式相同，在此不再赘述。
需要说明的是，在一种可能的实现方式中，网络设备可以主动针对第一模型，获取第一配置信息，并发送至终端设备。
示例性的，网络设备可以在检测到空口资源受限时，如空口资源拥塞时，针对第一模型，获取第一配置信息。其中，空口资源拥塞可以为网络设备无线资源管理(radio resource management，RRM)模块检测到的。示例性的，当网络设备检测到当前可用的空口资源数量小于预设空口资源阈值时，可以根据当前可用的空口资源数量，获取第一模型的第一配置信息。例如，网络设备可以通过第一配置信息提高终端设备预处理的程度，调整终端设备数据预处理方式，使得数据压缩率增高，终端设备需要上报的数据量减少，减少空口压力。
进一步的，当网络设备检测到空口资源拥塞的问题缓解或者恢复，可以再次针对第一模型，获取第一配置信息，并将获取到的第一配置信息下发至终端设备。
402、终端设备接收来自网络设备的第一配置信息。
403、终端设备根据第一配置信息，进行相应的配置。
其中，步骤402-步骤403的具体实现方式与上述步骤202-步骤203的具体实现方式相同，在此不再赘述。
在本申请实施例中，终端设备可以接收来自网络设备的第一配置信息，并根据该第一配置信息更新终端设备自身的配置信息，进而使用更新后的配置信息中的数据采集、预处理和/或上报方式，将经过采集并预处理后的数据上报至网络设备。通过网络设备动态配置终端设备的配置信息，可以更好的应对通信环境或者资源的变化，有利于增强通信网络的性能。
请一并参阅图5和图6，图5和图6均为本申请实施例提供的一种激活方式的流程示意图。
在一种可能的实现方式中，如图5所示，在终端设备接收到第一配置信息后，直接激活。终端设备根据第一配置信息，针对第一模型，进行相应的配置，以及根据更新后的第一模型的配置信息，进行数据的采集、预处理，并发送至网络设备。其中，直接激活的方式可以适用于终端设备处于连接态和非连接态的场景。
在一种可能的实现方式中，如图6所示，在终端设备接收到第一配置信息后，可以在终端设备处于连接态时，当该第一配置信息并不立即适用的情况下，终端设备可以将第一配置信息存储在本地，并等待网络设备发送激活消息。
网络设备可以在该第一配置信息的配置生效时间范围内，下发激活消息，以使终端设备在接收到激活消息后，根据第一配置信息，进行相应的配置。并根据更新后的第一模型的数据采集方式、数据预处理方式和/或数据上报方式，将数据上报给网络设备。其中，激活消息可以为媒体接入控制控制元素(medium access control-control element，MAC CE)消息，或者激活消息也可以作为MAC CE消息的一部分，下发至终端设备。
相比直接激活的方式，使用激活消息的激活方式更加灵活，同时在第一配置信息已经存储至终端时，使用激活消息的激活方式具有更快的执行和响应速度。
在一种可能的实现方式中，网络设备还可以向终端设备发送去激活消息，该去激活消息也可以承载于MAC CE消息中，用于在上述第一配置信息的配置生效时间范围内，去激活该第一配置信息。
在一种可能的实现方式中，如图6所示的步骤602和步骤603可以同时执行，也可以先后执行，本申请对此不作限定。即网络设备在向终端发送第一配置信息时，可以同时下发MAC CE消息，也可以先向终端设备发送第一配置信息，再向终端设备发送针对第一模型的MAC CE消息。
在一种可能的实现方式中，上述直接激活的方式可以与下发激活消息激活的方式结合起来。示例性的，当终端设备处于连接态时，可以接收网络设备发送的RRC消息，直接激活终端根据第一配置信息进行配置。也可以接收网络设备发送的针对网络设备使用的第三配置信息的MAC CE消息，激活终端设备根据存储的第三配置信息进行配置，第三配置信息为网络设备使用的第三模型的配置信息，第三配置信息中可以包括针对第三模型的数据采集方式、数据预处理方式和/或数据上报方式。具体的激活方式可以基于实际应用场景需求确定，本申请在此不作限制。
在本申请实施例中，终端设备可以接收来自网络设备的第一配置信息，并根据该第一配置信息更新终端设备自身的配置信息，进而使用更新后的配置信息中的数据采集、预处理和/或上报方式，将经过采集并预处理后的数据上报至网络设备。通过网络设备动态配置终端设备的配置信息，可以更好的应对通信环境或者资源的变化，有利于增强通信网络的性能。
