WO2023097870A1 - Procédé et dispositif de traitement de communication sans fil par intelligence artificielle - Google Patents

Procédé et dispositif de traitement de communication sans fil par intelligence artificielle Download PDF

Info

Publication number
WO2023097870A1
WO2023097870A1 PCT/CN2022/070730 CN2022070730W WO2023097870A1 WO 2023097870 A1 WO2023097870 A1 WO 2023097870A1 CN 2022070730 W CN2022070730 W CN 2022070730W WO 2023097870 A1 WO2023097870 A1 WO 2023097870A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
artificial intelligence
downlink
feedback
model
Prior art date
Application number
PCT/CN2022/070730
Other languages
English (en)
Chinese (zh)
Inventor
王志勤
刘晓峰
杜滢
魏贵明
徐菲
Original Assignee
中国信息通信研究院
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 中国信息通信研究院 filed Critical 中国信息通信研究院
Publication of WO2023097870A1 publication Critical patent/WO2023097870A1/fr

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 technical field of wireless communication, and in particular to an artificial intelligence processing method and device.
  • AI artificial intelligence
  • AI technology to design a communication system requires a series of processes such as data collection and model transfer.
  • the data set and model construction of the mobile communication system directly affect the effect of using AI technology to solve related problems.
  • the actual system construction needs to combine the basic theory of wireless communication system and AI basic theory, and consider the constraints of various practical situations.
  • This application proposes a wireless communication artificial intelligence processing method and equipment, and provides a solution that combines data set construction and AI model use.
  • Using the method and device provided by the present invention can effectively carry out wireless data collection, processing and model transfer , to support the application of various practical wireless communication systems based on AI technology.
  • the present application proposes a wireless communication artificial intelligence processing method, comprising the following steps:
  • the downlink information includes first information, and the first information is used to indicate N kinds of artificial intelligence model downlink services for selection, and each artificial intelligence model includes neural network structural characteristics and parameters;
  • Each of the artificial intelligence models is used for corresponding network-side and mobile-side performance processing.
  • the first information is high-level signaling or downlink control signaling DCI; the first information includes N bits, and each bit identifies one artificial intelligence model downlink service.
  • the first information is also used to indicate a first feedback time for the first information.
  • the uplink information includes third information as feedback to the first information
  • the third information includes selection instructions for the N types of artificial intelligence model download services.
  • the downlink information further includes second information, and the second information is used to indicate a second feedback time and a type of feedback data; at the second feedback time, the uplink information includes the feedback data.
  • the downlink information includes fourth information, and the fourth information includes one or more of the N types of artificial intelligence models.
  • the method described in any one embodiment of the first aspect of the present application is used for network equipment, and includes the following steps:
  • uplink information includes selection instructions for the N types of artificial intelligence model downlink services
  • the downlink information includes one or more of the N types of artificial intelligence models.
  • the method described in any one embodiment of the first aspect of the present application is used for a terminal device, and includes the following steps:
  • the uplink information includes selection instructions for the N artificial intelligence model downlink services.
  • the downlink information includes one or more artificial intelligence models corresponding to the selection indication;
  • downlink information is received, and the downlink information also includes an indication of the type of feedback data and the feedback time;
  • the present application also proposes a network device for implementing the method described in any one of the embodiments of the first aspect of the present application, at least one module in the network device is used for at least one of the following functions: sending downlink information , the downlink information includes the first information; receive uplink information, the uplink information includes selection instructions for the N types of artificial intelligence model downlink services; in response to the selection instructions, the downlink information includes the N types of artificial intelligence models 1 or more of the smart models.
  • the present application also proposes a terminal device for implementing the method described in any one of the embodiments of the first aspect of the present application, at least one module in the terminal device is used for at least one of the following functions: receiving downlink information , the downlink information includes the first information; sending uplink information, the uplink information includes selection instructions for the N artificial intelligence model downlink services; receiving downlink information, the downlink information includes 1 corresponding to the selection instructions One or more artificial intelligence models; execute the artificial intelligence model to generate feedback data; receive downlink information, and the downlink information also includes an indication of the type of feedback data and feedback time; at the feedback time indicated by the downlink information, send the feedback data.
  • the present application also proposes a communication device, including: a memory, a processor, and a computer program stored in the memory and operable on the processor, when the computer program is executed by the processor Implement the steps of the method described in any one embodiment of the first aspect of the present application.
  • the present application also proposes a computer-readable medium, on which a computer program is stored, and when the computer program is executed by a processor, the computer program as described in any one of the embodiments of the first aspect of the present application is implemented. method steps.
  • the present application further proposes a mobile communication system, including at least one network device as described in any embodiment of the present application and/or at least one terminal device as described in any embodiment of the present application.
  • the method, device and communication system provided by the present invention can enable network devices and terminal devices to realize data set construction, AI model training, AI model deployment and use for different applications through necessary information exchange, and to solve problems through artificial intelligence technology. Effects of several key issues in wireless mobile communication systems. This information exchange mechanism is critical for using AI technology to solve mobile communication problems.
