WO2022233294A1 - Procédé et appareil de communication et dispositif électronique - Google Patents

Procédé et appareil de communication et dispositif électronique Download PDF

Info

Publication number
WO2022233294A1
WO2022233294A1 PCT/CN2022/090896 CN2022090896W WO2022233294A1 WO 2022233294 A1 WO2022233294 A1 WO 2022233294A1 CN 2022090896 W CN2022090896 W CN 2022090896W WO 2022233294 A1 WO2022233294 A1 WO 2022233294A1
Authority
WO
WIPO (PCT)
Prior art keywords
model
indication information
user equipment
segmentation
network
Prior art date
Application number
PCT/CN2022/090896
Other languages
English (en)
Chinese (zh)
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 WO2022233294A1 publication Critical patent/WO2022233294A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/02—Arrangements for optimising operational condition
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/06—Testing, supervising or monitoring using simulated traffic

Definitions

  • the present application relates to the field of communication technologies, and in particular, to a communication method, apparatus and electronic device.
  • network equipment and user equipment can utilize artificial intelligence (AI) models for data processing to optimize network functions.
  • AI artificial intelligence
  • the user equipment can use part of the AI model to process data, and send the obtained data processing result to the network device, and the network device uses another part of the AI model to process data from the user equipment.
  • the data processing results continue to be processed to obtain the corresponding data.
  • This approach helps reduce the requirements for data processing capabilities of user equipment, and also helps reduce the possibility of user privacy leakage.
  • the segmentation method of the AI model is fixed, and therefore, the flexibility of the segmentation of the AI model in the prior art is poor.
  • Embodiments of the present application provide a communication method, apparatus, and electronic device, so as to make the application of the AI model segmentation method more flexible, and improve the data processing capability of the device and the utilization rate of network resources during the communication process.
  • an embodiment of the present application provides a communication method, characterized in that the method includes: a first device determines a segmentation method of an artificial intelligence AI model; the first device sends first indication information to a second device, The first indication information is used to indicate a division manner of the AI model.
  • the first device is a user equipment
  • the second device is a network device
  • the first device determines a segmentation method of the AI model, including: the first device according to its own device capability, and/or network resource information, to determine the segmentation method of the AI model.
  • the network resource information is used to indicate at least one of the following information: air interface resources; and device capabilities of the second device.
  • the method further includes: receiving, by the first device, network resource information from the second device.
  • the first device is a network device
  • the second device is a user equipment
  • the first device determines a segmentation method of the AI model, including: the first device according to network resource information , and/or the device capability of the second device to determine the segmentation method of the AI model.
  • the network resource information is used to indicate at least one of the following information: air interface resources; and device capabilities of the first device.
  • the method further includes: receiving, by the first device, second indication information from the second device, where the second indication information is used to indicate a device capability of the second device .
  • the method further includes: receiving, by the first device, third indication information sent by the second device, where the third indication information is used to indicate approval of the division method of the AI model .
  • the method further includes: receiving, by the first device, fourth indication information sent by the second device, where the fourth indication information is used to indicate rejection of the segmentation method of the AI model .
  • the method further includes: the first device communicates with the second device based on a default segmentation method of the AI model.
  • the fourth indication information is further used to indicate the reason for rejecting the segmentation method of the AI model, and/or the recommended segmentation method of the AI model.
  • the method further includes: the first device determines a segmentation method of the AI model according to at least one of the following information: the device capability of the first device, the network Resource information, the device capability of the second device, the reason for rejecting the segmentation method of the AI model, or the recommended segmentation method of the AI model.
  • the sending, by the first device, the first indication information to the second device includes: the first device sending data to the second device, where the data includes the first indication information .
  • an embodiment of the present application provides a communication method, wherein the method includes: a second device receiving first indication information sent by a first device, where the first indication information is used to indicate an artificial intelligence AI model The segmentation method; the second device confirms the segmentation method of the AI model, and communicates with the first device.
  • the second device is a network device
  • the first device is user equipment
  • the method further includes: the second device sends network resource information to the first device, and the The network resource information is used to indicate at least one of the following information: air interface resources; and device capabilities of the second device.
  • the second device is a user equipment
  • the first device is a network device
  • the method further includes: the second device sends second indication information to the first device, The second indication information is used to indicate the device capability of the second device.
  • the second device confirming the division method of the AI model includes: the second device determines, according to the network resource information and/or the device capability of the second device, determining Whether to support the segmentation method of the AI model.
  • the method includes: if the second device supports the split mode of the AI model, the second device sends third indication information to the first device, the third indication Information is used to indicate consent to the segmentation of the AI model.
  • the method further includes: if the second device does not support the AI model segmentation method, sending, by the second device, fourth indication information to the first device, and the first device The four indication information is used to indicate the rejection of the segmentation method of the AI model.
  • the method further includes: the second device communicates with the first device based on a default segmentation method of the AI model.
  • the fourth indication information is further used to indicate the reason for rejecting the segmentation method of the AI model, and/or the recommended segmentation method of the AI model.
  • the second device receiving the first indication information sent by the first device includes: receiving, by the second device, data sent by the first device, the data including the first indication information .
  • an embodiment of the present application provides a communication device, which is characterized by comprising: a determining module, configured to determine a segmentation method of an artificial intelligence AI model; a sending module, configured to send first indication information to a second device, where the The first indication information is used to indicate the segmentation mode of the AI model.
  • an embodiment of the present application provides a communication device, which is characterized by comprising: a receiving module configured to receive first indication information sent by a first device, where the first indication information is used to indicate an artificial intelligence AI model Segmentation mode; a confirmation module, used to confirm the segmentation mode of the AI model, and communicate with the first device.
  • an embodiment of the present application provides an electronic device, including: at least one processor; and at least one memory communicatively connected to the processor, wherein: the memory stores a program executable by the processor Instructions, the processor invoking the program instructions to be able to perform the method of the first aspect.
  • an embodiment of the present application provides an electronic device, including: at least one processor; and at least one memory communicatively connected to the processor, wherein: the memory stores a program executable by the processor Instructions, the processor invoking the program instructions to be able to perform the method of the second aspect.
  • an embodiment of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores computer instructions, and the computer instructions cause the computer to execute the methods described in the first and second aspects.
  • the first device determines the segmentation method of the artificial intelligence AI model, and sends first indication information to the second device to indicate the segmentation method of the AI model. Then, the second device receives the first indication information, and confirms the indicated division mode of the AI model. Finally, the first device and the second device may communicate based on the determined segmentation mode of the AI model. Therefore, the application of the AI model segmentation method can be made more flexible, and the data processing capability of the device and the utilization rate of network resources can be improved during the communication process.
  • FIG. 1 is a schematic diagram of a scenario of a communication system provided by an embodiment of the present invention.
  • FIG. 2 is a schematic diagram of a scenario of a communication method provided by an embodiment of the present application.
  • FIG. 3 is a schematic diagram of a scenario of another communication method provided by an embodiment of the present application.
  • FIG. 4 is a schematic flowchart of a communication method provided by an embodiment of the present application.
  • FIG. 5 is a schematic flowchart of another communication method provided by an embodiment of the present application.
  • FIG. 6 is a schematic flowchart of another communication method provided by an embodiment of the present application.
  • FIG. 7 is a schematic flowchart of another communication method provided by an embodiment of the present application.
  • FIG. 8 is a schematic flowchart of another communication method provided by an embodiment of the present application.
  • FIG. 9 is a schematic flowchart of another communication method provided by an embodiment of the present application.
  • FIG. 10 is a schematic flowchart of another communication method provided by an embodiment of the present application.
  • FIG. 11 is a schematic flowchart of another communication method provided by an embodiment of the present application.
  • FIG. 13 is a schematic flowchart of another communication method provided by an embodiment of the present application.
  • 15 is a schematic flowchart of another communication method provided by an embodiment of the present application.
  • FIG. 16 is a schematic flowchart of another communication method provided by an embodiment of the present application.
  • FIG. 17 is a schematic structural diagram of a communication device according to an embodiment of the present application.
  • FIG. 18 is a schematic structural diagram of another communication apparatus provided by an embodiment of the present application.
  • FIG. 19 is a schematic structural diagram of an electronic device provided by an embodiment of the application.
  • FIG. 20 is a schematic structural diagram of another electronic device provided by an embodiment of the present application.