请参阅图7，图7示出了本申请实施例的一种通信装置的结构示意图。该装置可以是终端设备，也可以是终端设备中的装置，或者是能够和终端设备匹配使用的装置。图7所示的通信装置可以包括处理单元701和通信单元702。其中，处理单元701，用于进行数据处理。通信单元702集成有接收单元和发送单元。通信单元702也可以称为收发单元。或者，也可将通信单元702拆分为接收单元和发送单元。
上述通信单元702，用于接收来自网络设备的第一配置信息；上述第一配置信息用于指示针对第一模型的数据采集方式、数据预处理方式和/或数据上报方式，上述第一模型为上述网络设备使用的人工智能AI模型；上述处理单元701，用于根据上述第一配置信息，进行相应的配置。
在一种可能的实现方式中，当上述第一配置信息用于指示针对上述第一模型的数据采集方式、预处理方式和上报方式时，上述第一配置信息，包括：第一指示信息、第二指示信息、第三指示信息、第四指示信息，上述第一指示信息用于指示上述第一模型，上述第二指示信息用于指示数据采集方式，上述第三指示信息用于指示数据预处理方式，上述第四指示信息用于指示数据上报方式。
在一种可能的实现方式中，其特征在于，上述通信单元702，还用于向上述网络设备发送配置信息获取请求，上述配置信息获取请求用于请求上述第一配置信息。
在一种可能的实现方式中，上述配置信息获取请求包括上述终端设备的设备能力信息。
在一种可能的实现方式中，上述通信单元702向上述网络设备发送配置信息获取请求，具体用于：当设备处理能力受限时，向上述网络设备发送配置信息获取请求；或者，当变更数据精度要求时，向上述网络设备发送配置信息获取请求。
在一种可能的实现方式中，上述处理单元701，还用于根据上述第一配置信息，向上述网络设备上报数据。
在一种可能的实现方式中，上述通信单元702，还用于接收来自上述网络设备发送激活消息，上述激活消息用于激活根据上述第一配置信息的配置。
在一种可能的实现方式中，上述通信单元702接收来自网络设备的第一配置信息，具体用于：接收来自网络设备无线资源控制RRC消息，上述RRC消息包括上述第一配置信息。
在一种可能的实现方式中，上述第一配置信息还用于指示第二模型；上述处理单元701，还用于根据上述第二模型，调整自身使用的AI模型。
在本申请实施例中，终端设备可以接收来自网络设备的第一配置信息，并根据该第一配置信息更新终端设备自身的配置信息，进而使用更新后的配置信息中的数据采集、预处理和/或上报方式，将经过采集并预处理后的数据上报至网络设备。通过网络设备动态配置终端设备的配置信息，可以更好的应对通信环境或者资源的变化，有利于增强通信网络的性能。
上述通信装置例如可以是：芯片、或者芯片模组。关于上述实施例中描述的各个装置、产品包含的各个模块，其可以是软件模块，也可以是硬件模块，或者也可以部分是软件模块，部分是硬件模块。例如，对于应用于或集成于芯片的各个装置、产品，其包含的各个模块可以都采用电路等硬件的方式实现，或者，至少部分模块可以采用软件程序的方式实现，该软件程序运行于芯片内部集成的处理器，剩余的(如果有)部分模块可以采用电路等硬件方式实现；对于应用于或集成于芯片模组的各个装置、产品，其包含的各个模块可以都采用电路等硬件的方式实现，不同的模块可以位于芯片模组的同一组件(例如芯片、电路模块等)或者不同组件中，或者，至少部分模块可以采用软件程序的方式实现，该软件程序运行于芯片模组内部集成的处理器，剩余的(如果有)部分模块可以采用电路等硬件方式实现；对于应用于或集成于终端的各个装置、产品，其包含的各个模块可以都采用电路等硬件的方式实现，不同的模块可以位于终端内同一组件(例如，芯片、电路模块等)或者不同组件中，或者，至少部分模块可以采用软件程序的方式实现，该软件程序运行于终端内部集成的处理器，剩余的(如果有)部分模块可以采用电路等硬件方式实现。
请参阅图8，图8示出了本申请实施例的另一种通信装置的结构示意图。该装置可以是网络设备，也可以是网络设备中的装置，或者是能够和网络设备匹配使用的装置。图8所示的通信装置可以包括处理单元801和通信单元802。其中，处理单元801，用于进行数 据处理。通信单元802集成有接收单元和发送单元。通信单元802也可以称为收发单元。或者，也可将通信单元802拆分为接收单元和发送单元。
上述处理单元801，用于针对第一模型，获取第一配置信息，上述第一配置信息用于指示针对第一模型的数据采集方式、数据预处理方式和/或数据上报方式，上述第一模型为上述网络设备使用的人工智能AI模型；上述通信单元802，用于向终端设备发送第一配置信息。