  • the method provided by the present invention enables the terminal equipment and network equipment to determine the scene using the AI model and how to construct the data set through information exchange, thereby realizing efficient and accurate data set establishment and AI model exchange, and improving the communication system using AI technology to solve Efficiency on key issues.
  • Fig. 1 is the embodiment flowchart of the application method
  • Fig. 2 is a schematic diagram of an embodiment in which multiple artificial intelligence models are issued simultaneously with the second information and the fourth information;
  • Fig. 3 is the schematic diagram of the embodiment that multiple artificial intelligence models are downloaded independently;
  • Fig. 4 is a schematic diagram of an embodiment of the artificial intelligence model downloading of the pre-upload data requirements
  • FIG. 5 is a flow chart of an embodiment of the method of the present application applied to a network device
  • FIG. 6 is a flow chart of an embodiment of the method of the present application applied to a terminal device
  • FIG. 7 is a schematic diagram of an embodiment of a network device
  • FIG. 8 is a schematic diagram of an embodiment of a terminal device
  • FIG. 9 is a schematic structural diagram of a network device according to another embodiment of the present invention.
  • Fig. 10 is a block diagram of a terminal device according to another embodiment of the present invention.
  • a network device can simultaneously send and receive data to multiple terminal devices.
  • Network devices and terminal devices send data through the downlink data shared channel (PDSCH) and uplink data shared channel (PUSCH); through the synchronization and broadcast channel (SS/PBCH) downlink control channel (PDCCH) and uplink access channel (PRACH) and control Channel (PUCCH) to exchange control information.
  • SS/PBCH transmits synchronization signals and broadcast information
  • the terminal control unit performs synchronization and acquisition of basic system information by receiving SS/PBCH.
  • the PDCCH transmits downlink control information (DCI), and performs specific transmission format-related content of the PDSCH, PUSCH and PUCCH.
  • DCI downlink control information
  • the terminal initiates PRACH-based access to the network device according to the control information sent by the network device and the terminal data reception status, or feedbacks whether the data is received correctly with ACK/NACK information.
  • the basic time transmission unit in the system is a symbol, and 14 symbols form a time slot.
  • Fig. 1 is a flowchart of an embodiment of the method of the present application.
  • this application proposes a wireless communication artificial intelligence processing method, including the following steps 101-104:
  • Step 101 the downlink information includes first information, and the first information is used to indicate N kinds of artificial intelligence model downlink services for selection.
  • Each of the artificial intelligence models includes neural network structural features and parameters; each of the artificial intelligence models is used for corresponding network-side and mobile-side performance processing.
  • the first information is high-level signaling or downlink control signaling DCI; the first information includes N bits, and each bit identifies one artificial intelligence model downlink service.
  • the first information is also used to indicate a first feedback time for the first information.
  • the uplink information includes third information as feedback to the first information
  • the third information includes selection instructions for the N types of artificial intelligence model download services.
  • the downlink information further includes second information, and the second information is used to indicate a second feedback time and a type of feedback data; at the second feedback time, the uplink information includes the feedback data.
  • the feedback data includes at least one of the following data:
  • the downlink information includes fourth information, and the fourth information includes one or more of the N types of artificial intelligence models.
  • the fourth information may be carried by the PDSCH, or the fourth information is jointly indicated by DCI information carried by the PDCCH, and the artificial intelligence model is included in the PDSCH indicated by the DCI.
  • the network device provides the AI service that the network device can provide to the terminal device through the first information and the second information, and provides required feedback information, data and corresponding feedback location.
  • the terminal device performs the third information feedback according to the first and second information, determines the AI model to be used, and starts corresponding data feedback.
  • the network device issues the fourth information according to the third information and data feedback by the terminal.
  • step 104 In order to execute step 104, according to the feedback of the first information and the second information, data set construction and AI model training for different applications can be implemented, and then AI model deployment can be provided. After receiving the fourth information, the terminal device uses the AI model to generate a processing result.
  • Fig. 2 is a schematic diagram of an embodiment in which multiple artificial intelligence models are issued simultaneously with the second information and the fourth information.
  • the first bit is 1, which means that the artificial intelligence model download service of "channel estimation” can be provided
  • the second bit is 1, which means that the artificial intelligence model download service of "channel information feedback” can be provided
  • the third bit is 0 means that the "positioning" artificial intelligence model download service cannot be provided
  • the fourth bit is 1, which means that the "beam management” artificial intelligence model download service can be provided
  • the fifth bit is 0, which means that the "mobility management” artificial intelligence model cannot be provided Model download service.
  • the first information is sent by DCI information carried by the PDCCH.
  • the first information also indicates the first feedback time, for example, the terminal feeds back the third information in the 10th time slot after the PDCCH carrying the first information.
  • the AI model to be used is determined by selecting an instruction.
  • the network device After receiving the third information sent by the terminal device, the network device sends the second information to the terminal device, where the second information indicates the second feedback time and the type and quantity of feedback data.
  • the terminal device supports two types of AI model feedback data, the quantity of each type of data, and the feedback period.
