WO2023116350A1 - 一种通信方法及通信装置 - Google Patents

一种通信方法及通信装置 Download PDF

Info

Publication number
WO2023116350A1
WO2023116350A1 PCT/CN2022/134683 CN2022134683W WO2023116350A1 WO 2023116350 A1 WO2023116350 A1 WO 2023116350A1 CN 2022134683 W CN2022134683 W CN 2022134683W WO 2023116350 A1 WO2023116350 A1 WO 2023116350A1
Authority
WO
WIPO (PCT)
Prior art keywords
computing power
information
terminal device
instance
configuration information
Prior art date
Application number
PCT/CN2022/134683
Other languages
English (en)
French (fr)
Inventor
刘哲
彭程晖
王君
王恩博
吴建军
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2023116350A1 publication Critical patent/WO2023116350A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08—Configuration management of networks or network elements
    • H04L41/0803—Configuration setting
    • H04L41/0813—Configuration setting characterised by the conditions triggering a change of settings
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
    • G06F9/5055—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering software capabilities, i.e. software resources associated or available to the machine
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08—Configuration management of networks or network elements
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08—Configuration management of networks or network elements
    • H04L41/0876—Aspects of the degree of configuration automation
    • H04L41/0886—Fully automatic configuration
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/02—Traffic management, e.g. flow control or congestion control
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/02—Traffic management, e.g. flow control or congestion control
    • H04W28/08—Load balancing or load distribution
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W88/00—Devices specially adapted for wireless communication networks, e.g. terminals, base stations or access point devices
    • H04W88/18—Service support devices; Network management devices