在本申请实施例中，终端设备可以接收来自网络设备的第一配置信息，并根据该第一配置信息更新终端设备自身的配置信息，进而使用更新后的配置信息中的数据采集、预处理和/或上报方式，将经过采集并预处理后的数据上报至网络设备。通过网络设备动态配置终端设备的配置信息，可以更好的应对通信环境或者资源的变化，有利于增强通信网络的性能。
在一种可能的实现方式中，当上述第一配置信息用于指示针对上述第一模型的数据采集方式、预处理方式和上报方式时，上述第一配置信息，包括：第一指示信息、第二指示信息、第三指示信息、第四指示信息，上述第一指示信息用于指示上述第一模型，上述第二指示信息用于指示数据采集方式，上述第三指示信息用于指示数据预处理方式，上述第四指示信息用于指示数据上报方式。
在一种可能的实现方式中，上述通信单元802，还用于接收到来自上述终端设备的配置信息获取请求，上述配置信息获取请求用于请求上述第一配置信息。
在一种可能的实现方式中，上述配置信息获取请求包括上述终端设备的设备能力信息。
在一种可能的实现方式中，上述处理单元801针对第一模型，获取第一配置信息，具体用于：检测到空口资源拥塞时，针对第一模型，获取第一配置信息。
在一种可能的实现方式中，上述通信单元802，还用于接收上述终端设备根据上述第一配置信息上报的数据。
在一种可能的实现方式中，上述通信单元802，还用于向上述终端设备发送激活消息，上述激活消息用于激活上述终端设备根据上述第一配置信息的配置。
在一种可能的实现方式中，上述通信单元802向终端设备发送第一配置信息，具体用于：向上述终端设备发送无线资源控制RRC消息，上述RRC消息包括上述第一配置信息。
在一种可能的实现方式中，上述第一配置信息还用于指示上述终端设备使用的第二模型。
上述通信装置例如可以是：芯片、或者芯片模组。关于上述实施例中描述的各个装置、产品包含的各个模块，其可以是软件模块，也可以是硬件模块，或者也可以部分是软件模块，部分是硬件模块。例如，对于应用于或集成于芯片的各个装置、产品，其包含的各个模块可以都采用电路等硬件的方式实现，或者，至少部分模块可以采用软件程序的方式实现，该软件程序运行于芯片内部集成的处理器，剩余的(如果有)部分模块可以采用电路等硬件方式实现；对于应用于或集成于芯片模组的各个装置、产品，其包含的各个模块可以都采用电路等硬件的方式实现，不同的模块可以位于芯片模组的同一组件(例如芯片、 电路模块等)或者不同组件中，或者，至少部分模块可以采用软件程序的方式实现，该软件程序运行于芯片模组内部集成的处理器，剩余的(如果有)部分模块可以采用电路等硬件方式实现；对于应用于或集成于终端的各个装置、产品，其包含的各个模块可以都采用电路等硬件的方式实现，不同的模块可以位于终端内同一组件(例如，芯片、电路模块等)或者不同组件中，或者，至少部分模块可以采用软件程序的方式实现，该软件程序运行于终端内部集成的处理器，剩余的(如果有)部分模块可以采用电路等硬件方式实现。
请参阅图9，图9为本申请实施例提供的又一种通信装置90，用于实现上述图2和图6中终端设备的功能。该装置可以是终端设备或用于终端设备的装置。用于终端设备的装置可以为终端设备内的芯片系统或芯片。其中，芯片系统可以由芯片构成，也可以包含芯片和其他分立器件。
或者，通信装置90，用于实现上述图2和图6中网络设备的功能。该装置90可以是网络设备或用于网络设备的装置。用于网络设备的装置可以为网络设备内的芯片系统或芯片。
通信装置90包括至少一个处理器920，用于实现本申请实施例提供的方法中终端设备的数据处理功能。装置90还可以包括通信接口910，用于实现本申请实施例提供的方法中终端设备的收发操作。在本申请实施例中，通信接口可以是收发器、电路、总线、模块或其它类型的通信接口，用于通过传输介质和其它设备进行通信。例如，通信接口910用于装置90中的装置可以和其它设备进行通信。处理器920利用通信接口910收发数据，并用于实现上述方法实施例图2上述的方法。
装置90还可以包括至少一个存储器930，用于存储程序指令和/或数据。存储器930和处理器920耦合。本申请实施例中的耦合是装置、单元或模块之间的间接耦合或通信连接，可以是电性，机械或其它的形式，用于装置、单元或模块之间的信息交互。处理器920可能和存储器930协同操作。处理器920可能执行存储器930中存储的程序指令。上述至少一个存储器中的至少一个可以包括于处理器中。