  • the data that needs to be fed back to support "channel estimation” is the feedback of 1 bit to the model effect every 100 time slots
  • the feedback required to support "channel information feedback” is 10 CSI raw data to be compressed every 100 time slots
  • "1-bit model 1 feedback” in FIG. 2 includes evaluation feedback for model 1, for example, indicating "good” or "bad".
  • the network device sends the fourth information to the terminal device while sending the second information
  • the fourth information includes the AI model used for "channel estimation” and “channel information feedback” One for each, sent on the PDSCH where the second information is located.
  • Fig. 3 is a schematic diagram of an embodiment of independent downloading of various artificial intelligence models.
  • the standard stipulates that the 5G network can explicitly support 5 kinds of AI model services, such as the model for "channel estimation”, the model for "channel information feedback”, the “positioning” model, the “beam management” model, the “mobile Sex Management” model, N 5.
  • the network device can provide three kinds of AI model services, such as channel estimation, channel information feedback, and beam management.
  • the first information is sent by DCI information carried by the PDCCH.
  • the first information also indicates the first feedback time, for example, the terminal feeds back the third information in the 10th time slot after the PDCCH carrying the first information, and the AI model to be used is determined by selecting an indication in the third information .
  • the terminal wishes to use an AI-based "channel estimation” and "positioning" model to feed back the third information at the position indicated by the first information, that is, the 10th time slot after the PDCCH carrying the first information: 10100.
  • the network device After receiving the third information sent by the terminal device, the network device first sends the second information related to "channel estimation" to the terminal device, indicating the feedback data type, quantity, and second feedback time.
  • the network device in the PDSCH in the same time slot as the second information, the network device sends "channel estimation" corresponding to the fourth information to the terminal device, and the fourth information includes Use AI models.
  • the network device sends the second information to the terminal again.
  • the second information is indication information related to "positioning", indicating the feedback data type, quantity, second Feedback time.
  • the network device sends the fourth information corresponding to positioning to the terminal device, and the fourth information includes the AI model used for positioning.
  • the channel impulse response in Figure 3 is a general term for the impact of the channel on the amplitude and phase information of the input signal.
  • Fig. 4 is a schematic diagram of an embodiment of artificial intelligence model downloading for pre-uploading data requirements.
  • the standard stipulates that the 5G network can explicitly support 5 kinds of AI model services, such as the model for "channel estimation”, the model for "channel information feedback”, the “positioning” model, the “beam management” model, the “mobile Sex Management” model, N 5.
  • the first information also indicates the first feedback time, for example, instructs the terminal to feed back the third information in the 10th time slot after the PDCCH carrying the first information, and determines the AI model to use.
  • the terminal wishes to adopt an AI-based beam management model, and feed back the third information: 00010 at the location indicated by the first information, that is, the 10th time slot after the PDCCH carrying the first information.
  • the network device After receiving the third information sent by the terminal device, the network device first sends the second information related to beam management to the terminal device, indicating a second feedback time and a feedback data type.
  • Fig. 5 is a flow chart of an embodiment of the method of the present application applied to a network device.
  • the method described in any one embodiment of the first aspect of the present application is used for network equipment, and includes the following steps 201-205:
  • Step 201 Send downlink information, the downlink information includes the first information; the first information is used to indicate N kinds of artificial intelligence model downlink services for selection.
  • Each of the artificial intelligence models includes neural network structural features and parameters; each of the artificial intelligence models is used for corresponding network-side and mobile-side performance processing.
  • the network device notifies the type of the AI model supported by the terminal device through the first information.
  • the network device supports at least N types of AI models, where N is a positive integer greater than or equal to 1, and each of the AI models can serve different functions.
  • Each AI model function is agreed upon by the network device and the terminal device.
  • the first information may be DCI information carried by the PDCCH, or may be high-layer signaling. Contains N bits, representing the support of the network device to the N types of AI models.
  • the first information may include confirmation request information that the terminal device feeds back whether to adopt the first information indicating model, and a first feedback time.
  • Step 202 receiving uplink information, the uplink information includes selection instructions for the N types of artificial intelligence model downlink services;
  • the uplink information includes third information as a feedback to the first information; the third information includes selection instructions for the N artificial intelligence model downlink services.
  • the network device receives fed back third information at a corresponding time point according to the first information.
  • the third information feedback indicates whether to use the first information to provide AI model indication information. N bits are used to select the model indicated by the first information.
  • the corresponding time point is the first feedback time indicated by the first information.
  • Step 203 sending downlink information, the downlink information also includes second information, and the second information is used to indicate the second feedback time and the type of feedback data;
  • the network device sends the data feedback information required by each model in the third information to the terminal device through the second information.
  • the data feedback information includes the type of the feedback data, the quantity of each type of data, the period of the feedback data, the starting point of the feedback, and the like.
  • Step 204 In response to the selection instruction, the downlink information includes one or more of the N types of artificial intelligence models.
  • the downlink information includes fourth information