Definitions

  • the present application relates to the field of wireless technologies, and in particular to a communication method and a communication device.
  • Wireless communication refers to the transmission and communication between two or more communication nodes without propagation through conductors or cables.
  • the communication nodes generally include network equipment and terminal equipment.
  • a communication node generally has signal sending and receiving capabilities and computing capabilities. Take, for example, a communication node that is an end device with computing power.
  • the computing capability of the terminal device needs to provide computing power support for the signal sending and receiving capability (for example: calculating the time domain resources and frequency domain resources carrying the signal), so as to realize the communication between the terminal device and other communication nodes;
  • the computing power of the terminal device needs to provide computing power support for the calculation of local applications (for example: computing the generation and display of data such as language, text, or images), so as to realize the presentation of local applications on the terminal device.
  • the computing capability of the current communication node is to support the communication between different communication nodes and the presentation of the local application of the communication node.
  • computing power may also need to be taken into account, so as to realize the network endogenous computing power in the communication system.
  • the embodiment of the present application provides a communication method and a communication device, which are used to configure the computing power of the terminal device through the network device based on the first configuration information, so that the terminal device participates in the calculation process corresponding to the calculation example as a calculation node, It can effectively improve the reuse degree of computing resources to improve network revenue.
  • the first aspect of the present application provides a communication method, the method is executed by a terminal device, or the method is executed by some components in the terminal device (such as a processor, a chip or a chip system, etc.), or the method can also be executed by A logic module or software implementation that realizes all or part of the functions of a terminal device.
  • the communication method is executed by a terminal device as an example for description.
  • the terminal device receives a first message from the network device, the first message includes first configuration information, wherein the first configuration information includes configuration information of at least one computing power instance; the terminal device acquires the first information , the first information is used to indicate a first computing power instance, and the first computing power instance is a computing power instance in the at least one computing power instance; the terminal device executes the first computing power instance based on the first information.
  • the terminal device receives a first message from the network device that includes first configuration information, where the first configuration information includes configuration information of at least one computing power instance. After the terminal device acquires first information indicating a first computing power instance in the at least one computing power instance, the terminal device executes the first computing power instance based on the first information. In other words, after the terminal device configures the computing power instance based on the instruction of the network device, the terminal device executes the corresponding computing power instance based on the first information.
  • the wireless network system where the terminal device and the network device are located can become a dual infrastructure of communication connection and computing, and the network device configures the computing power of the terminal device based on the first configuration information, so that the terminal device participates in the calculation example as a computing node
  • the calculation process corresponding to the example can effectively increase the reuse of computing resources to improve network revenue.
  • the first computing power example may be a computing power instance jointly calculated by the network device and one or more terminal devices, so that when the terminal device executes the computing power instance based on the first configuration information, it can share Computing resources on the network device side to solve the problem of insufficient computing resources on terminal devices.
  • the first computing power example may be a computing power instance jointly calculated by the terminal device and other computing nodes, so that when the terminal device executes the computing power instance based on the first configuration information, it can share the terminal Computing resources on the device side, so that the computing resources of the terminal device can be shared, and the degree of reuse of computing resources can be improved.
  • other computing nodes may include other terminal devices and/or other network devices.
  • the first message further includes second configuration information, where the second configuration information includes configuration information of at least one computing power resource, and the at least one computing power resource is associated with the At least one computing power instance.
  • the second configuration information is included in other messages.
  • computing power resources or called executors
  • the computing power resources may indicate the operating environment of the computing power instance, such as the storage, electricity, memory, computing power, etc. required for the running of the computing power instance.
  • computing power examples involved in this application may indicate a mode or method of computing resource usage related to computing power, model, location of split learning or reasoning segmentation points, number of local iterations of federated learning, etc. .
  • the terminal device further receives second configuration information including configuration information of at least one computing power resource, where the at least one computing power resource is associated with the at least one computing power instance. Therefore, while configuring the computing power of the terminal device so that the terminal device participates in the calculation process corresponding to the calculation example as a computing node, the terminal device is made clear based on the second configuration information that the computing power in the execution of at least one calculation example Computing resources used during the instance process.
  • the first information includes an identifier of the first computing power instance and/or an identifier of computing power resource information corresponding to the first computing power instance; the terminal device obtains the first computing power instance
  • the first information includes: the terminal device receives the first information, and the first information is carried in layer 1 (layer 1, L1) control information or layer 2 (layer 2, L2) control information or layer 3 (layer 3, L3) message middle.
  • the terminal device may receive first information indicating the first computing power instance from the network device, so that the terminal device executes the first computing power instance based on the instruction of the network device. Therefore, while configuring the computing power of the terminal device so that the terminal device participates in the calculation process corresponding to the calculation instance as a computing node, the network device can also dynamically adjust the computing power instance executed by the terminal device based on the first message.
  • the method before the terminal device receives the first information, the method further includes: the terminal device receives a reference signal (reference signal, RS); the terminal device sends a reference signal corresponding to the RS measurement results.
  • a reference signal reference signal, RS
  • the terminal device may receive the RS and send the measurement result corresponding to the RS, so that the network device may use the RS measurement result as a basis for the network device to send the first information.
  • the measurement result of the RS can reflect the channel information between the terminal device and the network device, so that the network device can use the computing power instance performed by the terminal device (and/or the terminal device) based on the measurement result of the RS Computing resources corresponding to the executed computing instances) are dynamically adjusted.
  • the first computing power instance is a default computing power instance; and/or, the computing power resource information corresponding to the first computing power instance is default computing power resource information.
  • the default computing power instance may also be called a basic computing power instance, a pre-configured computing power instance, etc.
  • the default computing power resource information may also be referred to as basic computing power resource information, pre-configured basic computing power resource information, and the like.
  • both the network device and the terminal device have (or pre-store) the default calculation example.
  • the default computing example may be a computing power instance with low power consumption/low overhead/low computing capability requirements.
  • the first computing power instance indicated by the first information may be the default computing power instance, and/or, the computing power resource information corresponding to the first calculation instance indicated by the first information is the default computing power resource information . Therefore, based on the implementation of the default calculation example, it can be ensured that the terminal device can also execute the This default computing power example enables the terminal device to still participate in the calculation process corresponding to the calculation example as a computing node, so as to improve the reuse of computing resources.
  • the acquiring the first information by the terminal device includes: generating the first information by the terminal device when at least one of the following is satisfied, including:
  • the first timer expires, wherein the configuration information of the first timer is included in the first message; or,
  • the power of the terminal device is lower than the first threshold; or,
  • the terminal device enters the radio resource control idle RRC idle state; or,
  • the signal quality of the RS measured by the terminal device is less than a threshold, or;
  • the terminal device performs a cell handover
  • the terminal device performs RRM measurements; or,
  • the calculation amount corresponding to the calculation example currently executed by the terminal device is higher than the threshold; or,
  • the terminal device determines that a requirement for quality of service information (quality of service, QOS) is lower than a threshold.
  • the above signal quality may include reference signal receiving power (reference signal receiving power, RSRP), reference signal receiving quality (reference signal receiving quality, RSRQ) or signal to interference plus noise ratio (signal to interference plus noise ratio, SINR ) etc. at least one.
  • reference signal receiving power reference signal receiving power, RSRP
  • reference signal receiving quality reference signal receiving quality, RSRQ
  • SINR signal to interference plus noise ratio
  • the terminal device may trigger generation of the first information based on the occurrence of at least one event above.
  • the terminal device can realize dynamic switching of calculation instances executed by the terminal device based on at least one of the above events. Therefore, in the event that the transmission of signaling (such as reconfiguration signaling, scheduling signaling, etc.) Participate in the calculation process corresponding to the calculation example as a computing node to improve the reuse of computing resources.
  • signaling such as reconfiguration signaling, scheduling signaling, etc.
  • the method before the terminal device receives the first message from the network device, the method further includes: the terminal device sends first indication information to the network device, and the first indication information uses To indicate the computing power status of the terminal device.
  • the terminal device may send the first indication information for indicating the computing power status of the terminal device to the network device, so that the network device can The instance status is used as a basis for the network device to send the first message. Therefore, the network device can dynamically adjust the computing power instance executed by the terminal device (and/or the computing power resource corresponding to the computing power instance executed by the terminal device) based on the computing power state of the terminal device.
  • the method before the terminal device receives the first message from the network device, the method further includes: the terminal device sends second indication information to the network device, and the second indication information It is used to indicate the computing power resource information and/or computing power instance expected by the terminal device.
  • the terminal device may send to the network device second indication information for indicating the computing power resource information and/or computing power instance expected by the terminal device, so that the network
  • the device may use the computing power resource information and/or computing power instance expected by the terminal device as a basis for the network device to send the first message. Therefore, the network device can, based on the computing power resource information and/or computing power instance expected by the terminal device, calculate the computing power instance executed by the terminal device (and/or the computing power resource corresponding to the computing power instance executed by the terminal device ) to make dynamic adjustments, so that the provided configuration information can meet the requirements of the terminal device.
  • the method further includes: when the terminal device executes the first computing power instance based on the first information, the terminal device sends third indication information, and the third indication information uses to indicate the computing power adjustment information of the terminal device; the terminal device receives third configuration information from the network device, the third configuration information is used to update the first configuration information and/or the third configuration information is used to update the Second configuration information.
  • the terminal device may send third indication information for indicating computing power adjustment information of the terminal device to the network device, so that the network device can use the computing power adjustment information of the terminal device as the basis for the network device to send the updated configuration (that is, the third configuration information used to update the first configuration information and/or the third configuration information used to update the second configuration information) . Therefore, based on the computing power adjustment information of the terminal device, the network device can dynamically adjust the computing power instance executed by the terminal device (and/or the computing power resource corresponding to the computing power instance executed by the terminal device), in order to achieve The configuration information provided can meet the computing power adjustment requirements of the terminal device.
  • the second aspect of the present application provides a communication method, the method is executed by a network device, or the method is executed by some components in the network device (such as a processor, a chip or a chip system, etc.), or the method can also be executed by A logic module or software implementation that realizes all or part of network device functions.
  • the communication method is executed by a network device as an example for description.
  • a network device generates a first message, where the first message includes first configuration information, where the first configuration information includes configuration information of at least one computing power instance; the network device sends the first message.
  • the first message sent by the network device includes first configuration information, where the first configuration information includes configuration information of at least one computing power instance.
  • the terminal device After the terminal device acquires first information indicating a first computing power instance in the at least one computing power instance, the terminal device executes the first computing power instance based on the first information.
  • the terminal device executes the corresponding computing power instance based on the first information. Therefore, the wireless network system where the terminal device and the network device are located can become a dual infrastructure for communication connection and computing, and the network device configures the computing power of the terminal device based on the first configuration information, so that the terminal device participates in computing as a computing node.
  • the calculation process corresponding to the example can effectively improve the reuse of computing resources and improve network revenue.
  • the first message further includes second configuration information, where the second configuration information includes configuration information of at least one computing power resource, and the at least one computing power resource is associated with the At least one computing power instance.
  • the second configuration information is included in other messages.
  • the network device further sends second configuration information including configuration information of at least one computing power resource, where the at least one computing power resource is associated with the at least one computing power instance. Therefore, while configuring the computing power of the terminal device so that the terminal device participates in the calculation process corresponding to the calculation example as a computing node, the terminal device is made clear based on the second configuration information that the computing power in the execution of at least one calculation example Computing resources used during the instance process.
  • the method further includes: the network device sending first information, where the first information is used to indicate a first computing power instance, and the first computing power instance is the at least one computing power instance A computing power instance in a power instance, the first information includes the identification of the first computing power instance and/or the identification of the computing power resource information corresponding to the first computing power instance; wherein, the first information is carried in the L1 control information Or L2 control information or L3 message.
  • the network device may send the first information indicating the first computing power instance, so that the terminal device executes the first computing power instance based on the instruction of the network device. Therefore, while configuring the computing power of the terminal device so that the terminal device participates in the calculation process corresponding to the calculation instance as a computing node, the network device can also dynamically adjust the computing power instance executed by the terminal device based on the first message.
  • the first computing power instance may be a computing power instance jointly calculated by the network device and one or more terminal devices, so that the terminal device executes the first computing power instance based on the first information indicated by the network device
  • computing resources on the network device side can be shared to solve the problem of insufficient computing resources on terminal devices.
  • the network device also needs to execute part of the calculation process of the first computing power instance based on the first information, or in other words, the network device also needs to locally adjust the first computing power instance corresponding to the first information, so that the network device In the process of cooperative computing with terminal equipment, dynamic synchronous adjustment can be realized.
  • the first computing power instance may be a computing power instance jointly calculated by the terminal device and other computing nodes, so that when the terminal device executes the first computing power instance based on the first information, it can share the computing power instance Computing resources on the terminal device side, so that the computing resources of the terminal device can be shared, and the degree of multiplexing of computing resources can be improved.
  • the network device since the execution of the first computing power instance may not require the participation of the network device, the network device may not need to execute part of the calculation process of the first computing power instance based on the first information, or in other words, the network device does not need to At the same time, the first computing power instance corresponding to the first information is adjusted locally.
  • other computing nodes may include other terminal devices and/or other network devices.
  • the method before the network device sends the first information, the method further includes: the network device sends a reference signal RS; the network device receives a measurement result corresponding to the RS; the network device The first information is generated based on the measurement result corresponding to the RS.
  • the network device before the network device sends the first information, it can send the RS and receive the measurement result corresponding to the RS, so that the network device can use the RS measurement result as a basis for the network device to send the first information.
  • the measurement result of the RS can reflect the channel information between the terminal device and the network device, so that the network device can use the computing power instance performed by the terminal device (and/or the terminal device) based on the measurement result of the RS Computing resources corresponding to the executed computing instances) are dynamically adjusted.
  • the method before the network device sends the first information, the method further includes: the network device receiving first indication information from the terminal device, where the first indication information is used to indicate The computing power state of the terminal device; the network device determines the first information based on the first indication information.
  • the network device before the network device sends the first message, the network device receives the first indication information used to indicate the computing power state of the terminal device, so that the network device can use the calculation state of the terminal device as the network The basis for the device to send the first message. Therefore, the network device can dynamically adjust the computing power instance executed by the terminal device (and/or the computing power resource corresponding to the computing power instance executed by the terminal device) based on the computing power state of the terminal device.
  • the method before the network device sends the first information, the method further includes: the network device receiving second indication information from the terminal device, where the second indication information is used to indicate The computing power resource information and/or computing power instance expected by the terminal device; the network device determines the first information based on the second indication information.
  • the network device before the network device sends the first message, the network device receives the second indication information used to indicate the expected computing power resource information and/or computing power instance of the terminal device, so that the network device can
  • the computing power resource information and/or computing power instance expected by the device is used as a basis for the network device to send the first message. Therefore, the network device can, based on the computing power resource information and/or computing power instance expected by the terminal device, calculate the computing power instance executed by the terminal device (and/or the computing power resource corresponding to the computing power instance executed by the terminal device ) to make dynamic adjustments, so that the provided configuration information can meet the requirements of the terminal device.
  • the method further includes: the network device receives third indication information from the terminal device, where the third indication information is used to indicate The computing power adjustment information of the terminal device; the network device sends third configuration information based on the third indication information, the third configuration information is used to update the first configuration information and/or the third configuration information is used to update the first configuration information Two configuration information.
  • the network device may also receive third indication information for indicating the computing power adjustment information of the terminal device, so that the network device may send the updated configuration information as the network device with the computing power adjustment information of the terminal device (that is, the basis for updating the first configuration information and/or the third configuration information for updating the second configuration information). Therefore, based on the computing power adjustment information of the terminal device, the network device can dynamically adjust the computing power instance executed by the terminal device (and/or the computing power resource corresponding to the computing power instance executed by the terminal device), in order to achieve The configuration information provided can meet the computing power adjustment requirements of the terminal device.
  • the computing power instance in the at least one computing power instance includes at least one of the following: execution time information, computing power size information, model information, split learning position , location of inference split point or number of local iterations of federated learning.
  • the at least one computing power resource information includes at least one of the following:
  • Central processor unit central processor unit, CPU type information, storage information, execution time information, memory information or power information.
  • the at least one computing power resource associated with the at least one computing power instance includes:
  • Each computing power resource of the at least one computing power resource corresponds to each computing power instance in the at least one computing power instance
  • One of the computing power resources in the at least one computing power resource corresponds to one or more computing power instances in the at least one computing power instance.
  • the computing power resource corresponding to at least one computing power resource is greater than or equal to the maximum value of computing power resources required by the at least one computing power instance.
  • At least one computing power resource configured by the second configuration information is associated with at least one computing example instance configured by the first configuration information, wherein the computing power resource in the at least one computing power resource is related to the at least one computing power resource
  • Computing power instances in instance instances can have a one-to-one relationship, or a one-to-one or one-to-many relationship, so as to improve the flexibility of network devices in the process of configuring computing instance instances and computing power resources.
  • the terminal device when one of the at least one computing power resource corresponds to multiple computing power instances in the at least one computing power instance, that is, the computing power resource in the at least one computing power resource is different from the at least one computing power resource.
  • the terminal device since the terminal device can execute multiple different computing power instances with this computing power resource, the terminal device does not need to determine ( or reconfiguring, preparing, activating, etc.) a new computing power resource, so that the terminal device can quickly switch between multiple different calculation examples corresponding to the computing power resource.
  • the first indication information includes at least one of the following:
  • CPU type information storage information, memory information, battery information, computing power utilization information.
  • the third indication information includes:
  • Memory information battery information, computing power utilization information.
  • the third aspect of the present application provides a communication method, the method is executed by a terminal device, or the method is executed by some components in the terminal device (such as a processor, a chip or a chip system, etc.), or the method can also be executed by A logic module or software implementation that realizes all or part of the functions of a terminal device.
  • the communication method is executed by a terminal device as an example for description.
  • the terminal device sends computing power indication information to the network device; the terminal device receives a first message from the network device, and the first message includes first configuration information, wherein the first configuration information is used to configure at least A calculation example.
  • the network device After the terminal device sends the computing power indication information, the network device generates and sends the first message containing the first configuration information based on the computing power indication information, and the first configuration information is used to configure at least one computing instance For example, the terminal device receives the first configuration information.
  • the network device configures the computing power instance executed by the terminal device based on the information. Therefore, the wireless network system where the terminal device and the network device are located can become a dual infrastructure for communication connection and computing, and the network device configures the computing power of the terminal device based on the first configuration information, so that the terminal device participates in computing as a computing node.
  • the calculation process corresponding to the example can effectively improve the reuse of computing resources and improve network revenue.
  • the first computing power example may be a computing power instance jointly calculated by the network device and one or more terminal devices, so that when the terminal device executes the computing power instance based on the first configuration information, it can share Computing resources on the network device side to solve the problem of insufficient computing resources on terminal devices.
  • the first computing power instance may be a computing power instance jointly calculated by the terminal device and other computing nodes, so that when the terminal device executes the computing power instance based on the first configuration information, it can share the terminal device side computing resources, so that the computing resources of the terminal device can be shared, and the degree of reuse of computing resources can be improved.
  • other computing nodes may include other terminal devices and/or other network devices.
  • the method before the terminal device sends the computing power indication information to the network device, the method further includes: the terminal device receives a second message from the network device, and the second message includes the initial Configuration information, wherein the initial configuration information is used to configure at least one computing power instance.
  • the terminal device may also receive a second message including initial configuration information, where the initial configuration information is used to configure at least one computing power instance.
  • the terminal device may send computing power indication information to the network device, so that the network device sends updated configuration information, that is, the first configuration information.
  • the terminal device may update the initial configuration information based on the first configuration information, so as to obtain computing power configuration information adapted to the terminal device.
  • the method further includes: the terminal device sending a response message or a confirmation message to the first message.
  • the terminal device can also send a response message or confirmation message of the first message, so that the network device can clarify the The terminal device has received the first message, and will configure the at least one calculation instance with the first configuration information included in the first message.
  • the fourth aspect of the present application provides a communication method, the method is executed by a network device, or the method is executed by some components in the network device (such as a processor, a chip or a chip system, etc.), or the method can also be executed by A logic module or software implementation that realizes all or part of network device functions.
  • the communication method is executed by a network device as an example for description.
  • the network device receives computing power indication information from the terminal device; the network device sends a first message to the terminal device based on the computing power indicating information, and the first message includes first configuration information, wherein the first Configuration information is used to configure at least one computing power instance.
  • the network device after the network device receives the computing power indication information, the network device generates and sends the first message containing the first configuration information based on the computing power indication information, and the first configuration information is used to configure at least one calculation example For example, the terminal device receives the first configuration information.
  • the network device configures the computing power instance executed by the terminal device based on the information. Therefore, the wireless network system where the terminal device and the network device are located can become a dual infrastructure for communication connection and computing, and the network device configures the computing power of the terminal device based on the first configuration information, so that the terminal device participates in computing as a computing node.
  • the calculation process corresponding to the example can effectively improve the reuse of computing resources and improve network revenue.
  • the method before the network device receives the computing power indication information from the terminal device, the method further includes: the network device sends a second message to the terminal device, and the second message includes the initial Configuration information, wherein the initial configuration information is used to configure at least one computing power instance.
  • the network device may also send a second message including initial configuration information, where the initial configuration information is used to configure at least one computing power instance.
  • the terminal device may send computing power indication information to the network device, so that the network device sends updated configuration information, that is, the first configuration information.
  • the terminal device may update the initial configuration information based on the first configuration information, so as to obtain computing power configuration information adapted to the terminal device.
  • the method further includes: the network device receiving a response message or a confirmation message of the first message from the terminal device.
  • the network device may also receive a response message or an acknowledgment message of the first message, so that the network device can specify the The terminal device has received the first message, and will configure the at least one calculation instance with the first configuration information included in the first message.
  • the computing power indication information includes first indication information, where the first indication information is used to indicate the computing power state of the terminal device.
  • the computing power indication information sent by the terminal device includes first indication information for indicating the computing power state of the terminal device.
  • the terminal device may send the first indication information for indicating the computing power status of the terminal device to the network device, so that the network device may use the calculation state of the terminal device as A basis for the network device to send the first message. Therefore, the network device can dynamically adjust the computing power instance executed by the terminal device (and/or the computing power resource corresponding to the computing power instance executed by the terminal device) based on the computing power state of the terminal device.
  • the first indication information includes at least one of the following:
  • CPU type information storage information, memory information, battery information, computing power utilization information.
  • the computing power indication information includes second indication information, and the second indication information is used to indicate the expected computing power resource information and/or computing power of the terminal device. instance.
  • the computing power indication information sent by the terminal device includes second indication information for indicating computing power resource information and/or computing power instances expected by the terminal device.
  • the terminal device may send to the network device second indication information for indicating the computing power resource information and/or computing power instance expected by the terminal device, so that the network device may send
  • the computing power resource information and/or computing power instance expected by the terminal device is used as a basis for the network device to send the first message.
  • the network device can, based on the computing power resource information and/or computing power instance expected by the terminal device, calculate the computing power instance executed by the terminal device (and/or the computing power resource corresponding to the computing power instance executed by the terminal device ) to make dynamic adjustments, so that the provided configuration information can meet the requirements of the terminal device.
  • the computing power indication information includes third indication information, where the third indication information is used to indicate computing power adjustment information of the terminal device.
  • the computing power indication information sent by the terminal device includes third indication information for indicating computing power adjustment information of the terminal device.
  • the terminal device may send to the network device second indication information for indicating the computing power adjustment information of the terminal device, so that the network device can adjust the computing power of the terminal device
  • the information is used as a basis for the network device to send the first message. Therefore, based on the computing power adjustment information of the terminal device, the network device can dynamically adjust the computing power instance executed by the terminal device (and/or the computing power resource corresponding to the computing power instance executed by the terminal device), in order to achieve The configuration information provided can meet the computing power adjustment requirements of the terminal device.
  • the third indication information includes:
  • Memory information battery information, computing power utilization information.
  • the first message further includes second configuration information, where the second configuration information is used to configure at least one computing power resource information, and the at least one computing power The resource information is associated with the at least one computing power instance.
  • the at least one computing power resource associated with the at least one computing power instance includes:
  • Each computing power resource of the at least one computing power resource corresponds to each computing power instance in the at least one computing power instance
  • One of the computing power resources in the at least one computing power resource corresponds to one or more computing power instances in the at least one computing power instance.
  • the computing power resource corresponding to at least one computing power resource is greater than or equal to the maximum value of computing power resources required by the at least one computing power instance.
  • At least one computing power resource configured by the second configuration information is associated with at least one computing example instance configured by the first configuration information, wherein the computing power resource in the at least one computing power resource is related to the at least one computing power resource
  • Computing power instances in instance instances can have a one-to-one relationship, or a one-to-one or one-to-many relationship, so as to improve the flexibility of network devices in the process of configuring computing instance instances and computing power resources.
  • the network device indicates the first computing power instance based on the first information
  • the network device can also improve the performance of the network device in indicating the first computing instance instance and/or the computing power resource corresponding to the first computing power instance. Process flexibility.
  • the terminal device when one of the at least one computing power resource corresponds to multiple computing power instances in the at least one computing power instance, that is, the computing power resource in the at least one computing power resource is different from the at least one computing power resource.
  • the terminal device since the terminal device can execute multiple different computing power instances with this computing power resource, the terminal device does not need to determine ( or reconfiguring, preparing, activating, etc.) a new computing power resource, so that the terminal device can quickly switch between multiple different calculation examples corresponding to the computing power resource.
  • the at least one computing power resource information includes at least one of the following:
  • CPU type information storage information, execution time information, memory information or power information.
  • the computing power instance in the at least one computing power instance includes at least one of the following:
  • Execution time information computing power size information, model information, split learning position, inference split point position or local iteration number of federated learning.
  • a fifth aspect of the present application provides a communications device, which can implement the method in the first aspect or any possible implementation manner of the first aspect.
  • the apparatus includes corresponding units or modules for performing the above method.
  • the units or modules included in the device can be realized by means of software and/or hardware.
  • the device may be a terminal device, or the device may be a component in the terminal device (such as a processor, a chip or a chip system, etc.), or the device may also be a logic module or logic module capable of realizing all or part of the functions of the terminal device. software.
  • the device includes a transceiver unit and a processing unit;
  • the transceiving unit is configured to receive a first message from a network device, where the first message includes first configuration information, where the first configuration information includes configuration information of at least one computing power instance;
  • the processing unit is configured to acquire first information, where the first information is used to indicate a first computing power instance, where the first computing power instance is a computing power instance in the at least one computing power instance;
  • the processing unit is further configured to execute the first computing power instance based on the first information.
  • the first message further includes second configuration information, where the second configuration information includes configuration information of at least one computing power resource, and the at least one computing power resource is associated with the At least one computing power instance.
  • the first information includes an identifier of the first computing power instance and/or an identifier of computing power resource information corresponding to the first computing power instance;
  • the processing unit for the first information includes:
  • the processing unit is configured to control the transceiver unit to receive the first information, and the first information is carried in L1 control information or L2 control information or L3 message.
  • the transceiver unit is also used to receive a reference signal RS;
  • the transceiver unit is further configured to send the measurement result corresponding to the RS.
  • the first computing power instance is the default computing power instance; and/or,
  • the computing power resource information corresponding to the first computing power instance is the default computing power resource information.
  • the processing unit configured to obtain the first information includes:
  • the processing unit is configured to generate the first information, including:
  • the first timer expires, wherein the configuration information of the first timer is included in the first message; or,
  • the power of the terminal device is lower than the first threshold; or,
  • the terminal equipment enters the radio resource control idle RRC idle state.
  • the transceiving unit is further configured to send first indication information to the network device, where the first indication information is used to indicate the computing power state of the terminal device.
  • the transceiving unit is further configured to send second indication information to the network device, where the second indication information is used to indicate computing power resource information and/or computing power instances expected by the terminal device.
  • the transceiver unit is further configured to send third indication information, where the third indication information is used to indicate computing power adjustment information of the terminal device;
  • the transceiver unit is further configured to receive third configuration information from the network device, where the third configuration information is used to update the first configuration information and/or the third configuration information is used to update the second configuration information.
  • implementation process of the communication device provided by the fifth aspect of the present application can refer to the implementation process described in the first aspect, and achieve corresponding technical effects, which will not be repeated here.
  • a sixth aspect of the present application provides a communications device, which can implement the method in the second aspect or any possible implementation manner of the second aspect.
  • the apparatus includes corresponding units or modules for performing the above method.
  • the units or modules included in the device can be realized by means of software and/or hardware.
  • the device may be a network device, or the device may be a component in the network device (such as a processor, a chip or a chip system, etc.), or the device may also be a logic module or logic module capable of realizing all or part of the functions of the network device. software.
  • the device includes a transceiver unit and a processing unit;
  • the processing unit is configured to generate a first message, where the first message includes first configuration information, where the first configuration information includes configuration information of at least one computing power instance;
  • the transceiver unit is used to send the first message.
  • the first message further includes second configuration information, where the second configuration information includes configuration information of at least one computing power resource, and the at least one computing power resource is associated with the At least one computing power instance.
  • the transceiver unit is further configured to send first information, the first information is used to indicate a first computing power instance, the first computing power instance is a computing power instance in the at least one computing power instance, and the first information includes the The identification of the first computing power instance and/or the identification of the computing power resource information corresponding to the first computing power instance;
  • the first information is carried in L1 control information or L2 control information or L3 message.
  • the transceiver unit is also used to send a reference signal RS;
  • the transceiver unit is also used to receive the measurement result corresponding to the RS;
  • the processing unit is further configured to generate the first information based on the measurement result corresponding to the RS.
  • the transceiving unit is further configured to receive first indication information from the terminal device, where the first indication information is used to indicate the computing power status of the terminal device;
  • the processing unit is further configured to determine the first information based on the first indication information.
  • the transceiving unit is further configured to receive second indication information from the terminal device, where the second indication information is used to indicate computing power resource information and/or computing power instances expected by the terminal device;
  • the processing unit is further configured to determine the first information based on the second indication information.
  • the transceiver unit is further configured to receive third indication information from the terminal device, where the third indication information is used to indicate computing power adjustment information of the terminal device;
  • the processing unit is further configured to send third configuration information based on the third indication information, where the third configuration information is used to update the first configuration information and/or the third configuration information is used to update the second configuration information.
  • the computing power instance in the at least one computing power instance includes at least one of the following:
  • Execution time information computing power size information, model information, split learning position, inference split point position or local iteration number of federated learning.
  • the at least one computing resource information includes at least one of the following:
  • CPU type information storage information, execution time information, memory information or power information.
  • the at least one computing power resource associated with the at least one computing power instance includes:
  • Each computing power resource of the at least one computing power resource corresponds to each computing power instance in the at least one computing power instance
  • One of the computing power resources in the at least one computing power resource corresponds to one or more computing power instances in the at least one computing power instance.
  • the computing power resource corresponding to at least one computing power resource is greater than or equal to the maximum value of computing power resources required by the at least one computing power instance.
  • the first indication information includes at least one of the following:
  • CPU type information storage information, memory information, battery information, computing power utilization information.
  • the third indication information includes:
  • Memory information battery information, computing power utilization information.
  • implementation process of the communication device provided by the sixth aspect of the present application can refer to the implementation process described in the second aspect above, and achieve corresponding technical effects, which will not be repeated here.
  • a seventh aspect of the present application provides a communications device, which can implement the method in the above third aspect or any possible implementation manner of the third aspect.
  • the apparatus includes corresponding units or modules for performing the above method.
  • the units or modules included in the device can be realized by means of software and/or hardware.
  • the device may be a terminal device, or the device may be a component in the terminal device (such as a processor, a chip or a chip system, etc.), or the device may also be a logic module or logic module capable of realizing all or part of the functions of the terminal device. software.
  • the device includes a transceiver unit and a processing unit;
  • the processing unit is used to determine computing power indication information
  • the transceiver unit is used to send computing power indication information to network equipment;
  • the transceiving unit is further configured to receive a first message from the network device, where the first message includes first configuration information, where the first configuration information is used to configure at least one computing power instance.
  • the transceiving unit is further configured to receive a second message from the network device, where the second message includes initial configuration information, where the initial configuration information is used to configure at least one computing power instance.
  • the transceiving unit is further configured to send a response message or a confirmation message of the first message.
  • implementation process of the communication device provided by the seventh aspect of the present application can refer to the implementation process described in the third aspect, and achieve corresponding technical effects, which will not be repeated here.
  • the eighth aspect of the present application provides a communications device, which can implement the method in the fourth aspect or any possible implementation manner of the fourth aspect.
  • the apparatus includes corresponding units or modules for performing the above method.
  • the units or modules included in the device can be realized by means of software and/or hardware.
  • the device may be a network device, or the device may be a component in the network device (such as a processor, a chip or a chip system, etc.), or the device may also be a logic module or logic module capable of realizing all or part of the functions of the network device. software.
  • the device includes a transceiver unit and a processing unit;
  • the transceiver unit is used to receive computing power indication information from the terminal device
  • the processing unit is configured to determine a first message to the terminal device based on the computing power indication information, where the first message includes first configuration information, where the first configuration information is used to configure at least one computing power instance;
  • the transceiver unit is also used to send the first message.
  • the transceiver unit is further configured to send a second message to the terminal device, where the second message includes initial configuration information, where the initial configuration information is used to configure at least one computing power instance.
  • the transceiving unit is further configured to receive a response message or a confirmation message of the first message from the terminal device.
  • the computing power indication information includes first indication information, and the first indication information is used to indicate the computing power state of the terminal device.
  • the first indication information includes at least one of the following:
  • CPU type information storage information, memory information, battery information, computing power utilization information.
  • the computing power indication information includes second indication information, and the second indication information is used to indicate the expected computing power resource information and/or computing power of the terminal device. instance.
  • the computing power indication information includes third indication information, where the third indication information is used to indicate computing power adjustment information of the terminal device.
  • the third indication information includes:
  • Memory information battery information, computing power utilization information.
  • the first message further includes second configuration information, where the second configuration information is used to configure at least one computing power resource information, and the at least one computing power The resource information is associated with the at least one computing power instance.
  • the at least one computing power resource associated with the at least one computing power instance includes:
  • Each computing power resource of the at least one computing power resource corresponds to each computing power instance in the at least one computing power instance
  • One of the computing power resources in the at least one computing power resource corresponds to one or more computing power instances in the at least one computing power instance.
  • the at least one computing power resource information includes at least one of the following:
  • CPU type information storage information, execution time information, memory information or power information.
  • the computing power instance in the at least one computing power instance includes at least one of the following:
  • Execution time information computing power size information, model information, split learning position, inference split point position or local iteration number of federated learning.
  • implementation process of the communication device provided in the eighth aspect of the present application can refer to the implementation process described in the fourth aspect, and achieve corresponding technical effects, which will not be repeated here.
  • the ninth aspect of the embodiment of the present application provides a communication device, including at least one processor, the at least one processor is coupled to a memory; the memory is used to store programs or instructions; the at least one processor is used to execute the programs or instructions, To enable the device to implement the method described in the aforementioned first aspect or any possible implementation of the first aspect, or to enable the device to implement the aforementioned second aspect or the method described in any possible implementation of the second aspect method, or to enable the device to implement the method described in any one of the aforementioned third aspects or any possible implementation of the third aspect, or to enable the device to implement the aforementioned fourth aspect or any of the possible implementations of the fourth aspect method described in the method.
  • the tenth aspect of the embodiment of the present application provides a computer-readable storage medium that stores one or more computer-executable instructions.
  • the processor executes any one of the above-mentioned first aspect or the first aspect.
  • the method described in one possible implementation manner, or, the processor executes the method described in the second aspect or any possible implementation manner of the second aspect, or, the processor executes the method described in the third aspect or the first aspect
  • the eleventh aspect of the embodiment of the present application provides a computer program product (or computer program) storing one or more computers.
  • the processor executes the above-mentioned first aspect or the first aspect.
  • the method in any possible implementation manner, or, the processor executes the method described in the above second aspect or any possible implementation manner of the second aspect, or, the processor executes the method described in the above third aspect or The method described in any possible implementation manner of the third aspect, or, the processor executes the method described in the fourth aspect or any possible implementation manner of the fourth aspect.
  • the twelfth aspect of the embodiment of the present application provides a chip system, the chip system includes at least one processor, configured to support the communication device to implement the functions involved in the above-mentioned first aspect or any possible implementation of the first aspect , or, used to support the communication device to realize the functions involved in the above-mentioned second aspect or any possible implementation of the second aspect, or, used to support the communication device to realize the above-mentioned third aspect or any one of the possibilities of the third aspect