当装置90开机后，处理器920可以读取存储器930中的软件程序，解释并执行软件程序的指令，处理软件程序的数据。当需要通过无线发送数据时，处理器920对待发送的数据进行基带处理后，输出基带信号至射频电路(图未示意)，射频电路将基带信号进行射频处理后将射频信号通过天线以电磁波的形式向外发送。当有数据发送到装置90时，射频电路通过天线接收到射频信号，将射频信号转换为基带信号，并将基带信号输出至处理器920，处理器920将基带信号转换为数据并对该数据进行处理。
在另一种实现中，上述的射频电路和天线可以独立于进行基带处理的处理器920而设置，例如在分布式场景中，射频电路和天线可以与独立于通信装置，呈拉远式的布置。
本申请实施例中不限定上述通信接口910、处理器920以及存储器930之间的具体连接介质。本申请实施例在图9中以存储器930、处理器920以及通信接口910之间通过总线940连接，总线在图9中以粗线表示，其它部件之间的连接方式，仅是进行示意性说明，并不引以为限。上述总线可以分为地址总线、数据总线、控制总线等。为便于表示，图9 中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。
装置90具体是用于终端设备时，例如装置90具体是芯片或者芯片系统时，通信接口910所输出或接收的可以是基带信号。装置90具体是终端设备时，通信接口910所输出或接收的可以是射频信号。在本申请实施例中，处理器可以是通用处理器、数字信号处理器、专用集成电路、现场可编程门阵列或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件，可以实现或者执行本申请实施例中的公开的各方法、操作及逻辑框图。通用处理器可以是微处理器或者任何常规的处理器等。结合本申请实施例所公开的方法的操作可以直接体现为硬件处理器执行完成，或者用处理器中的硬件及软件模块组合执行完成。
需要说明的是，该通信装置90可以执行前述方法实施例中终端设备或网络设备的相关步骤，具体可参见上述各个步骤所提供的实现方式，在此不再赘述。
对于应用于或集成于通信装置的各个装置、产品，其包含的各个模块可以都采用电路等硬件的方式实现，不同的模块可以位于终端内同一组件(例如，芯片、电路模块等)或者不同组件中，或者，至少部分模块可以采用软件程序的方式实现，该软件程序运行于终端内部集成的处理器，剩余的(如果有)部分模块可以采用电路等硬件方式实现。
本申请实施例还提供一种芯片，该芯片可以执行前述方法实施例中终端设备的相关步骤。上述芯片用于：接收来自网络设备的第一配置信息；上述第一配置信息用于指示针对第一模型的数据采集方式、数据预处理方式和/或数据上报方式，上述第一模型为上述网络设备使用的人工智能AI模型；根据上述第一配置信息，进行相应的配置。
在一种可能的实现方式中，当上述第一配置信息用于指示针对上述第一模型的数据采集方式、预处理方式和上报方式时，上述第一配置信息，包括：第一指示信息、第二指示信息、第三指示信息、第四指示信息，上述第一指示信息用于指示上述第一模型，上述第二指示信息用于指示数据采集方式，上述第三指示信息用于指示数据预处理方式，上述第四指示信息用于指示数据上报方式。
在一种可能的实现方式中，其特征在于，上述芯片还用于：向上述网络设备输出配置信息获取请求，上述配置信息获取请求用于请求上述第一配置信息。
在一种可能的实现方式中，上述配置信息获取请求包括上述终端设备的设备能力信息。
在一种可能的实现方式中，上述芯片用于向上述网络设备发送配置信息获取请求，具体用于：
当设备处理能力受限时，向上述网络设备发送配置信息获取请求；或者，当变更数据精度要求时，向上述网络设备输出配置信息获取请求。
在一种可能的实现方式中，上述芯片还用于：上述终端设备根据上述第一配置信息，向上述网络设备上报数据。
在一种可能的实现方式中，上述芯片还用于：接收来自上述网络设备发送激活消息，上述激活消息用于激活根据上述第一配置信息的配置。
在一种可能的实现方式中，上述芯片用于接收来自网络设备的第一配置信息，具体用于：接收来自网络设备无线资源控制RRC消息，上述RRC消息包括上述第一配置信息。
在一种可能的实现方式中，上述第一配置信息还用于指示第二模型；上述芯片还用于根据上述第二模型，调整自身使用的AI模型。