  • the fourth information includes one or more of the N types of artificial intelligence models.
  • the network device sends the fourth information to the terminal after receiving the third information fed back by the terminal.
  • the fourth information includes model feedback for the model that needs to be used in the feedback in the third information.
  • step 204 can be performed multiple times, that is, the fourth information can be sent multiple times to implement model updating.
  • the number of the fourth information for the same type of AI model may be greater than or equal to 1.
  • the fourth information may be fed back in the same time slot as the second information, and indicated by the DCI where the second information is located.
  • the network device can realize data set construction and AI model training for different applications according to the feedback of the terminal device to the first information and the second information, and then provide AI model deployment.
  • Step 205 Receive uplink information at the second feedback time, where the uplink information includes the feedback data.
  • steps 204 and 205 are optional, and when the data fed back contains the data needed to generate or train the artificial intelligence model, the second feedback time before step 204 should be received in the uplink information feedback data.
  • the feedback data includes the result data obtained by running the artificial intelligence model or the data evaluating the operation effect of the artificial intelligence model, the feedback data in the uplink information should be received at the second feedback time after step 204 .
  • FIG. 6 is a flow chart of an embodiment in which the method of the present application is applied to a terminal device.
  • the method described in any one embodiment of the first aspect of the present application is used for a terminal device, and includes the following steps:
  • Step 301 Receive downlink information, the downlink information includes the first information, and is used to indicate N kinds of artificial intelligence model downlink services for selection.
  • Each of the artificial intelligence models includes neural network structural features and parameters; each of the artificial intelligence models is used for corresponding network-side and mobile-side performance processing.
  • the terminal device recognizes the first information, and determines an optional artificial intelligence model and a first feedback time.
  • Step 302 Send uplink information, the uplink information includes selection instructions for the N artificial intelligence model downlink services.
  • the uplink information includes third information as a feedback to the first information; the third information includes selection instructions for the N artificial intelligence model downlink services.
  • the terminal device performs third information feedback at a corresponding time point according to the first information.
  • the third information feedback indicates whether to use the first information to provide AI model indication information. N bits are used to select the model indicated by the first information.
  • the corresponding time point is the first feedback time indicated by the first information.
  • Step 303 receiving downlink information, which also includes an indication of the type of feedback data and feedback time;
  • downlink information is received, and the downlink information includes second information, where the second information is used to indicate the second feedback time and the type and quantity of feedback data.
  • the type of the feedback data includes at least one of the following data:
  • Step 304 Further, receive downlink information, which includes one or more artificial intelligence models corresponding to the selection indication;
  • fourth information is included in the downlink information, and the fourth information includes one or more of the N types of artificial intelligence models.
  • step 304 is performed multiple times, that is, the fourth information can be received multiple times to implement model updating.
  • Step 305 Execute the artificial intelligence model to generate feedback data.
  • the generated feedback data includes: result data obtained by running the artificial intelligence model; and data evaluating the operating effect of the artificial intelligence model.
  • Step 306 Send the feedback data at the feedback time indicated by the downlink information.
  • uplink information is received, and the uplink information includes the feedback data.
  • step 306 should be executed before step 304 when the type of feedback data is the data required for generating and training the artificial intelligence model.
  • the terminal device performs feedback of data information according to the feedback time and the feedback data type indicated by the second information. Multiple models require feedback data that can be sent at the same time. When multiple models require the same type and period of feedback data, only one piece of data can be fed back.
  • Fig. 7 is a schematic diagram of an embodiment of a network device.
  • the embodiment of the present application also proposes a network device, using the method in any one of the embodiments of the present application, the network device is used to: send downlink information, the downlink information includes the first information, the second information, the first information At least one of the four pieces of information: receiving uplink information, where the uplink information includes the third information.
  • the network device is used to: send downlink information, the downlink information includes the first information, the second information, the first information At least one of the four pieces of information: receiving uplink information, where the uplink information includes the third information.
  • the network device is used to: send downlink information, the downlink information includes the first information, the second information, the first information At least one of the four pieces of information: receiving uplink information, where the uplink information includes the third information.
  • the uplink information includes the third information.
  • the feedback data is received at a second feedback time.
  • a network device 400 proposed in this application includes a network sending module 401 , a network determining module 402 , and a network receiving module 403 .
  • the network sending module is configured to send downlink information, including at least one of first information, second information, and fourth information.
  • the network determination module is used to determine the first feedback time, the second feedback time, N artificial intelligence model download services for selection, each artificial intelligence model includes neural network structural characteristics and parameters, and uplink information indication The type of artificial intelligence model selected. Further, the network determination module is also used for training the artificial intelligence model according to the feedback data.