  • the chip system may further include a memory for storing necessary program instructions and data of the communication device.
  • the system-on-a-chip may consist of chips, or may include chips and other discrete devices.
  • the chip system further includes an interface circuit, and the interface circuit provides program instructions and/or data for the at least one processor.
  • the thirteenth aspect of the embodiment of the present application provides a communication system, the communication system includes the communication device mentioned in the fifth aspect and the sixth aspect above, and/or, the communication system includes the communication device mentioned in the seventh aspect and the eighth aspect above.
  • the communication device involved, and/or, the communication system includes the communication device of the ninth aspect above.
  • the technical effects brought about by any one of the design methods in the fifth aspect to the twelfth aspect can refer to the technical effects brought about by the different implementation methods in the above-mentioned first aspect to the fourth aspect, and will not be repeated here.
  • the terminal device receives the first message from the network device that includes the first configuration information, where the first configuration information includes configuration information of at least one computing power instance. After the terminal device acquires first information indicating a first computing power instance in the at least one computing power instance, the terminal device executes the first computing power instance based on the first information. In other words, after the terminal device configures the computing power instance based on the instruction of the network device, the terminal device executes the corresponding computing power instance based on the first information.
  • the wireless network system where the terminal device and the network device are located can become a dual infrastructure for communication connection and computing, and the network device configures the computing power of the terminal device based on the first configuration information, so that the terminal device participates in computing as a computing node.
  • the calculation process corresponding to the example can effectively improve the reuse of computing resources and improve network revenue.
  • Fig. 1 is a schematic diagram of the communication system provided by the present application.
  • Figure 2a is a schematic diagram of the network architecture involving computing power in this application.
  • Figure 2b is another schematic diagram of the network architecture involving computing power in this application.
  • FIG. 3a is a schematic diagram of communication protocol stack interaction provided by the present application.
  • Fig. 3b is a schematic diagram of the communication system provided by the present application.
  • Fig. 4 is a schematic diagram of the communication method provided by the present application.
  • Fig. 5a is another schematic diagram of the communication method provided by the present application.
  • Fig. 5b is another schematic diagram of the communication method provided by the present application.
  • Fig. 6a is another schematic diagram of the communication method provided by the present application.
  • FIG. 6b is another schematic diagram of the communication method provided by the present application.
  • FIG. 6c is another schematic diagram of the communication method provided by the present application.
  • FIG. 7 is another schematic diagram of the communication method provided by the present application.
  • FIG. 8 is another schematic diagram of the communication method provided by the present application.
  • FIG. 9 is a schematic diagram of a communication device provided by the present application.
  • FIG. 10 is another schematic diagram of the communication device provided by the present application.
  • FIG. 11 is another schematic diagram of the communication device provided by the present application.
  • Fig. 12 is another schematic diagram of the communication device provided by the present application.
  • Terminal device it may be a wireless terminal device capable of receiving network device scheduling and instruction information, and a wireless terminal device may be a device that provides voice and/or data connectivity to users, or a handheld device with a wireless connection function, or Other processing devices connected to the wireless modem.
  • a terminal device can communicate with one or more core networks or the Internet via a radio access network (RAN), and the terminal device can be a mobile terminal device, such as a mobile phone (or "cellular" phone, mobile phone (mobile phone) phone)), computers and data cards, such as portable, pocket, hand-held, computer built-in or vehicle-mounted mobile devices, which exchange voice and/or data with the radio access network.
  • a mobile terminal device such as a mobile phone (or "cellular" phone, mobile phone (mobile phone) phone)
  • computers and data cards such as portable, pocket, hand-held, computer built-in or vehicle-mounted mobile devices, which exchange voice and/or data with the radio access network.
  • PCS personal communication service
  • SIP Session Initiation Protocol
  • WLL wireless local loop
  • PDAs personal digital assistants
  • Pad tablet Computer
  • the wireless terminal equipment may also be called a system, a subscriber unit (subscriber unit), a subscriber station (subscriber station), a mobile station (mobile station), a mobile station (mobile station, MS), a remote station (remote station), an access point ( access point (AP), remote terminal (remote terminal), access terminal (access terminal), user terminal (user terminal), user agent (user agent), subscriber station (subscriber station, SS), user terminal equipment (customer premises equipment, CPE), terminal (terminal), user equipment (user equipment, UE), mobile terminal (mobile terminal, MT), etc.
  • the terminal device may also be a wearable device.
  • Wearable devices can also be called wearable smart devices or smart wearable devices, etc., which is a general term for the application of wearable technology to intelligently design daily wear and develop wearable devices, such as glasses, gloves, watches, clothing and shoes wait.
  • a wearable device is a portable device that is worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not only a hardware device, but also achieve powerful functions through software support, data interaction, and cloud interaction.
  • Generalized wearable smart devices include full-featured, large-sized, complete or partial functions without relying on smart phones, such as smart watches or smart glasses, etc., and only focus on a certain type of application functions, and need to cooperate with other devices such as smart phones Use, such as various smart bracelets, smart helmets, smart jewelry, etc. for physical sign monitoring.
  • the terminal device may also be a terminal device in a future communication system (such as a sixth generation (6th generation, 6G) communication system, etc.) or a terminal device in a future evolved public land mobile network (public land mobile network, PLMN), etc. .
  • a future communication system such as a sixth generation (6th generation, 6G) communication system, etc.
  • a future evolved public land mobile network public land mobile network, PLMN
  • the 6G network can further expand the form and function of the fifth generation (5th generation, 5G) communication terminal
  • 6G terminal includes but not limited to car, cellular network terminal (integrated satellite terminal function), unmanned aerial vehicle, IoT.
  • Network device it may be a device in a wireless network, for example, a network device may be a RAN node (or device) that connects a terminal device to a wireless network, and may also be called a base station.
  • RAN equipment are: base station gNB (gNodeB), transmission reception point (transmission reception point, TRP), evolved Node B (evolved Node B, eNB), radio network controller (radio network) in the 5G communication system.
  • the network device may include a centralized unit (centralized unit, CU) node, or a distributed unit (distributed unit, DU) node, or a RAN device including a CU node and a DU node.
  • the network device can send configuration information (for example, carried in a scheduling message and/or an indication message) to the terminal device, and the terminal device further performs network configuration according to the configuration information, so that the network configuration between the network device and the terminal device is aligned; or , through the network configuration preset in the network device and the network configuration preset in the terminal device, the network configurations between the network device and the terminal device are aligned.
  • “alignment” refers to when there is an interaction message between the network device and the terminal device, the carrier frequency of the interaction message sent and received by the two, the determination of the type of the interaction message, the meaning of the field information carried in the interaction message, or The understanding of other configurations of interactive messages is the same.
  • the network equipment may be other devices that provide wireless communication functions for the terminal equipment.
  • the embodiment of the present application does not limit the specific technology and specific device form adopted by the network device. For the convenience of description, the embodiment of the present application does not limit it.
  • the network device may also include a core network device, for example, the core network device includes a mobility management entity (mobility management entity, MME) in a fourth generation (4th generation, 4G) network, a home subscriber server (home subscriber server, HSS), service Gateway (serving gateway, S-GW), policy and charging rules function (policy and charging rules function, PCRF), public data network gateway (public data network gateway, PDN gateway, P-GW); access and charging rules in the 5G network Network elements such as access and mobility management function (AMF), user plane function (UPF) or session management function (SMF).
  • the core network equipment may also include other core network equipment in the 5G network and the next-generation network of the 5G network.
  • the device for realizing the function of the network device may be a network device, or a device capable of supporting the network device to realize the function, such as a chip system, and the device may be installed in the network device.
  • the technical solution provided by the embodiment of the present application the technical solution provided by the embodiment of the present application is described by taking the network device as an example for realizing the function of the network device.
  • Configuration and pre-configuration In this application, both configuration and pre-configuration will be used.
  • the configuration means that the base station/server sends configuration information or values of some parameters to the terminal through messages or signaling, so that the terminal can determine communication parameters or resources during transmission according to these values or information.
  • Pre-configuration is similar to configuration. It can be the parameter information or parameter value negotiated by the base station/server and the terminal device in advance, or it can be the parameter information or parameter value adopted by the base station/server or terminal device specified in the standard protocol, or it can be a pre-stored Parameter information or parameter values at the base station/server or terminal equipment. This application does not limit this.
  • This application can be applied to a long term evolution (long term evolution, LTE) system, a new radio (new radio, NR) system, or other communication systems (such as 6G, etc.), wherein the communication system includes network equipment and terminal equipment , the network device acts as the configuration information sending entity, and the terminal device acts as the configuration information receiving entity.
  • the communication system includes network equipment and terminal equipment
  • the network device acts as the configuration information sending entity
  • the terminal device acts as the configuration information receiving entity.
  • there is an entity in the communication system that sends configuration information to another entity, and sends data to another entity, or receives data sent by another entity; another entity receives configuration information, and sends configuration information to the configuration information according to the configuration information.
  • the entity sends data, or receives data sent by the configuration information sending entity.
  • FIG. 1 is a schematic diagram of a communication system in this application.
  • a network device 101 and 6 terminal devices are exemplarily shown, and the 6 terminal devices are respectively terminal device 1, terminal device 2, terminal device 3, terminal device 4, terminal device 5 and terminal device 6, etc.
  • terminal device 1 is a smart teacup
  • terminal device 2 is a smart air conditioner
  • terminal device 3 is a smart fuel dispenser
  • terminal device 4 is a vehicle
  • terminal device 5 is a mobile phone
  • terminal device 6 is a The printer is given as an example.
  • the configuration information sending entity may be a network device.
  • the configuration information receiving entity can be terminal device 1-terminal device 6.
  • the network device and terminal device 1-terminal device 6 form a communication system.
  • terminal device 1-terminal device 6 can send uplink data to A network device, the network device needs to receive the uplink data sent by the terminal device 1-terminal device 6.
  • the network device can send configuration information to the terminal device 1 - the terminal device 6 .
  • UE4-UE6 may also form a communication system.
  • the terminal device 5 serves as a network device, that is, the configuration information sending entity; the terminal device 4 and the terminal device 6 serve as terminal devices, that is, the configuration information receiving entity.
  • terminal device 5 sends configuration information to terminal device 4 and terminal device 6 respectively, and receives uplink data sent by terminal device 4 and terminal device 6; correspondingly, terminal device 4 and terminal device 6 receive terminal device 5 configuration information sent, and send uplink data to the terminal device 5.
  • wireless communication refers to the transmission and communication between two or more communication nodes without propagation through conductors or cables.
  • the communication nodes generally include network equipment and terminal equipment.
  • a communication node generally has signal sending and receiving capabilities and computing capabilities. Take, for example, a communication node that is an end device with computing power.
  • the computing capability of the terminal device needs to provide computing power support for the signal sending and receiving capability (for example: calculating the time domain resources and frequency domain resources carrying the signal), so as to realize the communication between the terminal device and other communication nodes;
  • the computing power of the terminal device needs to provide computing power support for the calculation of local applications (for example: computing the generation and display of data such as language, text, or images), so as to realize the presentation of local applications on the terminal device.
  • the computing capability of the current communication node is to support the communication between different communication nodes and the presentation of the local application of the communication node.
  • computing power may also need to be taken into account, so as to realize the network endogenous computing power in the communication system.
  • the implementation with computing power in the communication system will be exemplified below.
  • MEC mobile/multi-access edge computing
  • FIG. 2a it is a schematic diagram of a network element architecture related to the MEC, wherein the terminal equipment is recorded as UE in the schematic diagram as an example for illustration.
  • network equipment includes:
  • Radio access network radio access network, RAN
  • access and mobility management function access and mobility management function
  • AMF access and mobility management function
  • user plane function user plane function, UPF
  • session management function session management function, SMF
  • policy control function policy control function
  • PCF policy control function
  • authorization server function authentication server function
  • AUSF unified data management
  • UDM network storage function
  • NRF network opening function
  • NEF network exposure function
  • data network data network
  • DN data network
  • application function application function
  • AF mobile/multi-access edge computing platform
  • MEP mobile/multi-access edge platform
  • the MEC in the network may include functions related to network elements such as AF, DN, and edge UPF.
  • the actual deployment position of the MEC in the wireless network is generally the corresponding To the local user plane function (user plane function, UPF) network element of the 5G core network (such as the UPF in Figure 2a).
  • UPF user plane function
  • the local UPF realizes local unloading and offloading of services, so as to realize localized processing of services and achieve the effect of acceleration.
  • MEC is an invisible network element in the 3GPP system architecture and does not belong to the scope of the network architecture defined by 3GPP, so it will not have a direct impact on the 3GPP system architecture.
  • the following will take the access network device as an example and further describe in combination with the manner shown in FIG. 2b.
  • the MEC and UPF may be located at the network aggregation node between the access network device and the core network device.
  • the application of MEC is combined with the existing core network data distribution mechanism of 3GPP, and the processing location of service data is lowered from the remote data network (generally public cloud) to the local MEC.
  • the most essential reason for acceleration is to push the application that processes business data from the physical deployment location to the vicinity of the core network of the wireless network as much as possible, that is, to co-locate the UPF of the core network element.
  • the UPF is set in the base station, and the MEC is externally connected to the UPF.
  • the MEC can be further sunk to the vicinity of the base station, that is, it can be deployed on the same physical node as the base station.
  • the deployment of MEC has solved the industry's demands for real-time and data security to a certain extent, but from the perspective of 3GPP logical architecture and data protocol processing flow, there is still room for further optimization.
  • AI artificial intelligence
  • each network element may not only have control and forwarding capabilities, but also computing power.
  • computing nodes are also deployed in the network. It is called the endogenous computing power of the network.
  • computing power is regarded as a basic element of the network. Computing power is distributed throughout the network, that is, computing power is widely distributed in the cloud, edge, end, and intermediate network elements, and computing power is integrated into the network. Computing power services, connection services, and services that comprehensively consider computing power and connections are all basic services that the network can provide to the outside world.
  • the endogenous computing power of the network can promote the development and deployment of endogenous intelligence, better support ubiquitous base stations and terminals with perception, communication and computing capabilities, and realize large-scale intelligent distributed collaborative services while maximizing the
  • the utility of communication and computing power adapts to the distribution of data and protects the privacy of data.
  • the control planes of network elements and computing units are connected, which can make up for the shortcomings of computing power fusion category 2, and can respond to mobile and network changes in a timely manner.
  • the endogenous computing power of the network can promote the emergence and development of future intelligent applications, such as: immersive cloud extended reality (XR), holographic communication, sensory interconnection, intelligent interaction, communication perception, and digital twins, etc.
  • XR immersive cloud extended reality
  • XR includes virtual reality (virtual reality, VR) technology, augmented reality (augmented reality, AR) or mixed reality (mixed reality, MR), etc.
  • VR virtual reality
  • AR augmented reality
  • MR mixed reality
  • 5G also introduces computing power, but it does not go far enough. It basically retains the scope and global architecture characteristics of the previous generation of products, and focuses on the sinking of computing power.
  • the network and computing parts are relatively loose.
  • the coupled design means that it is not the native capability of the architecture, so there is room for further improvement in terms of efficiency, deployment cost, security and privacy protection.
  • the UPF of the core network user plane network element can be co-located with the MEC; the MEC and UPF can even sink to the base station and be co-located with the base station, but in terms of logical architecture and control and management mechanisms, there are still two sets Relatively independent system, which leads to: when the computing power changes and the connection strategy needs to be adjusted or the connection pipeline changes and the computing power needs to be adjusted, the adjustment delay of the other party is relatively large, such as the adjustment delay at the minute level; the data required for calculation needs to be adjusted.
  • an embodiment of the present application provides a communication method and a communication device, which are used to configure the computing power of the terminal device through the network device based on the first configuration information, so that the terminal device participates in the calculation example as a computing node
  • the corresponding calculation process can effectively increase the reuse of computing resources to increase network revenue.
  • different nodes in the communication network can complete the configuration and execution of computing power during the process of interaction at the protocol layer of computing resource control (CRC).
  • CRC computing resource control
  • the terminal equipment is denoted as UE
  • the access network equipment included in the network equipment is denoted as xNB
  • the network equipment also includes computing management function (CMF) network elements
  • the CMF network element is used to implement the information processing process involved in the CRC protocol layer as an example for illustration.
  • the CMF network element is a network element implemented by logical functions, and can be deployed on core network equipment or access network equipment, which is not limited here.
  • the protocol layers involved in the control plane interaction between the terminal device and the network device include a radio resource control (radio resource control, RRC) protocol, a packet data convergence protocol (packet One or more of data convergence protocol (PDCP), radio link control (radio link control, RLC) protocol, media access control (media access control, MAC) layer protocol, and physical (physical, PHY) layer protocol.
  • RRC radio resource control
  • PDCP packet data convergence protocol
  • RLC radio link control
  • media access control media access control
  • MAC media access control
  • PHY physical (physical, PHY) layer protocol.
  • Alt1 in FIG. 3b it is a schematic diagram of network element interaction corresponding to Alt1 in FIG. 3a.
  • the newly added CMF network element of this application can be connected to UE and RAN respectively, and connected to a data network (data network, DN) through xPF including UPF and CDF.
  • DN data network
  • the protocol layers involved in the control plane interaction between the terminal device and the network device include one of the RRC protocol, PDCP, RLC protocol, MAC layer protocol, and PHY layer protocol. item or items.
  • the present application adds a CRC protocol layer, which can be an information element (IE) or an RRC container (container) of the RRC layer, an IE or a NAS container of a non-access stratum (NAS) container implementation.
  • IE information element
  • RRC container container of the RRC layer
  • IE information element
  • NAS container non-access stratum
  • Alt2 in FIG. 3b it is a schematic diagram of network element interaction corresponding to Alt2 in FIG. 3a.
  • the CMF network element newly added in this application can be connected to the AMF and connected to a data network (data network, DN).
  • the CMF involved in this application can be used to achieve at least one of the following:
  • Session Management Function SMF
  • CMF is a part of the task anchor (Task Anchor, TA) function (the three elements of AI include computing power, algorithm, and data.
  • TA Task Anchor
  • the three elements of AI include computing power, algorithm, and data.
  • unified management, control computing power, algorithm, data, and connection, computing management functions are mainly Manage computing power and connections, so CMF can be regarded as part of TA function).
  • CS convergence scheduling
  • the calculation data of the internal calculation service is determined by the base station to be calculated locally or routed to the calculation node in the network; or,
  • CS is a part of the Task Scheduling (TS) function (the three elements of AI include computing power, algorithm, and data, unified management, control computing power, algorithm, data, and connection under the task Manage computing power and connections, so CS can be regarded as a part of TS function).
  • TS Task Scheduling
  • FIG. 4 is a schematic diagram of the communication method provided by this application, and the method includes the following steps.
  • the network device sends a first message.
  • the network device sends the first message in step S401, and correspondingly, the terminal device receives the first message in step S401.
  • the first message includes first configuration information, where the first configuration information includes configuration information of at least one computing power instance.
  • the computing power instance in the at least one computing power instance includes at least one of the following: execution time information, computing power size information, model information, split learning position, reasoning split point position or federation Learn the number of local iterations.
  • the first message further includes second configuration information, where the second configuration information includes configuration information of at least one computing power resource, and the at least one computing power resource is associated with the at least one computing power instance.
  • the second configuration information is included in other messages.
  • the network device needs to send the second configuration information to the terminal device through other processes different from step S401, so that the terminal device receives the second configuration information.
  • the terminal device further receives second configuration information including configuration information of at least one computing power resource, where the at least one computing power resource is associated with the at least one computing power instance. Therefore, while configuring the computing power of the terminal device so that the terminal device participates in the calculation process corresponding to the calculation example as a calculation node, it makes it clear based on the second configuration information that the terminal device subsequently executes at least one calculation example in the calculation example. Computing resources used in the process of force instance.
  • the at least one computing power resource information includes at least one of the following:
  • Central processor unit central processor unit, CPU type information, storage information, execution time information, memory information or power information.
  • the at least one computing power resource associated with the at least one computing power instance includes:
  • Each computing power resource of the at least one computing power resource corresponds to each computing power instance in the at least one computing power instance
  • One of the computing power resources in the at least one computing power resource corresponds to one or more computing power instances in the at least one computing power instance.
  • the computing power resource corresponding to at least one computing power resource is greater than or equal to the maximum value of computing power resources required by the at least one computing power instance.
  • At least one computing power resource configured by the second configuration information is associated with at least one calculation example instance configured by the first configuration information, wherein the computing power resource in the at least one computing power resource is related to the at least one calculation example instance
  • Computing power instances in can have a one-to-one relationship, or a one-to-one or one-to-many relationship, so as to improve the flexibility of network devices in the process of configuring computing instance instances and computing power resources.
  • the terminal device when one of the at least one computing power resource corresponds to multiple computing power instances in the at least one computing power instance, that is, the computing power resource in the at least one computing power resource is different from the at least one computing power resource.
  • the terminal device since the terminal device can execute multiple different computing power instances with this computing power resource, the terminal device does not need to determine ( or reconfiguring, preparing, activating, etc.) a new computing power resource, so that the terminal device can quickly switch between multiple different calculation examples corresponding to the computing power resource.
  • the network device may generate the first configuration information based on various scheduling policies, so as to configure the computing power instance executed by the terminal device.
  • the network device can generate the first configuration information based on its own resource information (including computing power resources, storage resources, etc.), and the network device can also receive instructions from other network devices (such as core network devices) to generate the first configuration information.
  • the network device may also generate the first configuration information for the purpose of providing an adapted computing power configuration for the terminal device based on the information reported by the terminal device.
  • the network device generates the first configuration information for the purpose of providing an adapted computing power configuration for the terminal device based on the information reported by the terminal device.
  • Example 1 Before the terminal device receives the first message from the network device in step S401, the method further includes: the terminal device sends first indication information to the network device, and the first indication information is used to indicate the computing power of the terminal device state.
  • the terminal device may send the first indication information to the network device to indicate the computing power status of the terminal device, so that the network device may As a basis for the network device to send the first message. Therefore, the network device can dynamically adjust the computing power instance executed by the terminal device (and/or the computing power resource corresponding to the computing power instance executed by the terminal device) based on the computing power state of the terminal device.
  • the first indication information includes at least one of the following:
  • CPU type information storage information, memory information, battery information, computing power utilization information.
  • Example 2 Before the terminal device receives the first message from the network device, the method further includes: the terminal device sends second indication information to the network device, where the second indication information is used to indicate the expected computing power of the terminal device Resource information and/or computing power instances.
  • the terminal device may send to the network device second indication information for indicating the computing power resource information and/or computing power instance expected by the terminal device, so that the network device can
  • the computing power resource information and/or computing power instance expected by the terminal device is used as a basis for the network device to send the first message. Therefore, the network device can, based on the computing power resource information and/or computing power instance expected by the terminal device, calculate the computing power instance executed by the terminal device (and/or the computing power resource corresponding to the computing power instance executed by the terminal device ) to make dynamic adjustments, so that the provided configuration information can meet the requirements of the terminal device.
  • the terminal device acquires first information.
  • the terminal device obtains the first information in step S402, the first information is used to indicate the first computing power instance, and the first computing power instance is the at least one computing power configured by the first configuration information in step S401 A computing power instance in a force instance.
  • the first information includes the identification of the first computing power instance and/or the identification of the computing power resource information corresponding to the first computing power instance; Acquiring the first information in S402 includes: the terminal device receives the first information, and the first information is carried in layer 1 (layer 1, L1) control information or layer 2 (layer 2, L2) control information or layer 3 (layer 3, L3) message.
  • the terminal device may receive first information indicating the first computing power instance from the network device, so that the terminal device executes the first computing power instance based on the instruction of the network device. Therefore, while configuring the computing power of the terminal device so that the terminal device participates in the calculation process corresponding to the calculation instance as a computing node, the network device can also dynamically adjust the computing power instance executed by the terminal device based on the first message.
  • the method further includes: the terminal device receives a reference signal (reference signal, RS); and the terminal device sends a measurement result corresponding to the RS.
  • the terminal device may receive the RS and send a measurement result corresponding to the RS, so that the network device may use the RS measurement result as a basis for the network device to send the first information.
  • the measurement result of the RS can reflect the channel information between the terminal device and the network device, so that the network device can use the computing power instance performed by the terminal device (and/or the terminal device) based on the measurement result of the RS Computing resources corresponding to the executed computing instances) are dynamically adjusted.
  • the first computing power example may be a computing power instance jointly calculated by the network device and one or more terminal devices, so that the terminal device can execute the computing power based on the first information indicated by the network device after step S402.
  • computing resources on the network device side can be shared to solve the problem of insufficient computing resources on the terminal device.
  • the network device also needs to execute part of the calculation process of the first computing power instance based on the first information, or in other words, the network device also needs to locally adjust the first computing power instance corresponding to the first information, so that the network device In the process of cooperative computing with terminal equipment, dynamic synchronous adjustment can be realized.
  • the first computing power instance may be a computing power instance jointly calculated by the terminal device and other computing nodes, so that when the terminal device executes the first computing power instance based on the first information after step S402 , the computing resource on the terminal device side can be shared, so that the computing resource of the terminal device can be shared, and the multiplexing degree of the computing resource can be improved.
  • the network device since the execution of the first computing power instance may not require the participation of the network device, the network device may not need to execute part of the calculation process of the first computing power instance based on the first information, or in other words, the network device does not need to At the same time, the first computing power instance corresponding to the first information is adjusted locally.
  • other computing nodes may include other terminal devices and/or other network devices.
  • the first computing power instance is a default computing power instance; and/or, the computing power resource information corresponding to the first computing power instance is default computing power resource information.
  • the default computing power instance may also be called a basic computing power instance, a pre-configured computing power instance, etc.
  • the default computing power resource information may also be referred to as basic computing power resource information, pre-configured basic computing power resource information, and the like.
  • both the network device and the terminal device have (or pre-store) the default calculation example.
  • the default computing example may be a computing power instance with low power consumption/low overhead/low computing capability requirements.
  • the first computing power instance indicated by the first information may be a default computing power instance, and/or, the computing power resource information corresponding to the first computing instance indicated by the first information is the default computing power resource information. Therefore, based on the implementation of the default calculation example, it can be ensured that the terminal device can also execute the This default computing power example enables the terminal device to still participate in the calculation process corresponding to the calculation example as a computing node, so as to improve the reuse of computing resources.
  • the terminal device acquires the computing power resource information in step S402
  • the first information includes: when at least one of the following is satisfied, the terminal device generates the first information in step S402, including:
  • the first timer expires, wherein the configuration information of the first timer is included in the first message; or,
  • the power of the terminal device is lower than the first threshold.
  • the first threshold may be a fixed value stipulated in the agreement, such as 5%, 10%, etc., or it may be a value agreed between the network device and the terminal device, for example, it may be based on the currently implemented A value determined by the computing power instance, or a specific value temporarily determined; or,
  • the terminal device enters the radio resource control idle RRC idle state; or,
  • the signal quality of the RS measured by the terminal device is less than a threshold, or;
  • the terminal device performs a cell handover
  • the terminal device performs RRM measurements; or,
  • the calculation amount corresponding to the calculation example currently executed by the terminal device is higher than the threshold; or,
  • the terminal device determines that a requirement for quality of service information (quality of service, QoS) is lower than a threshold.
  • the above signal quality may include reference signal receiving power (reference signal receiving power, RSRP), reference signal receiving quality (reference signal receiving quality, RSRQ) or signal to interference plus noise ratio (signal to interference plus noise ratio, SINR ) etc. at least one.
  • reference signal receiving power reference signal receiving power, RSRP
  • reference signal receiving quality reference signal receiving quality, RSRQ
  • SINR signal to interference plus noise ratio
  • the terminal device may trigger generation of the first information based on the occurrence of at least one event above.
  • the terminal device can realize dynamic switching of calculation instances executed by the terminal device based on at least one of the above events. Therefore, in the event that the transmission of signaling (such as reconfiguration signaling, scheduling signaling, etc.) Participate in the calculation process corresponding to the calculation example as a computing node to improve the reuse of computing resources.
  • signaling such as reconfiguration signaling, scheduling signaling, etc.
  • the terminal device executes the first computing power instance based on the first information.
  • the terminal device After the terminal device acquires the first information in step S402, the terminal device executes the first computing power instance based on the first information in step S403.
  • step S403 during the process of the terminal device executing the first computing power instance based on the first information, the terminal device may also send third indication information, and the third indication information uses to indicate the computing power adjustment information of the terminal device; thereafter, the network device may send third configuration information to the terminal device with the third indication information used to indicate the computing power adjustment information of the terminal device; correspondingly, the terminal device may also Third configuration information can be received from the network device. Wherein, the third configuration information is used to update the first configuration information and/or the third configuration information is used to update the second configuration information.
  • the terminal device may send third indication information for indicating the computing power adjustment information of the terminal device to the network device , so that the network device can use the computing power adjustment information of the terminal device as the updated configuration (that is, the third configuration information used to update the first configuration information and/or the third configuration information used to update the second configuration information) sent by the network device in accordance with. Therefore, based on the computing power adjustment information of the terminal device, the network device can dynamically adjust the computing power instance executed by the terminal device (and/or the computing power resource corresponding to the computing power instance executed by the terminal device), in order to achieve The configuration information provided can meet the computing power adjustment requirements of the terminal device.
  • the third indication information includes:
  • Memory information battery information, computing power utilization information.
  • the third indication information includes power information as an example. If the computing power resource information corresponding to the first computing power instance executed by the terminal device in step S403 includes power information, for example, the power information contained in the computing power resource information indicates that the first computing power instance needs to It can only be executed when it is greater than a certain threshold (for example, the threshold can be 50%, 40%, 30%, 20% or other values, for the convenience of description, the threshold is 20 here % as an example).
  • a certain threshold for example, the threshold can be 50%, 40%, 30%, 20% or other values, for the convenience of description, the threshold is 20 here % as an example.
  • the terminal device when the terminal device executes the first computing power instance in step S403, when the terminal device determines that the power of the terminal device is lower than or equal to 20%, the terminal device may send the network device the The third indication information is used to indicate that the power information of the terminal device has been lower than or equal to 20%. That is to say, the threshold here may also be the first threshold mentioned in the foregoing embodiments.
  • the network device may issue third configuration information based on the third indication information, where the third configuration information is used to update the first configuration information And/or the third configuration information is used to update the second configuration information.
  • the terminal device updates the first configuration information and/or the second configuration information to obtain an updated computing power example configuration and/or an updated computing power resource configuration, and based on the updated The computing power example configuration and/or the updated computing power resource configuration execute other computing power instances or suspend the execution of the computing instance.
  • the terminal device when the terminal device executes the first computing power instance in step S403, when the terminal device determines that the power of the terminal device is lower than or equal to 20%, the terminal device may also switch to execute The default calculation example instance or the computing power instance corresponding to the default computing power resources.
  • the implementation process of the default calculation example instance and the default computing resources can refer to the description of the foregoing embodiments, and achieve corresponding technical effects, which will not be repeated here.
  • the terminal device receives in step S401 a first message including first configuration information from a network device, wherein the first configuration information includes configuration information of at least one computing power instance.
  • the terminal device acquires first information indicating a first computing power instance in the at least one computing power instance in step S402
  • the terminal device executes the first computing power instance based on the first information in step S403.
  • the terminal device executes the corresponding computing power instance based on the first information.
  • the wireless network system where the terminal device and the network device are located can become a dual infrastructure for communication connection and computing, and the network device configures the computing power of the terminal device based on the first configuration information, so that the terminal device participates in computing as a computing node.
  • the calculation process corresponding to the example can effectively improve the reuse of computing resources and improve network revenue.
  • the calculation process involved in the computing power instance is a neural network calculation process as an example for illustration below.
  • the coverage of the cell signal provided by the network device is a circle as an example. It should be understood that the coverage area of the cell signal may also be oval, rectangular, hexagonal or other regular or irregular shapes, which are not limited here.
  • the network device and the terminal device can execute computing power instances to implement a joint computing process.
  • the computing task of the neural network shown in FIG. 5a is used as an example of computing power, wherein the computing task of the neural network includes the computing process of the eight-layer neural network. Part of the calculation process of the eight-layer neural network can be performed between the network device and the terminal device, so as to realize the joint calculation process.
  • the left side of Figure 5b is an example of a scenario where the terminal device is located in the center of the cell, where the terminal device located in the center of the cell has a large channel capacity, and the terminal device can calculate fewer layers of the neural network (in the figure, the number of neural network layers indicates the computing power The size of the complexity of the instance), and the calculation of the output result and the remaining layers is handed over to the network device for calculation.
  • Example 2 of computing power performed by terminal equipment corresponds to the first four layers of neural network of the calculation task shown in Figure 5a
  • Example of calculation performed by network equipment 2 corresponds to the last four layers of neural networks for the computing task shown in Figure 5a, to complete the joint computing. Therefore, based on the implementation shown in FIG.
  • the terminal device after the terminal device configures the computing power instance based on the instruction of the network device in step S401, the terminal device obtains the first information in step S402, and in step S403 based on the first The information executes the corresponding computing power instance, so that the terminal device switches from the scene shown on the left side of Figure 5b to the scene shown on the right side of Figure 5b (or the terminal device switches from the scene shown on the right side of Figure 5b to the scene shown on the left side of Figure 5b In the process of the scenario), switching of calculation instance instances can be performed based on the first information.
  • the wireless network system where the terminal device and the network device are located can become a dual infrastructure for communication connection and computing, and the network device configures the computing power of the terminal device based on the first configuration information, so that the terminal device participates in computing as a computing node.
  • the calculation process corresponding to the example can effectively improve the reuse of computing resources and improve network revenue.
  • the first information is indicated by the network device in step S402. Therefore, while configuring the computing power of the terminal device so that the terminal device participates in the calculation process corresponding to the calculation instance as a computing node, the network device can also dynamically adjust the computing power instance executed by the terminal device based on the first message.
  • the first computing power example indicated by the first information is a default computing example, that is, the terminal device generates it in step S402 based on the triggering of some predefined events. Therefore, based on the implementation of this default calculation example, it can be guaranteed that the terminal device can also execute the This default computing power example enables the terminal device to still participate in the calculation process corresponding to the calculation example as a computing node, so as to improve the reuse of computing resources.
  • the computing power resource is adjusted through the computing power instance ID.
  • the first message sent by the network device in step S401 includes first configuration information and second configuration information.
  • the first configuration information of at least one calculation instance used for configuration includes the computing power instance ID (which can be task ID or other forms, which can be CMF/TA allocation, or TS/CS allocation) and computing power One-to-one correspondence with configurations related to the amount of computation, such as size, model, split learning or inference point location, local iteration times of federated learning; optional, computing power instance ID, or model ID, split learning or inference
  • the split point ID, federated learning iteration number ID, etc. are not limited here.
  • the second configuration information used to configure at least one instance resource information includes one or more executive IDs.
  • one executor can include multiple instances of computing power (that is, one executor can be used to execute multiple instances of computing power), and the configuration information of the executor includes the executor ID and the computing power of the executor.
  • Configuration information specifically including multiple computing power resources (CPU type, storage, memory, power information) or computing power containers (combination of the above computing power types).
  • the computing power resource of the execution body is greater than or equal to the maximum value of computing power resources required by the multiple computing power instances included in the execution body.
  • computing power resources or called executors
  • the computing power resources may indicate the operating environment of the computing power instance, such as the storage, electricity, memory, computing power, etc. required for the running of the computing power instance.
  • computing power examples involved in this application may indicate a mode or method of computing resource usage related to computing power, model, location of split learning or reasoning segmentation points, number of local iterations of federated learning, etc. .
  • the network device may also send the first information to the terminal device in step S402, so as to implement dynamic adjustment to the calculation example.
  • the first information sent by the network device in step S402 may be adjustment signaling, that is, computing power instance ID indication information, used to instruct the terminal device to execute the first computing power instance.
  • this implementation manner may be implemented through the scenario shown in FIG. 6a.
  • “computing power instance” is recorded as “instance” in Fig. 6a, including instance 1 and instance 2.
  • the process of the network device sending the first message to the terminal device in step S401 and the network device sending the first message to the terminal device in step S402 may be triggered based on CMF scheduling, wherein the CMF It can be deployed on the core network side or on the access network side, which is not limited in this application.
  • the network device may trigger the sending of the first information to the terminal device in step S402 based on the real-time convergence scheduling (convergence scheduling, CS) generated by itself.
  • convergence scheduling convergence scheduling
  • Example 1 the network device performs the calculation process of the last six layers, and the terminal device performs the calculation process of the first two layers; in other words, in Example 1, the terminal device can perform less calculations so that the terminal device can interact more The hidden layer feature information of the neural network.
  • Example 2 the network device performs the calculation process of the last four layers, and the terminal device performs the calculation process of the first four layers; in other words, compared with Example 1, in Example 2, the terminal device can perform more calculations, so that the terminal The device can interact with less feature information of the hidden layer of the neural network.
  • the network device when the terminal device is in the center of the cell, the network device can determine that the channel quality between the terminal device and the network device is good and the transmission bandwidth is large based on the channel information reported by the terminal device.
  • this example 1 needs to exchange more feature information, and both the terminal device and the network device use the configuration corresponding to the example 1 to jointly complete the split reasoning.
  • the network device may send the first information to the terminal device in step S402, for scheduling the terminal device to execute instance 1, so that the terminal device executes instance 1 in step S403.
  • the network device when the terminal device is at the edge of the cell, the network device can determine that the channel quality between the terminal device and the network device is poor and the transmission bandwidth is small based on the channel information reported by the terminal device.
  • the example 2 in the illustration the example 2 requires less interaction of feature information, and both the terminal device and the network device use the configuration corresponding to the example 1 to jointly complete the split reasoning.
  • the network device may send the first information to the terminal device in step S402, for scheduling the terminal device to execute instance 2, so that the terminal device executes instance 2 in step S403.
  • computing power resources are adjusted through computing power executive IDs.
  • the first message sent by the network device in step S401 includes first configuration information and second configuration information.
  • the first configuration information of at least one calculation instance used for configuration includes the computing power instance ID (which can be task ID or other forms, which can be CMF/TA allocation, or TS/CS allocation) and computing power
  • the second configuration information used to configure at least one instance resource information includes one or more executive IDs.
  • the execution body and the computing power instance ID can be one-to-one mapping;
  • the configuration information of the execution body includes the execution body ID, the computing power configuration information of the execution body, and specifically includes a computing power resource (CPU type, storage, memory, power information ) or computing power container (a combination of the above computing power types).
  • the computing power resource of the execution body is greater than or equal to the maximum value of computing power resources required by the multiple computing power instances included in the execution body.
  • the ID of the computing power executive can also be replaced by the ID of the model, the ID of the split point of split learning or reasoning, the ID of the number of federated learning iterations, etc., which are not limited here.
  • the network device may also send the first information to the terminal device in step S402, so as to implement dynamic adjustment to the calculation example.
  • the first information sent by the network device in step S402 may be adjustment signaling, that is, computing power instance ID indication information, used to instruct the terminal device to execute computing power resources corresponding to the first computing power instance.
  • this implementation manner may be implemented through the scenario shown in FIG. 6b.
  • the "computing resource corresponding to the computing power instance” is recorded as "execution body", including execution body 1 and execution body 2.
  • the process of the network device sending the first message to the terminal device in step S401 and the network device sending the first message to the terminal device in step S402 may be triggered based on CMF scheduling, wherein the CMF It can be deployed on the core network side or on the access network side, which is not limited in this application.
  • the network device may trigger the sending of the first information to the terminal device in step S402 based on the real-time convergence scheduling (convergence scheduling, CS) generated by itself.
  • convergence scheduling convergence scheduling
  • the network device and the terminal device jointly calculate the calculation task of the neural network shown in FIG. 5a as an example.
  • the network device executes the calculation process of the last six layers, and the terminal device executes the computing process of the first two layers; in other words, in the computing power instance corresponding to Executor 1, the terminal device can execute Fewer calculations, so that the terminal device can exchange more feature information of the hidden layer of the neural network.
  • the network device executes the computing process of the last four layers, and the terminal device executes the computing process of the first four layers; in other words, compared with the computing power instance corresponding to Executor 1, in the In the computing power example corresponding to 2, the terminal device can perform more calculations, so that the terminal device can interact with less feature information of the hidden layer of the neural network.
  • the network device when the terminal device is in the center of the cell, the network device can determine that the channel quality between the terminal device and the network device is of good quality and the transmission bandwidth is large based on the channel information reported by the terminal device.
  • the computing power instance corresponding to Executor 1 in the illustration the computing power instance corresponding to Executor 1 needs to exchange more feature information, and both terminal devices and network devices use the computing power instance corresponding to Executor 1 configuration together to complete the split reasoning.
  • the network device may send the first information to the terminal device in step S402, which is used to instruct the terminal device to execute the computing power instance corresponding to the execution body 1, so that the terminal device executes the computing power instance corresponding to the execution body 1 in step S403. computing power instance.