本申请实施例还提供了一种芯片，该芯片可以执行前述方法实施例中网络设备的相关步骤。该芯片，用于针对第一模型，获取第一配置信息，上述第一配置信息用于指示针对第一模型的数据采集方式、数据预处理方式和/或数据上报方式，上述第一模型为上述网络设备使用的人工智能AI模型；向终端设备输出的第一配置信息。
在一种可能的实现方式中，当上述第一配置信息用于指示针对上述第一模型的数据采集方式、预处理方式和上报方式时，上述第一配置信息，包括：第一指示信息、第二指示信息、第三指示信息、第四指示信息，上述第一指示信息用于指示上述第一模型，上述第二指示信息用于指示数据采集方式，上述第三指示信息用于指示数据预处理方式，上述第四指示信息用于指示数据上报方式。
在一种可能的实现方式中，上述芯片还用于：接收到来自上述终端设备的配置信息获取请求，上述配置信息获取请求用于请求上述第一配置信息。
在一种可能的实现方式中，上述配置信息获取请求包括上述终端设备的设备能力信息。
在一种可能的实现方式中，上述芯片用于针对第一模型，获取第一配置信息，具体用于：检测到空口资源拥塞时，针对第一模型，获取第一配置信息。
在一种可能的实现方式中，上述芯片，还用于接收上述终端设备根据上述第一配置信息上报的数据。
在一种可能的实现方式中，上述芯片，还用于向上述终端设备发送激活消息，上述激活消息用于激活上述终端设备根据上述第一配置信息的配置。
在一种可能的实现方式中，上述芯片，用于向终端设备发送第一配置信息，具体用于：向上述终端设备输出无线资源控制RRC消息，上述RRC消息包括上述第一配置信息。
在一种可能的实现方式中，上述第一配置信息还用于指示上述终端设备使用的第二模型。
在一种可能的实现方式中，上述芯片包括至少一个处理器、至少一个第一存储器和至少一个第二存储器；其中，前述至少一个第一存储器和前述至少一个处理器通过线路互联，前述第一存储器中存储有指令；前述至少一个第二存储器和前述至少一个处理器通过线路互联，前述第二存储器中存储前述方法实施例中需要存储的数据。
对于应用于或集成于芯片的各个装置、产品，其包含的各个模块可以都采用电路等硬件的方式实现，或者，至少部分模块可以采用软件程序的方式实现，该软件程序运行于芯片内部集成的处理器，剩余的(如果有)部分模块可以采用电路等硬件方式实现。
请参阅图10，图10是本申请实施例提供的一种模组设备的结构示意图。该模组设备100可以执行前述方法实施例中终端设备的相关步骤，该模组设备100包括：通信模组1001、电源模组1002、存储模组1003以及芯片模组1004。
其中，上述通信模组1001用于进行模组设备内部通信，或者用于上述模组设备与外部设备进行通信；上述电源模组1002用于为上述模组设备提供电能；上述存储模组1003用 于存储数据和指令；上述芯片模组1004用于：
接收来自网络设备的第一配置信息；上述第一配置信息用于指示针对第一模型的数据采集方式、数据预处理方式和/或数据上报方式，上述第一模型为上述网络设备使用的人工智能AI模型；根据上述第一配置信息，进行相应的配置。
在一种可能的实现方式中，当上述第一配置信息用于指示针对上述第一模型的数据采集方式、预处理方式和上报方式时，上述第一配置信息，包括：第一指示信息、第二指示信息、第三指示信息、第四指示信息，上述第一指示信息用于指示上述第一模型，上述第二指示信息用于指示数据采集方式，上述第三指示信息用于指示数据预处理方式，上述第四指示信息用于指示数据上报方式。
在一种可能的实现方式中，其特征在于，上述芯片模组1004还用于：向上述网络设备输出配置信息获取请求，上述配置信息获取请求用于请求上述第一配置信息。
在一种可能的实现方式中，上述配置信息获取请求包括上述终端设备的设备能力信息。
在一种可能的实现方式中，上述芯片模组1004用于向上述网络设备发送配置信息获取请求，具体用于：当设备处理能力受限时，向上述网络设备发送配置信息获取请求；或者，当变更数据精度要求时，向上述网络设备输出配置信息获取请求。
在一种可能的实现方式中，上述芯片模组1004还用于：上述终端设备根据上述第一配置信息，向上述网络设备上报数据。
在一种可能的实现方式中，上述芯片模组1004还用于：接收来自上述网络设备发送激活消息，上述激活消息用于激活根据上述第一配置信息的配置。
在一种可能的实现方式中，上述芯片模组1004用于接收来自网络设备的第一配置信息，具体用于：接收来自网络设备无线资源控制RRC消息，上述RRC消息包括上述第一配置信息。