  • the network receiving module is configured to receive uplink information, including third information, and also including the feedback data.
  • Fig. 8 is a schematic diagram of an embodiment of a terminal device.
  • the present application also proposes a terminal device, using the method of any one of the embodiments of the present application, the terminal device is used to: receive downlink information, the downlink information includes at least one of the first information, second information, and third information Type; sending uplink information, where the uplink information includes the third information.
  • the terminal device In response to the first information, send the uplink information at the first feedback time, including selection instructions for the N types of artificial intelligence model downlink services; receive downlink information, and the downlink information includes one type corresponding to the selection instructions or multiple artificial intelligence models; execute the artificial intelligence model to generate feedback data; receive downlink information, which also includes an indication of the type of feedback data and feedback time; at the second feedback time indicated by the downlink information, send the feedback data.
  • a terminal device 500 proposed in this application includes a terminal sending module 501 , a terminal determining module 502 , and a terminal receiving module 503 .
  • the terminal receiving module is configured to receive downlink information, including at least one of first information, second information, and fourth information.
  • the terminal determination module is used to determine N kinds of artificial intelligence model download services for selection, determine the selection instruction of the artificial intelligence model, run the artificial intelligence model, and determine the feedback data. Further, the terminal determining module is further configured to train an artificial intelligence model according to the feedback data.
  • the terminal sending module is configured to send uplink information, and the third information also includes the feedback data.
  • the terminal equipment mentioned in this application may refer to mobile terminal equipment.
  • a network device 600 includes a processor 601 , a wireless interface 602 , and a memory 603 .
  • the wireless interface may be a plurality of components, including a transmitter and a receiver, providing a unit for communicating with various other devices over a transmission medium.
  • the wireless interface realizes the communication function with the terminal equipment, and processes the wireless signal through the receiving and transmitting device, and the data carried by the signal communicates with the memory or the processor through the internal bus structure.
  • the memory 603 contains a computer program for executing any one embodiment of the present application, and the computer program runs or changes on the processor 601 .
  • the bus system includes a data bus, a power bus, a control bus and a status signal bus, which will not be repeated here.
  • Fig. 10 is a block diagram of a terminal device according to another embodiment of the present invention.
  • the terminal device 700 includes at least one processor 701 , a memory 702 , a user interface 703 and at least one network interface 704 .
  • Various components in the terminal device 700 are coupled together through a bus system.
  • a bus system is used to implement the link communication between these components.
  • the bus system includes data bus, power bus, control bus and status signal bus.
  • the user interface 703 may include a display, a keyboard, or a pointing device, such as a mouse, a trackball, a touch pad, or a touch screen.
  • Memory 702 stores executable modules or data structures.
  • An operating system and application programs can be stored in the memory.
  • the operating system includes various system programs, such as framework layer, core library layer, driver layer, etc., for realizing various basic services and processing tasks based on hardware.
  • the application program includes various application programs, such as a media player, a browser, etc., and is used to implement various application services.
  • the memory 702 includes a computer program for executing any embodiment of the present application, and the computer program is run or changed on the processor 701 .
  • the memory 702 includes a computer-readable storage medium, and the processor 701 reads the information in the memory 702 and completes the steps of the above method in combination with its hardware. Specifically, a computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor 701, each step of the method embodiment as described in any one of the foregoing embodiments is implemented.
  • the processor 701 may be an integrated circuit chip with signal processing capability. In the implementation process, each step of the method of the present application may be completed by an integrated logic circuit of hardware in the processor 701 or instructions in the form of software.
  • the processor 701 may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, an off-the-shelf programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component.
  • Various methods, steps and logic block diagrams disclosed in the embodiments of the present invention may be implemented or executed.
  • a general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.
  • the steps of the methods disclosed in the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor.
  • a device of the present application includes one or more processors (CPUs), input/output user interfaces, network interfaces and memory.
  • the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • the present application also proposes a computer-readable medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in any embodiment of the present application are implemented.
  • the memory 603, 702 of the present invention may include non-permanent memory in a computer-readable medium, random access memory (RAM) and/or non-volatile memory, such as read-only memory (ROM) or flash memory ( flash RAM).
  • Computer-readable media including both permanent and non-permanent, removable and non-removable media, can be implemented by any method or technology for storage of information.
  • Information may be computer readable instructions, data structures, modules of a program, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Flash memory or other memory technology, Compact Disc Read-Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic tape cartridge, tape magnetic disk storage or other magnetic storage device or any other non-transmission medium that can be used to store information that can be accessed by a computing device.
  • computer-readable media excludes transitory computer-readable media, such as modulated data signals and carrier waves.
  • this application also proposes a mobile communication system, including at least one embodiment of any terminal device in this application and/or at least one embodiment of any network device in this application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