  • the network device when the terminal device is at the edge of the cell, the network device can determine that the channel quality between the terminal device and the network device is poor and the transmission bandwidth is small based on the channel information reported by the terminal device.
  • the computing power instance corresponding to Executor 2 in the figure the computing power instance corresponding to Executor 2 requires less interaction of feature information, and both terminal devices and network devices use the configuration corresponding to instance 1 to complete split reasoning.
  • the network device may send the first information to the terminal device in step S402, which is used to instruct the terminal device to execute the computing power instance corresponding to the execution body 2, so that the terminal device executes the computing power instance corresponding to the execution body 2 in step S403. computing power instance.
  • the resources required by the executive body are configured according to the maximum value of resources required by multiple computing power instances, enabling fast switching between computing power instances.
  • the rapid switching of computing power instances matches the rapid changes in the channel between terminal devices and network devices, thereby supporting real-time dynamic integration and adjustment of computing power and connections.
  • the network device generates the configuration information of the computing power executive or computing power instance, the computing power executing body or computing power instance and the size of computing power, model, location of segmentation point, federation
  • the configuration related to the calculation amount such as learning the number of local iterations is mapped one by one and transmitted to the terminal; the network device sends the dynamic adjustment instruction information of the computing force executive or computing power instance to the terminal device, including the computing power executing body ID information or computing power Instance ID information; (due to one-to-one mapping, it can also be model ID information, segmentation point ID information, local iteration number ID information, etc.); so as to realize the fusion and dynamic adjustment of computing power and connections.
  • computing power instances are dynamically switched based on predefined events.
  • the first message sent by the network device in step S401 includes first configuration information and second configuration information.
  • the first configuration information of at least one calculation instance used for configuration includes the computing power instance ID (which can be task ID or other forms, which can be CMF/TA allocation, or TS/CS allocation) and computing power Size, model, split learning or location of reasoning split point, number of local iterations of federated learning, computing power duration, etc. are in one-to-one correspondence with the configuration related to the amount of calculation.
  • computing power instance ID which can be task ID or other forms, which can be CMF/TA allocation, or TS/CS allocation
  • computing power Size model, split learning or location of reasoning split point, number of local iterations of federated learning, computing power duration, etc. are in one-to-one correspondence with the configuration related to the amount of calculation.
  • the second configuration information used to configure at least one instance resource information includes one or more executive IDs.
  • one executive can include one or more computing power instances
  • the configuration information of the executing body includes the executing body ID and the computing power configuration information of the executing body, specifically including one or more computing power resources (CPU type, storage, memory, power information, computing power duration) or computing power container (combination of the above computing power types).
  • the computing power resource of the execution body is greater than or equal to the maximum value of computing power resources required by the multiple computing power instances included in the execution body.
  • one of the multiple computing power instances in the executive is used as the default computing power instance or one of the multiple computing power executives is used as the default computing power executing body.
  • the terminal base station switches to the default computing power instance or default computing power executive.
  • the ID of the computing power executive can also be replaced by the ID of the model, the ID of the split point of split learning or reasoning, the ID of the number of federated learning iterations, etc., which are not limited here.
  • the terminal device may generate first information by itself in step S402, which is used to instruct the terminal device to execute the first computing power instance. That is to say, the terminal device dynamically switches computing power instances based on predetermined events (if executives and computing power instances are mapped one by one, it can also be computing power executing body switching).
  • this implementation manner may be implemented through the scenario shown in FIG. 6c.
  • the "computing power instance” is recorded as “instance” in Fig. 6c, including default instance 1 and instance 2.
  • the process in which the network device sends the first message to the terminal device in step S401 and the network device determines in step S402 that the terminal device executes a default instance may be triggered based on CMF scheduling, wherein the CMF It can be deployed on the core network side or on the access network side, which is not limited in this application.
  • the network device may determine in step S402 that the terminal device executes a default instance based on the real-time convergence scheduling (convergence scheduling, CS) generated by itself.
  • CS convergence scheduling
  • the network device and the terminal device jointly calculate the calculation task of the neural network shown in FIG. 5a as an example.
  • the terminal device performs the calculation process of the first two layers, and the network device performs the calculation process of the last six layers; in other words, in instance 1, the terminal device can perform less calculations, so that the terminal device can interact more Many neural network hidden layer feature information.
  • the network device performs the calculation process of the first four layers, and the terminal device performs the calculation process of the last four layers; in other words, compared with the default example 1, in the example 2, the terminal device can perform more calculations, so that the The terminal device can interact with less feature information of the hidden layer of the neural network.
  • the network device when the terminal device is in the center of the cell, the network device can determine based on the channel information reported by the terminal device that the quality of the channel between the terminal device and the network device is good, and the transmission bandwidth is large.
  • this example 1 needs to exchange more feature information, and both the terminal device and the network device use the configuration corresponding to the example 1 to jointly complete the split reasoning.
  • the network device may send the first information to the terminal device in step S402, for instructing the terminal device to execute instance 1, so that the terminal device executes instance 1 in step S403.
  • the computing power instance based on the predefined event is dynamically switched (if the execution body and the computing power instance are mapped one by one, the computing power instance can also be Executor switching), that is, the terminal device triggers the generation of first information based on the predefined event in step S402, and executes the first computing power instance based on the first information in step S403.
  • the predefined event includes at least one of the following:
  • the timer pre-configured by the network device that is, switch to the default instance after working on a non-default instance for a period of time.
  • the terminal device and network device both work on instance 2.
  • the terminal device and network device will switch to the corresponding instance.
  • the terminal device When the terminal device determines that its own power is less than a threshold configured on the network side, or other computing resource events, it will switch to the default instance, for example, the terminal device and network device switch to default instance 1 to work, so as to ensure the normal operation of the calculation;
  • the terminal device If the RSRP of the terminal device is less than a certain threshold, or the terminal device enters the RRC idle state, or a cell handover or other RRM events occur, it will switch to the default instance, such as switching to the default instance 1 for terminal equipment and network equipment;
  • the predefined time may also include other broader events, such as 90% completion of computing tasks, reduction of user computing service QoS requirements, and the like.
  • the network device generates the configuration information of the computing force executive or computing power instance, and the computing power executing body or computing power instance is related to the size of computing power, model, location of segmentation point, and local iteration of federated learning.
  • the configuration related to the calculation amount such as the number of times is mapped one by one and transmitted to the terminal; the network device sends the dynamic adjustment instruction information of the computing power executive or computing power instance to the terminal device, including the ID information of the computing power executing body or the ID of the computing power instance Information; (due to one-to-one mapping, it can also be model ID information, segmentation point ID information, local iteration number ID information, etc.); so as to realize the fusion and dynamic adjustment of computing power and connection.
  • the indication information of dynamic signaling can also be saved. Moreover, it can be guaranteed that in the case of failure to transmit signaling (such as reconfiguration signaling, scheduling signaling, etc.) transmitted between the network device and the terminal device, it is ensured that the terminal device can also execute the default computing power example, so that the terminal device It can still participate in the calculation process corresponding to the calculation example as a calculation node to improve the reuse of computing resources.
  • signaling such as reconfiguration signaling, scheduling signaling, etc.
  • the terminal device can be based on the real-time converged scheduling (CS) of the network device in step S402 or based on a predefined event is triggered to acquire the first information. Thereafter, the terminal device executes the first computing power instance based on the first information in step S403, so that the terminal device participates in the calculation process corresponding to the calculation example as a computing node, which can effectively improve the reuse degree of computing resources and improve network revenue .
  • CS real-time converged scheduling
  • the first computing power example may be a computing power instance jointly calculated by the network device and one or more terminal devices, so that when the terminal device executes the computing power instance based on the first configuration information, it can share Computing resources on the network device side to solve the problem of insufficient computing resources on terminal devices.
  • the first computing power example may be a computing power instance jointly calculated by the terminal device and other computing nodes, so that when the terminal device executes the computing power instance based on the first configuration information, it can share the terminal Computing resources on the device side, so that the computing resources of the terminal device can be shared, and the degree of reuse of computing resources can be improved.
  • other computing nodes may include other terminal devices and/or other network devices.
  • FIG. 8 is another schematic diagram of the communication method provided by the present application.
  • the method includes the following steps.
  • the terminal device sends computing power indication information.
  • the terminal device sends computing power indication information in step S801, and correspondingly, the network device receives the computing power indication information in step S401.
  • the method further includes: the terminal device receives a second message from the network device, and the second message includes an initial configuration information, wherein the initial configuration information is used to configure at least one computing power instance.
  • the terminal device may also receive a second message including initial configuration information, where the initial configuration information is used to configure at least one computing power instance. Thereafter, when the terminal device determines that the initial configuration information needs to be updated (for example, the value of the terminal device's CPU type information, storage information, memory information, power information and/or computing power utilization rate information is lower than the threshold or high When the terminal device is greater than the threshold), the terminal device may send computing power indication information to the network device, so that the network device sends updated configuration information, that is, the first configuration information. Thereafter, the terminal device may update the initial configuration information based on the first configuration information, so as to obtain computing power configuration information adapted to the terminal device.
  • the initial configuration information for example, the value of the terminal device's CPU type information, storage information, memory information, power information and/or computing power utilization rate information is lower than the threshold or high
  • the terminal device may send computing power indication information to the network device, so that the network device sends updated configuration information, that is, the first configuration information. Thereafter, the terminal device may update the
  • the network device sends a first message.
  • the network device after the network device receives the computing power indication information in step S801, the network device sends a first message in step S802, and correspondingly, the terminal device receives the first message in step S802.
  • the method further includes: the terminal device sending a response message or a confirmation message to the first message.
  • the terminal device may also send a response message or an acknowledgment message to the first message, so that the network device can specify that the terminal device The first message has been received, and the at least one calculation instance will be configured with the first configuration information contained in the first message.
  • the computing power indication information sent by the terminal device in step S801 is used to indicate the computing power information of the terminal device, and there may be multiple implementation manners for the computing power indication information. Several examples are provided below for illustration.
  • the computing power indication information sent by the terminal device in step S801 includes first indication information, and the first indication information is used to indicate the computing power state of the terminal device.
  • the computing power indication information sent by the terminal device includes first indication information for indicating the computing power status of the terminal device.
  • the terminal device may send the first indication information for indicating the computing power status of the terminal device to the network device, so that the network device may use the calculation state of the terminal device as A basis for the network device to send the first message. Therefore, the network device can dynamically adjust the computing power instance executed by the terminal device (and/or the computing power resource corresponding to the computing power instance executed by the terminal device) based on the computing power state of the terminal device.
  • the first indication information includes at least one of the following:
  • CPU type information storage information, memory information, battery information, computing power utilization information.
  • the computing power indication information sent by the terminal device in step S801 includes second indication information, and the second indication information is used to indicate computing power resource information and/or computing power instances expected by the terminal device.
  • the computing power indication information sent by the terminal device includes second indication information for indicating computing power resource information and/or computing power instances expected by the terminal device.
  • the terminal device may send to the network device second indication information for indicating the computing power resource information and/or computing power instance expected by the terminal device, so that the network device may send The computing power resource information and/or computing power instance expected by the terminal device is used as a basis for the network device to send the first message.
  • the network device can, based on the computing power resource information and/or computing power instance expected by the terminal device, calculate the computing power instance executed by the terminal device (and/or the computing power resource corresponding to the computing power instance executed by the terminal device ) to make dynamic adjustments, so that the provided configuration information can meet the requirements of the terminal device.
  • the computing power indication information sent by the terminal device in step S801 includes third indication information, and the third indication information is used to indicate computing power adjustment information of the terminal device.
  • the computing power indication information sent by the terminal device includes third indication information for indicating computing power adjustment information of the terminal device.
  • the terminal device may send to the network device second indication information for indicating the computing power adjustment information of the terminal device, so that the network device can adjust the computing power of the terminal device The information is used as a basis for the network device to send the first message.
  • the network device can dynamically adjust the computing power instance executed by the terminal device (and/or the computing power resource corresponding to the computing power instance executed by the terminal device), in order to achieve The configuration information provided can meet the computing power adjustment requirements of the terminal device.
  • the third indication information includes:
  • Memory information battery information, computing power utilization information.
  • the first message sent by the network device in step S802 further includes second configuration information, where the second configuration information is used to configure at least one computing power resource information, and the at least one computing power resource Information is associated with the at least one computing power instance.
  • the at least one computing power resource associated with the at least one computing power instance includes:
  • Each computing power resource of the at least one computing power resource corresponds to each computing power instance in the at least one computing power instance
  • One of the computing power resources in the at least one computing power resource corresponds to one or more computing power instances in the at least one computing power instance.
  • At least one computing power resource configured by the second configuration information is associated with at least one calculation example instance configured by the first configuration information, wherein the computing power resource in the at least one computing power resource is related to the at least one calculation example instance
  • Computing power instances in can have a one-to-one relationship, or a one-to-one or one-to-many relationship, so as to improve the flexibility of network devices in the process of configuring computing instance instances and computing power resources.
  • the network device indicates the first computing power instance based on the first information
  • the network device can also improve the performance of the network device in indicating the first computing instance instance and/or the computing power resource corresponding to the first computing power instance. Process flexibility.
  • the terminal device when one of the at least one computing power resource corresponds to multiple computing power instances in the at least one computing power instance, that is, the computing power resource in the at least one computing power resource is different from the at least one computing power resource.
  • the terminal device since the terminal device can execute multiple different computing power instances with this computing power resource, the terminal device does not need to determine ( or reconfiguring, preparing, activating, etc.) a new computing power resource, so that the terminal device can quickly switch between multiple different calculation examples corresponding to the computing power resource.
  • the at least one computing power resource information includes at least one of the following:
  • CPU type information storage information, execution time information, memory information or power information.
  • the computing power instance in the at least one computing power instance includes at least one of the following:
  • Execution time information computing power size information, model information, split learning position, inference split point position or local iteration number of federated learning.
  • the terminal device after the terminal device sends the computing power indication information in step S801, it makes the network device generate and send the first message containing the first configuration information based on the computing power indication information.
  • the first configuration information is used to configure at least
  • the terminal device receives the first configuration information in step S802.
  • the network device configures the computing power instance executed by the terminal device based on the information. Therefore, the wireless network system where the terminal device and the network device are located can become a dual infrastructure for communication connection and computing, and the network device configures the computing power of the terminal device based on the first configuration information, so that the terminal device participates in computing as a computing node.
  • the calculation process corresponding to the example can effectively improve the reuse of computing resources and improve network revenue.
  • the network device may reconfigure the computing power instance and/or the computing power resource corresponding to the computing instance based on signaling.
  • the terminal device may perceive its own computing power status, and report computing power indication information to the network device in step S801, where the computing power indication information may include computing power status information, computing power adjustment request, or computing power suggestion information.
  • the computing power indication information may include computing power status information, computing power adjustment request, or computing power suggestion information.
  • the computing power status information includes one or more computing power (CPU type, storage, memory, power information) status information or utilization information; or computing power container (a combination of the above computing power types) status information or Use information.
  • computing power CPU type, storage, memory, power information
  • computing power container a combination of the above computing power types
  • the transmission mode of the computing power state information can be through L1 signaling, L2 MAC CE signaling or L3 RRC CRC container, CRC IE defined in RRC signaling, or the defined RRC computing power request message including the above computing power force information.
  • the computing power suggestion information includes the ID information of one computing power executive or one computing power instance among multiple computing power executives or multiple computing power instances configured on the network side, or includes terminal equipment The configuration information of the proposed computing power executive or the configuration information of the computing power instance.
  • the computing power instance ID or computing power executive body ID can also be the model ID, the split point ID of split learning or reasoning, the federated learning iteration number ID, etc., which are not limited here.
  • the computing power management function in the network device performs computing power adjustment, which can directly/indirectly reconfigure/schedule computing power, and execute step S802 to trigger RRC signaling reconfiguration Calculate the guaranteed rate of the logical channel mapped to the radio bearer, etc.
  • the basis for the network device to perform computing power adjustment may include: CSI/RSRP information reported by the terminal device, base station computing power load information, terminal computing power status report information, and the computing power indication sent by the terminal device in step S801 information etc.
  • the RRC computing power reconfiguration message includes: one executive (executive ID) may include one or more computing power instances, and the configuration information of the executing body includes the executing body ID and the computing power configuration information of the executing body, Specifically, it includes multiple computing power resources (CPU type, storage, memory, power information) or computing power container (combination of the above computing power types); the computing power resources of the execution body are greater than or equal to the requirements of multiple computing power instances included in the execution body The maximum value of computing resources.
  • one executive executive ID
  • the configuration information of the executing body includes the executing body ID and the computing power configuration information of the executing body, Specifically, it includes multiple computing power resources (CPU type, storage, memory, power information) or computing power container (combination of the above computing power types); the computing power resources of the execution body are greater than or equal to the requirements of multiple computing power instances included in the execution body The maximum value of computing resources.
  • the computing power instance ID (which can be task ID or other forms, can be CMF/TA allocation, or TS/CS allocation) is related to computing power size, model, split learning or inference split point location, federation One-to-one correspondence with the configuration related to the amount of calculation, such as learning the number of local iterations
  • the terminal after receiving the first message in step S802, the terminal sends a confirmation message.
  • the terminal adjusts the computing power based on the decision-making of the network equipment, and realizes the adjustment of the corresponding computing power in conjunction with the computing power demand of the terminal.
  • the wireless network system where the terminal device and the network device are located can become a dual infrastructure for communication connection and computing, and the network device configures the computing power of the terminal device based on the first configuration information, so that the terminal device participates in computing as a computing node.
  • the calculation process corresponding to the example can effectively improve the reuse of computing resources and improve network revenue.
  • the first computing power instance may be a computing power instance jointly calculated by the network device and one or more terminal devices, so that the terminal device executes the computing power instance based on the first configuration information contained in the first message
  • computing resources on the network device side can be shared to solve the problem of insufficient computing resources on terminal devices.
  • the first computing power example may be a computing power instance jointly calculated by the terminal device and other computing nodes, so that the terminal device executes the computing power instance based on the first configuration information contained in the first message , the computing resource on the terminal device side can be shared, so that the computing resource of the terminal device can be shared, and the multiplexing degree of the computing resource can be improved.
  • other computing nodes may include other terminal devices and/or other network devices.
  • the embodiment of the present application provides a communication device 900
  • the communication device 900 can realize the function of the terminal device (or network device) in the above method embodiment, so it can also realize the benefits of the above method embodiment Effect.
  • the communication device 900 may be a terminal device (or network device), or an integrated circuit or component inside the terminal device (or network device), such as a chip.
  • the following embodiments are described by taking the communication apparatus 900 as a terminal device or a network device as an example.
  • the apparatus 900 when the apparatus 900 is configured to execute the method performed by the terminal device in any of the foregoing embodiments, the apparatus 900 includes a processing unit 901 and a transceiver unit 902;
  • the transceiving unit 902 is configured to receive a first message from a network device, where the first message includes first configuration information, where the first configuration information includes configuration information of at least one computing power instance;
  • the processing unit 901 is configured to acquire first information, where the first information is used to indicate a first computing power instance, where the first computing power instance is a computing power instance in the at least one computing power instance;
  • the processing unit 901 is further configured to execute the first computing power instance based on the first information.
  • the first message further includes second configuration information, where the second configuration information includes configuration information of at least one computing power resource, and the at least one computing power resource is associated with the at least one computing power instance.
  • the first information includes an identifier of the first computing power instance and/or an identifier of computing power resource information corresponding to the first computing power instance;
  • the processing unit 901 is used for the first information to include:
  • the processing unit 901 is configured to control the transceiving unit 902 to receive the first information, where the first information is carried in L1 control information or L2 control information or L3 message.
  • the transceiver unit 902 is also configured to receive a reference signal RS;
  • the transceiver unit 902 is further configured to send the measurement result corresponding to the RS.
  • the first computing power instance is the default computing power instance; and/or,
  • the computing power resource information corresponding to the first computing power instance is the default computing power resource information.
  • the processing unit 901, configured to obtain the first information includes:
  • the processing unit 901 is configured to generate the first information, including:
  • the first timer expires, wherein the configuration information of the first timer is included in the first message; or,
  • the power of the terminal device is lower than the first threshold; or,
  • the terminal equipment enters the radio resource control idle RRC idle state.
  • the transceiving unit 902 is further configured to send first indication information to the network device, where the first indication information is used to indicate the computing power state of the terminal device.
  • the transceiving unit 902 is further configured to send second indication information to the network device, where the second indication information is used to indicate computing power resource information and/or computing power instances expected by the terminal device.
  • the transceiving unit 902 is further configured to send third indication information, where the third indication information is used to indicate computing power adjustment information of the terminal device;
  • the transceiving unit 902 is further configured to receive third configuration information from the network device, where the third configuration information is used to update the first configuration information and/or the third configuration information is used to update the second configuration information.
  • the computing power instance in the at least one computing power instance includes at least one of the following:
  • Execution time information computing power size information, model information, split learning position, inference split point position or local iteration number of federated learning.
  • the at least one computing power resource information includes at least one of the following:
  • CPU type information storage information, execution time information, memory information or power information.
  • the at least one computing power resource associated with the at least one computing power instance includes:
  • Each computing power resource of the at least one computing power resource corresponds to each computing power instance in the at least one computing power instance
  • One of the computing power resources in the at least one computing power resource corresponds to one or more computing power instances in the at least one computing power instance.
  • the first indication information includes at least one of the following:
  • CPU type information storage information, memory information, battery information, computing power utilization information.
  • the third indication information includes:
  • Memory information battery information, computing power utilization information.
  • the apparatus 900 when the apparatus 900 is configured to execute the method performed by the network device in any of the foregoing embodiments, the apparatus 900 includes a processing unit 901 and a transceiver unit 902;
  • the processing unit 901 is configured to generate a first message, where the first message includes first configuration information, where the first configuration information includes configuration information of at least one computing power instance;
  • the transceiving unit 902 is configured to send the first message.
  • the first message further includes second configuration information, where the second configuration information includes configuration information of at least one computing power resource, and the at least one computing power resource is associated with the at least one computing power instance.
  • the transceiver unit 902 is further configured to send first information, the first information is used to indicate a first computing power instance, the first computing power instance is a computing power instance in the at least one computing power instance, and the first information includes The identification of the first computing power instance and/or the identification of the computing power resource information corresponding to the first computing power instance;
  • the first information is carried in L1 control information or L2 control information or L3 message.
  • the transceiver unit 902 is also configured to send a reference signal RS;
  • the transceiver unit 902 is also configured to receive a measurement result corresponding to the RS;
  • the processing unit 901 is further configured to generate the first information based on the measurement result corresponding to the RS.
  • the transceiving unit 902 is further configured to receive first indication information from the terminal device, where the first indication information is used to indicate the computing power status of the terminal device;
  • the processing unit 901 is further configured to determine the first information based on the first indication information.
  • the transceiving unit 902 is further configured to receive second indication information from the terminal device, where the second indication information is used to indicate computing power resource information and/or computing power instances expected by the terminal device;
  • the processing unit 901 is further configured to determine the first information based on the second indication information.
  • the transceiving unit 902 is further configured to receive third indication information from the terminal device, where the third indication information is used to indicate computing power adjustment information of the terminal device;
  • the processing unit 901 is further configured to send third configuration information based on the third indication information, where the third configuration information is used to update the first configuration information and/or the third configuration information is used to update the second configuration information.
  • the computing power instance in the at least one computing power instance includes at least one of the following:
  • Execution time information computing power size information, model information, split learning position, inference split point position or local iteration number of federated learning.
  • the at least one computing power resource information includes at least one of the following:
  • CPU type information storage information, execution time information, memory information or power information.
  • the at least one computing power resource associated with the at least one computing power instance includes:
  • Each computing power resource of the at least one computing power resource corresponds to each computing power instance in the at least one computing power instance
  • One of the computing power resources in the at least one computing power resource corresponds to one or more computing power instances in the at least one computing power instance.
  • the first indication information includes at least one of the following:
  • CPU type information storage information, memory information, battery information, computing power utilization information.
  • the third indication information includes:
  • Memory information battery information, computing power utilization information.
  • the apparatus 900 when the apparatus 900 is configured to execute the method performed by the terminal device in any of the foregoing embodiments, the apparatus 900 includes a processing unit 901 and a transceiver unit 902;
  • the processing unit 901 is configured to determine computing power indication information
  • the transceiver unit 902 is configured to send computing power indication information to network devices;
  • the transceiving unit 902 is further configured to receive a first message from the network device, where the first message includes first configuration information, where the first configuration information is used to configure at least one computing power instance.
  • the transceiving unit 902 is further configured to receive a second message from the network device, where the second message includes initial configuration information, where the initial configuration information is used to configure at least one computing power instance.
  • the transceiving unit 902 is further configured to send a response message or a confirmation message of the first message.
  • the computing power indication information includes first indication information, where the first indication information is used to indicate the computing power state of the terminal device.
  • the first indication information includes at least one of the following:
  • CPU type information storage information, memory information, battery information, computing power utilization information.
  • the computing power indication information includes second indication information, where the second indication information is used to indicate computing power resource information and/or computing power instances expected by the terminal device.
  • the computing power indication information includes third indication information, where the third indication information is used to indicate computing power adjustment information of the terminal device.
  • the third indication information includes:
  • Memory information battery information, computing power utilization information.
  • the first message further includes second configuration information, where the second configuration information is used to configure at least one piece of computing power resource information, and the at least one piece of computing power resource information is associated with the at least one computing power resource. force instance.
  • the at least one computing power resource associated with the at least one computing power instance includes:
  • Each computing power resource of the at least one computing power resource corresponds to each computing power instance in the at least one computing power instance
  • One of the computing power resources in the at least one computing power resource corresponds to one or more computing power instances in the at least one computing power instance.
  • the at least one computing power resource information includes at least one of the following:
  • CPU type information storage information, execution time information, memory information or power information.
  • the computing power instance in the at least one computing power instance includes at least one of the following:
  • Execution time information computing power size information, model information, split learning position, inference split point position or local iteration number of federated learning.
  • the apparatus 900 when the apparatus 900 is configured to execute the method performed by the terminal device in any of the foregoing embodiments, the apparatus 900 includes a processing unit 901 and a transceiver unit 902;
  • the transceiver unit 902 is configured to receive computing power indication information from the terminal device;
  • the processing unit 901 is configured to determine a first message to the terminal device based on the computing power indication information, where the first message includes first configuration information, where the first configuration information is used to configure at least one computing power instance;
  • the transceiving unit 902 is also configured to send the first message.
  • the transceiving unit 902 is further configured to send a second message to the terminal device, where the second message includes initial configuration information, where the initial configuration information is used to configure at least one computing power instance.
  • the transceiving unit 902 is further configured to receive a response message or a confirmation message of the first message from the terminal device.
  • the computing power indication information includes first indication information, where the first indication information is used to indicate the computing power state of the terminal device.
  • the first indication information includes at least one of the following:
  • CPU type information storage information, memory information, battery information, computing power utilization information.
  • the computing power indication information includes second indication information, where the second indication information is used to indicate computing power resource information and/or computing power instances expected by the terminal device.
  • the computing power indication information includes third indication information, where the third indication information is used to indicate computing power adjustment information of the terminal device.
  • the third indication information includes:
  • Memory information battery information, computing power utilization information.
  • the first message further includes second configuration information, where the second configuration information is used to configure at least one piece of computing power resource information, and the at least one piece of computing power resource information is associated with the at least one computing power resource. force instance.
  • the at least one computing power resource associated with the at least one computing power instance includes:
  • Each computing power resource of the at least one computing power resource corresponds to each computing power instance in the at least one computing power instance
  • One of the computing power resources in the at least one computing power resource corresponds to one or more computing power instances in the at least one computing power instance.
  • the at least one computing power resource information includes at least one of the following:
  • CPU type information storage information, execution time information, memory information or power information.
  • the computing power instance in the at least one computing power instance includes at least one of the following:
  • Execution time information computing power size information, model information, split learning position, inference split point position or local iteration number of federated learning.
  • FIG. 10 is another schematic structural diagram of a communication device 1000 provided in this application.
  • the communication device 1000 includes at least an input and output interface 1002 .
  • the communication device 1000 may be a chip or an integrated circuit.
  • the communication device further includes a logic circuit 1001 .
  • the transceiver unit 902 shown in FIG. 9 may be a communication interface, and the communication interface may be the input and output interface 1002 in FIG. 10 , and the input and output interface 1002 may include an input interface and an output interface.
  • the communication interface may also be a transceiver circuit, and the transceiver circuit may include an input interface circuit and an output interface circuit.
  • the input-output interface 1002 is used to input the first message and the first information; the logic circuit 1001 is used to execute the first computing power instance based on the first information.
  • the logic circuit 1001 and the input/output interface 1002 can also perform other steps performed by the terminal device in any of the foregoing embodiments and achieve corresponding beneficial effects, which will not be repeated here.
  • the logic circuit 1001 is used to generate the first message; the input-output interface 1002 is used to send the first message.
  • the logic circuit 1001 and the input/output interface 1002 can also perform other steps performed by the network device in any embodiment and achieve corresponding beneficial effects, which will not be repeated here.
  • the processing unit 901 shown in FIG. 9 may be the logic circuit 1001 in FIG. 10 .
  • the logic circuit 1001 may be a processing device, and the functions of the processing device may be partially or completely implemented by software. Wherein, the functions of the processing device may be partially or completely implemented by software.
  • the processing device may include a memory and a processor, wherein the memory is used to store computer programs, and the processor reads and executes the computer programs stored in the memory to perform corresponding processing and/or steps in any method embodiment .
  • the processing means may only include a processor.
  • the memory for storing the computer program is located outside the processing device, and the processor is connected to the memory through circuits/wires to read and execute the computer program stored in the memory.
  • the memory and the processor may be integrated together, or may be physically independent of each other.
  • the processing means may be one or more chips, or one or more integrated circuits.
  • the processing device may be one or more field-programmable gate arrays (field-programmable gate array, FPGA), application specific integrated circuit (ASIC), system chip (system on chip, SoC), central processing unit (central processor unit, CPU), network processor (network processor, NP), digital signal processing circuit (digital signal processor, DSP), microcontroller (micro controller unit, MCU), programmable controller (programmable logic device, PLD) or other integrated chips, or any combination of the above chips or processors, etc.
  • the communication device 1100 involved in the above-mentioned embodiment provided for the embodiment of the present application can specifically be the communication device as a terminal device in the above-mentioned embodiment, the example shown in Figure 11 is a terminal A device is realized by a terminal device (or a component in a terminal device).
  • a schematic diagram of a possible logical structure of the communication device 1100 may include but not limited to at least one processor 1101 and a communication port 1102 .
  • the device may further include at least one of a memory 1103 and a bus 1104.
  • the at least one processor 1101 is configured to control and process actions of the communication device 1100.
  • the processor 1101 may be a central processing unit, a general processor, a digital signal processor, an application specific integrated circuit, a field programmable gate array or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It can implement or execute the various illustrative logical blocks, modules and circuits described in connection with the present disclosure.
  • the processor can also be a combination that realizes computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processor and a microprocessor, and the like.
  • the communication device 1100 shown in FIG. 11 can be specifically used to implement the steps implemented by the terminal device in the foregoing method embodiments, and realize the corresponding technical effects of the terminal device.
  • the specific implementation methods of the communication device shown in FIG. 11 are both Reference may be made to the descriptions in the foregoing method embodiments, and details are not repeated here.
  • FIG. 12 is a schematic structural diagram of the communication device involved in the above-mentioned embodiment provided by the embodiment of the present application.
  • the communication device may specifically be the communication device as a network device in the above-mentioned embodiment.
  • the example shown in FIG. 12 is The network device is realized by the network device (or components in the network device), wherein, the structure of the communication apparatus may refer to the structure shown in FIG. 12 .
  • the communication device includes at least one processor 1211 and at least one network interface 1214 . Further optionally, the communication device further includes at least one memory 1212 , at least one transceiver 1213 and one or more antennas 1215 .
  • the processor 1211, the memory 1212, the transceiver 1213 and the network interface 1214 are connected, for example, through a bus. In this embodiment of the application, the connection may include various interfaces, transmission lines or buses, which are not limited in this embodiment.
  • the antenna 1215 is connected to the transceiver 1213 .
  • the network interface 1214 is used to enable the communication device to communicate with other communication devices through a communication link.
  • the network interface 1214 may include a network interface between the communication device and a core network device, such as an S1 interface, and the network interface may include a network interface between the communication device and other communication devices (such as other network devices or core network devices), such as X2 Or Xn interface.
  • a core network device such as an S1 interface
  • the network interface may include a network interface between the communication device and other communication devices (such as other network devices or core network devices), such as X2 Or Xn interface.
  • the processor 1211 is mainly used to process communication protocols and communication data, control the entire communication device, execute software programs, and process data of the software programs, for example, to support the communication device to execute the actions described in the embodiments.
  • the communication device may include a baseband processor and a central processor.
  • the baseband processor is mainly used to process communication protocols and communication data.
  • the central processor is mainly used to control the entire terminal equipment, execute software programs, and process data of the software programs.
  • the processor 1211 in FIG. 12 can integrate the functions of the baseband processor and the central processing unit. Those skilled in the art can understand that the baseband processor and the central processing unit can also be independent processors, interconnected through technologies such as a bus.
  • a terminal device may include multiple baseband processors to adapt to different network standards, a terminal device may include multiple central processors to enhance its processing capability, and various components of the terminal device may be connected through various buses.
  • the baseband processor may also be expressed as a baseband processing circuit or a baseband processing chip.
  • the central processing unit may also be expressed as a central processing circuit or a central processing chip.
  • the function of processing the communication protocol and communication data can be built in the processor, or can be stored in the memory in the form of a software program, and the processor executes the software program to realize the baseband processing function.
  • Memory is primarily used to store software programs and data.
  • the memory 1212 may exist independently and be connected to the processor 1211 .
  • the memory 1212 may be integrated with the processor 1211, for example, integrated into one chip.
  • the memory 1212 can store program codes for executing the technical solutions of the embodiments of the present application, and the execution is controlled by the processor 1211 , and various types of computer program codes to be executed can also be regarded as drivers for the processor 1211 .
  • Figure 12 shows only one memory and one processor. In an actual terminal device, there may be multiple processors and multiple memories.
  • a memory may also be called a storage medium or a storage device.
  • the memory may be a storage element on the same chip as the processor, that is, an on-chip storage element, or an independent storage element, which is not limited in this embodiment of the present application.
  • the transceiver 1213 may be used to support receiving or sending radio frequency signals between the communication device and the terminal, and the transceiver 1213 may be connected to the antenna 1215 .
  • the transceiver 1213 includes a transmitter Tx and a receiver Rx.
  • one or more antennas 1215 can receive radio frequency signals
  • the receiver Rx of the transceiver 1213 is used to receive the radio frequency signals from the antennas, convert the radio frequency signals into digital baseband signals or digital intermediate frequency signals, and convert the digital baseband
  • the signal or the digital intermediate frequency signal is provided to the processor 1211, so that the processor 1211 performs further processing on the digital baseband signal or digital intermediate frequency signal, such as demodulation processing and decoding processing.
  • the transmitter Tx in the transceiver 1213 is also used to receive the modulated digital baseband signal or digital intermediate frequency signal from the processor 1211, and convert the modulated digital baseband signal or digital intermediate frequency signal into a radio frequency signal, and pass a The radio frequency signal is transmitted by one or more antennas 1215 .
  • the receiver Rx can selectively perform one or more stages of down-mixing processing and analog-to-digital conversion processing on the radio frequency signal to obtain a digital baseband signal or a digital intermediate frequency signal.
  • the order of the down-mixing processing and analog-to-digital conversion processing The order is adjustable.
  • the transmitter Tx can selectively perform one or more stages of up-mixing processing and digital-to-analog conversion processing on the modulated digital baseband signal or digital intermediate frequency signal to obtain a radio frequency signal.
  • the up-mixing processing and digital-to-analog conversion processing The sequence is adjustable.
  • Digital baseband signals and digital intermediate frequency signals can be collectively referred to as digital signals.
  • the transceiver 1213 may also be called a transceiver unit, a transceiver, a transceiver device, and the like.
  • the device used to realize the receiving function in the transceiver unit can be regarded as a receiving unit
  • the device used to realize the sending function in the transceiver unit can be regarded as a sending unit, that is, the transceiver unit includes a receiving unit and a sending unit, and the receiving unit also It can be called receiver, input port, receiving circuit, etc., and the sending unit can be called transmitter, transmitter, or transmitting circuit, etc.
  • the communication device shown in FIG. 12 can be used to implement the steps implemented by the network device in the foregoing method embodiments, and realize the corresponding technical effects of the network device.
  • the specific implementation of the communication device shown in FIG. 12 can be Reference is made to the descriptions in the foregoing method embodiments, and details are not repeated here one by one.
  • the embodiment of the present application also provides a computer-readable storage medium storing one or more computer-executable instructions.
  • the processor executes the Methods.
  • Embodiments of the present application also provide a computer-readable storage medium storing one or more computer-executable instructions.
  • the processor executes the network device as described in the possible implementation manners of the foregoing embodiments. Methods.
  • the embodiment of the present application also provides a computer program product (or computer program) storing one or more computers, and when the computer program product is executed by the processor, the processor executes the method of the above-mentioned possible implementation manner of the terminal device.
  • the embodiment of the present application also provides a computer program product storing one or more computers, and when the computer program product is executed by the processor, the processor executes the method of the above-mentioned possible implementation manner of the network device.
  • An embodiment of the present application further provides a system on chip, where the system on chip includes at least one processor, configured to support a communication device to implement the functions involved in the possible implementation manners of the above communication device.
  • the chip system further includes an interface circuit, and the interface circuit provides program instructions and/or data for the at least one processor.
  • the system-on-a-chip may further include a memory, and the memory is used for storing necessary program instructions and data of the communication device.
  • the system-on-a-chip may be composed of chips, or may include chips and other discrete devices, wherein the communication device may specifically be the terminal device in the aforementioned method embodiments.
  • An embodiment of the present application further provides a system on chip, where the system on chip includes at least one processor, configured to support a communication device to implement the functions involved in the possible implementation manners of the above communication device.
  • the chip system further includes an interface circuit, and the interface circuit provides program instructions and/or data for the at least one processor.
  • the system-on-a-chip may further include a memory, and the memory is used for storing necessary program instructions and data of the communication device.
  • the system-on-a-chip may consist of chips, or may include chips and other discrete devices, wherein the communication device may specifically be the network device in the aforementioned method embodiments.
  • An embodiment of the present application also provides a communication system, where the network system architecture includes the terminal device and the network device in any of the foregoing embodiments.
  • the disclosed system, device and method can be implemented in other ways.
  • the device 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 can be combined or May be integrated into another system, or some features may be ignored, or not implemented.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.
  • the above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units. If the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.
  • the technical solution of the present application is essentially or part of the contribution to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , including several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disc, etc., which can store program codes. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