在一种可能的实现方式中，上述第一配置信息还用于指示第二模型；上述芯片还用于根据上述第二模型，调整自身使用的AI模型。
对于应用于或集成于芯片模组的各个装置、产品，其包含的各个模块可以都采用电路等硬件的方式实现，不同的模块可以位于芯片模组的同一组件(例如芯片、电路模块等)或者不同组件中，或者，至少部分模块可以采用软件程序的方式实现，该软件程序运行于芯片模组内部集成的处理器，剩余的(如果有)部分模块可以采用电路等硬件方式实现。
请参阅图11，图11为本申请实施例提供的另一种模组设备的结构示意图。该模组设备110可以执行前述方法实施例中接入网设备的相关步骤，该模组设备110包括：通信模组1101、电源模组1102、存储模组1103以及芯片模组1104。
其中，上述通信模组1101用于进行模组设备内部通信，或者用于上述模组设备与外部设备进行通信；上述电源模组1102用于为上述模组设备提供电能；上述存储模组1103用于存储数据和指令；上述芯片模组1104用于：
针对第一模型，获取第一配置信息，上述第一配置信息用于指示针对第一模型的数据采集方式、数据预处理方式和/或数据上报方式，上述第一模型为上述网络设备使用的人工 智能AI模型；向终端设备输出的第一配置信息。
在一种可能的实现方式中，当上述第一配置信息用于指示针对上述第一模型的数据采集方式、预处理方式和上报方式时，上述第一配置信息，包括：第一指示信息、第二指示信息、第三指示信息、第四指示信息，上述第一指示信息用于指示上述第一模型，上述第二指示信息用于指示数据采集方式，上述第三指示信息用于指示数据预处理方式，上述第四指示信息用于指示数据上报方式。
在一种可能的实现方式中，上述芯片模组1104还用于：接收到来自上述终端设备的配置信息获取请求，上述配置信息获取请求用于请求上述第一配置信息。
在一种可能的实现方式中，上述配置信息获取请求包括上述终端设备的设备能力信息。
在一种可能的实现方式中，上述芯片模组1104用于针对第一模型，获取第一配置信息，具体用于：检测到空口资源拥塞时，针对第一模型，获取第一配置信息。
在一种可能的实现方式中，上述芯片模组1104，还用于接收上述终端设备根据上述第一配置信息上报的数据。
在一种可能的实现方式中，上述芯片模组1104，还用于向上述终端设备发送激活消息，上述激活消息用于激活上述终端设备根据上述第一配置信息的配置。
在一种可能的实现方式中，上述芯片模组1104，用于向终端设备发送第一配置信息，具体用于：向上述终端设备输出无线资源控制RRC消息，上述RRC消息包括上述第一配置信息。
在一种可能的实现方式中，上述第一配置信息还用于指示上述终端设备使用的第二模型。
对于应用于或集成于芯片模组的各个装置、产品，其包含的各个模块可以都采用电路等硬件的方式实现，不同的模块可以位于芯片模组的同一组件(例如芯片、电路模块等)或者不同组件中，或者，至少部分模块可以采用软件程序的方式实现，该软件程序运行于芯片模组内部集成的处理器，剩余的(如果有)部分模块可以采用电路等硬件方式实现。
本申请实施例还提供一种计算机可读存储介质，该计算机可读存储介质中存储有指令，当其在处理器上运行时，上述方法实施例的方法流程得以实现。
本申请实施例还提供一种计算机程序产品，当上述计算机程序产品在处理器上运行时，上述方法实施例的方法流程得以实现。
需要说明的是，对于前述的各方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本申请并不受所描述的动作顺序的限制，因为依据本申请，某些操作可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定是本申请所必须的。
本申请提供的各实施例的描述可以相互参照，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。为描述的方便和简洁，例如关于本申请实施例提供的各装置、设备的功能以及执行的操作可以参照本申请方法实施例 的相关描述，各方法实施例之间、各装置实施例之间也可以互相参考、结合或引用。
最后应说明的是：以上各实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述各实施例对本申请进行了详细的说明，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申请各实施例技术方案的范围。