  • At least one (a) of a, b or c may represent: a, b, c, a and b, a and c, b and c, or a, b and c, where a, b, c Each can be an element itself, or a collection containing one or more elements.
  • system and “network” are often used interchangeably, but those skilled in the art can understand their meanings.
  • the user equipment is a device with a wireless transceiver function, which may be referred to as a terminal (terminal), a terminal device, a mobile station (mobile station, MS), a mobile terminal (mobile terminal, MT), and an access terminal device.
  • a terminal terminal
  • a terminal device terminal device
  • a mobile station mobile station
  • a mobile terminal mobile terminal
  • MT mobile terminal
  • an access terminal device a terminal device
  • vehicle terminal equipment industrial control terminal equipment
  • UE unit UE station
  • UE station mobile station
  • remote station remote terminal equipment
  • mobile equipment UE terminal equipment
  • wireless communication equipment UE agent or UE device
  • User equipment may be stationary or mobile.
  • the user equipment may support at least one wireless communication technology, such as Long Termevolution (LTE), New Radio (NR), Wideband Code Division Multiple Access (WCDMA) Wait.
  • LTE Long Termevolution
  • NR New Radio
  • WCDMA Wideband Code Division Multiple Access
  • the user equipment may be a mobile phone (mobile phone), a tablet computer (pad), a desktop computer, a notebook computer, an all-in-one computer, a vehicle terminal, a virtual reality (VR) terminal device, an augmented reality (AR) terminal Equipment, wireless terminals in industrial control, wireless terminals in self driving, wireless terminals in remote medical surgery, wireless terminals in smart grid, transportation safety Wireless terminals in (transportation safety), wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless Wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to wireless modems, wearable devices, future mobile communications
  • the user equipment may also be a device with a transceiving function, such as a chip system. Wherein, the chip system may be a transceiving function
  • the network device in the embodiment of the present application is a device that provides a wireless communication function for user equipment, such as an access network device, a core network element, and the like.
  • An access network device may also be referred to as an access network element, a radio access network (RAN) device, or the like.
  • the access network device may support at least one wireless communication technology, such as LTE, NR, WCDMA, and the like.
  • the access network equipment includes, but is not limited to: a next-generation base station (generation nodeB, gNB), an evolved node B (evolved node B, eNB), wireless Network controller (radio network controller, RNC), node B (node B, NB), base station controller (base station controller, BSC), base transceiver station (base transceiver station, BTS), home base station (for example, home evolved node B, or home node B, HNB), baseband unit (BBU), transmitting and receiving point (TRP), transmitting point (TP), mobile switching center, etc.
  • generation nodeB, gNB next-generation base station
  • eNB evolved node B
  • eNB wireless Network controller
  • RNC radio network controller
  • the access network device may also be a wireless controller, a centralized unit (centralized unit, CU), and/or a distributed unit (DU) in a cloud radio access network (cloud radio access network, CRAN) scenario, or an access network.
  • the network access device may be a relay station, an access point, a vehicle-mounted device, a terminal device, a wearable device, and an access network device in future mobile communications or an access network device in a future evolved PLMN, and the like.
  • the access network device may also be an apparatus having a wireless communication function for the user equipment, such as a chip system.
  • the system-on-chip may include chips, and may also include other discrete devices.
  • the core network element may be a functional entity, may be a core network device, etc., and is located in the core network. For example, access and mobility management function (AMF) network elements.
  • AMF access and mobility management function
  • FIG. 1 is a schematic diagram of a scenario of a communication system provided by an embodiment of the present invention.
  • the communication system 100 may include at least one first device 101 and at least one second device 102 .
  • the first device 101 and the second device 102, the second device 102 and the second device 102, and the first device 101 and the first device 101 are connected through wired or wireless communication technology. It should be noted that the number and form of the second device 102 and the first device 101 shown in FIG. 1 do not constitute a limitation to the embodiment of the present invention.
  • wireless communication systems mentioned in the embodiments of the present invention include but are not limited to: Narrow Band-internet of Things (NB-IoT), Long Term Evolution (Long Termevolution, LTE), fifth generation Mobile communication system, vehicle wireless short-range communication system and future mobile communication system.
  • NB-IoT Narrow Band-internet of Things
  • LTE Long Term Evolution
  • 5 generation Mobile communication system fifth generation Mobile communication system
  • vehicle wireless short-range communication system future mobile communication system.
  • the first device 101 may be a user equipment or a network device.
  • the second device 102 may be a user device or a network device.
  • AI Artificial Intelligence
  • Different types of AI models can be used to perform different network functions.
  • the AI model when applying the AI model to perform related network functions, the AI model can be divided into multiple parts, and the data processing of each part is performed by different devices. Thus, multiple devices can jointly complete the data processing flow of related network functions.
  • the above-mentioned network function may be any network function, such as the positioning function of the base station for the terminal device, etc., which is not limited in this application.
  • the "segmentation" described in the embodiments of this application may be to divide the AI model into multiple parts, and only one part is deployed on each device. It is also possible that the full AI model is deployed on each device, but only a part of it is executed.
  • the segmentation of the AI model may be two-level segmentation, that is, a complete AI model is divided into two parts.
  • the device 1 uses the first part of the AI model to process the input initial data Input to obtain intermediate data data.
  • the device 2 uses the second part of the AI model to complete subsequent data processing, and obtain the final output data Output.
  • the segmentation of the AI model may also be multi-level segmentation, that is, a complete AI model is divided into multiple parts.
  • a complete AI model can be split into 3 parts.
  • the first part of the AI model is used by the device 1 to process the input initial data Input to obtain intermediate data data1.
  • the device 2 uses the second part of the AI model to process the intermediate data data1 to obtain the intermediate data data2.
  • the device 3 uses the third part of the AI model to complete subsequent data processing, and obtain the final output data Output.
  • the embodiments of the present application do not limit the data types of the above-mentioned input data, intermediate data, and output data.
  • possible data types include, but are not limited to: arrays, scalar data, vector data, and the like.
  • the communication method provided by the embodiment of the present application can be applied to any two devices with data interaction in the above two-level segmentation or multi-level segmentation scenario.
  • the communication method provided by the embodiment of the present application can enable each device to reach a consensus on the segmentation method of the AI model, so as to perform data processing based on the consistent AI model segmentation method.
  • the first device 101 and the second device 102 shown in FIG. 1 can be used to represent any two devices with data interaction.
  • any two devices may be user equipment and network equipment, user equipment and user equipment, network equipment and network equipment, and so on.
  • the actual scene corresponding to the user equipment and the user equipment may be, for example, vehicle wireless communication (Vehicle to Everything, V2X), device to device (Device to Device, D2D), and the like.
  • the actual scenarios corresponding to the network device and the network device may be, for example, an access network device and an access network device, an access network device and a core network network element, an access network device and an edge computing server, and the like.
  • the communication method provided by the present application can simultaneously configure the corresponding AI model segmentation mode for multiple network functions.
  • this application only takes any one as an example for description.
  • FIG. 4 is a schematic flowchart of a communication method provided by an embodiment of the present application. As shown in FIG. 4 , the communication method provided by the embodiment of the present application may include:
  • Step 101 the first device determines the segmentation method of the AI model.
  • Step 102 the first device sends first indication information to the second device to indicate the splitting mode of the AI model.
  • Step 103 The second device receives the first indication information sent by the first device.
  • Step 104 the second device confirms the segmentation method of the AI model, and communicates with the first device.
  • the communication method provided by the embodiment of the present application can make the segmentation of the AI model more flexible, so as to adapt to the device capabilities and network transmission capabilities of different devices. At the same time, it can also reduce invalid data transmission and ensure the normal realization of network functions.
  • FIG. 5 is a schematic flowchart of another communication method provided by an embodiment of the present application.
  • the first device is a user equipment
  • the second device is a network device.
  • the communication method provided by this embodiment of the present application may include:
  • step 201 the user equipment determines a segmentation method of the AI model according to its own equipment capabilities.
  • the same AI model when executing the same network function, there may be multiple AI models that can be selected. Moreover, the same AI model can also have multiple optional segmentation methods. Exemplarily, the segmentation method may define the segmentation point of the AI model, the number of segmentations, the execution device corresponding to each segmented part, and the like.
  • the amount of data to be processed and the amount of output data corresponding to each part of the AI model are different.
  • the amount of data to be processed is different, and the requirements for the processing capacity of the device are different; the amount of output data is different, and the requirements for the network transmission capacity are different.
  • the user equipment may determine the segmentation manner of the AI model.
  • the user equipment may determine a segmentation manner that can be supported by its own device capability from among the segmentation manners of the optional AI model according to its own device capability.
  • the device capabilities of the user equipment itself may include: computing power resources, available power, device heating conditions, running rates, and the like.
  • the user equipment may determine the segmentation method of the AI model according to its own device capabilities and its own privacy protection requirements. Due to different segmentation methods, the output data at the model segmentation points are different. Therefore, based on this implementation manner, the user equipment can not only ensure that its own processing capability can complete corresponding data processing, but also reduce the amount of user privacy data in the output data, thereby protecting user privacy.