一种通信方法及通信装置，用于通过网络设备基于第一配置信息对终端设备的算力进行配置的方式，使得终端设备作为计算节点参与算例示例对应的计算过程，可有效提升计算资源的复用程度，以提升网络收益。在该方法中，终端设备接收来自网络设备的第一消息，该第一消息包括第一配置信息，其中，该第一配置信息包括至少一个算力实例的配置信息；该终端设备获取第一信息，该第一信息用于指示第一算力实例，该第一算力实例为该至少一个算力实例中的算力实例；该终端设备基于该第一信息执行该第一算力实例。

Description

一种通信方法及通信装置
本申请要求于2021年12月24日提交中国国家知识产权局，申请号为202111603020.4，发明名称为“一种通信方法及通信装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及无线技术领域，尤其涉及一种通信方法及通信装置。
背景技术
无线通信，是指两个或两个以上的通信节点间不经由导体或缆线传播而进行的传输通讯，该通信节点一般包括网络设备和终端设备。
目前，在无线通信系统中，通信节点一般具备信号收发能力和计算能力。以具备计算能力的终端设备这一通信节点为例。一方面，终端设备的计算能力需要为信号收发能力提供算力支持(例如：对承载信号的时域资源、频域资源等进行计算)，以实现终端设备与其它通信节点的通信；另一方面，终端设备的计算能力需要为本地应用的计算提供算力支持(例如：对语言、文字或图像等数据的产生和展示进行计算)，以实现终端设备本地应用的呈现。换言之，当前的通信节点所具备的计算能力，是为了支持不同通信节点之间的通信以及支持该通信节点本地应用的呈现。
然而，在未来的通信网络中，不同通信节点之间除了需要进行通信之外，还可能需要兼顾计算能力，以实现通信系统中的网络内生算力。
为此，在通信网络中，如何实现算力的配置与执行，是一个亟待解决的技术问题。
发明内容
本申请实施例提供了一种通信方法及通信装置，用于通过网络设备基于第一配置信息对终端设备的算力进行配置的方式，使得终端设备作为计算节点参与算例示例对应的计算过程，可有效提升计算资源的复用程度，以提升网络收益。
本申请第一方面提供了一种通信方法，该方法由终端设备执行，或者，该方法由终端设备中的部分组件(例如处理器、芯片或芯片系统等)执行，或者该方法还可以由能实现全部或部分终端设备功能的逻辑模块或软件实现。在第一方面及其可能的实现方式中，以该通信方法由终端设备执行为例进行描述。在该方法中，终端设备接收来自网络设备的第一消息，该第一消息包括第一配置信息，其中，该第一配置信息包括至少一个算力实例的配置信息；该终端设备获取第一信息，该第一信息用于指示第一算力实例，该第一算力实例为该至少一个算力实例中的算力实例；该终端设备基于该第一信息执行该第一算力实例。
基于上述技术方案，终端设备接收来自网络设备的包含有第一配置信息的第一消息，其中，该第一配置信息包括至少一个算力实例的配置信息。该终端设备在获取用于指示该至少一个算力实例中的第一算力实例的第一信息之后，该终端设备基于该第一信息执行该第一算力实例。换言之，终端设备基于网络设备的指示对算力实例进行配置之后，该终端 设备基于第一信息执行相应的算力实例。从而，终端设备和网络设备所在的无线网络系统可以成为通信连接与计算双基础设施，网络设备基于该第一配置信息对终端设备的算力进行配置的方式，使得终端设备作为计算节点参与算例示例对应的计算过程，可有效提升计算资源的复用程度，以提升网络收益。
在一些实现方式中，该第一算力示例可以为网络设备与一个或多个终端设备协同计算的算力实例，使得该终端设备基于该第一配置信息执行算力实例的情况下，能够共享网络设备侧的计算资源，以解决终端设备计算资源不足的问题。
在一些实现方式中，该第一算力示例可以为终端设备与其它计算节点协同计算的算力实例，使得该终端设备基于该第一配置信息执行该算力实例的情况下，能够共享该终端设备侧的计算资源，以使得该终端设备的计算资源得以共享，提升计算资源的复用程度。
可选地，其它计算节点可以包括其它终端设备和/或其它网络设备。
在第一方面的一种可能的实现方式中，该第一消息还包括第二配置信息，其中，该第二配置信息包括至少一个算力资源的配置信息，该至少一个算力资源关联于该至少一个算力实例。
可选地，第二配置信息包含于其它消息。
应理解，本申请所涉及的算力资源(或称为执行体)可以指示算力实例的运行环境，如算力实例运行时需要的存储、电量、内存、算力等。
应理解，本申请所涉及的算力实例可以指示与算力大小、模型、拆分学习或推理切分点位置、联邦学习本地迭代次数等跟计算量相关的一种计算资源使用的模式或方法。
基于上述技术方案，终端设备还接收包含有至少一个算力资源的配置信息的第二配置信息，其中，该至少一个算力资源关联于该至少一个算力实例。从而，在对终端设备的算力进行配置使得终端设备作为计算节点参与算例示例对应的计算过程的同时，使得终端设备基于该第二配置信息明确，在执行至少一个算例示例中的算力实例的过程中所使用的算力资源。
在第一方面的一种可能的实现方式中，该第一信息包括该第一算力实例的标识和/或该第一算力实例对应的算力资源信息的标识；该终端设备获取该第一信息包括：该终端设备接收该第一信息，该第一信息承载于层1(layer 1，L1)控制信息或层2(layer 2，L2)控制信息或层3(layer 3，L3)消息中。
基于上述技术方案，终端设备可以接收来自网络设备的用于指示第一算力实例的第一信息，以使得终端设备基于网络设备的指示执行第一算力实例。从而，在对终端设备的算力进行配置使得终端设备作为计算节点参与算例示例对应的计算过程的同时，网络设备基于第一消息还可以实现对终端设备所执行的算力实例的动态调整。
在第一方面的一种可能的实现方式中，在该终端设备接收该第一信息之前，该方法还包括：该终端设备接收参考信号(reference signal，RS)；该终端设备发送该RS对应的测量结果。
基于上述技术方案，终端设备在接收第一信息之前，可以接收RS并发送该RS对应的测量结果，以便于网络设备可以将该RS的测量结果作为该网络设备发送第一信息的依据。 其中，该RS的测量结果可以反映出终端设备与网络设备之间的信道信息，从而，网络设备可以基于该RS的测量结果对该终端设备所执行的算力实例(和/或该终端设备所执行的算力实例对应的算力资源)进行动态调整。
在第一方面的一种可能的实现方式中，该第一算力实例为默认算力实例；和/或，该第一算力实例对应的算力资源信息为默认算力资源信息。
可选地，默认算力实例也可以称为基础算力实例、预配置的算力实例等。相应的，默认算力资源信息也可以称为基础算力资源信息、预配置的基础算力资源信息等。
可选地，网络设备和终端设备均具备(或预存储)该默认算例示例。
可选地，该默认算例示例可以为低功耗/低开销/计算能力要求低的算力实例。
基于上述技术方案，第一信息所指示的第一算力实例可以为默认算力实例，和/或，第一信息所指示的第一算例示例对应的算力资源信息为默认算力资源信息。从而，基于该默认算例示例的实现，可以保证在网络设备和终端设备之间所传输的信令(如重配信令、调度信令等)传输失败的情况下，确保该终端设备也能执行该默认算力示例，使得终端设备仍能作为计算节点参与算例示例对应的计算过程，以提升计算资源的复用程度。
在第一方面的一种可能的实现方式中，该终端设备获取该第一信息包括：在满足以下至少一项时，该终端设备生成该第一信息，包括：
第一定时器超时，其中，该第一定时器的配置信息包含于该第一消息；或，
该终端设备的电量低于第一阈值；或，
该终端设备进入无线资源控制空闲RRC idle态；或，
该终端设备测量得到的RS的信号质量小于阈值，或；
该终端设备执行小区切换；或，
该终端设备执行RRM测量；或，
该终端设备当前执行的算例示例对应的已执行计算量高于阈值；或，
该终端设备确定服务质量信息(quality of service，QOS)需求低于阈值。
可选地，上述信号质量可以包括参考信号接收功率(reference signal receiving power，RSRP)、参考信号接收质量(reference signal receiving quality，RSRQ)或信号与干扰加噪声比(signal to interference plus noise ratio，SINR)等至少一项。
基于上述技术方案，终端设备可以基于上述至少一项事件的发生，触发生成第一信息。换言之，无需网络设备的指示，该终端设备就可以基于上述至少一项事件实现对该终端设备所执行的算例示例的动态切换。从而，在网络设备和终端设备之间所传输的信令(如重配信令、调度信令等)传输失败的情况下，确保该终端设备也能执行该默认算力示例，使得终端设备仍能作为计算节点参与算例示例对应的计算过程，以提升计算资源的复用程度。
在第一方面的一种可能的实现方式中，在该终端设备接收来自网络设备的第一消息之前，该方法还包括：该终端设备向网络设备发送第一指示信息，该第一指示信息用于指示该终端设备的算力状态。
基于上述技术方案，终端设备在接收第一消息之前，该终端设备可以向该网络设备发送用于指示该终端设备的算力状态的第一指示信息，以便于网络设备可以将该终端设备的 算例状态作为该网络设备发送第一消息的依据。从而，网络设备可以基于该终端设备的算力状态，对该终端设备所执行的算力实例(和/或该终端设备所执行的算力实例对应的算力资源)进行动态调整。
在第一方面的一种可能的实现方式中，在该终端设备接收来自网络设备的第一消息之前，该方法还包括：该终端设备向该网络设备发送第二指示信息，该第二指示信息用于指示该终端设备期望的算力资源信息和/或算力实例。
基于上述技术方案，终端设备在接收第一消息之前，该终端设备可以向该网络设备发送用于指示该终端设备期望的算力资源信息和/或算力实例的第二指示信息，以便于网络设备可以将该终端设备期望的算力资源信息和/或算力实例作为该网络设备发送第一消息的依据。从而，网络设备可以基于该终端设备期望的算力资源信息和/或算力实例，对该终端设备所执行的算力实例(和/或该终端设备所执行的算力实例对应的算力资源)进行动态调整，以期所提供的配置信息能够满足该终端设备的需求。
在第一方面的一种可能的实现方式中，该方法还包括：该终端设备基于该第一信息执行该第一算力实例时，该终端设备发送第三指示信息，该第三指示信息用于指示该终端设备的算力调整信息；该终端设备接收来自该网络设备的第三配置信息，该第三配置信息用于更新该第一配置信息和/或该第三配置信息用于更新该第二配置信息。
基于上述技术方案，终端设备在基于该第一信息执行该第一算力实例的过程中，该终端设备可以向该网络设备发送用于指示该终端设备的算力调整信息的第三指示信息，以便于网络设备可以将该终端设备的算力调整信息作为该网络设备发送更新后的配置(即用于更新第一配置信息和/或用于更新第二配置信息的第三配置信息)的依据。从而，网络设备可以基于该终端设备的算力调整信息，对该终端设备所执行的算力实例(和/或该终端设备所执行的算力实例对应的算力资源)进行动态调整，以期所提供的配置信息能够满足该终端设备的算力调整需求。
本申请第二方面提供了一种通信方法，该方法由网络设备执行，或者，该方法由网络设备中的部分组件(例如处理器、芯片或芯片系统等)执行，或者该方法还可以由能实现全部或部分网络设备功能的逻辑模块或软件实现。在第二方面及其可能的实现方式中，以该通信方法由网络设备执行为例进行描述。在该方法中，网络设备生成第一消息，该第一消息包括第一配置信息，其中，该第一配置信息包括至少一个算力实例的配置信息；该网络设备发送该第一消息。
基于上述技术方案，网络设备所发送的第一消息包括第一配置信息，其中，该第一配置信息包括至少一个算力实例的配置信息。该终端设备在获取用于指示该至少一个算力实例中的第一算力实例的第一信息之后，该终端设备基于该第一信息执行该第一算力实例。换言之，终端设备基于网络设备的指示对算力实例进行配置之后，该终端设备基于第一信息执行相应的算力实例。从而，终端设备和网络设备所在的无线网络系统可以成为通信连接与计算双基础设施，通过网络设备基于该第一配置信息对终端设备的算力进行配置的方式，使得终端设备作为计算节点参与算例示例对应的计算过程，可有效提升计算资源的复 用程度，以提升网络收益。
在第二方面的一种可能的实现方式中，该第一消息还包括第二配置信息，其中，该第二配置信息包括至少一个算力资源的配置信息，该至少一个算力资源关联于该至少一个算力实例。
可选地，第二配置信息包含于其它消息。
基于上述技术方案，网络设备还发送包含有至少一个算力资源的配置信息的第二配置信息，其中，该至少一个算力资源关联于该至少一个算力实例。从而，在对终端设备的算力进行配置使得终端设备作为计算节点参与算例示例对应的计算过程的同时，使得终端设备基于该第二配置信息明确，在执行至少一个算例示例中的算力实例的过程中所使用的算力资源。
在第二方面的一种可能的实现方式中，该方法还包括：该网络设备发送第一信息，该第一信息用于指示第一算力实例，该第一算力实例为该至少一个算力实例中的算力实例，该第一信息包括该第一算力实例的标识和/或该第一算力实例对应的算力资源信息的标识；其中，该第一信息承载于L1控制信息或L2控制信息或L3消息中。
基于上述技术方案，网络设备设备可以发送用于指示第一算力实例的第一信息，以使得终端设备基于网络设备的指示执行第一算力实例。从而，在对终端设备的算力进行配置使得终端设备作为计算节点参与算例示例对应的计算过程的同时，网络设备基于第一消息还可以实现对终端设备所执行的算力实例的动态调整。
在一些实现方式中，该第一算力示例可以为网络设备与一个或多个终端设备协同计算的算力实例，使得该终端设备基于网络设备所指示的第一信息执行该第一算力实例的情况下，能够共享网络设备侧的计算资源，以解决终端设备计算资源不足的问题。相应的，网络设备也需要基于该第一信息执行第一算力实例的部分计算过程，或者说，该网络设备也需要同时在本地调整该第一信息对应的第一算力实例，使得网络设备和终端设备在协同计算的过程中能够实现动态的同步调整。
在一些实现方式中，该第一算力示例可以为终端设备与其它计算节点协同计算的算力实例，使得该终端设备基于该第一信息执行该第一算力实例的情况下，能够共享该终端设备侧的计算资源，以使得该终端设备的计算资源得以共享，提升计算资源的复用程度。相应的，由于该第一算力实例的执行有可能不需要该网络设备参与，因此，网络设备可能无需基于该第一信息执行第一算力实例的部分计算过程，或者说，该网络设备无需同时在本地调整该第一信息对应的第一算力实例。
可选地，其它计算节点可以包括其它终端设备和/或其它网络设备。
在第二方面的一种可能的实现方式中，在该网络设备发送第一信息之前，该方法还包括：该网络设备发送参考信号RS；该网络设备接收该RS对应的测量结果；该网络设备基于该RS对应的测量结果生成该第一信息。
基于上述技术方案，网络设备发送第一信息之前，可以发送RS并接收该RS对应的测量结果，以便于网络设备可以将该RS的测量结果作为该网络设备发送第一信息的依据。其中，该RS的测量结果可以反映出终端设备与网络设备之间的信道信息，从而，网络设备可 以基于该RS的测量结果对该终端设备所执行的算力实例(和/或该终端设备所执行的算力实例对应的算力资源)进行动态调整。
在第二方面的一种可能的实现方式中，在该网络设备发送第一信息之前，该方法还包括：该网络设备接收来自该终端设备的第一指示信息，该第一指示信息用于指示该终端设备的算力状态；该网络设备基于该第一指示信息确定该第一信息。
基于上述技术方案，网络设备在发送第一消息之前，该网络设备接收用于指示该终端设备的算力状态的第一指示信息，以便于网络设备可以将该终端设备的算例状态作为该网络设备发送第一消息的依据。从而，网络设备可以基于该终端设备的算力状态，对该终端设备所执行的算力实例(和/或该终端设备所执行的算力实例对应的算力资源)进行动态调整。
在第二方面的一种可能的实现方式中，在该网络设备发送第一信息之前，该方法还包括：该网络设备接收来自该终端设备的第二指示信息，该第二指示信息用于指示该终端设备期望的算力资源信息和/或算力实例；该网络设备基于该第二指示信息确定该第一信息。
基于上述技术方案，网络设备在发送第一消息之前，该网络设备接收用于指示该终端设备期望的算力资源信息和/或算力实例的第二指示信息，以便于网络设备可以将该终端设备期望的算力资源信息和/或算力实例作为该网络设备发送第一消息的依据。从而，网络设备可以基于该终端设备期望的算力资源信息和/或算力实例，对该终端设备所执行的算力实例(和/或该终端设备所执行的算力实例对应的算力资源)进行动态调整，以期所提供的配置信息能够满足该终端设备的需求。
在第二方面的一种可能的实现方式中，在该网络设备发送第一信息之后，该方法还包括：该网络设备接收来自该终端设备的第三指示信息，该第三指示信息用于指示该终端设备的算力调整信息；该网络设备基于该第三指示信息发送第三配置信息，该第三配置信息用于更新该第一配置信息和/或该第三配置信息用于更新该第二配置信息。
基于上述技术方案，网络设备还可以接收用于指示该终端设备的算力调整信息的第三指示信息，以便于网络设备可以将该终端设备的算力调整信息作为该网络设备发送更新后的配置(即用于更新第一配置信息和/或用于更新第二配置信息的第三配置信息)的依据。从而，网络设备可以基于该终端设备的算力调整信息，对该终端设备所执行的算力实例(和/或该终端设备所执行的算力实例对应的算力资源)进行动态调整，以期所提供的配置信息能够满足该终端设备的算力调整需求。
在第一方面或第二方面的一种可能的实现方式中，该至少一个算力实例中的算力实例包括以下至少一项：执行时长信息、算力大小信息、模型信息、拆分学习位置、推理切分点位置或联邦学习本地迭代次数。
在第一方面或第二方面的一种可能的实现方式中，该至少一个算力资源信息包括以下至少一项：
中央处理器(central processor unit，CPU)类型信息、存储信息、执行时长信息、内存信息或电量信息。
在第一方面或第二方面的一种可能的实现方式中，该至少一个算力资源关联于该至少 一个算力实例包括：
该至少一个算力资源中的每一个算力资源与该至少一个算力实例中的每一个算力实例一一对应；
或，
该至少一个算力资源中的其中一个算力资源对应于该至少一个算力实例中的一个或多个算力实例。
可选地，至少一个算力资源对应的算力资源大于或等于该至少一个算力实例所需算力资源的最大值。
基于上述技术方案，第二配置信息所配置的至少一个算力资源关联于第一配置信息所配置的至少一个算例实例，其中，该至少一个算力资源中的算力资源与该至少一个算例实例中的算力实例可以是一一对应的关系，也可以是一对一或一对多的关系，以提升网络设备在对算例实例和算力资源进行配置的过程的灵活性。
此外，在该至少一个算力资源中的其中一个算力资源对应于该至少一个算力实例中的多个算力实例时，即在至少一个算力资源中的算力资源与该至少一个算例实例中的算力实例为一对多的关系的情况下，由于终端设备可以该算力资源执行多个不同的算力实例，使得终端设备在执行算例示例的切换过程中，无需确定(或重新配置、准备、激活等)新的算力资源，使得该终端设备可以快速地切换该算力资源对应的多个不同的算例示例。
在第一方面或第二方面的一种可能的实现方式中，该第一指示信息包括以下至少一项：
CPU类型信息、存储信息、内存信息、电量信息、算力利用率信息。
在第一方面或第二方面的一种可能的实现方式中，该第三指示信息包括：
内存信息、电量信息、算力利用率信息。
本申请第三方面提供了一种通信方法，该方法由终端设备执行，或者，该方法由终端设备中的部分组件(例如处理器、芯片或芯片系统等)执行，或者该方法还可以由能实现全部或部分终端设备功能的逻辑模块或软件实现。在第三方面及其可能的实现方式中，以该通信方法由终端设备执行为例进行描述。在该方法中，终端设备向网络设备发送算力指示信息；该终端设备接收来自该网络设备的第一消息，该第一消息包括第一配置信息，其中，该第一配置信息用于配置至少一个算力实例。
基于上述技术方案，终端设备在发送算力指示信息之后，使得网络设备基于该算力指示信息生成并发送包含有第一配置信息的第一消息，该第一配置信息用于配置至少一个算例实例，使得终端设备接收该第一配置信息。换言之，终端设备在发送用于指示该终端设备的算力相关的信息之后，使得网络设备基于该信息对该终端设备所执行的算力实例进行配置。从而，终端设备和网络设备所在的无线网络系统可以成为通信连接与计算双基础设施，通过网络设备基于该第一配置信息对终端设备的算力进行配置的方式，使得终端设备作为计算节点参与算例示例对应的计算过程，可有效提升计算资源的复用程度，以提升网络收益。
在一些实现方式中，该第一算力示例可以为网络设备与一个或多个终端设备协同计算 的算力实例，使得该终端设备基于该第一配置信息执行算力实例的情况下，能够共享网络设备侧的计算资源，以解决终端设备计算资源不足的问题。
在一些实现方式中，该第一算力示例可以为终端设备与其它计算节点协同计算的算力实例，使得该终端设备基于该第一配置信息执行算力实例的情况下，能够共享该终端设备侧的计算资源，以使得该终端设备的计算资源得以共享，提升计算资源的复用程度。
可选地，其它计算节点可以包括其它终端设备和/或其它网络设备。
在第三方面的一种可能的实现方式中，在终端设备向网络设备发送算力指示信息之前，该方法还包括：该终端设备接收来自该网络设备的第二消息，该第二消息包括初始配置信息，其中，该初始配置信息用于配置至少一个算力实例。
基于上述技术方案，在终端设备向网络设备发送算力指示信息之前，该终端设备还可以接收包含有初始配置信息的第二消息，该初始配置信息用于配置至少一个算力实例。此后，该终端设备在确定需要对该初始配置信息进行更新(例如，该终端设备的CPU类型信息、存储信息、内存信息、电量信息和/或算力利用率信息的取值低于阈值或高于阈值)时，该终端设备可以向网络设备发送算力指示信息，以使得网络设备下发更新后的配置信息，即第一配置信息。此后，该终端设备可以基于该第一配置信息对初始配置信息进行更新，以得到适配于该终端设备的算力配置信息。
在第三方面的一种可能的实现方式中，该方法还包括：该终端设备发送该第一消息的响应消息或确认消息。
基于上述技术方案，该终端设备在接收该第一消息之后，该终端设备还可以发送该第一消息的响应消息或确认消息，以使得网络设备基于该第一消息的响应消息或确认消息明确该终端设备已接收该第一消息，并将以该第一消息所包含的第一配置信息配置该至少一个算例示例。
本申请第四方面提供了一种通信方法，该方法由网络设备执行，或者，该方法由网络设备中的部分组件(例如处理器、芯片或芯片系统等)执行，或者该方法还可以由能实现全部或部分网络设备功能的逻辑模块或软件实现。在第三方面及其可能的实现方式中，以该通信方法由网络设备执行为例进行描述。在该方法中，网络设备接收来自终端设备的算力指示信息；该网络设备基于该算力指示信息向该终端设备发送第一消息，该第一消息包括第一配置信息，其中，该第一配置信息用于配置至少一个算力实例。
基于上述技术方案，网络设备在接收算力指示信息之后，该网络设备基于该算力指示信息生成并发送包含有第一配置信息的第一消息，该第一配置信息用于配置至少一个算例实例，使得终端设备接收该第一配置信息。换言之，网络设备在接收用于指示该终端设备的算力相关的信息之后，该网络设备基于该信息对该终端设备所执行的算力实例进行配置。从而，终端设备和网络设备所在的无线网络系统可以成为通信连接与计算双基础设施，通过网络设备基于该第一配置信息对终端设备的算力进行配置的方式，使得终端设备作为计算节点参与算例示例对应的计算过程，可有效提升计算资源的复用程度，以提升网络收益。
在第四方面的一种可能的实现方式中，在网络设备接收来自终端设备的算力指示信息之前，该方法还包括：该网络设备向该终端设备发送第二消息，该第二消息包括初始配置 信息，其中，该初始配置信息用于配置至少一个算力实例。
基于上述技术方案，在网络设备接收算力指示信息之前，该网络设备还可以发送包含有初始配置信息的第二消息，该初始配置信息用于配置至少一个算力实例。此后，使得该终端设备在确定需要对该初始配置信息进行更新(例如，该终端设备的CPU类型信息、存储信息、内存信息、电量信息和/或算力利用率信息的取值低于阈值或高于阈值)时，该终端设备可以向网络设备发送算力指示信息，以使得网络设备下发更新后的配置信息，即第一配置信息。此后，该终端设备可以基于该第一配置信息对初始配置信息进行更新，以得到适配于该终端设备的算力配置信息。
在第四方面的一种可能的实现方式中，该方法还包括：该网络设备接收来自该终端设备的该第一消息的响应消息或确认消息。
基于上述技术方案，该网络设备在发送该第一消息之后，该网络设备还可以接收该第一消息的响应消息或确认消息，以使得网络设备基于该第一消息的响应消息或确认消息明确该终端设备已接收该第一消息，并将以该第一消息所包含的第一配置信息配置该至少一个算例示例。
在第三方面或第四方面的一种可能的实现方式中，该算力指示信息包括第一指示信息，该第一指示信息用于指示该终端设备的算力状态。
基于上述技术方案，终端设备所发送的算力指示信息包括用于指示该终端设备的算力状态的第一指示信息。换言之，终端设备在接收第一消息之前，该终端设备可以向该网络设备发送用于指示该终端设备的算力状态的第一指示信息，以便于网络设备可以将该终端设备的算例状态作为该网络设备发送第一消息的依据。从而，网络设备可以基于该终端设备的算力状态，对该终端设备所执行的算力实例(和/或该终端设备所执行的算力实例对应的算力资源)进行动态调整。
在第三方面或第四方面的一种可能的实现方式中，该第一指示信息包括以下至少一项：
CPU类型信息、存储信息、内存信息、电量信息、算力利用率信息。
在第三方面或第四方面的一种可能的实现方式中，该算力指示信息包括第二指示信息，该第二指示信息用于指示该终端设备期望的算力资源信息和/或算力实例。
基于上述技术方案，终端设备所发送的算力指示信息包括用于指示该终端设备期望的算力资源信息和/或算力实例的第二指示信息。换言之，终端设备在接收第一消息之前，该终端设备可以向该网络设备发送用于指示该终端设备期望的算力资源信息和/或算力实例的第二指示信息，以便于网络设备可以将该终端设备期望的算力资源信息和/或算力实例作为该网络设备发送第一消息的依据。从而，网络设备可以基于该终端设备期望的算力资源信息和/或算力实例，对该终端设备所执行的算力实例(和/或该终端设备所执行的算力实例对应的算力资源)进行动态调整，以期所提供的配置信息能够满足该终端设备的需求。
在第三方面或第四方面的一种可能的实现方式中，该算力指示信息包括第三指示信息，该第三指示信息用于指示该终端设备的算力调整信息。
基于上述技术方案，终端设备所发送的算力指示信息包括用于指示该终端设备的算力调整信息的第三指示信息。换言之，终端设备在接收第一消息之前，该终端设备可以向该 网络设备发送用于指示该终端设备的算力调整信息的第二指示信息，以便于网络设备可以将该终端设备的算力调整信息作为该网络设备发送第一消息的依据。从而，网络设备可以基于该终端设备的算力调整信息，对该终端设备所执行的算力实例(和/或该终端设备所执行的算力实例对应的算力资源)进行动态调整，以期所提供的配置信息能够满足该终端设备的算力调整需求。
在第三方面或第四方面的一种可能的实现方式中，该第三指示信息包括：
内存信息、电量信息、算力利用率信息。
在第三方面或第四方面的一种可能的实现方式中，该第一消息还包括第二配置信息，其中，该第二配置信息用于配置至少一个算力资源信息，该至少一个算力资源信息关联于该至少一个算力实例。
在第三方面或第四方面的一种可能的实现方式中，该至少一个算力资源关联于该至少一个算力实例包括：
该至少一个算力资源中的每一个算力资源与该至少一个算力实例中的每一个算力实例一一对应；
或，
该至少一个算力资源中的其中一个算力资源对应于该至少一个算力实例中的一个或多个算力实例。
可选地，至少一个算力资源对应的算力资源大于或等于该至少一个算力实例所需算力资源的最大值。
基于上述技术方案，第二配置信息所配置的至少一个算力资源关联于第一配置信息所配置的至少一个算例实例，其中，该至少一个算力资源中的算力资源与该至少一个算例实例中的算力实例可以是一一对应的关系，也可以是一对一或一对多的关系，以提升网络设备在对算例实例和算力资源进行配置的过程的灵活性。此外，在网络设备基于第一信息对第一算力实例进行指示的情况下，也可以提升该网络设备在对第一算例实例和/或第一算力实例对应的算力资源进行指示的过程的灵活性。
此外，在该至少一个算力资源中的其中一个算力资源对应于该至少一个算力实例中的多个算力实例时，即在至少一个算力资源中的算力资源与该至少一个算例实例中的算力实例为一对多的关系的情况下，由于终端设备可以该算力资源执行多个不同的算力实例，使得终端设备在执行算例示例的切换过程中，无需确定(或重新配置、准备、激活等)新的算力资源，使得该终端设备可以快速地切换该算力资源对应的多个不同的算例示例。
在第三方面或第四方面的一种可能的实现方式中，该至少一个算力资源信息包括以下至少一项：
CPU类型信息、存储信息、执行时长信息、内存信息或电量信息。
在第三方面或第四方面的一种可能的实现方式中，该至少一个算力实例中的算力实例包括以下至少一项：
执行时长信息、算力大小信息、模型信息、拆分学习位置、推理切分点位置或联邦学习本地迭代次数。
本申请第五方面提供了一种通信装置，该装置可以实现上述第一方面或第一方面任一种可能的实现方式中的方法。该装置包括用于执行上述方法的相应的单元或模块。该装置包括的单元或模块可以通过软件和/或硬件方式实现。例如，该装置可以为终端设备，或者，该装置可以为终端设备中的组件(例如处理器、芯片或芯片系统等)，或者该装置还可以为能实现全部或部分终端设备功能的逻辑模块或软件。
该装置包括收发单元和处理单元；
该收发单元，用于接收来自网络设备的第一消息，该第一消息包括第一配置信息，其中，该第一配置信息包括至少一个算力实例的配置信息；
该处理单元，用于获取第一信息，该第一信息用于指示第一算力实例，该第一算力实例为该至少一个算力实例中的算力实例；
该处理单元，还用于基于该第一信息执行该第一算力实例。
在第五方面的一种可能的实现方式中，该第一消息还包括第二配置信息，其中，该第二配置信息包括至少一个算力资源的配置信息，该至少一个算力资源关联于该至少一个算力实例。
在第五方面的一种可能的实现方式中，该第一信息包括该第一算力实例的标识和/或该第一算力实例对应的算力资源信息的标识；
该处理单元，用于该第一信息包括：
该处理单元，用于控制该收发单元接收该第一信息，该第一信息承载于L1控制信息或L2控制信息或L3消息中。
在第五方面的一种可能的实现方式中，
该收发单元，还用于接收参考信号RS；
该收发单元，还用于发送该RS对应的测量结果。
在第五方面的一种可能的实现方式中，
该第一算力实例为默认算力实例；和/或，
该第一算力实例对应的算力资源信息为默认算力资源信息。
在第五方面的一种可能的实现方式中，该处理单元，用于获取该第一信息包括：
在满足以下至少一项时，该处理单元，用于生成该第一信息，包括：
第一定时器超时，其中，该第一定时器的配置信息包含于该第一消息；或，
该终端设备的电量低于第一阈值；或，
该终端设备进入无线资源控制空闲RRC idle态。
在第五方面的一种可能的实现方式中，
该收发单元，还用于向网络设备发送第一指示信息，该第一指示信息用于指示该终端设备的算力状态。
在第五方面的一种可能的实现方式中，
该收发单元，还用于向该网络设备发送第二指示信息，该第二指示信息用于指示该终端设备期望的算力资源信息和/或算力实例。
在第五方面的一种可能的实现方式中，
该处理单元在基于该第一信息执行该第一算力实例时，该收发单元，还用于发送第三指示信息，该第三指示信息用于指示该终端设备的算力调整信息；
该收发单元，还用于接收来自该网络设备的第三配置信息，该第三配置信息用于更新该第一配置信息和/或该第三配置信息用于更新该第二配置信息。
需要说明的是，本申请第五方面提供的通信装置的实现过程可以参考实现前述第一方面所描述的实现过程，并实现相应的技术效果，此处不做赘述。
本申请第六方面提供了一种通信装置，该装置可以实现上述第二方面或第二方面任一种可能的实现方式中的方法。该装置包括用于执行上述方法的相应的单元或模块。该装置包括的单元或模块可以通过软件和/或硬件方式实现。例如，该装置可以为网络设备，或者，该装置可以为网络设备中的组件(例如处理器、芯片或芯片系统等)，或者该装置还可以为能实现全部或部分网络设备功能的逻辑模块或软件。
该装置包括收发单元和处理单元；
该处理单元，用于生成第一消息，该第一消息包括第一配置信息，其中，该第一配置信息包括至少一个算力实例的配置信息；
该收发单元，用于发送该第一消息。
在第六方面的一种可能的实现方式中，该第一消息还包括第二配置信息，其中，该第二配置信息包括至少一个算力资源的配置信息，该至少一个算力资源关联于该至少一个算力实例。
在第六方面的一种可能的实现方式中，
该收发单元，还用于发送第一信息，该第一信息用于指示第一算力实例，该第一算力实例为该至少一个算力实例中的算力实例，该第一信息包括该第一算力实例的标识和/或该第一算力实例对应的算力资源信息的标识；
其中，该第一信息承载于L1控制信息或L2控制信息或L3消息中。
在第六方面的一种可能的实现方式中，
该收发单元，还用于发送参考信号RS；
该收发单元，还用于接收该RS对应的测量结果；
该处理单元，还用于基于该RS对应的测量结果生成该第一信息。
在第六方面的一种可能的实现方式中，
该收发单元，还用于接收来自该终端设备的第一指示信息，该第一指示信息用于指示该终端设备的算力状态；
该处理单元，还用于基于该第一指示信息确定该第一信息。
在第六方面的一种可能的实现方式中，
该收发单元，还用于接收来自该终端设备的第二指示信息，该第二指示信息用于指示该终端设备期望的算力资源信息和/或算力实例；
该处理单元，还用于基于该第二指示信息确定该第一信息。
在第六方面的一种可能的实现方式中，
该收发单元，还用于接收来自该终端设备的第三指示信息，该第三指示信息用于指示该终端设备的算力调整信息；
该处理单元，还用于基于该第三指示信息发送第三配置信息，该第三配置信息用于更新该第一配置信息和/或该第三配置信息用于更新该第二配置信息。
在第五方面或第六方面的一种可能的实现方式中，该至少一个算力实例中的算力实例包括以下至少一项：
执行时长信息、算力大小信息、模型信息、拆分学习位置、推理切分点位置或联邦学习本地迭代次数。
在第五方面或第六方面的一种可能的实现方式中，该至少一个算力资源信息包括以下至少一项：
CPU类型信息、存储信息、执行时长信息、内存信息或电量信息。
在第五方面或第六方面的一种可能的实现方式中，该至少一个算力资源关联于该至少一个算力实例包括：
该至少一个算力资源中的每一个算力资源与该至少一个算力实例中的每一个算力实例一一对应；
或，
该至少一个算力资源中的其中一个算力资源对应于该至少一个算力实例中的一个或多个算力实例。
可选地，至少一个算力资源对应的算力资源大于或等于该至少一个算力实例所需算力资源的最大值。
在第五方面或第六方面的一种可能的实现方式中，该第一指示信息包括以下至少一项：
CPU类型信息、存储信息、内存信息、电量信息、算力利用率信息。
在第五方面或第六方面的一种可能的实现方式中，该第三指示信息包括：
内存信息、电量信息、算力利用率信息。
需要说明的是，本申请第六方面提供的通信装置的实现过程可以参考实现前述第二方面所描述的实现过程，并实现相应的技术效果，此处不做赘述。
本申请第七方面提供了一种通信装置，该装置可以实现上述第三方面或第三方面任一种可能的实现方式中的方法。该装置包括用于执行上述方法的相应的单元或模块。该装置包括的单元或模块可以通过软件和/或硬件方式实现。例如，该装置可以为终端设备，或者，该装置可以为终端设备中的组件(例如处理器、芯片或芯片系统等)，或者该装置还可以为能实现全部或部分终端设备功能的逻辑模块或软件。
该装置包括收发单元和处理单元；
该处理单元，用于确定算力指示信息；
该收发单元，用于向网络设备发送算力指示信息；
该收发单元，还用于接收来自该网络设备的第一消息，该第一消息包括第一配置信息， 其中，该第一配置信息用于配置至少一个算力实例。
在第七方面的一种可能的实现方式中，
该收发单元，还用于接收来自该网络设备的第二消息，该第二消息包括初始配置信息，其中，该初始配置信息用于配置至少一个算力实例。
在第七方面的一种可能的实现方式中，
该收发单元，还用于发送该第一消息的响应消息或确认消息。
需要说明的是，本申请第七方面提供的通信装置的实现过程可以参考实现前述第三方面所描述的实现过程，并实现相应的技术效果，此处不做赘述。
本申请第八方面提供了一种通信装置，该装置可以实现上述第四方面或第四方面任一种可能的实现方式中的方法。该装置包括用于执行上述方法的相应的单元或模块。该装置包括的单元或模块可以通过软件和/或硬件方式实现。例如，该装置可以为网络设备，或者，该装置可以为网络设备中的组件(例如处理器、芯片或芯片系统等)，或者该装置还可以为能实现全部或部分网络设备功能的逻辑模块或软件。
该装置包括收发单元和处理单元；
该收发单元，用于接收来自终端设备的算力指示信息；
该处理单元，用于基于该算力指示信息向该终端设备确定第一消息，该第一消息包括第一配置信息，其中，该第一配置信息用于配置至少一个算力实例；
该收发单元，还用于发送该第一消息。
在第八方面的一种可能的实现方式中，
该收发单元，还用于向该终端设备发送第二消息，该第二消息包括初始配置信息，其中，该初始配置信息用于配置至少一个算力实例。
在第八方面的一种可能的实现方式中，
该收发单元，还用于接收来自该终端设备的该第一消息的响应消息或确认消息。
在第七方面或第八方面的一种可能的实现方式中，该算力指示信息包括第一指示信息，该第一指示信息用于指示该终端设备的算力状态。
在第七方面或第八方面的一种可能的实现方式中，该第一指示信息包括以下至少一项：
CPU类型信息、存储信息、内存信息、电量信息、算力利用率信息。
在第七方面或第八方面的一种可能的实现方式中，该算力指示信息包括第二指示信息，该第二指示信息用于指示该终端设备期望的算力资源信息和/或算力实例。
在第七方面或第八方面的一种可能的实现方式中，该算力指示信息包括第三指示信息，该第三指示信息用于指示该终端设备的算力调整信息。
在第七方面或第八方面的一种可能的实现方式中，该第三指示信息包括：
内存信息、电量信息、算力利用率信息。
在第七方面或第八方面的一种可能的实现方式中，该第一消息还包括第二配置信息，其中，该第二配置信息用于配置至少一个算力资源信息，该至少一个算力资源信息关联于该至少一个算力实例。
在第七方面或第八方面的一种可能的实现方式中，该至少一个算力资源关联于该至少 一个算力实例包括：
该至少一个算力资源中的每一个算力资源与该至少一个算力实例中的每一个算力实例一一对应；
或，
该至少一个算力资源中的其中一个算力资源对应于该至少一个算力实例中的一个或多个算力实例。
在第七方面或第八方面的一种可能的实现方式中，该至少一个算力资源信息包括以下至少一项：
CPU类型信息、存储信息、执行时长信息、内存信息或电量信息。
在第七方面或第八方面的一种可能的实现方式中，该至少一个算力实例中的算力实例包括以下至少一项：
执行时长信息、算力大小信息、模型信息、拆分学习位置、推理切分点位置或联邦学习本地迭代次数。
需要说明的是，本申请第八方面提供的通信装置的实现过程可以参考实现前述第四方面所描述的实现过程，并实现相应的技术效果，此处不做赘述。
本申请实施例第九方面提供了一种通信装置，包括至少一个处理器，该至少一个处理器与存储器耦合；该存储器用于存储程序或指令；该至少一个处理器用于执行该程序或指令，以使该装置实现前述第一方面或第一方面任意一种可能的实现方式所述的方法，或，以使该装置实现前述第二方面或第二方面任意一种可能的实现方式所述的方法，或，以使该装置实现前述第三方面或第三方面任意一种可能的实现方式所述的方法，或，以使该装置实现前述第四方面或第四方面任意一种可能的实现方式所述的方法。
本申请实施例第十方面提供一种存储一个或多个计算机执行指令的计算机可读存储介质，当计算机执行指令被处理器执行时，该处理器执行如上述第一方面或第一方面任意一种可能的实现方式所述的方法，或，该处理器执行如上述第二方面或第二方面任意一种可能的实现方式所述的方法，或，该处理器执行如上述第三方面或第三方面任意一种可能的实现方式所述的方法，或，该处理器执行如上述第四方面或第四方面任意一种可能的实现方式所述的方法。
本申请实施例第十一方面提供一种存储一个或多个计算机的计算机程序产品(或称计算机程序)，当计算机程序产品被该处理器执行时，该处理器执行如上述第一方面或第一方面任意一种可能实现方式的方法，或，该处理器执行如上述第二方面或第二方面任意一种可能的实现方式所述的方法，或，该处理器执行如上述第三方面或第三方面任意一种可能的实现方式所述的方法，或，该处理器执行如上述第四方面或第四方面任意一种可能的实现方式所述的方法。
本申请实施例第十二方面提供了一种芯片系统，该芯片系统包括至少一个处理器，用于支持通信装置实现上述第一方面或第一方面任意一种可能的实现方式中所涉及的功能，或，用于支持通信装置实现上述第二方面或第二方面任意一种可能的实现方式中所涉及的功能，或，用于支持通信装置实现上述第三方面或第三方面任意一种可能的实现方式中所 涉及的功能，或，用于支持通信装置实现上述第四方面或第四方面任意一种可能的实现方式中所涉及的功能。
在一种可能的设计中，该芯片系统还可以包括存储器，用于保存该通信装置必要的程序指令和数据。该芯片系统，可以由芯片构成，也可以包含芯片和其他分立器件。可选的，该芯片系统还包括接口电路，该接口电路为该至少一个处理器提供程序指令和/或数据。
本申请实施例第十三方面提供了一种通信系统，该通信系统包括上述第五方面和第六方面所涉及的通信装置，和/或，该通信系统包括上述第七方面和第八方面所涉及的通信装置，和/或，该通信系统包括上述第九方面的通信装置。
其中，第五方面至第十二方面中任一种设计方式所带来的技术效果可参见上述第一方面至第四方面中不同实现方式所带来的技术效果，在此不再赘述。
从以上技术方案可以看出，终端设备接收来自网络设备的包含有第一配置信息的第一消息，其中，该第一配置信息包括至少一个算力实例的配置信息。该终端设备在获取用于指示该至少一个算力实例中的第一算力实例的第一信息之后，该终端设备基于该第一信息执行该第一算力实例。换言之，终端设备基于网络设备的指示对算力实例进行配置之后，该终端设备基于第一信息执行相应的算力实例。从而，终端设备和网络设备所在的无线网络系统可以成为通信连接与计算双基础设施，通过网络设备基于该第一配置信息对终端设备的算力进行配置的方式，使得终端设备作为计算节点参与算例示例对应的计算过程，可有效提升计算资源的复用程度，以提升网络收益。