Claims (26)

  1. 一种数据获取方法，其特征在于，所述方法包括：
    终端设备接收来自网络设备的第一配置信息；所述第一配置信息用于指示针对第一模型的数据采集方式、数据预处理方式和/或数据上报方式，所述第一模型为所述网络设备使用的人工智能AI模型；
    所述终端设备根据所述第一配置信息，进行相应的配置。
  2. 根据权利要求1所述的方法，其特征在于，当所述第一配置信息用于指示针对所述第一模型的数据采集方式、预处理方式和上报方式时，所述第一配置信息，包括：
    第一指示信息、第二指示信息、第三指示信息、第四指示信息，所述第一指示信息用于指示所述第一模型，所述第二指示信息用于指示数据采集方式，所述第三指示信息用于指示数据预处理方式，所述第四指示信息用于指示数据上报方式。
  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：
    所述终端设备向所述网络设备发送配置信息获取请求，所述配置信息获取请求用于请求所述第一配置信息。
  4. 根据权利要求3所述的方法，其特征在于，所述配置信息获取请求包括所述终端设备的设备能力信息。
  5. 根据权利要求4所述的方法，其特征在于，所述终端设备向所述网络设备发送配置信息获取请求，包括：
    所述终端设备当设备处理能力受限时，向所述网络设备发送配置信息获取请求；或者，
    所述终端设备当变更数据精度要求时，向所述网络设备发送配置信息获取请求。
  6. 根据权利要求1至5任一项所述的方法，其特征在于，所述方法还包括：
    所述终端设备根据所述第一配置信息，向所述网络设备上报数据。
  7. 根据权利要求1至6任一项所述的方法，其特征在于，所述方法还包括：
    所述终端设备接收来自所述网络设备发送激活消息，所述激活消息用于激活根据所述第一配置信息的配置。
  8. 根据权利要求1至7任一项所述的方法，其特征在于，所述终端设备接收来自网络设备的第一配置信息，包括：
    所述终端设备接收来自网络设备无线资源控制RRC消息，所述RRC消息包括所述第一配置信息。
  9. 根据权利要求1至8任一项所述的方法，其特征在于，所述第一配置信息还用于指示第二模型；所述方法还包括：
    所终端设备根据所述第二模型，调整自身使用的AI模型。
  10. 一种数据获取方法，其特征在于，所述方法包括：
    网络设备针对第一模型，获取第一配置信息，所述第一配置信息用于指示针对第一模型的数据采集方式、数据预处理方式和/或数据上报方式，所述第一模型为所述网络设备使用的人工智能AI模型；
    所述网络设备向终端设备发送第一配置信息。
  11. 根据权利要求10所述的方法，其特征在于，当所述第一配置信息用于指示针对所述第一模型的数据采集方式、预处理方式和上报方式时，所述第一配置信息，包括：
    第一指示信息、第二指示信息、第三指示信息、第四指示信息，所述第一指示信息用于指示所述第一模型，所述第二指示信息用于指示数据采集方式，所述第三指示信息用于指示数据预处理方式，所述第四指示信息用于指示数据上报方式。
  12. 根据权利要求10或11所述的方法，其特征在于，所述方法还包括：
    所述网络设备接收到来自所述终端设备的配置信息获取请求，所述配置信息获取请求用于请求所述第一配置信息。
  13. 根据权利要求12所述的方法，其特征在于，所述配置信息获取请求包括所述终端设备的设备能力信息。
  14. 根据权利要求10或11所述的方法，其特征在于，所述网络设备针对第一模型，获取第一配置信息，包括：
    所述网络设备检测到空口资源拥塞时，针对第一模型，获取第一配置信息。
  15. 根据权利要求10至14任一项所述的方法，其特征在于，所述方法还包括：
    所述网络设备接收所述终端设备根据所述第一配置信息上报的数据。
  16. 根据权利要求10至15任一项所述的方法，其特征在于，所述方法还包括：
    所述网络设备向所述终端设备发送激活消息，所述激活消息用于激活所述终端设备根据所述第一配置信息的配置。
  17. 根据权利要求10至16任一所述的方法，其特征在于，所述网络设备向终端设备发 送第一配置信息，包括：
    所述网络设备向所述终端设备发送无线资源控制RRC消息，所述RRC消息包括所述第一配置信息。
  18. 根据权利要求10至17任一项所述的方法，其特征在于，所述第一配置信息还用于指示所述终端设备使用的第二模型。
  19. 一种通信装置，其特征在于，包括用于实现权利要求1～18中任意一项所述方法的单元。
  20. 一种通信装置，其特征在于，包括处理器和收发器；
    所述收发器，用于接收或发送信号；
    所述处理器，用于执行如权利要求1～18中任一项所述的方法。
  21. 根据权利要求20所述的通信装置，其特征在于，所述通信装置还包括存储器：
    所述存储器，用于存储计算机程序；
    所述处理器，具体用于从所述存储器中调用所述计算机程序执行如权利要求1～18中任一项所述的方法。
  22. 一种芯片，其特征在于，
    所述芯片，用于接收来自网络设备的第一配置信息；所述第一配置信息用于指示针对第一模型的数据采集方式、数据预处理方式和/或数据上报方式，所述第一模型为所述网络设备使用的人工智能AI模型；
    所述芯片，还用于根据所述第一配置信息，进行相应的配置。
  23. 一种芯片，其特征在于，
    所述芯片，用于针对第一模型，获取第一配置信息，所述第一配置信息用于指示针对第一模型的数据采集方式、数据预处理方式和/或数据上报方式，所述第一模型为所述网络设备使用的人工智能AI模型；
    所述芯片，还用于向终端设备输出的第一配置信息。
  24. 一种模组设备，其特征在于，所述模组设备包括通信模组、电源模组、存储模组以及芯片模组，其中：
    所述通信模组用于进行模组设备内部通信，或者用于所述模组设备与外部设备进行通信；
    所述电源模组用于为所述模组设备提供电能；
    所述存储模组用于存储数据和指令；
    所述芯片模组用于：
    接收来自网络设备的第一配置信息；所述第一配置信息用于指示针对第一模型的数据采集方式、数据预处理方式和/或数据上报方式，所述第一模型为所述网络设备使用的人工智能AI模型；
    根据所述第一配置信息，进行相应的配置。
  25. 一种模组设备，其特征在于，所述模组设备包括通信模组、电源模组、存储模组以及芯片模组，其中：
    所述通信模组用于进行模组设备内部通信，或者用于所述模组设备与外部设备进行通信；
    所述电源模组用于为所述模组设备提供电能；
    所述存储模组用于存储数据和指令；
    所述芯片模组用于：
    针对第一模型，获取第一配置信息，所述第一配置信息用于指示针对第一模型的数据采集方式、数据预处理方式和/或数据上报方式，所述第一模型为所述网络设备使用的人工智能AI模型；
    向终端设备输出的第一配置信息。
  26. 一种计算机可读存储介质，其特征在于，所述计算机存储介质中存储有计算机可读指令，当所述计算机可读指令在通信装置上运行时，使得所述通信装置执行权利要求1～18中任一项所述的方法。
PCT/CN2022/074979 2021-02-07 2022-01-29 一种数据获取方法及装置 WO2022166886A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110169420.2 2021-02-07
CN202110169420.2A CN114915983A (zh) 2021-02-07 2021-02-07 一种数据获取方法及装置