  • Step 202 the user equipment sends first indication information to the network device to indicate the splitting mode of the AI model.
  • each device can jointly complete the data processing of related network functions only if they have a consistent understanding of the AI model segmentation method.
  • the user equipment determines the division mode of the AI model, it can send the first indication information to the network device.
  • the first indication information may be used to notify the network device of the determined split mode of the AI model.
  • the user equipment is in a connected state.
  • the user equipment may carry the first indication information into radio resource control (Radio Resource Control, RRC) signaling, and send it to the network device.
  • RRC Radio Resource Control
  • the user equipment may carry the first indication information into a medium access control layer control element (Medium Access Control Control Element, MAC CE) signaling, and send it to the network device.
  • MAC CE Medium Access Control Control Element
  • the user equipment is in an idle state or an inactive state.
  • the user equipment may first transition to the connected state. After that, in the connected state, the user equipment carries the first indication information into RRC signaling or MAC CE signaling, and sends it to the network device.
  • the user equipment is in an idle state or an inactive state.
  • the user equipment may send the first indication information to the network device in a small packet transmission (Small Data Transmission, SDT) manner.
  • SDT Small Data Transmission
  • Step 203 The network device receives the first indication information sent by the user equipment.
  • Step 204 the network device determines, according to the network resource information, whether to support the AI model segmentation mode indicated by the first indication information. If yes, go to step 205; otherwise, go to step 206.
  • the segmentation mode of the AI model indicated by the user equipment is determined by the user equipment based on its own device capabilities. Therefore, after receiving the AI model segmentation method indicated by the user equipment, the network device may confirm the AI model segmentation method to determine whether the network resources support the AI model segmentation method.
  • the network resources may include, but are not limited to: device capabilities of network devices, air interface resources, buffer occupancy status, and channel quality.
  • the air interface resources refer to air interface resources of a cell that provides services for the user equipment.
  • the device capability of the network device may be, for example, the base station load.
  • Step 205 The network device may send third indication information to the user equipment.
  • the third indication information may be used to indicate approval of the currently determined division method of the AI model.
  • the sending manner of the third indication information may be determined according to the current state of the user equipment.
  • the network device determines that the user equipment is in a connected state.
  • the network device may carry the third indication information into RRC signaling and send it to the user equipment.
  • the network device may carry the first indication information into the MAC CE signaling and send it to the user equipment.
  • the network device determines that the user equipment is in an idle state or an inactive state.
  • the network device may send a paging message to the user equipment.
  • the paging message can be used to notify the user equipment to enter the connected state.
  • the network device may carry the third indication information into RRC signaling or MAC CE signaling, and send it to the user equipment.
  • the network device determines that the user equipment is in an idle state or an inactive state.
  • the network device may send the enhanced paging message to the user equipment.
  • the third indication message may be carried in the enhanced paging message.
  • the segmentation method of the AI model may be activated.
  • Activating the segmentation method of the AI model refers to modifying the configuration parameters of the segmentation method of the AI model.
  • the network device may activate the segmentation method of the AI model immediately after confirming that it agrees with the segmentation method of the current AI model.
  • the network device may store the information of the segmentation manner of the AI model after confirming that it agrees with the segmentation manner of the current AI model. Then, after receiving the activation indication information sent by the user equipment, activate the user equipment.
  • the activation indication information may be sent by the user equipment after receiving the third indication information. Further, the activation indication information may be carried in RRC signaling or MAC CE signaling for transmission.
  • the user equipment and the network equipment can communicate based on the determined segmentation of the AI model.
  • Step 206 the network device may send fourth indication information to the user equipment.
  • the fourth indication information may be used to indicate rejection of the currently determined segmentation method of the AI model.
  • the network device may determine the sending manner of the fourth indication information according to the current state of the user equipment.
  • the network device determines that the user equipment is in a connected state.
  • the network device may carry the fourth indication information into RRC signaling or MAC CE signaling, and send it to the user equipment.
  • the network device determines that the user equipment is in an idle state or an inactive state.
  • the network device may send a paging message to the user equipment.
  • the paging message can be used to notify the user equipment to enter the connected state.
  • the network equipment may carry the fourth indication information into RRC signaling or MAC CE signaling, and send it to the user equipment.
  • the network device determines that the user equipment is in an idle state or an inactive state.
  • the network device may send the enhanced paging message to the user equipment.
  • Fourth indication information may be carried in the enhanced paging message.
  • the user equipment and the network equipment can communicate based on the default segmentation of the AI model.
  • the default division mode can be preset.
  • the default segmentation method of the AI model can be set when the AI model is deployed or updated.
  • the default segmentation method can also include a method of not segmenting the AI model.
  • the fourth indication information may further include the reason why the network device rejects the AI model segmentation method indicated by the user equipment, the AI model segmentation method recommended by the network device, and the like.
  • the user equipment may re-determine the segmentation method of the AI model according to its own device capability, the reason for rejection indicated by the network device, and the segmentation method recommended by the network device, etc. .
  • the communication method provided by this embodiment of the present application may further include step 207 .
  • Step 207 the user equipment sends the first indication information to the network device again.
  • the re-sent first indication information may include the split mode of the AI model re-determined by the user equipment.
  • For the sending manner of the re-sent first indication information reference may be made to the foregoing step 202, which will not be repeated here.
  • the specific manner in which the user equipment and the network equipment communicate using the determined AI model segmentation manner is as follows.
  • the communication process may be initiated by the user equipment.
  • the user equipment uses the determined AI model segmentation method to process the initial data, and output intermediate data. Then, the user equipment may send the intermediate data, or data generated after performing data processing (eg, compression processing) on the intermediate data, to the network equipment, and the network equipment will perform further processing.
  • data processing eg, compression processing
  • the segmentation method of the determined AI model is the non-segmentation method
  • the corresponding intermediate data can be the initial data that has not been processed by the AI model, or the initial data that is generated after data processing (such as compression processing). data.
  • the communication process may be initiated by the network device.
  • the network device processes the initial data by using the determined segmentation method of the AI model, and obtains the intermediate data. Then, the network device may send the intermediate data, or data generated after performing data processing (eg, compression processing) on the intermediate data, to the user equipment, and the user equipment performs further processing.
  • the segmentation method of the determined AI model is the non-segmentation method
  • the corresponding intermediate data can be the initial data that has not been processed by the AI model, or the initial data is generated after data processing (such as compression processing). data.
  • the user equipment can determine the AI model segmentation method according to its own device capabilities, and send the first indication information to the network device for confirmation. After the network device confirms that it supports the segmentation method of the AI model, the network device and the user equipment can implement related network functions based on the segmentation method of the AI model.
  • the segmentation of the AI model can be made more flexible to adapt to the device capabilities and network transmission capabilities of different devices. At the same time, it can avoid invalid data transmission and ensure the normal realization of network functions.
  • FIG. 7 is a schematic flowchart of another communication method provided by an embodiment of the present application.
  • the first device is a user equipment
  • the second device is a network device.
  • the communication method provided by the embodiment of the present application includes the following processes:
  • Step 301 the network device sends network resource information to the user equipment.
  • the network resources may include, but are not limited to: device capabilities of network devices, air interface resources, buffer occupancy status, and channel quality.
  • the air interface resources refer to air interface resources of a cell that provides services for the user equipment.
  • the device capability of the network device may be, for example, the base station load.
  • Step 302 the user equipment receives the network resource information sent by the network device.
  • Step 303 the user equipment determines the segmentation method of the artificial intelligence AI model according to the network resource information and its own device capabilities.
  • the user equipment when determining the splitting method of the AI model, can take into account its own device capabilities and network resource status at the same time.
  • Step 304 the user equipment sends first indication information to the network device to indicate the splitting mode of the AI model.
  • the user equipment is in a connected state.
  • the user equipment may carry the first indication information into RRC signaling or MAC CE signaling, and send it to the network device.
  • the user equipment is in an idle state or an inactive state.
  • the user equipment may first transition to the connected state. After that, in the connected state, the user equipment carries the first indication information into RRC signaling or MAC CE signaling, and sends it to the network device.
  • the user equipment is in an idle state or an inactive state.
  • the user equipment may send the first indication information to the network device in an SDT manner.
  • Step 305 The network device receives the first indication information sent by the user equipment.
  • Step 306 the network device confirms the segmentation method of the AI model, and communicates with the user equipment.