附图说明
图1为本申请提供的通信系统的一个示意图；
图2a为本申请中涉及算力的网络架构的一个示意图；
图2b为本申请中涉及算力的网络架构的另一个示意图；
图3a为本申请提供的通信协议栈交互的一个示意图；
图3b为本申请提供的通信系统的一个示意图；
图4为本申请提供的通信方法的一个示意图；
图5a为本申请提供的通信方法的另一个示意图；
图5b为本申请提供的通信方法的另一个示意图；
图6a为本申请提供的通信方法的另一个示意图；
图6b为本申请提供的通信方法的另一个示意图；
图6c为本申请提供的通信方法的另一个示意图；
图7为本申请提供的通信方法的另一个示意图；
图8为本申请提供的通信方法的另一个示意图；
图9为本申请提供的通信装置的一个示意图；
图10为本申请提供的通信装置的另一个示意图；
图11为本申请提供的通信装置的另一个示意图；
图12为本申请提供的通信装置的另一个示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行描述。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
首先，对本申请实施例中的部分用语进行解释说明，以便于本领域技术人员理解。
(1)终端设备：可以是能够接收网络设备调度和指示信息的无线终端设备，无线终端设备可以是指向用户提供语音和/或数据连通性的设备，或具有无线连接功能的手持式设备，或连接到无线调制解调器的其他处理设备。
终端设备可以经无线接入网(radio access network，RAN)与一个或多个核心网或者互联网进行通信，终端设备可以是移动终端设备，如移动电话(或称为“蜂窝”电话，手机(mobile phone))、计算机和数据卡，例如，可以是便携式、袖珍式、手持式、计算机内置的或者车载的移动装置，它们与无线接入网交换语音和/或数据。例如，个人通信业务(personal communication service，PCS)电话、无绳电话、会话发起协议(SIP)话机、无线本地环路(wireless local loop，WLL)站、个人数字助理(personal digital assistant，PDA)、平板电脑(Pad)、带无线收发功能的电脑等设备。无线终端设备也可以称为系统、订户单元(subscriber unit)、订户站(subscriber station)，移动站(mobile station)、移动台(mobile station，MS)、远程站(remote station)、接入点(access point，AP)、远程终端设备(remote terminal)、接入终端设备(access terminal)、用户终端设备(user terminal)、用户代理(user agent)、用户站(subscriber station，SS)、用户端设备(customer premises equipment，CPE)、终端(terminal)、用户设备(user equipment，UE)、移动终端(mobile terminal，MT)等。
作为示例而非限定，在本申请实施例中，该终端设备还可以是可穿戴设备。可穿戴设备也可以称为穿戴式智能设备或智能穿戴式设备等，是应用穿戴式技术对日常穿戴进行智能化设计、开发出可以穿戴的设备的总称，如眼镜、手套、手表、服饰及鞋等。可穿戴设备即直接穿在身上，或是整合到用户的衣服或配件的一种便携式设备。可穿戴设备不仅仅是一种硬件设备，更是通过软件支持以及数据交互、云端交互来实现强大的功能。广义穿戴式智能设备包括功能全、尺寸大、可不依赖智能手机实现完整或者部分的功能，例如：智能手表或智能眼镜等，以及只专注于某一类应用功能，需要和其它设备如智能手机配合使用，如各类进行体征监测的智能手环、智能头盔、智能首饰等。
此外，终端设备也可以是未来通信系统(例如第六代(6th generation，6G)通信系统等)中的终端设备或者未来演进的公共陆地移动网络(public land mobile network，PLMN)中的终端设备等。示例性的，6G网络可以进一步扩展第五代(5th generation，5G)通信终端的形态和功能，6G终端包括但不限于车、蜂窝网络终端(融合卫星终端功能)、无人机、IoT。
(2)网络设备：可以是无线网络中的设备，例如网络设备可以为将终端设备接入到无线网络的RAN节点(或设备)，又可以称为基站。目前，一些RAN设备的举例为：5G通信系统中的基站gNB(gNodeB)、传输接收点(transmission reception point，TRP)、演 进型节点B(evolved Node B，eNB)、无线网络控制器(radio network controller，RNC)、节点B(Node B，NB)、家庭基站(例如，home evolved Node B，或home Node B，HNB)、基带单元(base band unit，BBU)，或无线保真(wireless fidelity，Wi-Fi)接入点AP等。另外，在一种网络结构中，网络设备可以包括集中单元(centralized unit，CU)节点、或分布单元(distributed unit，DU)节点、或包括CU节点和DU节点的RAN设备。
其中，网络设备能够向终端设备发送配置信息(例如承载于调度消息和/或指示消息中)，终端设备进一步根据该配置信息进行网络配置，使得网络设备与终端设备之间的网络配置对齐；或者，通过预设于网络设备的网络配置以及预设于终端设备的网络配置，使得网络设备与终端设备之间的网络配置对齐。具体来说，“对齐”是指网络设备与终端设备之间存在交互消息时，两者对于交互消息收发的载波频率、交互消息类型的确定、交互消息中所承载的字段信息的含义、或者是交互消息的其它配置的理解一致。
此外，在其它可能的情况下，网络设备可以是其它为终端设备提供无线通信功能的装置。本申请的实施例对网络设备所采用的具体技术和具体设备形态不做限定。为方便描述，本申请实施例并不限定。
网络设备还可以包括核心网设备，核心网设备例如包括第四代(4th generation，4G)网络中的移动性管理实体(mobility management entity，MME)，归属用户服务器(home subscriber server，HSS)，服务网关(serving gateway，S-GW)，策略和计费规则功能(policy and charging rules function，PCRF)，公共数据网网关(public data network gateway，PDN gateway，P-GW)；5G网络中的访问和移动管理功能(access and mobility management function，AMF)、用户面功能(user plane function，UPF)或会话管理功能(session management function，SMF)等网元。此外，该核心网设备还可以包括5G网络以及5G网络的下一代网络中的其他核心网设备。
本申请实施例中，用于实现网络设备的功能的装置可以是网络设备，也可以是能够支持网络设备实现该功能的装置，例如芯片系统，该装置可以被安装在网络设备中。在本申请实施例提供的技术方案中，以用于实现网络设备的功能的装置是网络设备为例，描述本申请实施例提供的技术方案。
(3)配置与预配置：在本申请中，会同时用到配置与预配置。其中，配置是指基站/服务器通过消息或信令将一些参数的配置信息或参数的取值发送给终端，以便终端根据这些取值或信息来确定通信的参数或传输时的资源。预配置与配置类似，可以是基站/服务器预先与终端设备协商好的参数信息或参数值，也可以是标准协议规定的基站/服务器或终端设备采用的参数信息或参数值，还可以是预先存储在基站/服务器或终端设备的参数信息或参数值。本申请对此不做限定。
进一步地，这些取值和参数，是可以变化或更新的。
(4)本申请实施例中的术语“系统”和“网络”可被互换使用。“多个”是指两个或两个以上。“和/或”，描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A、同时存在A和B、单独存在B的情况，其中A，B可以是单数或者复数。字符“/”一般表示前后关联对象是一种“或”的关系。“以下至少一项(个)”或 其类似表达，是指的这些项中的任意组合，包括单项(个)或复数项(个)的任意组合。例如“A，B和C中的至少一项”包括A，B，C，AB，AC，BC或ABC。以及，除非有特别说明，本申请实施例提及“第一”、“第二”等序数词是用于对多个对象进行区分，不用于限定多个对象的顺序、时序、优先级或者重要程度。
本申请中，除特殊说明外，各个实施例之间相同或相似的部分可以互相参考。在本申请中各个实施例、以及各实施例中的各个实施方式/实施方法/实现方法中，如果没有特殊说明以及逻辑冲突，不同的实施例之间、以及各实施例中的各个实施方式/实施方法/实现方法之间的术语和/或描述具有一致性、且可以相互引用，不同的实施例、以及各实施例中的各个实施方式/实施方法/实现方法中的技术特征根据其内在的逻辑关系可以组合形成新的实施例、实施方式、实施方法、或实现方法。以下所述的本申请实施方式并不构成对本申请保护范围的限定。
本申请可以应用于长期演进(long term evolution，LTE)系统、新无线(new radio，NR)系统，或者是其它的通信系统(例如6G等)，其中，该通信系统中包括网络设备和终端设备，网络设备作为配置信息发送实体，终端设备作为配置信息接收实体。具体来说，该通信系统中存在实体向另一实体发送配置信息，并向另一实体发送数据、或接收另一实体发送的数据；另一个实体接收配置信息，并根据配置信息向配置信息发送实体发送数据、或接收配置信息发送实体发送的数据。
请参阅图1，为本申请中通信系统的一种示意图。图1中，示例性的示出了一个网络设备101和6个终端设备，6个终端设备分别为终端设备1、终端设备2、终端设备3、终端设备4、终端设备5以及终端设备6等。在图1所示的示例中，是以终端设备1为智能茶杯，终端设备2为智能空调，终端设备3为智能加油机，终端设备4为交通工具，终端设备5为手机，终端设备6为打印机进行举例说明的。
如图1所示，配置信息发送实体可以为网络设备。配置信息接收实体可以为终端设备1-终端设备6，此时，网络设备和终端设备1-终端设备6组成一个通信系统，在该通信系统中，终端设备1-终端设备6可以发送上行数据给网络设备，网络设备需要接收终端设备1-终端设备6发送的上行数据。同时，网络设备可以向终端设备1-终端设备6发送配置信息。
示例性的，在图1中，UE4-UE6也可以组成一个通信系统。其中，终端设备5作为网络设备，即配置信息发送实体；终端设备4和终端设备6作为终端设备，即配置信息接收实体。例如车联网系统中，终端设备5分别向终端设备4和终端设备6发送配置信息，并且接收终端设备4和终端设备6发送的上行数据；相应的，终端设备4和终端设备6接收终端设备5发送的配置信息，并向终端设备5发送上行数据。
如图1所示的通信系统是无线通信中的一个典型的应用场景。一般的，无线通信是指两个或两个以上的通信节点间不经由导体或缆线传播而进行的传输通讯，该通信节点一般包括网络设备和终端设备。
目前，在无线通信系统中，通信节点一般具备信号收发能力和计算能力。以具备计算能力的终端设备这一通信节点为例。一方面，终端设备的计算能力需要为信号收发能力提 供算力支持(例如：对承载信号的时域资源、频域资源等进行计算)，以实现终端设备与其它通信节点的通信；另一方面，终端设备的计算能力需要为本地应用的计算提供算力支持(例如：对语言、文字或图像等数据的产生和展示进行计算)，以实现终端设备本地应用的呈现。换言之，当前的通信节点所具备的计算能力，是为了支持不同通信节点之间的通信以及支持该通信节点本地应用的呈现。
然而，在未来的通信网络中，不同通信节点之间除了需要进行通信之外，还可能需要兼顾计算能力，以实现通信系统中的网络内生算力。下面将对通信系统中具备算力的实现进行示例性说明。
一种算力实现中，为欧洲电信标准协会(european telecommunications standards institute，ETSI)于2016年发布了与移动/多接入边缘计算(mobile/multi-access edge computing，MEC)相关标准所涉及的内容。其中，MEC可以看作是一个运行在移动网络边缘的、运行特定任务的云服务器，ETSI定义的MEC是在靠近移动用户的RAN网络中为用户提供基于IT架构和云计算的能力的平台。
示例性的，如图2a所示，为涉及MEC的网元架构的一个示意图，其中，该示意图中将终端设备记为UE为例进行说明。
在图2a中，除了UE之外，其它网元均可以视为网络设备，该网络设备包括：
无线接入网(radio access network，RAN)，接入和移动性管理功能(access and mobility management function，AMF)，用户平面功能(user plane function，UPF)，会话管理功能(session management function，SMF)，策略控制功能(policy control function，PCF)，授权服务器功能(authentication server function，AUSF)，统一数据管理(unified data management，UDM)，网络存储功能(NF repository function，NRF)，网络开放功能(network exposure function，NEF)，数据网络(data network，DN)，应用功能(application function，AF)，移动/多接入边缘计算平台(mobile/multi-access eedge platform，MEP)。
此外，如图2a所示，MEC在网络中，可以包括AF、DN、边缘UPF等网元所涉及的功能。
结合到3GPP定义的5G架构，即TS.23501 5G系统的系统结构(TS.23501 System architecture for the 5G System)标准文档所即在的内容中，MEC在无线网络中实际部署的位置，一般是对应到5G核心网的本地用户平面功能(user plane function，UPF)网元(如图2a中的UPF)。本地UPF基于与本地数据网络(DN)之间的N6接口实现业务的本地卸载和分流，从而实现业务的本地化处理，达到加速的效果。从上面的3GPP 5G系统架构可以看出，MEC在3GPP系统架构中是不可见的网元，不属于3GPP定义的网络架构范围，因此也不会对3GPP系统架构有直接的影响。
下面将以接入网设备为基站作为示例，结合图2b所示方式进一步描述。
可选地，如图2b所示的“MEC/本地UPF与网络汇聚节点合设”的实现方式中，MEC与UPF可以位于接入网设备与核心网设备之间的网络汇聚节点。MEC的应用，是结合3GPP已有的核心网数据本地分流机制，将业务数据的处理位置，从远端的数据网络(一般是公有云)， 下沉到本地的MEC上，这是MEC实现业务加速最本质的原因，即将处理业务数据的应用，尽可能的从物理部署位置上推到无线网络的核心网附近，即于核心网网元UPF共置。
可选地，如图2b所示的“MEC/本地UPF与接入网合设”的实现方式中，UPF设置于基站，MEC外接于该UPF。换言之，MEC可以进一步下沉到基站附近，即与基站共物理节点部署。MEC的部署一定程度上解决了行业对实时性和数据安全的诉求，但从3GPP逻辑架构和数据协议处理流程看，依然存在进一步优化的空间。由于通信网络能力开放给网管平台，分布的外挂算力也呈现在网管平台；因此，人工智能(artificial intelligence，AI)应用等服务署可以综合考虑网络的信息以及分布的算力资源，进行业务的优化部署、调整等。
应理解，图2a和图2b所示示例中所涉及的网元/设备的名称、接口的名称仅仅为示例，基于前述终端设备和网络设备的定义，可以替换为其他描述，此处不做限定。
然而，此类算力上的AI等业务部署是通过管理面实现的，动态性不强，无法实现网络和算力在控制面的统一，无法及时响应用户的移动以及网络的变化；网络连接和业务连接是相对独立的，属于叠加模型，因此在资源的使用上有时无法达到最优。
此外，新型算力网络架构中，各网元可能不仅有控制和转发能力，还可以兼顾计算能力，除网元之外，网络中还部署了计算节点，这种算网一体模式产生的算力称为网络内生算力。在网络设计之初，把算力当作网络的一种基本元素。算力遍布于网络，即算力广泛分布于云、边、端、中间网元，算力融于网络。算力服务、连接服务、以及综合考虑算力和连接的服务，都作为网络对外能提供的基本服务。网络内生算力可以促进内生智能的发展和部署，可以更好地支持无处不在的具有感知、通信和计算能力的基站和终端，实现大规模智能分布式协同服务，同时最大化网络中通信与算力的效用，适配数据的分布性并保护数据的隐私性。在新型网络架构中，网元和计算单元的控制面拉通，可以弥补算力融合类别2中的不足，可以及时的响应移动和网络的变化。网络内生算力可以促进未来智能应用的产生和发展，例如：沉浸式云扩展现实(extended reality，XR)、全息通信、感官互联、智慧交互、通信感知以及数字孪生等。
可选地，XR包括虚拟现实(virtual reality，VR)技术，增强现实(augmented reality，AR)或混合现实(mixed reality，MR)等。
由上述内容可知，在5G MEC方案中，UPF可以与MEC合设；MEC、UPF甚至可以下沉到基站，并与基站合设。换言之，5G也引入了计算能力，但它并没有走得足够远，基本保留了上一代产品的范围和全局架构特征，并将重点放在了计算能力下沉上，网络和计算部分相对是松耦合的设计，意味着并不是架构的原生能力，因此在效率、部署成本、安全和隐私保护等方面存在进一步提升的空间。在5G MEC方案中，核心网用户面网元UPF可以与MEC合设；MEC、UPF甚至可以下沉到基站，与基站合设，但在逻辑架构层面，及控制管理机制上，都还是两套相对独立的系统，从而导致：当算力变化需要调整连接策略或连接管道发生变化需要调整算力时，另一方的调整时延比较大，例如分钟级别的调整时延；计算所需的数据要通过本地(local)UPF路由到MEC进行再计算迁移，计算迁移时计算数据的传输延时大；AI异构资源是分布式、混合多类型的，这和云(Cloud)AI的资源分布以及类型是完全不同的，在管理面拉通进行连接和算力的管理和控制不再适用。因此，在管理面拉通对连接 和算力进行管理难以支撑未来通信网络(例如6G)内生智能、内生感知等需要原生的计算和通信深度耦合的普惠服务。
综上所述，在具备网络设备和终端设备的通信网络中，如何实现算力的配置与执行，是一个亟待解决的技术问题。
为了解决上述问题，本申请实施例提供了一种通信方法及通信装置，用于通过网络设备基于第一配置信息对终端设备的算力进行配置的方式，使得终端设备作为计算节点参与算例示例对应的计算过程，可有效提升计算资源的复用程度，以提升网络收益。下面将结合附图从多个方面对本申请进行描述。
本申请实施例中，通信网络中不同节点(包括网络设备和终端设备)能够在计算资源控制(computing resource control，CRC)这一协议层进行交互的过程中，完成算力的配置与执行。
下面将在图3a和图3b所示实现示例中，以终端设备记为UE，网络设备所包含的接入网设备记为xNB，网络设备还包括计算管理功能(computing management function，CMF)网元，且该CMF网元用于实现CRC协议层所涉及的信息处理过程为例进行说明。
需要说明的是，CMF网元为逻辑功能实现的网元，可以部署在核心网设备，也可以部署在接入网设备，此处不做限定。
应理解，下述示例中所涉及的网元/设备的名称、接口的名称仅仅为示例，基于前述终端设备和网络设备的定义，可以替换为其他描述，此处不做限定。
可选的，如图3a的方式一(Alt1)所示，终端设备和网络设备之间的控制面交互涉及的协议层包括无线资源控制(radio resource control，RRC)协议、分组数据汇聚协议(packet data convergence protocol，PDCP)、无线链路控制(radio link control，RLC)协议、媒体接入控制(media access control，MAC)层协议、物理(physical，PHY)层协议中的一项或多项。本申请新增了CRC协议层，使得UE、基站、CMF都具有CRC协议层，即计算资源控制层。
进一步可选地，如图3b的Alt1所示，为图3a的Alt1对应的网元交互示意图。其中，本申请新增的CMF网元可以分别与UE和RAN连接，并通过包含有UPF和CDF的xPF连接至数据网络(data network，DN)。
可选的，如图3a的方式二(Alt2)所示，终端设备和网络设备之间的控制面交互涉及的协议层包括RRC协议、PDCP、RLC协议、MAC层协议、PHY层协议中的一项或多项。本申请新增了CRC协议层，该CRC协议层可以是RRC层的信元(information element，IE)或RRC容器(container)、非接入层(non-access atratum，NAS)的IE或NAS container容器实现。
进一步可选地，如图3b的Alt2所示，为图3a的Alt2对应的网元交互示意图。其中，本申请新增的CMF网元可以与AMF连接，并连接至数据网络(data network，DN)。
此外，本申请涉及的CMF可以用于实现下述至少一项：
算力管理；或，
计算承载管理；或，
与会话管理功能(Session Management Function，SMF)协作，实现连接联合调整终端通过空口使用基站、核心网的计算服务；或，
任务架构下，CMF是任务锚点(Task Anchor，TA)功能一部分(AI的三要素包括算力、算法、数据，任务架构下统一管理、控制算力、算法、数据、连接，计算管理功能主要管理算力、连接，因此CMF可以看做TA功能的一部分)。
此外，本申请涉及的网络设备具备融合调度(convergence scheduling，CS)新功能，即算力、连接的融合控制与调度，可以用于实现下述至少一项：
对内计算服务的计算数据由基站确定是本地计算还是路由到网内计算节点；或，
算力状态感知与感知结果上报；或，
终端算力异构资源的建立、修改、挂起、恢复、释放；或，
算力控制；或，
计算无线承载管理；或，
任务架构下，CS是任务调度(Task Scheduling，TS)功能的一部分(AI的三要素包括算力、算法、数据，任务架构下统一管理、控制算力、算法、数据、连接，计算管理功能主要管理算力、连接，因此CS可以看做TS功能的一部分)。
下面将通过更多的附图和实施例对本申请进行说明。
请参阅图4，为本申请提供的通信方法的一个示意图，该方法包括如下步骤。
S401.网络设备发送第一消息。
本实施例中，网络设备在步骤S401中发送第一消息，相应的，终端设备在步骤S401中接收该第一消息。其中，第一消息包括第一配置信息，其中，该第一配置信息包括至少一个算力实例的配置信息。
在一种可能的实现方式中，该至少一个算力实例中的算力实例包括以下至少一项：执行时长信息、算力大小信息、模型信息、拆分学习位置、推理切分点位置或联邦学习本地迭代次数。
在一种可能的实现方式中，该第一消息还包括第二配置信息，其中，该第二配置信息包括至少一个算力资源的配置信息，该至少一个算力资源关联于该至少一个算力实例。
可选地，第二配置信息包含于其它消息。换言之，网络设备在步骤S402之前，还需要通过不同于步骤S401的其他过程，向该终端设备发送第二配置信息，使得终端设备接收该第二配置信息。
具体地，终端设备还接收包含有至少一个算力资源的配置信息的第二配置信息，其中，该至少一个算力资源关联于该至少一个算力实例。从而，在对终端设备的算力进行配置使得终端设备作为计算节点参与算例示例对应的计算过程的同时，使得终端设备基于该第二配置信息明确，后续在执行至少一个算例示例中的算力实例的过程中所使用的算力资源。
可选地，该至少一个算力资源信息包括以下至少一项：
中央处理器(central processor unit，CPU)类型信息、存储信息、执行时长信息、内存信息或电量信息。
在一种可能的实现方式中，该至少一个算力资源关联于该至少一个算力实例包括：
该至少一个算力资源中的每一个算力资源与该至少一个算力实例中的每一个算力实例一一对应；
或，
该至少一个算力资源中的其中一个算力资源对应于该至少一个算力实例中的一个或多个算力实例。
可选地，至少一个算力资源对应的算力资源大于或等于该至少一个算力实例所需算力资源的最大值。
具体地，第二配置信息所配置的至少一个算力资源关联于第一配置信息所配置的至少一个算例实例，其中，该至少一个算力资源中的算力资源与该至少一个算例实例中的算力实例可以是一一对应的关系，也可以是一对一或一对多的关系，以提升网络设备在对算例实例和算力资源进行配置的过程的灵活性。
此外，在该至少一个算力资源中的其中一个算力资源对应于该至少一个算力实例中的多个算力实例时，即在至少一个算力资源中的算力资源与该至少一个算例实例中的算力实例为一对多的关系的情况下，由于终端设备可以该算力资源执行多个不同的算力实例，使得终端设备在执行算例示例的切换过程中，无需确定(或重新配置、准备、激活等)新的算力资源，使得该终端设备可以快速地切换该算力资源对应的多个不同的算例示例。
在一种可能的实现方式中，在步骤S401之前，网络设备可以基于多种调度策略生成该第一配置信息，以实现对该终端设备所执行的算力实例进行配置。例如，该网络设备可以基于自身的资源信息(包括算力资源、存储资源等)的使用情况生成该第一配置信息，该网络设备也可以接收其它网络设备(例如核心网设备)的指示以生成该第一配置信息，该网络设备还可以基于终端设备所上报的信息，出于为终端设备提供所适配的算力配置的目的而生成该第一配置信息。
下面将以网络设备基于终端设备所上报的信息，出于为终端设备提供所适配的算力配置的目的而生成该第一配置信息为例，提供多个示例进行说明。
示例一、终端设备在步骤S401中接收来自网络设备的第一消息之前，该方法还包括：该终端设备向网络设备发送第一指示信息，该第一指示信息用于指示该终端设备的算力状态。
具体地，终端设备在接收第一消息之前，该终端设备可以向该网络设备发送用于指示该终端设备的算力状态的第一指示信息，以便于网络设备可以将该终端设备的算例状态作为该网络设备发送第一消息的依据。从而，网络设备可以基于该终端设备的算力状态，对该终端设备所执行的算力实例(和/或该终端设备所执行的算力实例对应的算力资源)进行动态调整。
可选地，该第一指示信息包括以下至少一项：
CPU类型信息、存储信息、内存信息、电量信息、算力利用率信息。
示例二、在该终端设备接收来自网络设备的第一消息之前，该方法还包括：该终端设备向该网络设备发送第二指示信息，该第二指示信息用于指示该终端设备期望的算力资源信息和/或算力实例。
具体地，终端设备在接收第一消息之前，该终端设备可以向该网络设备发送用于指示该终端设备期望的算力资源信息和/或算力实例的第二指示信息，以便于网络设备可以将该终端设备期望的算力资源信息和/或算力实例作为该网络设备发送第一消息的依据。从而，网络设备可以基于该终端设备期望的算力资源信息和/或算力实例，对该终端设备所执行的算力实例(和/或该终端设备所执行的算力实例对应的算力资源)进行动态调整，以期所提供的配置信息能够满足该终端设备的需求。
S402.终端设备获取第一信息。
本实施例中，终端设备在步骤S402中获取第一信息，该第一信息用于指示第一算力实例，该第一算力实例为步骤S401中第一配置信息所配置的该至少一个算力实例中的算力实例。
在一种可能的实现方式中，在步骤S402中，该第一信息包括该第一算力实例的标识和/或该第一算力实例对应的算力资源信息的标识；该终端设备在步骤S402中获取该第一信息包括：该终端设备接收该第一信息，该第一信息承载于层1(layer 1，L1)控制信息或层2(layer 2，L2)控制信息或层3(layer 3，L3)消息中。
具体地，终端设备可以接收来自网络设备的用于指示第一算力实例的第一信息，以使得终端设备基于网络设备的指示执行第一算力实例。从而，在对终端设备的算力进行配置使得终端设备作为计算节点参与算例示例对应的计算过程的同时，网络设备基于第一消息还可以实现对终端设备所执行的算力实例的动态调整。
此外，在该终端设备接收该第一信息之前，该方法还包括：该终端设备接收参考信号(reference signal，RS)；该终端设备发送该RS对应的测量结果。具体地，终端设备在接收第一信息之前，可以接收RS并发送该RS对应的测量结果，以便于网络设备可以将该RS的测量结果作为该网络设备发送第一信息的依据。其中，该RS的测量结果可以反映出终端设备与网络设备之间的信道信息，从而，网络设备可以基于该RS的测量结果对该终端设备所执行的算力实例(和/或该终端设备所执行的算力实例对应的算力资源)进行动态调整。
在一些实现方式中，该第一算力示例可以为网络设备与一个或多个终端设备协同计算的算力实例，使得该终端设备在步骤S402之后可以基于网络设备所指示的第一信息执行该第一算力实例的情况下，能够共享网络设备侧的计算资源，以解决终端设备计算资源不足的问题。相应的，网络设备也需要基于该第一信息执行第一算力实例的部分计算过程，或者说，该网络设备也需要同时在本地调整该第一信息对应的第一算力实例，使得网络设备和终端设备在协同计算的过程中能够实现动态的同步调整。
在一些实现方式中，该第一算力示例可以为终端设备与其它计算节点协同计算的算力实例，使得该终端设备在步骤S402之后基于该第一信息执行该第一算力实例的情况下，能够共享该终端设备侧的计算资源，以使得该终端设备的计算资源得以共享，提升计算资源的复用程度。相应的，由于该第一算力实例的执行有可能不需要该网络设备参与，因此， 网络设备可能无需基于该第一信息执行第一算力实例的部分计算过程，或者说，该网络设备无需同时在本地调整该第一信息对应的第一算力实例。
可选地，其它计算节点可以包括其它终端设备和/或其它网络设备。
在一种可能的实现方式中，该第一算力实例为默认算力实例；和/或，该第一算力实例对应的算力资源信息为默认算力资源信息。
可选地，默认算力实例也可以称为基础算力实例、预配置的算力实例等。相应的，默认算力资源信息也可以称为基础算力资源信息、预配置的基础算力资源信息等。
可选地，网络设备和终端设备均具备(或预存储)该默认算例示例。
可选地，该默认算例示例可以为低功耗/低开销/计算能力要求低的算力实例。
具体地，第一信息所指示的第一算力实例可以为默认算力实例，和/或，第一信息所指示的第一算例示例对应的算力资源信息为默认算力资源信息。从而，基于该默认算例示例的实现，可以保证在网络设备和终端设备之间所传输的信令(如重配信令、调度信令等)传输失败的情况下，确保该终端设备也能执行该默认算力示例，使得终端设备仍能作为计算节点参与算例示例对应的计算过程，以提升计算资源的复用程度。
此外，在该第一算力实例为默认算力实例；和/或，该第一算力实例对应的算力资源信息为默认算力资源信息的情况下，该终端设备在步骤S402中获取该第一信息包括：在满足以下至少一项时，该终端设备在步骤S402中生成该第一信息，包括：
第一定时器超时，其中，该第一定时器的配置信息包含于该第一消息；或，
该终端设备的电量低于第一阈值，该第一阈值可以是协议规定的固定值，比如5％，10％等，也可以是网络设备与终端设备约定的值，例如可以是根据当前执行的算力实例确定的一个值，还可以是临时确定的一个具体值；或，
该终端设备进入无线资源控制空闲RRC idle态；或，
该终端设备测量得到的RS的信号质量小于阈值，或；
该终端设备执行小区切换；或，
该终端设备执行RRM测量；或，
该终端设备当前执行的算例示例对应的已执行计算量高于阈值；或，
该终端设备确定服务质量信息(quality of service，QoS)需求低于阈值。
可选地，上述信号质量可以包括参考信号接收功率(reference signal receiving power，RSRP)、参考信号接收质量(reference signal receiving quality，RSRQ)或信号与干扰加噪声比(signal to interference plus noise ratio，SINR)等至少一项。
具体地，终端设备在步骤S402中可以基于上述至少一项事件的发生，触发生成第一信息。换言之，无需网络设备的指示，该终端设备就可以基于上述至少一项事件实现对该终端设备所执行的算例示例的动态切换。从而，在网络设备和终端设备之间所传输的信令(如重配信令、调度信令等)传输失败的情况下，确保该终端设备也能执行该默认算力示例，使得终端设备仍能作为计算节点参与算例示例对应的计算过程，以提升计算资源的复用程度。
S403.终端设备基于第一信息执行第一算力实例。
本实施例中，终端设备在步骤S402中获取第一信息之后，该终端设备在步骤S403中基于该第一信息执行第一算力实例。
在一种可能的实现方式中，在步骤S403中，该终端设备基于该第一信息执行该第一算力实例的过程中，该终端设备还可以发送第三指示信息，该第三指示信息用于指示该终端设备的算力调整信息；此后，该网络设备可以用于指示该终端设备的算力调整信息的第三指示信息向该终端设备发送第三配置信息；相应的，该终端设备还可以接收来自该网络设备的第三配置信息。其中，该第三配置信息用于更新该第一配置信息和/或该第三配置信息用于更新该第二配置信息。
具体地，终端设备在步骤S403中基于该第一信息执行该第一算力实例的过程中，该终端设备可以向该网络设备发送用于指示该终端设备的算力调整信息的第三指示信息，以便于网络设备可以将该终端设备的算力调整信息作为该网络设备发送更新后的配置(即用于更新第一配置信息和/或用于更新第二配置信息的第三配置信息)的依据。从而，网络设备可以基于该终端设备的算力调整信息，对该终端设备所执行的算力实例(和/或该终端设备所执行的算力实例对应的算力资源)进行动态调整，以期所提供的配置信息能够满足该终端设备的算力调整需求。
可选地，该第三指示信息包括：
内存信息、电量信息、算力利用率信息。
示例性的，以该第三指示信息包括电量信息为例。若该终端设备在步骤S403中所执行的第一算力实例所对应的算力资源信息包括电量信息，例如，该算力资源信息所包含的电量信息指示该第一算力实例需要在满足电量大于某个阈值时才可以执行(示例性的，该阈值可以取值可以为50％、40％、30％、20％等或者其它的取值，为便于描述，此处以该阈值取值为20％为例)。在这种情况下，该终端设备在步骤S403执行该第一算力实例的过程中，当该终端设备确定该终端设备的电量低于或等于20％时，该终端设备可以向网络设备发送该第三指示信息，用以指示该终端设备的电量信息已低于或等于20％。也就是说，这里的阈值也可以是前面实施例中提到的第一阈值。
在一些实现方式中，该网络设备在接收该第三指示信息之后，该网络设备可以基于该第三指示信息下发第三配置信息，其中，该第三配置信息用于更新该第一配置信息和/或该第三配置信息用于更新该第二配置信息。使得该终端设备接收该第三配置信息之后，对第一配置信息和/或第二配置信息进行更新，得到更新后的算力示例配置和/或更新后的算力资源配置，并基于更新后的算力示例配置和/或更新后的算力资源配置执行其他的算力实例或暂停执行算例实例。
在另一些实现方式中，该终端设备在步骤S403执行该第一算力实例的过程中，当该终端设备确定该终端设备的电量低于或等于20％时，该终端设备也可以切换为执行默认算例实例或执行默认算力资源对应的算力实例。其中，默认算例实例和默认算力资源的实现过程可以参考前述实施例的描述，并实现相应的技术效果，此处不做赘述。
基于图4所示技术方案，终端设备在步骤S401中接收来自网络设备的包含有第一配置信息的第一消息，其中，该第一配置信息包括至少一个算力实例的配置信息。该终端设备 在步骤S402中获取用于指示该至少一个算力实例中的第一算力实例的第一信息之后，该终端设备在步骤S403中基于该第一信息执行该第一算力实例。换言之，终端设备基于网络设备的指示对算力实例进行配置之后，该终端设备基于第一信息执行相应的算力实例。从而，终端设备和网络设备所在的无线网络系统可以成为通信连接与计算双基础设施，通过网络设备基于该第一配置信息对终端设备的算力进行配置的方式，使得终端设备作为计算节点参与算例示例对应的计算过程，可有效提升计算资源的复用程度，以提升网络收益。
示例性的，下面将以算力实例所涉及的计算过程为神经网络的计算过程为例进行说明。以图5a和图5b所示实现场景为例，其中，网络设备所提供的小区信号的覆盖范围为圆形作为示例。应理解，该小区信号的覆盖范围还可以为椭圆形、矩形、六边形或者其他规则或不规则的形状，此处不做限定。
一种可能的实现方式中，网络设备和终端设备可以执行算力示例，以实现联合计算过程。例如，如图5a所示神经网络的计算任务作为一个算力示例，其中，该神经网络的计算任务包括八层神经网络的计算过程。网络设备和终端设备之间可以分别执行该八层神经网络的部分计算过程，以实现联合计算过程。
图5b左侧为终端设备位于小区中心的场景示例，其中，位于小区中心的终端设备的信道容量大，终端设备可以计算神经网络的更少层(图中以神经网络层数的多少指示算力实例的复杂程度的大小)，将输出结果及剩下层的计算交给网络设备计算。如图中“终端设备执行的算力实例1”对应于图5a所示计算任务的前面两层神经网络，“网络设备执行的算例实例1”对应于图5a所示计算任务的后面六层神经网络；图5b右侧终端设备位于小区边缘的场景示例，其中，相比于终端设备位于小区中心的场景，位于小区边缘的终端设备的信道容量小，终端设备可以执行更多的计算层数，将输出结果及剩下层的计算交给基站计算，如图中“终端设备执行的算力实例2”对应于图5a所示计算任务的前面四层神经网络，“网络设备执行的算例实例2”对应于图5a所示计算任务的后面四层神经网络，用以完成联合计算。从而，基于图4所示实现方式，终端设备可以在步骤S401中基于网络设备的指示对算力实例进行配置之后，该终端设备在步骤S402中获取第一信息，并在步骤S403中基于第一信息执行相应的算力实例，使得终端设备在图5b左侧所示场景切换至图5b右侧所示场景的过程(或终端设备在图5b右侧所示场景切换至图5b左侧所示场景的过程)中，能够基于该第一信息执行算例实例的切换。从而，终端设备和网络设备所在的无线网络系统可以成为通信连接与计算双基础设施，通过网络设备基于该第一配置信息对终端设备的算力进行配置的方式，使得终端设备作为计算节点参与算例示例对应的计算过程，可有效提升计算资源的复用程度，以提升网络收益。
一种可能的实现方式中，该第一信息为网络设备在步骤S402中所指示的。从而，在对终端设备的算力进行配置使得终端设备作为计算节点参与算例示例对应的计算过程的同时，网络设备基于第一消息还可以实现对终端设备所执行的算力实例的动态调整。
另一种可能的实现方式中，该第一信息所指示的第一算力示例为默认算例示例，即终端设备基于一些预定义的事件的触发，而在步骤S402中生成。从而，基于该默认算例示例的实现，可以保证在网络设备和终端设备之间所传输的信令(如重配信令、调度信令等) 传输失败的情况下，确保该终端设备也能执行该默认算力示例，使得终端设备仍能作为计算节点参与算例示例对应的计算过程，以提升计算资源的复用程度。
下面将结合更多的实施例，对图4所示通信方法进一步描述。
图4所示通信方法的一种实现方式中，通过算力实例ID调整算力资源。其中，网络设备在步骤S401所发送的第一消息包括第一配置信息和第二配置信息。
可选地，用于配置的至少一个算例示例的第一配置信息包括算力实例ID(可以是任务ID或其他形式，可以是CMF/TA分配，也可能是TS/CS分配)与算力大小、模型、拆分学习或推理切分点位置、联邦学习本地迭代次数等跟计算量相关的配置一一对应；可选的，算力实例ID，也可以是模型ID、拆分学习或推理的拆分点ID、联邦学习迭代次数ID等等，这里不做限定。
可选地，用于配置至少一个算例资源信息的第二配置信息包括一个或多个执行体ID。其中，1个执行体(执行体ID)可以包括多个算力实例(即1个执行体可以用于执行多个算力实例)，执行体的配置信息包括执行体ID、执行体的算力配置信息，具体包括多项算力资源(CPU类型、存储、内存、电量信息)或算力容器(上述算力类型的组合)。进一步可选地，执行体的算力资源大于等于执行体包括的多个算力实例所需算力资源的最大值。
应理解，本申请所涉及的算力资源(或称为执行体)可以指示算力实例的运行环境，如算力实例运行时需要的存储、电量、内存、算力等。
应理解，本申请所涉及的算力实例可以指示与算力大小、模型、拆分学习或推理切分点位置、联邦学习本地迭代次数等跟计算量相关的一种计算资源使用的模式或方法。
在该实现方式中，网络设备还可以在步骤S402中向终端设备发送第一信息，以实现对算例示例的动态调整。可选地，网络设备在步骤S402所发送的第一信息可以为调整信令，即算力实例ID指示信息，用于指示该终端设备执行第一算力实例。
示例性的，该实现方式可以通过图6a所示场景实现。为便于描述，在图6a中将“算力实例”记为“实例”，包括实例1和实例2。
可选地，图6a所示场景中，网络设备在步骤S401向终端设备发送第一消息和网络设备在步骤S402中向终端设备发送第一信息的过程可以基于CMF的调度所触发，其中，CMF可以部署在核心网侧，也可以部署在接入网侧，本申请不做限定。
可选地，图6a所示场景中，网络设备可以基于自身生成的实时融合调度(convergence scheduling，CS)，触发执行步骤S402中向终端设备发送第一信息。
如图6a所示，此处仍以网络设备和终端设备联合计算图5a所示神经网络的计算任务为例。在实例1中，网络设备执行后面六层的计算过程，终端设备执行前面两层的计算过程；换言之，在实例1中，终端设备可以执行较少的计算，以便于该终端设备可以交互较多的神经网络隐藏层特征信息。在实例2中，网络设备执行后面四层的计算过程，终端设备执行前面四层的计算过程；换言之，相比于实例1，在实例2中，终端设备可以执行较多的计算，使得该终端设备可以交互较少的神经网络隐藏层特征信息。