La présente invention concerne un procédé de traitement de communication sans fil par intelligence artificielle (IA) qui comprend les étapes suivantes : des informations de liaison descendante comprennent des premières informations, les premières informations étant utilisées pour indiquer N services de téléchargement de modèle d'IA parmi lesquels effectuer une sélection, et chaque modèle d'IA comprenant des caractéristiques et des paramètres de structure de réseau neuronal; chaque modèle d'IA est utilisé pour effectuer un traitement de performance d'un côté réseau et d'un côté mobile correspondants. La présente invention comprend en outre un appareil servant à mettre en œuvre le procédé. Au moyen du procédé et de l'appareil décrits dans la présente invention, la collecte et le traitement de données sans fil ainsi que la circulation de modèles peuvent être efficacement réalisés, et diverses applications réelles de systèmes de communication sans fil basés sur la technologie d'IA sont prises en charge.
PCT/CN2022/070730 2021-12-03 2022-01-07 Procédé et dispositif de traitement de communication sans fil par intelligence artificielle WO2023097870A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111471065.0A CN114189889B (zh) 2021-12-03 2021-12-03 一种无线通信人工智能处理方法和设备
CN202111471065.0 2021-12-03

Publications (1)

Publication Number Publication Date
WO2023097870A1 true WO2023097870A1 (fr) 2023-06-08