Publications (1)

Publication Number Publication Date
WO2022166886A1 true WO2022166886A1 (zh) 2022-08-11

Family

ID=82740860

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/074979 WO2022166886A1 (zh) 2021-02-07 2022-01-29 一种数据获取方法及装置

Country Status (2)

Country Link
CN (1) CN114915983A (zh)
WO (1) WO2022166886A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024060139A1 (zh) * 2022-09-22 2024-03-28 华为技术有限公司 通信方法、装置、存储介质及程序产品
CN117596619B (zh) * 2024-01-12 2024-04-23 北京小米移动软件有限公司 通信方法、设备和存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109902820A (zh) * 2019-02-20 2019-06-18 腾讯科技（深圳）有限公司 Ai模型训练方法、装置、存储介质及设备
US20190294954A1 (en) * 2018-03-21 2019-09-26 Lg Electronics Inc. Artificial intelligence server
CN111368991A (zh) * 2018-12-25 2020-07-03 杭州海康威视数字技术股份有限公司 深度学习模型的训练方法、装置及电子设备
CN111837425A (zh) * 2020-06-10 2020-10-27 北京小米移动软件有限公司 一种接入方法、接入装置及存储介质
CN111957047A (zh) * 2020-08-12 2020-11-20 超参数科技(深圳)有限公司 关卡配置数据调整方法、计算机设备及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190294954A1 (en) * 2018-03-21 2019-09-26 Lg Electronics Inc. Artificial intelligence server
CN111368991A (zh) * 2018-12-25 2020-07-03 杭州海康威视数字技术股份有限公司 深度学习模型的训练方法、装置及电子设备
CN109902820A (zh) * 2019-02-20 2019-06-18 腾讯科技（深圳）有限公司 Ai模型训练方法、装置、存储介质及设备
CN111837425A (zh) * 2020-06-10 2020-10-27 北京小米移动软件有限公司 一种接入方法、接入装置及存储介质
CN111957047A (zh) * 2020-08-12 2020-11-20 超参数科技(深圳)有限公司 关卡配置数据调整方法、计算机设备及存储介质

Also Published As

Publication number Publication date
CN114915983A (zh) 2022-08-16

Similar Documents

Publication Publication Date Title
CN111819872B (zh) 信息传输方法、装置、通信设备及存储介质
WO2022166886A1 (zh) 一种数据获取方法及装置
CN110351828B (zh) 一种定位方法及装置
US20230232266A1 (en) Method and terminal for reporting location measurement data, and storage medium
US20200213903A1 (en) Data transmission method and device
CN108901079B (zh) 超时时间确定方法、装置、设备及存储介质
WO2015154248A1 (zh) 一种系统信息的传输方法及基站、用户设备
JP2021513762A (ja) データの伝送方法、端末デバイス及びネットワークデバイス
KR20230002537A (ko) 포지셔닝 신호 처리 방법 및 장치
WO2022160265A1 (zh) 通信方法和通信装置
US20220417842A1 (en) Information processing method and communication apparatus
CN113271623B (zh) 通信方法及装置
WO2021047666A1 (zh) 一种探测参考信号传输的方法、相关设备以及存储介质
EP3179705A1 (en) Message processing method, system and related device
CN114339469A (zh) Mqtt通信方法、装置、电子设备及存储介质
CN105357654B (zh) 一种基于北斗的应急通信服务系统及其工作方法
CN109151430B (zh) 一种数据处理方法、终端、服务器和计算机存储介质
CN112740826B (zh) 一种能力上报方法及终端设备
WO2020220787A1 (zh) 通信方法、装置及系统
CN113938355B (zh) 数据传输方法、系统及存储介质
CN110933607B (zh) 一种定位信息的传输方法、装置及设备
GB2506839A (en) Management of dormancy timers in wireless communications
CN113490236A (zh) 数据传输方法和装置、存储介质及电子设备
CN105635998B (zh) 一种数据上传方法、装置和终端
WO2024012326A1 (zh) 一种通信方法、装置及系统

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: 22749165

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: 22749165

Country of ref document: EP

Kind code of ref document: A1