  • the device capabilities of the user equipment and the network device and the air interface resource status are taken into consideration when the AI model is divided into the user equipment. Therefore, the likelihood of network devices agreeing with the segmentation of the AI model can be greatly increased.
  • the user equipment can jointly determine the AI model segmentation method according to its own device capabilities and network resources. Thereby, the efficiency of determining the splitting manner of the AI model between the network device and the user equipment can be improved.
  • the embodiments of the present application can make the application of the AI model segmentation method more flexible, so as to adapt to the device capabilities and network transmission capabilities of different devices.
  • FIG. 8 is a schematic flowchart of another communication method provided by an embodiment of the present application.
  • the first device is a user equipment
  • the second device is a network device.
  • the communication method provided by the embodiment of the present application may include the following processes:
  • Step 401 The network device sends network resource information to the user equipment.
  • the network resources may include, but are not limited to: device capabilities of network devices, air interface resources, buffer occupancy status, and channel quality.
  • the air interface resources refer to air interface resources of a cell that provides services for the user equipment.
  • the device capability of the network device may be, for example, the base station load.
  • Step 402 the user equipment receives the network resource information sent by the network device.
  • Step 403 the user equipment determines a segmentation method of the artificial intelligence AI model according to the network resource information and its own device capabilities.
  • Step 404 the user equipment sends data to the network device, where the data includes first indication information to indicate the division mode of the AI model.
  • the data sent by the user equipment may include first indication information, which is used to indicate the division mode of the AI model.
  • the data may also include intermediate data.
  • the intermediate data refers to the data that the user equipment processes the initial data to the output data of the model segmentation point by using the determined segmentation method of the AI model.
  • the user equipment is in a connected state.
  • the sending form of data may be RRC signaling, MAC CE signaling, or data radio bearer (Data Radio Bearer, DRB), etc.
  • the user equipment is in an idle state or an inactive state.
  • the sending form of the data may be an SDT manner, a connection establishment request MsgA message, and the like.
  • Step 405 the network device receives the data sent by the user equipment.
  • Step 406 the network device confirms the segmentation method of the AI model according to the received data, and communicates with the user equipment.
  • the network device may determine, according to the first indication information included in the data, the splitting manner of the AI model indicated by the user equipment. After that, the network device can continue to process the intermediate data contained in the data based on the segmentation method of the AI model.
  • the user equipment after the user equipment determines the segmentation method of the AI model, it can send the intermediate data and the information of the segmentation method to the network device together.
  • the network device can perform further data on the intermediate data based on the segmentation method of the AI model.
  • the application of the AI model segmentation method can be made more flexible, so as to adapt to the device capability and network transmission capability of each device.
  • the method of transmitting the indication information of the split mode together with the intermediate data can improve the efficiency of performing related network functions between devices.
  • FIG. 9 is a schematic flowchart of another communication method provided by an embodiment of the present application.
  • the first device is a user equipment
  • the second device is a network device.
  • the communication method provided by the embodiment of the present application may include the following processes:
  • step 501 the user equipment determines a segmentation method of the AI model according to its own equipment capabilities.
  • Step 502 the user equipment sends data to the network device, where the data includes first indication information to indicate the division mode of the AI model.
  • the data sent by the user equipment may include first indication information, which is used to indicate the division manner of the AI model.
  • the data can also contain intermediate data.
  • the user equipment is in a connected state.
  • the sending form of the data may be RRC signaling, MAC CE signaling, or DRB, etc.
  • the user equipment is in an idle state or an inactive state.
  • the transmission form of the data may be an SDT method, a MsgA message, or the like.
  • Step 503 the network device receives the data sent by the user equipment.
  • Step 504 The network device determines, according to the network resource information, whether to support the splitting method of the AI model indicated by the first indication information. If supported, go to step 505; otherwise, go to step 506.
  • the network device may obtain the division mode of the AI model indicated by the user equipment according to the first indication information included in the data.
  • the segmentation mode of the AI model indicated by the user equipment is determined by the user equipment based on its own device capabilities. Therefore, the network device can judge the division method of the AI model to determine whether the network resource supports the division method of the AI model.
  • Step 505 the network device sends third indication information to the user equipment.
  • the third indication information is used to indicate approval of the splitting manner of the AI model indicated by the first indication information.
  • the sending manner of the third indication information may be determined according to the current state of the user equipment.
  • the network device determines that the user equipment is in a connected state.
  • the network device may carry the third indication information into RRC signaling and send it to the user equipment.
  • the network device may carry the third indication information into the MAC CE signaling and send it to the user equipment.
  • the network device determines that the user equipment is in an idle state or an inactive state.
  • the network device may send a paging message to the user equipment.
  • the paging message can be used to notify the user equipment to enter the connected state.
  • the network device may carry the third indication information into RRC signaling or MAC CE signaling, and send it to the user equipment.
  • the network device determines that the user equipment is in an idle state or an inactive state.
  • the network device may send the enhanced paging message to the user equipment.
  • the third indication message may be carried in the enhanced paging message.
  • the segmentation method of the AI model can be activated. After that, the network device can obtain the intermediate data from the data sent by the user equipment, and continue to process the intermediate data based on the segmentation method of the AI model.
  • Step 506 the network device sends fourth prompt information to the user equipment.
  • the network device may discard the intermediate data included in the data.
  • the network device may retain the intermediate data contained in the data, and continue to process the intermediate data in appropriate scenarios.
  • a suitable scenario may be a scenario in which the state of the network resources can support the above-mentioned segmentation method of the AI model.
  • the network device may send fourth indication information to the user equipment.
  • the fourth indication information may be used to indicate the rejection of the division manner of the AI model indicated by the user equipment.
  • the network device may determine the sending manner of the fourth indication information according to the current state of the user equipment.
  • the network device determines that the user equipment is in a connected state.
  • the network device may carry the fourth indication information into RRC signaling and send it to the user equipment.
  • the network device may carry the fourth indication information into the MAC CE signaling and send it to the user equipment.
  • the network device determines that the user equipment is in an idle state or an inactive state.
  • the network device may send a paging message to the user equipment.
  • the paging message can be used to notify the user equipment to enter the connected state.
  • the network equipment may carry the fourth indication information into RRC signaling or MAC CE signaling, and send it to the user equipment.
  • the network device determines that the user equipment is in an idle state or an inactive state.
  • the network device may send the enhanced paging message to the user equipment.
  • Fourth indication information may be carried in the enhanced paging message.
  • the network device and the user equipment may communicate based on the default segmentation method.
  • the fourth indication information may also indicate the reason why the network device rejects the AI model segmentation method indicated by the user equipment, the AI model segmentation method recommended by the network device, and the like.
  • the communication method provided by the embodiment of the present application may further include step 507 .
  • Step 507 the user equipment sends data to the network device again.
  • the re-sent data may include the first indication information re-determined by the user equipment and the intermediate data.
  • the specific sending manner of re-sending the data reference may be made to the foregoing step 502, which will not be repeated here.
  • receiving the information of the division mode re-determined by the user equipment may be receiving data re-sent by the user equipment.
  • the re-sent data may include the re-determined first indication information and the intermediate data.
  • the user equipment determines the segmentation method of the AI model
  • it can send the intermediate data and the information of the segmentation method to the network device together.
  • the network device can confirm the AI model segmentation method according to the network resource information.
  • the AI model segmentation method is determined through negotiation between devices, which can make the application of the AI model segmentation method more flexible to adapt to the device capabilities and network transmission capabilities of each device.
  • the instruction information of the AI model segmentation method is transmitted together with the intermediate data, which can improve the efficiency of performing related network functions between devices.
  • FIG. 11 is a schematic flowchart of another communication method provided by an embodiment of the present application.
  • the first device is a network device
  • the second device is a user equipment.
  • the communication method provided by this embodiment of the present application may include:
  • step 601 the network device determines the segmentation method of the AI model according to the network resource information.
  • the network device can determine the AI model segmentation mode that can be supported by the network device from each optional AI model segmentation mode according to the network resource information.
  • the network resource information may include: device capabilities of the network device itself, air interface resources, buffer occupancy status, channel quality, and the like.
  • Step 602 The network device sends first indication information to the user equipment to indicate the splitting mode of the AI model.
  • the network device may determine a specific form of sending the first indication information according to the current state of the user equipment.
  • the network device may send RRC signaling or MAC CE signaling to the user equipment.
  • the first indication information may be carried in the RRC signaling or the MAC CE signaling to indicate the corresponding AI model division mode.
  • the network device may send a paging message to the user equipment to notify the user equipment to enter the connected state. Then, the network device may send RRC signaling or MAC CE signaling to the connected state user equipment, and carry the first indication information in the RRC signaling or MAC CE signaling.
  • the network device may send an enhanced paging message to the user equipment.
  • the enhanced paging message may carry the first indication information to indicate the division manner of the corresponding AI model.
  • Step 603 the user equipment receives the first indication information sent by the network device.
  • Step 604 the user equipment determines whether to support the AI model segmentation mode indicated by the first indication information according to its own device capabilities. If yes, go to step 605; otherwise, go to step 606.
  • the segmentation method of the AI model indicated by the network device is determined by the network device based on network resource information. Therefore, after receiving the segmentation method of the AI model indicated by the network device, the user equipment can confirm the segmentation method of the AI model to determine whether its own device capability supports the segmentation method of the AI model.
  • the device capabilities of the user equipment itself may include: computing power resources, available power, device heating conditions, running rates, and privacy protection requirements.
  • Step 605 the user equipment sends third indication information to the network device.
  • the third indication information may be used to indicate agreeing with the splitting manner of the AI model determined by the network device.
  • the user equipment may determine the sending form of the third indication information according to the current equipment state.
  • the user equipment is in a connected state.
  • the user equipment may carry the third indication information into RRC signaling or MAC CE signaling, and send it to the network device.
  • the user equipment is in an idle state or an inactive state.
  • the user equipment may first transition to the connected state. After that, in the connected state, the user equipment carries the third indication information into RRC signaling or MAC CE signaling, and sends it to the network device.
  • the user equipment is in an idle state or an inactive state.
  • the user equipment may send the third indication information to the network equipment by means of SDT.
  • the user equipment and the network equipment can communicate based on the determined segmentation of the AI model.
  • Step 606 the user equipment sends fourth indication information to the network device.
  • the fourth indication information may be used to indicate rejecting the splitting manner of the AI model determined by the network device.
  • the user equipment may determine the sending form of the fourth indication information according to the current equipment state.
  • the user equipment is in a connected state.
  • the user equipment may carry the fourth indication information into RRC signaling or MAC CE signaling, and send it to the network device.
  • the user equipment is in an idle state or an inactive state.
  • the user equipment may first transition to the connected state. After that, in the connected state, the user equipment carries the fourth indication information into RRC signaling or MAC CE signaling, and sends it to the network device.
  • the user equipment is in an idle state or an inactive state.
  • the user equipment may send the fourth indication information to the network equipment in an SDT manner.
  • the user equipment and the network equipment can communicate based on the default segmentation of the AI model.
  • the default division mode can be preset.
  • the default segmentation method of the AI model can be set when the AI model is deployed or updated.
  • the default segmentation method can include a method that does not segment the AI model.
  • the fourth indication information may further indicate the reason why the user equipment rejects the AI model segmentation method, the AI model segmentation method recommended by the user equipment, and the like.
  • the network device may re-determine the segmentation method of the AI model according to the network resource information, the rejection reason of the user equipment, and the segmentation method recommended by the user equipment.
  • the communication method provided by this embodiment of the present application may further include step 607 .
  • Step 607 the network device sends the first indication information to the user equipment again.
  • the re-sent first indication information may include the division mode of the AI model re-determined by the network device.
  • For the sending manner of the re-sent first indication information reference may be made to the foregoing step 602, which will not be repeated here.
  • the specific manner in which the user equipment and the network equipment communicate using the determined AI model segmentation manner is as follows.
  • the communication process may be initiated by the user equipment.
  • the user equipment uses the determined AI model segmentation method to process the initial data to obtain the intermediate data. Then, the user equipment may send the intermediate data, or data generated after performing data processing (eg, compression processing) on the intermediate data, to the network equipment, and the network equipment will perform further processing.
  • data processing eg, compression processing
  • the segmentation method of the determined AI model is the non-segmentation method
  • the corresponding intermediate data can be the initial data that has not been processed by the AI model, or the initial data that is generated after data processing (such as compression processing). data.
  • the communication process may be initiated by the network device.
  • the network device processes the initial data by using the determined AI model segmentation method to obtain intermediate data. Then, the network device may send the intermediate data, or data generated after performing data processing (eg, compression processing) on the intermediate data, to the user equipment, and the user equipment performs further processing.
  • the segmentation method of the determined AI model is the non-segmentation method
  • the corresponding intermediate data can be the initial data that has not been processed by the AI model, or the initial data is generated after data processing (such as compression processing). data.
  • the network device can determine the splitting method of the AI model, and send the first indication information to the user equipment for confirmation.
  • the network device and the user equipment can implement related network functions based on the segmentation method of the AI model.
  • the segmentation of the AI model can be made more flexible to adapt to the device capabilities and network transmission capabilities of different devices.
  • invalid data transmission can be reduced to ensure the normal realization of network functions.
  • FIG. 13 is a schematic flowchart of another communication method provided by an embodiment of the present application.
  • the first device is a network device
  • the second device is a user equipment.
  • the communication method provided by the embodiment of the present application includes the following processes:
  • Step 701 The user equipment sends second indication information to the network device to indicate the device capability of the user equipment.
  • the user equipment may determine the sending form of the second indication information according to the current equipment state.
  • the user equipment is in a connected state.
  • the user equipment may carry the second indication information into RRC signaling or MAC CE signaling, and send it to the network device.
  • the user equipment is in an idle state or an inactive state.
  • the user equipment may first transition to the connected state. After that, in the connected state, the user equipment carries the second indication information into RRC signaling or MAC CE signaling, and sends it to the network device.
  • the user equipment is in an idle state or an inactive state.
  • the user equipment may send the second indication information to the network device in an SDT manner.
  • Step 702 The network device receives the second indication information sent by the user equipment.
  • Step 703 The network device determines a segmentation method of the AI model according to the device capability of the user equipment and the network resource information.
  • the network device when determining the division method of the AI model, can take into account the device capability of the user equipment and the state of the network resources at the same time.
  • Step 704 the network device sends the first indication information to the user equipment to indicate the division mode of the AI model.
  • the network device may determine a specific form of sending the first indication information according to the current state of the user equipment.
  • the network device may send RRC signaling or MAC CE signaling to the user equipment.
  • the first indication information may be carried in the RRC signaling or the MAC CE signaling to indicate the corresponding AI model division mode.
  • the network device may send a paging message to the user equipment to notify the user equipment to enter the connected state. Then, the network device may send the RRC signaling or the MAC CE signaling to the connected state user equipment, and carry the first indication information in the RRC signaling or the MAC CE signaling.
  • the network device may send an enhanced paging message to the user equipment.
  • the enhanced paging message may carry the first indication information to indicate the division manner of the corresponding AI model.
  • Step 705 The user equipment receives the first indication information sent by the network device.
  • Step 706 the user equipment confirms the segmentation method of the AI model according to the first indication information, and communicates with the network device.
  • the segmentation method of the AI model determined by the network device can be adapted to the device capabilities and air interface resource status of the network device and the user equipment at the same time.
  • the likelihood that the user equipment agrees with the segmentation method of the AI model can be greatly improved.
  • the network can jointly determine the AI model segmentation method according to the network resource information and the device capability of the user equipment.
  • the efficiency of determining the splitting mode of the AI model between the network device and the user device can be improved.
  • the embodiments of the present application can make the application of the AI model segmentation method more flexible, and can adapt to the device capabilities and network transmission capabilities of different devices.
  • FIG. 14 is a schematic flowchart of another communication method provided by an embodiment of the present application.
  • the first device is a network device
  • the second device is a user equipment.
  • the communication method provided by the embodiment of the present application includes the following processes:
  • Step 801 the user equipment sends second indication information to the network device to indicate the device capability of the user equipment.
  • the user equipment may determine the sending form of the second indication information according to the current equipment state.
  • the user equipment is in a connected state.
  • the user equipment may carry the second indication information into RRC signaling or MAC CE signaling, and send it to the network device.
  • the user equipment is in an idle state or an inactive state.
  • the user equipment may first transition to the connected state. After that, in the connected state, the user equipment carries the second indication information into RRC signaling or MAC CE signaling, and sends it to the network device.
  • the user equipment is in an idle state or an inactive state.