Family

ID=80542248

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/070730 WO2023097870A1 (fr) 2021-12-03 2022-01-07 Procédé et dispositif de traitement de communication sans fil par intelligence artificielle

Country Status (2)

Country Link
CN (1) CN114189889B (fr)
WO (1) WO2023097870A1 (fr)

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116963092A (zh) * 2022-04-15 2023-10-27 维沃移动通信有限公司 模型确定方法、信息传输方法、装置及相关设备
WO2023245589A1 (fr) * 2022-06-23 2023-12-28 北京小米移动软件有限公司 Procédé et appareil de détermination de modèle de positionnement
WO2024016363A1 (fr) * 2022-07-22 2024-01-25 北京小米移动软件有限公司 Procédé, appareil et système d'interaction de modèle pour cadre d'intelligence artificielle (ia) hétérogène
CN117882453A (zh) * 2022-08-11 2024-04-12 北京小米移动软件有限公司 通信方法、装置、存储介质及芯片
WO2024040378A1 (fr) * 2022-08-22 2024-02-29 Apple Inc. Gestion et activation ou désactivation de modèle d'ia ou de ml
CN118235492A (zh) * 2022-10-19 2024-06-21 北京小米移动软件有限公司 一种基于ai模型的终端定位方法及装置
WO2024092660A1 (fr) * 2022-11-03 2024-05-10 北京小米移动软件有限公司 Procédé et appareil de sélection de modèle
WO2024092812A1 (fr) * 2022-11-04 2024-05-10 北京小米移动软件有限公司 Procédé et appareil de surveillance de modèle ia ou ml, et dispositif de communication et support d'enregistrement
CN118525493A (zh) * 2022-12-19 2024-08-20 北京小米移动软件有限公司 模型管理方法和装置
CN118282869A (zh) * 2022-12-29 2024-07-02 维沃移动通信有限公司 模型更新方法、装置及设备
WO2024073969A1 (fr) * 2023-01-12 2024-04-11 Lenovo (Beijing) Limited Procédés et appareils de gestion de modèle d'ia
WO2024103543A1 (fr) * 2023-02-10 2024-05-23 Zte Corporation Transfert de modèles de gestion de réseau d'intelligence artificielle dans des systèmes de communication sans fil

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111222046A (zh) * 2020-01-03 2020-06-02 腾讯科技（深圳）有限公司 服务配置方法、用于服务配置的客户端、设备及电子设备
US20210133562A1 (en) * 2019-11-01 2021-05-06 Lg Electronics Inc. Artificial intelligence server
WO2021203437A1 (fr) * 2020-04-10 2021-10-14 Oppo广东移动通信有限公司 Procédé d'attribution de ressources, dispositif, appareil et support d'enregistrement