在图6a所示场景的实现过程中，当终端设备在小区中心时，网络设备可以基于该终端设备上报的信道信息确定该终端设备与网络设备之间的信道质量好，传输带宽大，可以执行图示中的实例1，该实例1需要交互更多的特征信息，终端设备和网络设备都使用对应实例1的配置共同完成拆分推理。此时，网络设备可以在步骤S402中向终端设备发送第一信息，用于调度该终端设备执行实例1，使得终端设备在步骤S403中执行实例1。
在图6a所示场景的实现过程中，当终端设备在小区边缘时，网络设备可以基于该终端设备上报的信道信息确定该终端设备与网络设备之间的信道质量差，传输带宽小，可以执行图示中的实例2，该实例2需要交互较少的特征信息，终端设备和网络设备都使用对应实例1的配置共同完成拆分推理。此时，网络设备可以在步骤S402中向终端设备发送第一信息，用于调度该终端设备执行实例2，使得终端设备在步骤S403中执行实例2。
图4所示通信方法的另一种实现方式中，通过算力执行体ID调整算力资源。其中，网络设备在步骤S401所发送的第一消息包括第一配置信息和第二配置信息。
可选地，用于配置的至少一个算例示例的第一配置信息包括算力实例ID(可以是任务ID或其他形式，可以是CMF/TA分配，也可能是TS/CS分配)与算力大小、模型、切分点位置等跟计算量相关的配置一一对应。
可选地，用于配置至少一个算例资源信息的第二配置信息包括一个或多个执行体ID。其中，执行体和算力实例ID可以是一一映射；执行体的配置信息包括执行体ID、执行体的算力配置信息，具体包括一项算力资源(CPU类型、存储、内存、电量信息)或算力容器(上述算力类型的组合)。进一步可选地，执行体的算力资源大于等于执行体包括的多个算力实例所需算力资源的最大值。
进一步可选地，算力执行体ID，也可以换成模型ID、拆分学习或推理的拆分点ID、联邦学习迭代次数ID等等，这里不做限定。
在该实现方式中，网络设备还可以在步骤S402中向终端设备发送第一信息，以实现对算例示例的动态调整。可选地，网络设备在步骤S402所发送的第一信息可以为调整信令，即算力实例ID指示信息，用于指示该终端设备执行第一算力实例对应的算力资源。
示例性的，该实现方式可以通过图6b所示场景实现。为便于描述，在图6b中将“算力实例对应的算力资源”记为“执行体”，包括执行体1和执行体2。
可选地，图6b所示场景中，网络设备在步骤S401向终端设备发送第一消息和网络设备在步骤S402中向终端设备发送第一信息的过程可以基于CMF的调度所触发，其中，CMF可以部署在核心网侧，也可以部署在接入网侧，本申请不做限定。
可选地，图6b所示场景中，网络设备可以基于自身生成的实时融合调度(convergence scheduling，CS)，触发执行步骤S402中向终端设备发送第一信息。
如图6b所示，此处仍以网络设备和终端设备联合计算图5a所示神经网络的计算任务为例。在执行体1所对应的算力实例中，网络设备执行后面六层的计算过程，终端设备执行前面两层的计算过程；换言之，在执行体1所对应的算力实例中，终端设备可以执行较少的计算，以便于该终端设备可以交互较多的神经网络隐藏层特征信息。在执行体2所对应的算力 实例中，网络设备执行后面四层的计算过程，终端设备执行前面四层的计算过程；换言之，相比于执行体1所对应的算力实例，在执行体2所对应的算力实例中，终端设备可以执行较多的计算，使得该终端设备可以交互较少的神经网络隐藏层特征信息。
在图6b所示场景的实现过程中，当终端设备在小区中心时，网络设备可以基于该终端设备上报的信道信息确定该终端设备与网络设备之间的信道质量好，传输带宽大，可以执行图示中的执行体1所对应的算力实例，该执行体1所对应的算力实例需要交互更多的特征信息，终端设备和网络设备都使用执行体1所对应的算力实例所对应的配置共同完成拆分推理。此时，网络设备可以在步骤S402中向终端设备发送第一信息，用于指示该终端设备执行该执行体1所对应的算力实例，使得终端设备在步骤S403中执行该执行体1所对应的算力实例。
在图6b所示场景的实现过程中，当终端设备在小区边缘时，网络设备可以基于该终端设备上报的信道信息确定该终端设备与网络设备之间的信道质量差，传输带宽小，可以执行图示中的执行体2所对应的算力实例，该执行体2所对应的算力实例需要交互较少的特征信息，终端设备和网络设备都使用对应实例1的配置共同完成拆分推理。此时，网络设备可以在步骤S402中向终端设备发送第一信息，用于指示该终端设备执行该执行体2所对应的算力实例，使得终端设备在步骤S403中执行该执行体2所对应的算力实例。
从而，在图6a和图6b所示该实现方式中，执行体所需资源按多个算力实例所需资源最大值配置，使能算力实例之间能快速切换。算力实例的快速切换，匹配终端设备与网络设备之间信道的快速变化，从而支撑算力、连接的实时动态融合调整。
此外，在图6a和图6b所示该实现方式中，网络设备生成算力执行体或算力实例配置信息，算力执行体或算力实例与算力大小、模型、切分点位置、联邦学习本地迭代次数等计算量相关的配置是一一映射，并传输给终端；网络设备向终端设备发送算力执行体或算力实例的动态调整指示信息，包括算力执行体ID信息或算力实例的ID信息；(由于一一映射，也可以是模型ID信息、切分点ID信息、本地迭代次数ID信息等等)；从而实现算力、连接的融合动态调整。
图4所示通信方法的另一种实现方式中，基于预定义的事件算力实例动态切换。其中，网络设备在步骤S401所发送的第一消息包括第一配置信息和第二配置信息。
可选地，用于配置的至少一个算例示例的第一配置信息包括算力实例ID(可以是任务ID或其他形式，可以是CMF/TA分配，也可能是TS/CS分配)与算力大小、模型、拆分学习或推理切分点位置、联邦学习本地迭代次数、算力时长等跟计算量相关的配置一一对应。
可选地，用于配置至少一个算例资源信息的第二配置信息包括一个或多个执行体ID。其中，1个执行体(执行体ID)可以包括1个或多个算力实例，执行体的配置信息包括执行体ID、执行体的算力配置信息，具体包括一项或多项算力资源(CPU类型、存储、内存、电量信息、算力时长)或算力容器(上述算力类型的组合)。进一步可选地，执行体的算力资源大于等于执行体包括的多个算力实例所需算力资源的最大值。
此外，执行体中多个算力实例中的1个作为默认(default)算力实例或多个算力执行体中的1个作为默认算力执行体，当预定时事件发生时，终端基站切换到默认算力实例或默认算力执行体。
进一步可选地，算力执行体ID，也可以换成模型ID、拆分学习或推理的拆分点ID、联邦学习迭代次数ID等等，这里不做限定。
在该实现方式中，终端设备可以在步骤S402中自身生成第一信息，用于指示该终端设备执行第一算力实例。即该终端设备基于预定时事件的算力实例动态切换(若执行体与算力实例一一映射，则也可以是算力执行体切换)。
示例性的，该实现方式可以通过图6c所示场景实现。为便于描述，在图6c中将“算力实例”记为“实例”，包括default实例1和实例2。
可选地，图6c所示场景中，网络设备在步骤S401向终端设备发送第一消息和网络设备在步骤S402中确定该终端设备执行默认实例的过程可以基于CMF的调度所触发，其中，CMF可以部署在核心网侧，也可以部署在接入网侧，本申请不做限定。
可选地，图6c所示场景中，网络设备可以基于自身生成的实时融合调度(convergence scheduling，CS)，在步骤S402中确定该终端设备执行默认实例。
如图6c所示，此处仍以网络设备和终端设备联合计算图5a所示神经网络的计算任务为例。在default实例1中，终端设备执行前面两层的计算过程，网络设备执行后面六层的计算过程；换言之，在实例1中，终端设备可以执行较少的计算，以便于该终端设备可以交互较多的神经网络隐藏层特征信息。在实例2中，网络设备执行前面四层的计算过程，终端设备执行后面四层的计算过程；换言之，相比于default实例1，在实例2中，终端设备可以执行较多的计算，使得该终端设备可以交互较少的神经网络隐藏层特征信息。
在图6c所示场景的实现过程中，当终端设备在小区中心时，网络设备可以基于该终端设备上报的信道信息确定该终端设备与网络设备之间的信道质量好，传输带宽大，可以执行图示中的实例1，该实例1需要交互更多的特征信息，终端设备和网络设备都使用对应实例1的配置共同完成拆分推理。此时，网络设备可以在步骤S402中向终端设备发送第一信息，用于指示该终端设备执行实例1，使得终端设备在步骤S403中执行实例1。
在图6c所示场景的实现过程中，当终端设备在执行实例2的过程中，基于预定义事件的算力实例动态切换(若执行体与算力实例一一映射，则也可以是算力执行体切换)，即该终端设备在步骤S402中基于该预定义的事件触发生成第一信息，并在步骤S403中基于该第一信息执行第一算力实例。
可选地，该预定义的事件包括以下至少一项：
网络设备预先配置的定时器，即在非default实例上工作一段时间后切换到默认实例，例如终端设备、网络设备都在实例2上工作，定时器超时后，终端设备和网络设备都会切换到对应的default实例1上工作；
终端设备确定自身电量小于一个网络侧配置的阈值，或其他算力资源事件，则切换到默认实例，例如终端设备、网络设备切换到default实例1上工作，从而保证计算的正常进行；
终端设备的RSRP小于某个阈值，或终端设备进入RRC idle态，或发生小区切换或其他RRM事件，则切换到默认实例，例如终端设备、网络设备切换到default实例1上工作；
进一步可选地，该预定义的时间还可以包括其他更广泛的事件，例如计算任务完成90％、用户计算服务QoS需求降低等等。
从而，在图6c所示该实现方式中，网络设备生成算力执行体或算力实例配置信息，算力执行体或算力实例与算力大小、模型、切分点位置、联邦学习本地迭代次数等计算量相关的配置是一一映射，并传输给终端；网络设备向终端设备发送算力执行体或算力实例的动态调整指示信息，包括算力执行体ID信息或算力实例的ID信息；(由于一一映射，也可以是模型ID信息、切分点ID信息、本地迭代次数ID信息等等)；从而实现算力、连接的融合动态调整。
此外，基于该默认算例示例的实现，还可以节省动态信令的指示信息。并且，可以保证在网络设备和终端设备之间所传输的信令(如重配信令、调度信令等)传输失败的情况下，确保该终端设备也能执行该默认算力示例，使得终端设备仍能作为计算节点参与算例示例对应的计算过程，以提升计算资源的复用程度。
综上所述，基于前述图4至图6c所示任一实现方式可以看出，如图7所示，终端设备可以在步骤S402中基于网络设备的实时融合调度(CS)或基于预定义事件的触发，获取该第一信息。此后，该终端设备在步骤S403中基于该第一信息执行第一算力实例，使得终端设备作为计算节点参与算例示例对应的计算过程，可有效提升计算资源的复用程度，以提升网络收益。
在一些实现方式中，该第一算力示例可以为网络设备与一个或多个终端设备协同计算的算力实例，使得该终端设备基于该第一配置信息执行算力实例的情况下，能够共享网络设备侧的计算资源，以解决终端设备计算资源不足的问题。
在一些实现方式中，该第一算力示例可以为终端设备与其它计算节点协同计算的算力实例，使得该终端设备基于该第一配置信息执行该算力实例的情况下，能够共享该终端设备侧的计算资源，以使得该终端设备的计算资源得以共享，提升计算资源的复用程度。
可选地，其它计算节点可以包括其它终端设备和/或其它网络设备。
请参阅图8，为本申请提供的通信方法的另一个示意图，该方法包括如下步骤。
S801.终端设备发送算力指示信息。
本实施例中，终端设备在步骤S801中发送算力指示信息，相应的，网络设备在步骤S401中接收该算力指示信息。
在一种可能的实现方式中，终端设备在步骤S801中向网络设备发送算力指示信息之前，该方法还包括：该终端设备接收来自该网络设备的第二消息，该第二消息包括初始配置信息，其中，该初始配置信息用于配置至少一个算力实例。
具体地，终端设备在步骤S801中向网络设备发送算力指示信息之前，该终端设备还可以接收包含有初始配置信息的第二消息，该初始配置信息用于配置至少一个算力实例。此后，该终端设备在确定需要对该初始配置信息进行更新(例如，该终端设备的CPU类型信息、 存储信息、内存信息、电量信息和/或算力利用率信息的取值低于阈值或高于阈值)时，该终端设备可以向网络设备发送算力指示信息，以使得网络设备下发更新后的配置信息，即第一配置信息。此后，该终端设备可以基于该第一配置信息对初始配置信息进行更新，以得到适配于该终端设备的算力配置信息。
S802.网络设备发送第一消息。
本实施例中，网络设备在步骤S801中接收算力指示信息之后，该网络设备在步骤S802中发送第一消息，相应的，该终端设备在步骤S802中接收该第一消息。
在一种可能的实现方式中，在步骤S802之后，该方法还包括：该终端设备发送该第一消息的响应消息或确认消息。具体地，该终端设备在接收该第一消息之后，该终端设备还可以发送该第一消息的响应消息或确认消息，以使得网络设备基于该第一消息的响应消息或确认消息明确该终端设备已接收该第一消息，并将以该第一消息所包含的第一配置信息配置该至少一个算例示例。
在一种可能的实现方式中，终端设备在步骤S801所发送的算力指示信息用于指示该终端设备的算力信息，该算力指示信息可以存在多种实现方式。下面将提供多个示例进行说明。
示例一、终端设备在步骤S801所发送的算力指示信息包括第一指示信息，该第一指示信息用于指示该终端设备的算力状态。具体地，终端设备所发送的算力指示信息包括用于指示该终端设备的算力状态的第一指示信息。换言之，终端设备在接收第一消息之前，该终端设备可以向该网络设备发送用于指示该终端设备的算力状态的第一指示信息，以便于网络设备可以将该终端设备的算例状态作为该网络设备发送第一消息的依据。从而，网络设备可以基于该终端设备的算力状态，对该终端设备所执行的算力实例(和/或该终端设备所执行的算力实例对应的算力资源)进行动态调整。
可选地，该第一指示信息包括以下至少一项：
CPU类型信息、存储信息、内存信息、电量信息、算力利用率信息。
示例二、终端设备在步骤S801所发送的算力指示信息包括第二指示信息，该第二指示信息用于指示该终端设备期望的算力资源信息和/或算力实例。具体地，终端设备所发送的算力指示信息包括用于指示该终端设备期望的算力资源信息和/或算力实例的第二指示信息。换言之，终端设备在接收第一消息之前，该终端设备可以向该网络设备发送用于指示该终端设备期望的算力资源信息和/或算力实例的第二指示信息，以便于网络设备可以将该终端设备期望的算力资源信息和/或算力实例作为该网络设备发送第一消息的依据。从而，网络设备可以基于该终端设备期望的算力资源信息和/或算力实例，对该终端设备所执行的算力实例(和/或该终端设备所执行的算力实例对应的算力资源)进行动态调整，以期所提供的配置信息能够满足该终端设备的需求。
示例三、终端设备在步骤S801所发送的算力指示信息包括第三指示信息，该第三指示信息用于指示该终端设备的算力调整信息。具体地，终端设备所发送的算力指示信息包括用于指示该终端设备的算力调整信息的第三指示信息。换言之，终端设备在接收第一消息之前，该终端设备可以向该网络设备发送用于指示该终端设备的算力调整信息的第二指示 信息，以便于网络设备可以将该终端设备的算力调整信息作为该网络设备发送第一消息的依据。从而，网络设备可以基于该终端设备的算力调整信息，对该终端设备所执行的算力实例(和/或该终端设备所执行的算力实例对应的算力资源)进行动态调整，以期所提供的配置信息能够满足该终端设备的算力调整需求。
可选地，该第三指示信息包括：
内存信息、电量信息、算力利用率信息。
在一种可能的实现方式中，网络设备在步骤S802所发送的第一消息还包括第二配置信息，其中，该第二配置信息用于配置至少一个算力资源信息，该至少一个算力资源信息关联于该至少一个算力实例。
可选地，该至少一个算力资源关联于该至少一个算力实例包括：
该至少一个算力资源中的每一个算力资源与该至少一个算力实例中的每一个算力实例一一对应；
或，
该至少一个算力资源中的其中一个算力资源对应于该至少一个算力实例中的一个或多个算力实例。
具体地，第二配置信息所配置的至少一个算力资源关联于第一配置信息所配置的至少一个算例实例，其中，该至少一个算力资源中的算力资源与该至少一个算例实例中的算力实例可以是一一对应的关系，也可以是一对一或一对多的关系，以提升网络设备在对算例实例和算力资源进行配置的过程的灵活性。此外，在网络设备基于第一信息对第一算力实例进行指示的情况下，也可以提升该网络设备在对第一算例实例和/或第一算力实例对应的算力资源进行指示的过程的灵活性。
此外，在该至少一个算力资源中的其中一个算力资源对应于该至少一个算力实例中的多个算力实例时，即在至少一个算力资源中的算力资源与该至少一个算例实例中的算力实例为一对多的关系的情况下，由于终端设备可以该算力资源执行多个不同的算力实例，使得终端设备在执行算例示例的切换过程中，无需确定(或重新配置、准备、激活等)新的算力资源，使得该终端设备可以快速地切换该算力资源对应的多个不同的算例示例。
在一种可能的实现方式中，该至少一个算力资源信息包括以下至少一项：
CPU类型信息、存储信息、执行时长信息、内存信息或电量信息。
在一种可能的实现方式中，该至少一个算力实例中的算力实例包括以下至少一项：
执行时长信息、算力大小信息、模型信息、拆分学习位置、推理切分点位置或联邦学习本地迭代次数。
基于上述技术方案，终端设备在步骤S801中发送算力指示信息之后，使得网络设备基于该算力指示信息生成并发送包含有第一配置信息的第一消息，该第一配置信息用于配置至少一个算例实例，使得终端设备在步骤S802中接收该第一配置信息。换言之，终端设备在发送用于指示该终端设备的算力相关的信息之后，使得网络设备基于该信息对该终端设备所执行的算力实例进行配置。从而，终端设备和网络设备所在的无线网络系统可以成为通信连接与计算双基础设施，通过网络设备基于该第一配置信息对终端设备的算力进行配 置的方式，使得终端设备作为计算节点参与算例示例对应的计算过程，可有效提升计算资源的复用程度，以提升网络收益。
作为图8所示通信方法的另一种实现方式，网络设备在步骤S802中可以基于信令重配置算力实例和/或算例示例对应的算力资源。
示例性的，终端设备可以感知自身的算力状态，并在步骤S801中向网络设备上报算力指示信息，该算力指示信息可以包括算力状态信息或算力调整请求或算力建议信息。
可选地，算力状态信息包括一项或多项算力(CPU类型、存储、内存、电量信息)状态信息或利用率信息；或算力容器(上述算力类型的组合)的状态信息或利用信息。
可选地，算力状态信息的传输方式可以是通过L1信令、L2 MAC CE信令或L3的RRC CRC容器、RRC信令中定义的CRC IE、或定义的RRC算力请求消息包括上述算力信息。
可选地，算力建议信息中包括网络侧配置的多个算力执行体或多个算力实例中的1个算力执行体的ID信息或1个算力实例的ID信息或包括终端设备所建议的算力执行体的配置信息或算力实例的配置信息。
可选地，算力实例ID或算力执行体ID，也可以是模型ID、拆分学习或推理的拆分点ID、联邦学习迭代次数ID等等，这里不做限定。
此外，网络设备在步骤S801中接收算力指示信息之后，该网络设备中的算力管理功能执行算力调整，可以直接/间接重配/调度算力，执行步骤S802以触发RRC信令重配计算无线承载映射的逻辑信道的保证速率等。
可选地，该网络设备执行算力调整的依据可以包括：终端设备上报的CSI/RSRP信息、基站算力负载信息、终端的算力状态上报信息、终端设备在步骤S801所发送的算力指示信息等。
可选地，RRC算力重配消息中包括：1个执行体(执行体ID)可以包括一个或多个算力实例，执行体的配置信息包括执行体ID、执行体的算力配置信息，具体包括多项算力资源(CPU类型、存储、内存、电量信息)或算力容器(上述算力类型的组合)；执行体的算力资源大于等于执行体包括的多个算力实例所需算力资源的最大值。
可选地，算力实例ID(可以是任务ID或其他形式，可以是CMF/TA分配，也可能是TS/CS分配)与算力大小、模型、拆分学习或推理切分点位置、联邦学习本地迭代次数等跟计算量相关的配置一一对应
从而，终端在步骤S802接收第一消息之后，发送确认消息。使得终端基于网络设备的决策调整算力大小，实现联合终端算力需求调整对应的算力大小。换言之，终端设备和网络设备所在的无线网络系统可以成为通信连接与计算双基础设施，通过网络设备基于该第一配置信息对终端设备的算力进行配置的方式，使得终端设备作为计算节点参与算例示例对应的计算过程，可有效提升计算资源的复用程度，以提升网络收益。
在一些实现方式中，该第一算力示例可以为网络设备与一个或多个终端设备协同计算的算力实例，使得该终端设备基于该第一消息所包含的第一配置信息执行算力实例的情况下，能够共享网络设备侧的计算资源，以解决终端设备计算资源不足的问题。
在一些实现方式中，该第一算力示例可以为终端设备与其它计算节点协同计算的算力实例，使得该终端设备基于该第一消息所包含的第一配置信息执行算力实例的情况下，能够共享该终端设备侧的计算资源，以使得该终端设备的计算资源得以共享，提升计算资源的复用程度。
可选地，其它计算节点可以包括其它终端设备和/或其它网络设备。
请参阅图9，本申请实施例提供了一种通信装置900，该通信装置900可以实现上述方法实施例中终端设备(或网络设备)的功能，因此也能实现上述方法实施例所具备的有益效果。在本申请实施例中，该通信装置900可以是终端设备(或网络设备)，也可以是终端设备(或网络设备)内部的集成电路或者元件等，例如芯片。下文实施例以该通信装置900为终端设备或网络设备为例进行说明。
一种可能的实现方式中，当该装置900为用于执行前述任一实施例中终端设备所执行的方法时，该装置900包括处理单元901和收发单元902；
该收发单元902，用于接收来自网络设备的第一消息，该第一消息包括第一配置信息，其中，该第一配置信息包括至少一个算力实例的配置信息；
该处理单元901，用于获取第一信息，该第一信息用于指示第一算力实例，该第一算力实例为该至少一个算力实例中的算力实例；
该处理单元901，还用于基于该第一信息执行该第一算力实例。
在一种可能的实现方式中，该第一消息还包括第二配置信息，其中，该第二配置信息包括至少一个算力资源的配置信息，该至少一个算力资源关联于该至少一个算力实例。
在一种可能的实现方式中，该第一信息包括该第一算力实例的标识和/或该第一算力实例对应的算力资源信息的标识；
该处理单元901，用于该第一信息包括：
该处理单元901，用于控制该收发单元902接收该第一信息，该第一信息承载于L1控制信息或L2控制信息或L3消息中。
在一种可能的实现方式中，
该收发单元902，还用于接收参考信号RS；
该收发单元902，还用于发送该RS对应的测量结果。
在一种可能的实现方式中，
该第一算力实例为默认算力实例；和/或，
该第一算力实例对应的算力资源信息为默认算力资源信息。
在一种可能的实现方式中，该处理单元901，用于获取该第一信息包括：
在满足以下至少一项时，该处理单元901，用于生成该第一信息，包括：
第一定时器超时，其中，该第一定时器的配置信息包含于该第一消息；或，
该终端设备的电量低于第一阈值；或，
该终端设备进入无线资源控制空闲RRC idle态。
在一种可能的实现方式中，
该收发单元902，还用于向网络设备发送第一指示信息，该第一指示信息用于指示该终端设备的算力状态。
在一种可能的实现方式中，
该收发单元902，还用于向该网络设备发送第二指示信息，该第二指示信息用于指示该终端设备期望的算力资源信息和/或算力实例。
在一种可能的实现方式中，
该处理单元901在基于该第一信息执行该第一算力实例时，该收发单元902，还用于发送第三指示信息，该第三指示信息用于指示该终端设备的算力调整信息；
该收发单元902，还用于接收来自该网络设备的第三配置信息，该第三配置信息用于更新该第一配置信息和/或该第三配置信息用于更新该第二配置信息。
在一种可能的实现方式中，该至少一个算力实例中的算力实例包括以下至少一项：
执行时长信息、算力大小信息、模型信息、拆分学习位置、推理切分点位置或联邦学习本地迭代次数。
在一种可能的实现方式中，该至少一个算力资源信息包括以下至少一项：
CPU类型信息、存储信息、执行时长信息、内存信息或电量信息。
在一种可能的实现方式中，该至少一个算力资源关联于该至少一个算力实例包括：
该至少一个算力资源中的每一个算力资源与该至少一个算力实例中的每一个算力实例一一对应；
或，
该至少一个算力资源中的其中一个算力资源对应于该至少一个算力实例中的一个或多个算力实例。
在一种可能的实现方式中，该第一指示信息包括以下至少一项：
CPU类型信息、存储信息、内存信息、电量信息、算力利用率信息。
在一种可能的实现方式中，该第三指示信息包括：
内存信息、电量信息、算力利用率信息。
一种可能的实现方式中，当该装置900为用于执行前述任一实施例中网络设备所执行的方法时，该装置900包括处理单元901和收发单元902；
该处理单元901，用于生成第一消息，该第一消息包括第一配置信息，其中，该第一配置信息包括至少一个算力实例的配置信息；
该收发单元902，用于发送该第一消息。
在一种可能的实现方式中，该第一消息还包括第二配置信息，其中，该第二配置信息包括至少一个算力资源的配置信息，该至少一个算力资源关联于该至少一个算力实例。
在一种可能的实现方式中，
该收发单元902，还用于发送第一信息，该第一信息用于指示第一算力实例，该第一算力实例为该至少一个算力实例中的算力实例，该第一信息包括该第一算力实例的标识和/或该第一算力实例对应的算力资源信息的标识；
其中，该第一信息承载于L1控制信息或L2控制信息或L3消息中。
在一种可能的实现方式中，
该收发单元902，还用于发送参考信号RS；
该收发单元902，还用于接收该RS对应的测量结果；
该处理单元901，还用于基于该RS对应的测量结果生成该第一信息。
在一种可能的实现方式中，
该收发单元902，还用于接收来自该终端设备的第一指示信息，该第一指示信息用于指示该终端设备的算力状态；
该处理单元901，还用于基于该第一指示信息确定该第一信息。
在一种可能的实现方式中，
该收发单元902，还用于接收来自该终端设备的第二指示信息，该第二指示信息用于指示该终端设备期望的算力资源信息和/或算力实例；
该处理单元901，还用于基于该第二指示信息确定该第一信息。
在一种可能的实现方式中，
该收发单元902，还用于接收来自该终端设备的第三指示信息，该第三指示信息用于指示该终端设备的算力调整信息；
该处理单元901，还用于基于该第三指示信息发送第三配置信息，该第三配置信息用于更新该第一配置信息和/或该第三配置信息用于更新该第二配置信息。
在一种可能的实现方式中，该至少一个算力实例中的算力实例包括以下至少一项：
执行时长信息、算力大小信息、模型信息、拆分学习位置、推理切分点位置或联邦学习本地迭代次数。
在一种可能的实现方式中，该至少一个算力资源信息包括以下至少一项：
CPU类型信息、存储信息、执行时长信息、内存信息或电量信息。
在一种可能的实现方式中，该至少一个算力资源关联于该至少一个算力实例包括：
该至少一个算力资源中的每一个算力资源与该至少一个算力实例中的每一个算力实例一一对应；
或，
该至少一个算力资源中的其中一个算力资源对应于该至少一个算力实例中的一个或多个算力实例。
在一种可能的实现方式中，该第一指示信息包括以下至少一项：
CPU类型信息、存储信息、内存信息、电量信息、算力利用率信息。
在一种可能的实现方式中，该第三指示信息包括：
内存信息、电量信息、算力利用率信息。
一种可能的实现方式中，当该装置900为用于执行前述任一实施例中终端设备所执行的方法时，该装置900包括处理单元901和收发单元902；
该处理单元901，用于确定算力指示信息；
该收发单元902，用于向网络设备发送算力指示信息；
该收发单元902，还用于接收来自该网络设备的第一消息，该第一消息包括第一配置信息，其中，该第一配置信息用于配置至少一个算力实例。
在一种可能的实现方式中，
该收发单元902，还用于接收来自该网络设备的第二消息，该第二消息包括初始配置信息，其中，该初始配置信息用于配置至少一个算力实例。
在一种可能的实现方式中，
该收发单元902，还用于发送该第一消息的响应消息或确认消息。
在一种可能的实现方式中，该算力指示信息包括第一指示信息，该第一指示信息用于指示该终端设备的算力状态。
在一种可能的实现方式中，该第一指示信息包括以下至少一项：
CPU类型信息、存储信息、内存信息、电量信息、算力利用率信息。
在一种可能的实现方式中，该算力指示信息包括第二指示信息，该第二指示信息用于指示该终端设备期望的算力资源信息和/或算力实例。
在一种可能的实现方式中，该算力指示信息包括第三指示信息，该第三指示信息用于指示该终端设备的算力调整信息。
在一种可能的实现方式中，该第三指示信息包括：
内存信息、电量信息、算力利用率信息。
在一种可能的实现方式中，该第一消息还包括第二配置信息，其中，该第二配置信息用于配置至少一个算力资源信息，该至少一个算力资源信息关联于该至少一个算力实例。
在一种可能的实现方式中，该至少一个算力资源关联于该至少一个算力实例包括：
该至少一个算力资源中的每一个算力资源与该至少一个算力实例中的每一个算力实例一一对应；
或，
该至少一个算力资源中的其中一个算力资源对应于该至少一个算力实例中的一个或多个算力实例。
在一种可能的实现方式中，该至少一个算力资源信息包括以下至少一项：
CPU类型信息、存储信息、执行时长信息、内存信息或电量信息。
在一种可能的实现方式中，该至少一个算力实例中的算力实例包括以下至少一项：
执行时长信息、算力大小信息、模型信息、拆分学习位置、推理切分点位置或联邦学习本地迭代次数。
一种可能的实现方式中，当该装置900为用于执行前述任一实施例中终端设备所执行的方法时，该装置900包括处理单元901和收发单元902；
该收发单元902，用于接收来自终端设备的算力指示信息；
该处理单元901，用于基于该算力指示信息向该终端设备确定第一消息，该第一消息包括第一配置信息，其中，该第一配置信息用于配置至少一个算力实例；
该收发单元902，还用于发送该第一消息。
在一种可能的实现方式中，
该收发单元902，还用于向该终端设备发送第二消息，该第二消息包括初始配置信息，其中，该初始配置信息用于配置至少一个算力实例。
在一种可能的实现方式中，
该收发单元902，还用于接收来自该终端设备的该第一消息的响应消息或确认消息。
在一种可能的实现方式中，该算力指示信息包括第一指示信息，该第一指示信息用于指示该终端设备的算力状态。
在一种可能的实现方式中，该第一指示信息包括以下至少一项：
CPU类型信息、存储信息、内存信息、电量信息、算力利用率信息。
在一种可能的实现方式中，该算力指示信息包括第二指示信息，该第二指示信息用于指示该终端设备期望的算力资源信息和/或算力实例。
在一种可能的实现方式中，该算力指示信息包括第三指示信息，该第三指示信息用于指示该终端设备的算力调整信息。
在一种可能的实现方式中，该第三指示信息包括：
内存信息、电量信息、算力利用率信息。
在一种可能的实现方式中，该第一消息还包括第二配置信息，其中，该第二配置信息用于配置至少一个算力资源信息，该至少一个算力资源信息关联于该至少一个算力实例。
在一种可能的实现方式中，该至少一个算力资源关联于该至少一个算力实例包括：
该至少一个算力资源中的每一个算力资源与该至少一个算力实例中的每一个算力实例一一对应；
或，
该至少一个算力资源中的其中一个算力资源对应于该至少一个算力实例中的一个或多个算力实例。
在一种可能的实现方式中，该至少一个算力资源信息包括以下至少一项：
CPU类型信息、存储信息、执行时长信息、内存信息或电量信息。
在一种可能的实现方式中，该至少一个算力实例中的算力实例包括以下至少一项：
执行时长信息、算力大小信息、模型信息、拆分学习位置、推理切分点位置或联邦学习本地迭代次数。
需要说明的是，上述通信装置900的单元的信息执行过程等内容，具体可参见本申请前述所示的方法实施例中的叙述，此处不再赘述。
请参阅图10，为本申请提供的通信装置1000的另一种示意性结构图，通信装置1000至少包括输入输出接口1002。其中，通信装置1000可以为芯片或集成电路。
可选的，该通信装置还包括逻辑电路1001。
其中，图9所示收发单元902可以为通信接口，该通信接口可以是图10中的输入输出接口1002，该输入输出接口1002可以包括输入接口和输出接口。或者，该通信接口也可以是收发电路，该收发电路可以包括输入接口电路和输出接口电路。
可选的，输入输出接口1002用于输入第一消息和第一信息；逻辑电路1001用于基于第一信息执行第一算力实例。其中，逻辑电路1001和输入输出接口1002还可以执行前述任一实施例中终端设备执行的其他步骤并实现对应的有益效果，此处不再赘述。
可选的，逻辑电路1001用于生成第一消息；输入输出接口1002用于发送该第一消息。其中，逻辑电路1001和输入输出接口1002还可以执行任一实施例中网络设备执行的其他步骤并实现对应的有益效果，此处不再赘述。
在一种可能的实现方式中，图9所示处理单元901可以为图10中的逻辑电路1001。
可选的，逻辑电路1001可以是一个处理装置，处理装置的功能可以部分或全部通过软件实现。其中，处理装置的功能可以部分或全部通过软件实现。
可选的，处理装置可以包括存储器和处理器，其中，存储器用于存储计算机程序，处理器读取并执行存储器中存储的计算机程序，以执行任意一个方法实施例中的相应处理和/或步骤。
可选地，处理装置可以仅包括处理器。用于存储计算机程序的存储器位于处理装置之外，处理器通过电路/电线与存储器连接，以读取并执行存储器中存储的计算机程序。其中，存储器和处理器可以集成在一起，或者也可以是物理上互相独立的。
可选地，该处理装置可以是一个或多个芯片，或一个或多个集成电路。例如，处理装置可以是一个或多个现场可编程门阵列(field-programmable gate array，FPGA)、专用集成芯片(application specific integrated circuit，ASIC)、系统芯片(system on chip，SoC)、中央处理器(central processor unit，CPU)、网络处理器(network processor，NP)、数字信号处理电路(digital signal processor，DSP)、微控制器(micro controller unit，MCU)，可编程控制器(programmable logic device，PLD)或其它集成芯片，或者上述芯片或者处理器的任意组合等。
请参阅图11，为本申请的实施例提供的上述实施例中所涉及的通信装置1100，该通信装置1100具体可以为上述实施例中的作为终端设备的通信装置，图11所示示例为终端设备通过终端设备(或者终端设备中的部件)实现。
其中，该通信装置1100的一种可能的逻辑结构示意图，该通信装置1100可以包括但不限于至少一个处理器1101以及通信端口1102。
进一步可选的，该装置还可以包括存储器1103、总线1104中的至少一个，在本申请的实施例中，该至少一个处理器1101用于对通信装置1100的动作进行控制处理。
此外，处理器1101可以是中央处理器单元，通用处理器，数字信号处理器，专用集成电路，现场可编程门阵列或者其他可编程逻辑器件、晶体管逻辑器件、硬件部件或者其任意组合。其可以实现或执行结合本申请公开内容所描述的各种示例性的逻辑方框，模块和电路。该处理器也可以是实现计算功能的组合，例如包含一个或多个微处理器组合，数字 信号处理器和微处理器的组合等等。所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
需要说明的是，图11所示通信装置1100具体可以用于实现前述方法实施例中终端设备所实现的步骤，并实现终端设备对应的技术效果，图11所示通信装置的具体实现方式，均可以参考前述方法实施例中的叙述，此处不再一一赘述。
请参阅图12，为本申请的实施例提供的上述实施例中所涉及的通信装置的结构示意图，该通信装置具体可以为上述实施例中的作为网络设备的通信装置，图12所示示例为网络设备通过网络设备(或者网络设备中的部件)实现，其中，该通信装置的结构可以参考图12所示的结构。
通信装置包括至少一个处理器1211以及至少一个网络接口1214。进一步可选的，该通信装置还包括至少一个存储器1212、至少一个收发器1213和一个或多个天线1215。处理器1211、存储器1212、收发器1213和网络接口1214相连，例如通过总线相连，在本申请实施例中，该连接可包括各类接口、传输线或总线等，本实施例对此不做限定。天线1215与收发器1213相连。网络接口1214用于使得通信装置通过通信链路，与其它通信设备通信。例如网络接口1214可以包括通信装置与核心网设备之间的网络接口，例如S1接口，网络接口可以包括通信装置和其他通信装置(例如其他网络设备或者核心网设备)之间的网络接口，例如X2或者Xn接口。
处理器1211主要用于对通信协议以及通信数据进行处理，以及对整个通信装置进行控制，执行软件程序，处理软件程序的数据，例如用于支持通信装置执行实施例中所描述的动作。通信装置可以包括基带处理器和中央处理器，基带处理器主要用于对通信协议以及通信数据进行处理，中央处理器主要用于对整个终端设备进行控制，执行软件程序，处理软件程序的数据。图12中的处理器1211可以集成基带处理器和中央处理器的功能，本领域技术人员可以理解，基带处理器和中央处理器也可以是各自独立的处理器，通过总线等技术互联。本领域技术人员可以理解，终端设备可以包括多个基带处理器以适应不同的网络制式，终端设备可以包括多个中央处理器以增强其处理能力，终端设备的各个部件可以通过各种总线连接。该基带处理器也可以表述为基带处理电路或者基带处理芯片。该中央处理器也可以表述为中央处理电路或者中央处理芯片。对通信协议以及通信数据进行处理的功能可以内置在处理器中，也可以以软件程序的形式存储在存储器中，由处理器执行软件程序以实现基带处理功能。
存储器主要用于存储软件程序和数据。存储器1212可以是独立存在，与处理器1211相连。可选的，存储器1212可以和处理器1211集成在一起，例如集成在一个芯片之内。其中，存储器1212能够存储执行本申请实施例的技术方案的程序代码，并由处理器1211来控制执行，被执行的各类计算机程序代码也可被视为是处理器1211的驱动程序。
图12仅示出了一个存储器和一个处理器。在实际的终端设备中，可以存在多个处理器和多个存储器。存储器也可以称为存储介质或者存储设备等。存储器可以为与处理器处于 同一芯片上的存储元件，即片内存储元件，或者为独立的存储元件，本申请实施例对此不做限定。
收发器1213可以用于支持通信装置与终端之间射频信号的接收或者发送，收发器1213可以与天线1215相连。收发器1213包括发射机Tx和接收机Rx。具体地，一个或多个天线1215可以接收射频信号，该收发器1213的接收机Rx用于从天线接收该射频信号，并将射频信号转换为数字基带信号或数字中频信号，并将该数字基带信号或数字中频信号提供给该处理器1211，以便处理器1211对该数字基带信号或数字中频信号做进一步的处理，例如解调处理和译码处理。此外，收发器1213中的发射机Tx还用于从处理器1211接收经过调制的数字基带信号或数字中频信号，并将该经过调制的数字基带信号或数字中频信号转换为射频信号，并通过一个或多个天线1215发送该射频信号。具体地，接收机Rx可以选择性地对射频信号进行一级或多级下混频处理和模数转换处理以得到数字基带信号或数字中频信号，该下混频处理和模数转换处理的先后顺序是可调整的。发射机Tx可以选择性地对经过调制的数字基带信号或数字中频信号时进行一级或多级上混频处理和数模转换处理以得到射频信号，该上混频处理和数模转换处理的先后顺序是可调整的。数字基带信号和数字中频信号可以统称为数字信号。
收发器1213也可以称为收发单元、收发机、收发装置等。可选的，可以将收发单元中用于实现接收功能的器件视为接收单元，将收发单元中用于实现发送功能的器件视为发送单元，即收发单元包括接收单元和发送单元，接收单元也可以称为接收机、输入口、接收电路等，发送单元可以称为发射机、发射器或者发射电路等。
需要说明的是，图12所示通信装置具体可以用于实现前述方法实施例中网络设备所实现的步骤，并实现网络设备对应的技术效果，图12所示通信装置的具体实现方式，均可以参考前述方法实施例中的叙述，此处不再一一赘述。
本申请实施例还提供一种存储一个或多个计算机执行指令的计算机可读存储介质，当计算机执行指令被处理器执行时，该处理器执行如前述实施例中终端设备可能的实现方式所述的方法。
本申请实施例还提供一种存储一个或多个计算机执行指令的计算机可读存储介质，当计算机执行指令被处理器执行时，该处理器执行如前述实施例中网络设备可能的实现方式所述的方法。
本申请实施例还提供一种存储一个或多个计算机的计算机程序产品(或称计算机程序)，当计算机程序产品被该处理器执行时，该处理器执行上述终端设备可能实现方式的方法。
本申请实施例还提供一种存储一个或多个计算机的计算机程序产品，当计算机程序产品被该处理器执行时，该处理器执行上述网络设备可能实现方式的方法。
本申请实施例还提供了一种芯片系统，该芯片系统包括至少一个处理器，用于支持通信装置实现上述通信装置可能的实现方式中所涉及的功能。可选的，所述芯片系统还包括接口电路，所述接口电路为所述至少一个处理器提供程序指令和/或数据。在一种可能的设计中，该芯片系统还可以包括存储器，存储器，用于保存该通信装置必要的程序指令和数 据。该芯片系统，可以由芯片构成，也可以包含芯片和其他分立器件，其中，该通信装置具体可以为前述方法实施例中终端设备。
本申请实施例还提供了一种芯片系统，该芯片系统包括至少一个处理器，用于支持通信装置实现上述通信装置可能的实现方式中所涉及的功能。可选的，所述芯片系统还包括接口电路，所述接口电路为所述至少一个处理器提供程序指令和/或数据。在一种可能的设计中，芯片系统还可以包括存储器，存储器，用于保存该通信装置必要的程序指令和数据。该芯片系统，可以由芯片构成，也可以包含芯片和其他分立器件，其中，该通信装置具体可以为前述方法实施例中网络设备。
本申请实施例还提供了一种通信系统，该网络系统架构包括上述任一实施例中的终端设备和网络设备。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统，装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。

Claims (41)

  1. 一种通信方法，其特征在于，包括：
    第一通信装置接收来自网络设备的第一消息，所述第一消息包括第一配置信息，其中，所述第一配置信息包括至少一个算力实例的配置信息；
    所述第一通信装置获取第一信息，所述第一信息用于指示第一算力实例，所述第一算力实例为所述至少一个算力实例中的算力实例；
    所述第一通信装置基于所述第一信息执行所述第一算力实例。
  2. 根据权利要求1所述的方法，其特征在于，所述第一消息还包括第二配置信息，其中，所述第二配置信息包括至少一个算力资源的配置信息，所述至少一个算力资源关联于所述至少一个算力实例。
  3. 根据权利要求2所述的方法，其特征在于，所述第一信息包括所述第一算力实例的标识和/或所述第一算力实例对应的算力资源信息的标识；
    所述第一通信装置获取所述第一信息包括：
    所述第一通信装置接收所述第一信息，所述第一信息承载于层1控制信息或层2控制信息或层3消息中。
  4. 根据权利要求3所述的方法，其特征在于，在所述第一通信装置接收所述第一信息之前，所述方法还包括：
    所述第一通信装置接收参考信号RS；
    所述第一通信装置发送所述RS对应的测量结果。
  5. 根据权利要求1或2所述的方法，其特征在于，
    所述第一算力实例为默认算力实例；和/或，
    所述第一算力实例对应的算力资源信息为默认算力资源信息。
  6. 根据权利要求5所述的方法，其特征在于，所述第一通信装置获取所述第一信息包括：
    在满足以下至少一项时，所述第一通信装置生成所述第一信息，包括：
    第一定时器超时，其中，所述第一定时器的配置信息包含于所述第一消息；或，
    所述第一通信装置的电量低于第一阈值；或，
    所述第一通信装置进入无线资源控制空闲RRC idle态。
  7. 根据权利要求1至6任一项所述的方法，其特征在于，在所述第一通信装置接收来自网络设备的第一消息之前，所述方法还包括：
    所述第一通信装置向网络设备发送第一指示信息，所述第一指示信息用于指示所述第 一通信装置的算力状态。
  8. 根据权利要求1至7任一项所述的方法，其特征在于，在所述第一通信装置接收来自网络设备的第一消息之前，所述方法还包括：
    所述第一通信装置向所述网络设备发送第二指示信息，所述第二指示信息用于指示所述第一通信装置期望的算力资源信息和/或算力实例。
  9. 根据权利要求1至8任一项所述的方法，其特征在于，所述方法还包括：
    所述第一通信装置基于所述第一信息执行所述第一算力实例时，所述第一通信装置发送第三指示信息，所述第三指示信息用于指示所述第一通信装置的算力调整信息；
    所述第一通信装置接收来自所述网络设备的第三配置信息，所述第三配置信息用于更新所述第一配置信息和/或所述第三配置信息用于更新所述第二配置信息。
  10. 一种通信方法，其特征在于，包括：
    第二通信装置生成第一消息，所述第一消息包括第一配置信息，其中，所述第一配置信息包括至少一个算力实例的配置信息；
    所述第二通信装置发送所述第一消息。
  11. 根据权利要求10所述的方法，其特征在于，所述第一消息还包括第二配置信息，其中，所述第二配置信息包括至少一个算力资源的配置信息，所述至少一个算力资源关联于所述至少一个算力实例。
  12. 根据权利要求11所述的方法，其特征在于，所述方法还包括：
    所述第二通信装置发送第一信息，所述第一信息用于指示第一算力实例，所述第一算力实例为所述至少一个算力实例中的算力实例，所述第一信息包括所述第一算力实例的标识和/或所述第一算力实例对应的算力资源信息的标识；
    其中，所述第一信息承载于层1控制信息或层2控制信息或层3消息中。
  13. 根据权利要求12所述的方法，其特征在于，在所述第二通信装置发送第一信息之前，所述方法还包括：
    所述第二通信装置发送参考信号RS；
    所述第二通信装置接收所述RS对应的测量结果；
    所述第二通信装置基于所述RS对应的测量结果生成所述第一信息。
  14. 根据权利要求12或13所述的方法，其特征在于，在所述第二通信装置发送第一信息之前，所述方法还包括：
    所述第二通信装置接收来自所述终端设备的第一指示信息，所述第一指示信息用于指 示所述终端设备的算力状态；
    所述第二通信装置基于所述第一指示信息确定所述第一信息。
  15. 根据权利要求12或13所述的方法，其特征在于，在所述第二通信装置发送第一信息之前，所述方法还包括：
    所述第二通信装置接收来自所述终端设备的第二指示信息，所述第二指示信息用于指示所述终端设备期望的算力资源信息和/或算力实例；
    所述第二通信装置基于所述第二指示信息确定所述第一信息。
  16. 根据权利要求12或13所述的方法，其特征在于，在所述第二通信装置发送第一信息之后，所述方法还包括：
    所述第二通信装置接收来自所述终端设备的第三指示信息，所述第三指示信息用于指示所述终端设备的算力调整信息；
    所述第二通信装置基于所述第三指示信息发送第三配置信息，所述第三配置信息用于更新所述第一配置信息和/或所述第三配置信息用于更新所述第二配置信息。
  17. 根据权利要求1至16任一项所述的方法，其特征在于，所述至少一个算力实例中的算力实例包括以下至少一项：
    执行时长信息、算力大小信息、模型信息、拆分学习位置、推理切分点位置或联邦学习本地迭代次数。
  18. 根据权利要求2至9、10至17任一项所述的方法，其特征在于，所述至少一个算力资源信息包括以下至少一项：
    中央处理器CPU类型信息、存储信息、执行时长信息、内存信息或电量信息。
  19. 一种通信装置，其特征在于，包括收发单元和处理单元；
    所述收发单元，用于接收来自网络设备的第一消息，所述第一消息包括第一配置信息，其中，所述第一配置信息包括至少一个算力实例的配置信息；
    所述处理单元，用于获取第一信息，所述第一信息用于指示第一算力实例，所述第一算力实例为所述至少一个算力实例中的算力实例；
    所述处理单元，用于基于所述第一信息执行所述第一算力实例。
  20. 根据权利要求19所述的装置，其特征在于，所述第一消息还包括第二配置信息，其中，所述第二配置信息包括至少一个算力资源的配置信息，所述至少一个算力资源关联于所述至少一个算力实例。
  21. 根据权利要求20所述的装置，其特征在于，所述第一信息包括所述第一算力实例 的标识和/或所述第一算力实例对应的算力资源信息的标识；
    所述处理单元，用于获取所述第一信息包括：
    所述处理单元，用于通过所述收发单元接收所述第一信息，所述第一信息承载于层1控制信息或层2控制信息或层3消息中。
  22. 根据权利要求21所述的装置，其特征在于，
    所述收发单元，还用于接收参考信号RS；
    所述收发单元，还用于发送所述RS对应的测量结果。
  23. 根据权利要求19或20所述的装置，其特征在于，
    所述第一算力实例为默认算力实例；和/或，
    所述第一算力实例对应的算力资源信息为默认算力资源信息。
  24. 根据权利要求23所述的装置，其特征在于，所述处理单元，用于获取所述第一信息包括：
    在满足以下至少一项时，所述处理单元，生成所述第一信息，包括：
    第一定时器超时，其中，所述第一定时器的配置信息包含于所述第一消息；或，
    所述终端设备的电量低于第一阈值；或，
    所述终端设备进入无线资源控制空闲RRC idle态。
  25. 根据权利要求19至24任一项所述的装置，其特征在于，
    所述收发单元，还用于向网络设备发送第一指示信息，所述第一指示信息用于指示所述终端设备的算力状态。
  26. 根据权利要求19至25任一项所述的装置，其特征在于，
    所述收发单元，还用于向所述网络设备发送第二指示信息，所述第二指示信息用于指示所述终端设备期望的算力资源信息和/或算力实例。
  27. 根据权利要求19至26任一项所述的装置，其特征在于，
    所述处理单元基于所述第一信息执行所述第一算力实例时，所述收发单元，还用于发送第三指示信息，所述第三指示信息用于指示所述终端设备的算力调整信息；
    所述收发单元，还用于接收来自所述网络设备的第三配置信息，所述第三配置信息用于更新所述第一配置信息和/或所述第三配置信息用于更新所述第二配置信息。
  28. 一种通信装置，其特征在于，包括处理单元和收发单元；
    所述处理单元，用于生成第一消息，所述第一消息包括第一配置信息，其中，所述第一配置信息包括至少一个算力实例的配置信息；
    所述收发单元，用于发送所述第一消息。
  29. 根据权利要求28所述的装置，其特征在于，所述第一消息还包括第二配置信息，其中，所述第二配置信息包括至少一个算力资源的配置信息，所述至少一个算力资源关联于所述至少一个算力实例。
  30. 根据权利要求29所述的装置，其特征在于，
    所述收发单元，还用于发送第一信息，所述第一信息用于指示第一算力实例，所述第一算力实例为所述至少一个算力实例中的算力实例，所述第一信息包括所述第一算力实例的标识和/或所述第一算力实例对应的算力资源信息的标识；
    其中，所述第一信息承载于层1控制信息或层2控制信息或层3消息中。
  31. 根据权利要求30所述的装置，其特征在于，
    所述收发单元，还用于发送参考信号RS；
    所述收发单元，还用于接收所述RS对应的测量结果；
    所述处理单元，还用于基于所述RS对应的测量结果生成所述第一信息。
  32. 根据权利要求28或29所述的装置，其特征在于，
    所述收发单元，还用于接收来自所述终端设备的第一指示信息，所述第一指示信息用于指示所述终端设备的算力状态；
    所述处理单元，还用于基于所述第一指示信息确定所述第一信息。
  33. 根据权利要求28或29所述的装置，其特征在于，
    所述收发单元，还用于接收来自所述终端设备的第二指示信息，所述第二指示信息用于指示所述终端设备期望的算力资源信息和/或算力实例；
    所述处理单元，还用于基于所述第二指示信息确定所述第一信息。
  34. 根据权利要求28或29所述的装置，其特征在于，
    所述收发单元，还用于接收来自所述终端设备的第三指示信息，所述第三指示信息用于指示所述终端设备的算力调整信息；
    所述处理单元，还用于基于所述第三指示信息确定所述第一信息。
  35. 根据权利要求19至34任一项所述的装置，其特征在于，所述至少一个算力实例中的算力实例包括以下至少一项：
    执行时长信息、算力大小信息、模型信息、拆分学习位置、推理切分点位置或联邦学习本地迭代次数。
  36. 根据权利要求20至27、29至35任一项所述的装置，其特征在于，所述至少一个算力资源信息包括以下至少一项：
    CPU类型信息、存储信息、执行时长信息、内存信息或电量信息。
  37. 一种通信装置，其特征在于，包括至少一个逻辑电路和输入输出接口；
    所述输入输出接口用于输入第一消息；
    所述逻辑电路用于执行如权利要求1至9中任一项所述的方法。
  38. 一种通信装置，其特征在于，包括至少一个逻辑电路和输入输出接口；
    所述输入输出接口用于输出第一消息；
    所述逻辑电路用于执行如权利要求10至18中任一项所述的方法。
  39. 一种计算机可读存储介质，其特征在于，所述介质存储有指令，当所述指令被计算机执行时，实现权利要求1至18中任一项所述的方法。
  40. 一种计算机程序产品，其特征在于，包括指令，当所述指令在计算机上运行时，使得计算机执行如权利要求1至18中任一项所述的方法。
  41. 一种通信系统，其特征在于，包括终端设备和网络设备，其中所述终端设备用于执行如权利要求1至9中任一项所述的方法，所述网络设备用于执行如权利要求10至18中任一项所述的方法。
PCT/CN2022/134683 2021-12-24 2022-11-28 一种通信方法及通信装置 WO2023116350A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111603020.4A CN116346593A (zh) 2021-12-24 2021-12-24 一种通信方法及通信装置
CN202111603020.4 2021-12-24

Publications (1)

Publication Number Publication Date
WO2023116350A1 true WO2023116350A1 (zh) 2023-06-29

Family

ID=86879512

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/134683 WO2023116350A1 (zh) 2021-12-24 2022-11-28 一种通信方法及通信装置

Country Status (2)

Country Link
CN (1) CN116346593A (zh)
WO (1) WO2023116350A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104796454A (zh) * 2014-01-22 2015-07-22 福特环球技术公司 用于云计算的车辆专用计算管理系统
CN110851529A (zh) * 2019-11-01 2020-02-28 腾讯科技（深圳）有限公司 算力调度方法及相关设备
CN111919506A (zh) * 2018-06-06 2020-11-10 英特尔公司 汽车边缘计算系统中的交通工具对外界会话和服务连续性
WO2021201933A1 (en) * 2020-04-01 2021-10-07 Intel Corporation Multi-radio access technology traffic management

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104796454A (zh) * 2014-01-22 2015-07-22 福特环球技术公司 用于云计算的车辆专用计算管理系统
CN111919506A (zh) * 2018-06-06 2020-11-10 英特尔公司 汽车边缘计算系统中的交通工具对外界会话和服务连续性
CN110851529A (zh) * 2019-11-01 2020-02-28 腾讯科技（深圳）有限公司 算力调度方法及相关设备
WO2021201933A1 (en) * 2020-04-01 2021-10-07 Intel Corporation Multi-radio access technology traffic management

Also Published As

Publication number Publication date
CN116346593A (zh) 2023-06-27

Similar Documents

Publication Publication Date Title
US11399361B2 (en) V2X sidelink communication
WO2019157945A1 (zh) 一种用于上行授权的方法及装置
US20230067851A1 (en) Communication method and apparatus
WO2020216133A1 (zh) 一种通信方法及设备
US20220022211A1 (en) Communication method and apparatus
WO2021249430A1 (zh) 一种通信方法及相关设备
WO2021258766A1 (zh) 一种配置终端设备的方法及设备
WO2021088006A1 (zh) 通信方法和通信装置
WO2023116350A1 (zh) 一种通信方法及通信装置
WO2022027672A1 (zh) 通信方法和通信装置
WO2020156185A1 (zh) 一种调度请求处理方法及装置
CN108616926A (zh) 一种层2中继中d2d接口的qos控制方法
JP2023537105A (ja) 通信方法および装置
WO2024066947A1 (zh) 一种通信方法及相关设备
WO2023060404A1 (zh) 逻辑信道优先级排序方法、装置、设备及存储介质
WO2023015573A1 (zh) 通信方法、设备及存储介质
WO2023155655A1 (zh) 算力能力感知方法和装置
WO2023065987A1 (zh) 一种传输信息的方法及装置
WO2024067869A1 (zh) 通信方法和通信装置
WO2022089335A1 (zh) 通信方法、装置及系统
WO2023160560A1 (zh) 一种切换方法及相关装置
WO2020221212A1 (zh) 一种资源调度方法及装置
WO2022213328A1 (zh) 侧行链路资源配置的方法和通信装置
WO2023169153A1 (zh) 通信方法和装置
WO2022247552A1 (zh) 一种对齐下行控制信息大小的方法和装置

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: 22909665

Country of ref document: EP

Kind code of ref document: A1