  • the user equipment may send the second indication information to the network device in an SDT manner.
  • Step 802 The network device receives the second indication information sent by the user equipment.
  • Step 803 The network device determines a segmentation method of the AI model according to the device capability of the user equipment and the network resource information.
  • Step 804 The network device sends data to the user equipment, where the data includes first indication information to indicate the splitting manner of the AI model.
  • the network device determines that the user equipment is in a connected state.
  • the sending form of the data may be RRC signaling, MAC CE signaling, or DRB, etc.
  • the network device determines that the user equipment is in an idle state or an inactive state.
  • the sending form of the data may be a multicast broadcast service (Multicast Broadcast Service, MBS) manner.
  • MBS Multicast Broadcast Service
  • the network device determines that the user equipment is in an idle state or an inactive state.
  • the network device may send a paging message to the user equipment to notify the user equipment to enter the connected state. Then, the network device may send data to the user equipment in the connected state.
  • the transmission form of data can be RRC signaling, MAC CE signaling or DRB, etc.
  • the data sent by the network device may include first indication information, which is used to indicate the division mode of the AI model.
  • the data may also include intermediate data.
  • the intermediate data refers to the data output after the network device processes the initial data to the split point by using the determined split method of the AI model.
  • Step 805 the user equipment receives the data sent by the network device.
  • Step 806 the user equipment confirms the segmentation method of the AI model according to the received data, and communicates with the network device.
  • the user equipment after receiving the data sent by the network device, the user equipment can determine the splitting method of the AI model according to the first indication information included in the data. Then, the intermediate data contained in the data can be processed based on the segmentation method of the AI model.
  • the network device after the network device determines the segmentation mode of the AI model, it can send the intermediate data and the information of the segmentation mode to the user equipment together.
  • the embodiments of the present application determine the AI model segmentation method through negotiation between devices, which can make the application of the AI model segmentation method more flexible, so as to adapt to the device capabilities and network transmission capabilities of different devices.
  • the intermediate data and the information of the segmentation method are sent together, which can further improve the efficiency of performing related network functions between devices.
  • FIG. 15 is a schematic flowchart of another communication method provided by an embodiment of the present application.
  • the first device is a network device
  • the second device is a user equipment.
  • the communication method provided by the embodiment of the present application includes the following processes:
  • Step 901 the network device determines the segmentation method of the AI model according to the network resource information.
  • the network device can determine the division mode of the AI model that can be supported by itself from the division modes of each optional AI model according to the network resource information.
  • the network resource information may include: device capabilities of the network device itself, air interface resources, buffer occupancy status, channel quality, and the like.
  • Step 902 The network device sends data to the user equipment, where the data includes first indication information to indicate the splitting mode of the AI model.
  • the network device determines that the user equipment is in a connected state.
  • the sending form of the data may be RRC signaling, MAC CE signaling, or DRB, etc.
  • the network device determines that the user equipment is in an idle state or an inactive state.
  • the transmission form of the data may be the MBS manner.
  • the network device determines that the user equipment is in an idle state or an inactive state.
  • the network device may send a paging message to the user equipment to notify the user equipment to enter the connected state. Then, the network device can send data to the user equipment in the connected state, and the data can be sent in the form of RRC signaling, MAC CE signaling, or DRB.
  • the data sent by the network device may include the first indication information.
  • the first indication information is used to indicate the segmentation mode of the AI model.
  • the data can also contain intermediate data.
  • the intermediate data refers to the data output after the network device processes the initial data to the split point by using the determined split method of the AI model.
  • Step 903 the user equipment receives data sent by the network device.
  • Step 904 the user equipment determines whether to support the AI model segmentation mode indicated by the network device according to its own device capabilities. If yes, go to step 905; otherwise, go to step 906.
  • the user equipment After receiving the data sent by the network device, the user equipment can obtain the segmentation mode of the AI model indicated by the network device according to the first indication information included in the data.
  • the segmentation method of the AI model indicated by the network device is determined by the network device based on its own device capability. Therefore, the user equipment can judge the segmentation method of the AI model to determine whether its own device capability supports the segmentation method of the AI model.
  • Step 905 the user equipment sends third indication information to the network device.
  • the third indication information is used to indicate that the division mode indicated by the network device is agreed.
  • the user equipment may determine the sending form of the third indication information according to the current equipment state.
  • the user equipment is in a connected state.
  • the user equipment may carry the third indication information into RRC signaling or MAC CE signaling, and send it to the network device.
  • the user equipment is in an idle state or an inactive state.
  • the user equipment may first transition to the connected state. After that, in the connected state, the user equipment carries the third indication information into RRC signaling or MAC CE signaling, and sends it to the network device.
  • the user equipment is in an idle state or an inactive state.
  • the user equipment may send the third indication information to the network device in an SDT manner.
  • the user equipment may obtain intermediate data from the data sent by the network equipment. Then, based on the segmentation method of the AI model, continue to process the intermediate data.
  • Step 906 the user equipment sends fourth indication information to the network device.
  • a suitable scenario may be a scenario in which the device capability of the user equipment can support the above-mentioned segmentation method of the AI model.
  • the user equipment may send fourth indication information to the network device.
  • the fourth indication information is used to indicate the rejection of the division mode indicated by the network device.
  • the user equipment may determine the sending form of the fourth indication information according to the current equipment state.
  • the user equipment is in a connected state.
  • the user equipment may carry the fourth indication information into RRC signaling or MAC CE signaling, and send it to the network device.
  • the user equipment is in an idle state or an inactive state.
  • the user equipment may first transition to the connected state. After that, in the connected state, the user equipment carries the fourth indication information into RRC signaling or MAC CE signaling, and sends it to the network device.
  • the user equipment is in an idle state or an inactive state.
  • the user equipment may send the fourth indication information to the network device in an SDT manner.
  • the network device and the user equipment may communicate based on the default segmentation method.
  • the fourth indication information may further include the reason why the user equipment rejects the segmentation method indicated by the network device, the segmentation method of the AI model recommended by the user equipment, and the like.
  • the communication method provided by this embodiment of the present application may further include step 907 .
  • Step 907 the network device sends data to the user equipment again.
  • the re-sent data may include the first indication information re-determined by the network device and the intermediate data.
  • the specific sending manner of sending the data again reference may be made to the foregoing step 902, which will not be repeated here.
  • receiving the information of the division mode re-determined by the network device may be receiving data re-sent by the network device.
  • the re-sent data may include the re-determined first indication information and the intermediate data.
  • the network device determines the segmentation mode of the AI model
  • it can send the intermediate data and the information of the segmentation mode to the user equipment together.
  • the user equipment can confirm the AI model segmentation method according to the network resource information.
  • the AI model segmentation method is determined through negotiation between devices, which can make the application of the AI model segmentation method more flexible to adapt to the device capabilities and network transmission capabilities of each device.
  • the instruction information of the AI model segmentation method is transmitted together with the intermediate data, which can improve the efficiency of performing related network functions between devices.
  • FIG. 17 is a schematic structural diagram of a communication apparatus according to an embodiment of the present application.
  • the first device 20 may include: a determining module 21 and a sending module 22 .
  • the determination module 21 is used for determining the segmentation mode of the artificial intelligence AI model.
  • the sending module 22 is configured to send first indication information to the second device, where the first indication information is used to indicate a division mode of the AI model.
  • the determining module 21 may be specifically configured to determine the segmentation method of the AI model according to its own device capability and/or network resource information.
  • the network resource information is used to indicate at least one of the following information: air interface resources, and device capabilities of the second device.
  • the communication apparatus provided in this embodiment of the present application may further include a first receiving module 23, configured to receive network resource information from the second device.
  • the determining module 21 is further configured to determine the division mode of the AI model according to the network resource information and/or the device capability of the second device.
  • the network resource information is used to indicate at least one of the following information: air interface resources, and device capabilities of the first device.
  • the first receiving module 23 is further configured to receive second indication information from the second device, where the second indication information is used to indicate the device capability of the second device.
  • the first receiving module 23 is further configured to receive third indication information sent by the second device, where the third indication information is used to indicate agreeing with the division method of the AI model.
  • the first receiving module 23 is further configured to receive fourth indication information sent by the second device, where the fourth indication information is used to indicate the rejection of the split mode of the AI model.
  • the communication apparatus in this embodiment of the present application may further include a first communication module 24, configured to communicate with the second device based on the default segmentation method of the AI model.
  • the determining module 21 is further configured to, according to at least one of the following information, determine the AI model segmentation method: the device capability of the first device, the network resource information, the device capability of the second device, the rejection The reason for the segmentation method of the AI model, or the recommended segmentation method of the AI model.
  • the sending module 22 is specifically configured to send data to the second device, where the data includes the first indication information.
  • FIG. 18 is a schematic structural diagram of another communication apparatus provided by an embodiment of the present application.
  • FIG. 18 shows a possible schematic structural diagram of the second device involved in the foregoing embodiment.
  • the second device 30 may include: a receiving module 31 and a confirming module 32 .
  • the receiving module 31 is configured to receive first indication information sent by the first device, where the first indication information is used to indicate a division method of the artificial intelligence AI model.
  • the confirmation module 32 is used to confirm the segmentation mode of the AI model and communicate with the first device.
  • the communication apparatus in this embodiment of the present application may further include a first sending module 33, configured to send network resource information to the first device, where the network resource information is used to indicate at least one of the following information: air interface resources ; The device capability of the second device.
  • a first sending module 33 configured to send network resource information to the first device, where the network resource information is used to indicate at least one of the following information: air interface resources ; The device capability of the second device.
  • the first sending module 33 is further configured for the first device to send second indication information, where the second indication information is used to indicate the device capability of the second device.
  • the confirmation module 32 is specifically configured to, according to the network resource information and/or the device capability of the second device, determine whether to support the segmentation method of the AI model.
  • the first sending module 33 is further configured to send third indication information to the first device, and the third indication information is used to indicate that the How the AI model is segmented.
  • the first sending module 33 is further configured to send fourth indication information to the first device, where the fourth indication information is used to indicate rejection of AI How the model is split.
  • the communication apparatus provided in this embodiment of the present application further includes a second communication module 34 .
  • the second communication module 34 may be configured to communicate with the first device based on the default segmentation mode of the AI model.
  • the receiving module 31 is further configured to receive data sent by the first device, where the data includes the first indication information.
  • FIG. 19 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention.
  • a simplified schematic diagram of a possible design structure of the first device involved in the above method embodiment is shown in FIG. 19 .
  • the first device includes a transceiver 401, a processor 402, a memory 403 and a modem 404, and the transceiver 401, the processor 402, the memory 403 and the modem 404 are connected by a bus.
  • Transceiver 401 conditions (eg, analog converts, filters, amplifies, and frequency converts, etc.) the output samples and generates a signal, which is transmitted via an antenna to the second device in the above-described embodiments.
  • the antenna receives the signal from the second device in the above embodiment.
  • the transceiver 401 conditions (eg, filters, amplifies, frequency converts, and digitizes, etc.) the signal received from the antenna and provides input samples.
  • encoder 4041 receives and processes (eg, formats, encodes, and interleaves) the traffic data and signaling messages to be transmitted.
  • Modulator 4042 further processes (eg, symbol mapping and modulation) the encoded traffic data and signaling messages and provides the output samples described above.
  • a demodulator 4043 processes (eg, demodulates) the input samples and provides symbol estimates.
  • a decoder 4044 processes (eg, de-interleaves and decodes) the symbol estimates and provides decoded data and signaling messages for transmission to the first device.
  • the encoder 4041 , the modulator 4042 , the demodulator 4043 and the decoder 4044 may be implemented by the combined modem 404 . These elements are processed according to the radio access technology employed by the radio access network (eg, access technologies for LTE, 5G, and other evolved systems).
  • the transceiver 401 is integrated by the transmitter and the receiver. In other embodiments, the transmitter and the receiver may be independent of each other.
  • the processor 402 controls and manages the first device, and is configured to execute the processing steps performed by the first device in the foregoing method embodiments.
  • the processor 402 may include one or more processors, such as one or more CPUs, and the processor 402 may be integrated into a chip, or may be the chip itself.
  • the memory 403 is used to store relevant instructions and data, as well as program codes and data of the terminal.
  • the memory 403 includes, but is not limited to, a random access memory (Random Access Memory, RAM), a read-only memory (Read-Only Memory, ROM), an erasable programmable read-only memory (Erasable Programmable Read) Only Memory, EPROM), non-transitory computer readable storage medium (non-transitory computer readable storage medium) or portable read-only memory (Compact Disc Read-Only Memory, CDROM).
  • the memory 403 is independent of the processor 402 . In other embodiments, the memory 403 may also be integrated in the processor 402 .
  • Figure 19 only shows a simplified design of the first device.
  • the first device may include any number of transmitters, receivers, processors, memories, etc., and all first devices that can implement the present application are within the protection scope of the present application.
  • FIG. 20 is a schematic structural diagram of another electronic device provided by an embodiment of the present invention.
  • a simplified schematic diagram of a possible design structure of the second device involved in the above method embodiment is shown in FIG. 20 .
  • the second device includes a transceiver 501, a processor 502, a memory 503 and a modem 504, and the transceiver 501, the processor 502, the memory 503 and the modem 504 are connected by a bus.
  • the transceiver 501 conditions (eg, analog converts, filters, amplifies and frequency converts, etc.) the output samples and generates a signal that is transmitted via the antenna to the first device in the above-described embodiments.
  • the antenna receives the signal from the first device in the above embodiment.
  • Transceiver 501 conditions (e.g., filters, amplifies, frequency converts, and digitizes, etc.) the signal received from the antenna and provides input samples.
  • encoder 5041 receives and processes (eg, formats, encodes, and interleaves) the traffic data and signaling messages to be transmitted.
  • Modulator 5042 further processes (eg, symbol mapping and modulation) the encoded traffic data and signaling messages and provides the output samples described above.
  • a demodulator 5043 processes (eg, demodulates) the input samples and provides symbol estimates.
  • a decoder 5044 processes (eg, deinterleaves and decodes) the symbol estimates and provides decoded data and signaling messages for transmission to the second device.
  • the encoder 5041 , the modulator 5042 , the demodulator 5043 and the decoder 5044 may be implemented by the combined modem 504 . These elements are processed according to the radio access technology employed by the radio access network (eg, access technologies for LTE, 5G, and other evolved systems).
  • the transceiver 501 is integrated by the transmitter and the receiver. In other embodiments, the transmitter and the receiver may be independent of each other.
  • the processor 502 controls and manages the second device, and is configured to execute the processing steps performed by the second device in the foregoing method embodiments.
  • the processor 502 may include one or more processors, such as one or more CPUs, and the processor 502 may be integrated into a chip, or may be the chip itself.
  • the memory 503 is used to store relevant instructions and data, as well as program codes and data of the terminal.
  • the memory 503 includes, but is not limited to, a random access memory (Random Access Memory, RAM), a read-only memory (Read-Only Memory, ROM), an erasable programmable read-only memory (Erasable Programmable Read) Only Memory, EPROM), non-transitory computer readable storage medium (non-transitory computer readable storage medium) or portable read-only memory (Compact Disc Read-Only Memory, CDROM).
  • the memory 503 is independent of the processor 502 . In other embodiments, the memory 503 may also be integrated in the processor 502 .
  • Figure 20 only shows a simplified design of the second device.
  • the second device may include any number of transmitters, receivers, processors, memories, etc., and all second devices that can implement the present application are within the protection scope of the present application.
  • an embodiment of the present invention further provides a communication system, where the communication system includes the first device shown in FIG. 19 and the second device shown in FIG. 20 .
  • an embodiment of the present invention further provides a communication chip, where the communication chip may be a chip that implements the first device structure.
  • the communication chip includes: a processor for executing computer program instructions stored in the memory, wherein, when the computer program instructions are executed by the processor, the communication chip is triggered to execute the first step in the above embodiment. A method performed by a device.
  • embodiments of the present invention further provide a communication chip, where the communication chip may be a chip that implements the second device structure.
  • the communication chip includes: a processor for executing computer program instructions stored in the memory, wherein, when the computer program instructions are executed by the processor, the communication chip is triggered to execute the first step in the above embodiment. Two methods performed by the device.
  • the present application further provides a computer storage medium, wherein the computer storage medium can store a program, and when the program is executed, it can include some or all of the steps in the various embodiments provided in the present application.
  • the storage medium may be a magnetic disk, an optical disk, a read-only memory (English: read-only memory, abbreviated as: ROM) or a random access memory (English: random access memory, abbreviated as: RAM) and the like.
  • an embodiment of the present invention further provides a computer program product, where the computer program product includes executable instructions, and when the executable instructions are executed on a computer, causes the computer to execute part or some of the above method embodiments. all steps.
  • the disclosed system, apparatus and method may be implemented in other manners.
  • the apparatus embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components may be combined. Either it can be integrated into another system, or some features can be omitted, or not implemented.
  • the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.
  • the above-mentioned integrated unit may be implemented in the form of hardware, or may be implemented in the form of hardware plus software functional units.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

La présente demande se rapporte au domaine technique des communications, et fournit un procédé et un appareil de communication et un dispositif électronique. Le procédé de communication est le suivant : tout d'abord, un premier dispositif détermine un mode de segmentation de modèle d'intelligence artificielle (AI), et envoie des premières informations d'Indication à un second dispositif pour indiquer le mode de segmentation de modèle d'AI ; puis, le second dispositif reçoit les premières informations d'indication, et confirme le mode de segmentation de modèle d'AI indiqué ; et en fin de compte, le premier dispositif et le second dispositif peuvent communiquer sur la base du mode de segmentation de modèle d'AI déterminé. Ainsi, l'application du mode de segmentation de modèle d'AI peut être plus flexible, et la capacité de traitement de données du dispositif et le taux d'utilisation de ressources réseau pendant un processus de communication sont améliorés.
PCT/CN2022/090896 2021-05-07 2022-05-05 Procédé et appareil de communication et dispositif électronique WO2022233294A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110497171.XA CN115314915A (zh) 2021-05-07 2021-05-07 通信方法、装置和电子设备
CN202110497171.X 2021-05-07

Publications (1)

Publication Number Publication Date
WO2022233294A1 true WO2022233294A1 (fr) 2022-11-10

Family

ID=83853080

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/090896 WO2022233294A1 (fr) 2021-05-07 2022-05-05 Procédé et appareil de communication et dispositif électronique

Country Status (2)

Country Link
CN (1) CN115314915A (fr)
WO (1) WO2022233294A1 (fr)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112005565A (zh) * 2020-06-29 2020-11-27 北京小米移动软件有限公司 用户设备辅助信息的上报方法及装置、用户设备、存储介质
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
WO2021212347A1 (fr) * 2020-04-21 2021-10-28 Oppo广东移动通信有限公司 Procédé de communication et dispositif associé

Patent Citations (4)

* 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
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
WO2021212347A1 (fr) * 2020-04-21 2021-10-28 Oppo广东移动通信有限公司 Procédé de communication et dispositif associé
CN112005565A (zh) * 2020-06-29 2020-11-27 北京小米移动软件有限公司 用户设备辅助信息的上报方法及装置、用户设备、存储介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
OPPO, SAMSUNG: "Update to AMMT use case - Session-specific model transfer split computation decision operation", 3GPP DRAFT; S1-210378, vol. SA WG1, 15 March 2021 (2021-03-15), pages 1 - 4, XP051986485 *

Also Published As

Publication number Publication date
CN115314915A (zh) 2022-11-08

Similar Documents

Publication Publication Date Title
CN109716700B (zh) 一种指示方法及相关设备
US11489760B2 (en) Multicast group creation method, multicast group joining method, and apparatus
US20110069681A1 (en) Method and apparatus for supporting short messaging service of mobile station during idle mode in wireless communication system
US11259362B2 (en) Method for repeatedly transmitting data and device
CN113973284A (zh) 侧行链路信令无线承载配置的方法和通信装置
WO2021134577A1 (fr) Dispositif et procédé de transmission de données
WO2020220787A1 (fr) Procédé, appareil et système de communication
WO2018059170A1 (fr) Procédé de communication, station de base, et terminal
WO2017156789A1 (fr) Procédé et terminal de communication de dispositif à dispositif
WO2022233294A1 (fr) Procédé et appareil de communication et dispositif électronique
WO2022063186A1 (fr) Procédé de commutation de liaison de transmission et produit associé
WO2021190233A1 (fr) Procédé et dispositif de transmission de données
JP7401669B2 (ja) 接続再開方法及び装置
WO2021078170A1 (fr) Procédé et appareil de communication
CN112291848B (zh) 一种终端能力配置的方法及通信装置
WO2021087886A1 (fr) Procédé de réglage de temporisateur et dispositif associé
CN115701177A (zh) 一种传输配置指示tci状态激活方法及相关设备
WO2022104711A1 (fr) Procédé et appareil de communication
WO2022067525A1 (fr) Procédé d'indication d'état de service, station de base et terminal
WO2023125343A1 (fr) Procédé et appareil d'accès aléatoire
WO2022152325A1 (fr) Procédé de réception de données d'un service mbs et dispositif associé
WO2023087262A1 (fr) Procédé de communication et appareil de communication
WO2022222736A1 (fr) Procédé, appareil et système de traitement de service, support de stockage lisible, et dispositif électronique
WO2023010791A1 (fr) Procédé de communication, dispositif électronique et support de stockage
WO2022206914A1 (fr) Procédé et appareil de surveillance, terminal et dispositif de réseau

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: 22798634

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: 22798634

Country of ref document: EP

Kind code of ref document: A1