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11100398B2 (en) * 2016-06-30 2021-08-24 Cogniac, Corp. Operating machine-learning models on different platforms
WO2020091842A2 (fr) * 2018-05-18 2020-05-07 Parallel Wireless, Inc. Apprentissage automatique pour l'estimation de canal
CN111510848A (zh) * 2019-01-11 2020-08-07 中国移动通信有限公司研究院 一种终端位置预测方法、装置、介质和设备
CN113543305A (zh) * 2020-04-22 2021-10-22 维沃移动通信有限公司 定位方法、通信设备和网络设备
CN111819872B (zh) * 2020-06-03 2023-08-22 北京小米移动软件有限公司 信息传输方法、装置、通信设备及存储介质

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210133562A1 (en) * 2019-11-01 2021-05-06 Lg Electronics Inc. Artificial intelligence server
CN111222046A (zh) * 2020-01-03 2020-06-02 腾讯科技（深圳）有限公司 服务配置方法、用于服务配置的客户端、设备及电子设备
WO2021203437A1 (fr) * 2020-04-10 2021-10-14 Oppo广东移动通信有限公司 Procédé d'attribution de ressources, dispositif, appareil et support d'enregistrement

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
OPPO: "Discussion on Enhanced 5G functionalities for application AI/ML services", 3GPP DRAFT; S1-214038, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, vol. SA WG1, no. Electronic Meeting; 20211111 - 20211118, 29 October 2021 (2021-10-29), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France, XP052072571 *

Also Published As

Publication number Publication date
CN114189889A (zh) 2022-03-15
CN114189889B (zh) 2024-07-05

Similar Documents

Publication Publication Date Title
WO2023097870A1 (fr) Procédé et dispositif de traitement de communication sans fil par intelligence artificielle
WO2023029338A1 (fr) Procédé et dispositif de renvoi d'informations d'état de canal basé sur une technologie de l'intelligence artificielle
CN114172765B (zh) 一种无线通信人工智能信道估计方法和设备
US20220116934A1 (en) Psfch sending method and apparatus
TWI566623B (zh) 傳輸裝置、傳輸方法及電腦程式產品
WO2019137492A1 (fr) Procédé et dispositif de transmission d'informations de commande en liaison montante
CN110915157B (zh) 数据发送与接收的方法、装置、终端及存储介质
CN108811151A (zh) 一种发送上行信息的方法、终端设备以及接入网设备
KR101385439B1 (ko) Ｓｒｉｏ 인터페이스로 연결된 ｆｐｇａ와 ｄｓｐ간 데이터 전송 방법
WO2021160102A1 (fr) Procédé et dispositifs d'indication de structure de créneaux temporels de transmission
CN107888343A (zh) 一种上行控制信息发送方法、装置及终端
TWI759507B (zh) 回饋應答訊息的傳輸方法、裝置及系統
JP2018512006A (ja) フィードバック・情報の送信及びその制御方法及び装置
WO2020029130A1 (fr) Procédé et appareil de rétroaction de demande de répétition automatique hybride
CN115580877A (zh) 一种移动通信网络数据与模型联合部署方法和设备
JP2023544578A (ja) ビーム指示方法、装置、ネットワーク側機器及び端末
WO2022116458A1 (fr) Procédé de détermination de tbs
WO2021159988A1 (fr) Procédé de transmission de données de liaison montante, équipement d'utilisateur et support de stockage lisible
WO2019238014A1 (fr) Procédé et dispositif de transmission d'informations de rétroaction
WO2022077876A1 (fr) Procédé de communication et appareil
WO2018137510A1 (fr) Procédé et appareil de transmission de données
WO2022213289A1 (fr) Procédé de rétroaction d'accusé de réception de demande de répétition automatique hybride et appareil associé
CN115767605A (zh) 一种移动通信网络ai模型部署方法和设备
WO2023227021A1 (fr) Procédés de transmission d'informations de faisceau et dispositif associé
WO2023116829A1 (fr) Procédé de transmission d'informations, procédé et appareil d'indication de transmission d'informations, et équipement utilisateur

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: 22899696

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE