Communication method and apparatus used for training machine learning model
Patent Information
- Authority / Receiving Office
- AU · AU
- Patent Type
- Applications
- Current Assignee / Owner
- HUAWEI TECH CO LTD
- Filing Date
- 2023-03-27
- Publication Date
- 2026-07-30
AI Technical Summary
Current communication systems lack efficient mechanisms for determining when to perform machine learning model training, leading to potential resource wastage and inefficiencies.
A communication apparatus and method that includes a transceiver module and processing module, enabling the exchange of information between devices to determine training conditions and control parameters for machine learning models, allowing for controlled and optimized training processes based on network conditions and performance requirements.
This approach ensures that machine learning model training is performed only when necessary, reducing resource wastage and optimizing training processes by leveraging network conditions and performance requirements.
Smart Images
Figure 00000001_0000 
Figure 00000062_0000 
Figure 00000062_0001
Abstract
Description
[00269] When the communication apparatus is configured to implement the first device provided in this embodiment of this application, the communication apparatus may include the first device. In other words, the first device may include the transceiver module 1301 and the processing module 1302. The transceiver module 1301 may be configured to receive first information from the second device, where the first information includes at least one of a first indication and a training condition of an ML model. A value range of the first indication includes a first value and a second value, where the first value indicates the communication apparatus to perform training on the ML model, the second value indicates the communication apparatus not to perform training on the ML model, and a value of the first indication is the first value. The processing module may be configured to perform training on the ML model based on the first information. The communication apparatus includes a model training producer, and the second device includes a model training consumer.
[00270] In a possible implementation, the transceiver module 1301 may further send a training result of the ML model to the second device.
[00271] In a possible implementation, the first information includes the first indication, and the processing module 1302 may further start the training on the ML model. The transceiver module 1301 may be further configured to send a second indication to the second device, where the second indication is used to notify the starting of the training on the ML model, indicates the second device to determine whether to perform training on the ML model, or indicates the second device to determine whether the first device performs training on the ML model.
[00272] In a possible implementation, the transceiver module 1301 may further send a third indication to the second device, where the third indication is used to request a training control parameter of the ML model. The transceiver module 1301 receives the training control parameter of the ML model from the second device, where the training control parameter of the ML model is used by the communication apparatus to perform training on the ML model.
[00273] In a possible implementation, the training control parameter of the ML model includes at least one of the following: an identifier of the ML model; type information of the ML model; iteration times of the training on the ML model; a performance requirement of the ML model; training time of the ML model; or data used to train the ML model.
[00274] In a possible implementation, the data used to train the ML model includes at least one of the following: a data source, an updated network state, and updated training data.
[00275] In a possible implementation, the training condition of the ML model includes at least one of the following: a network load condition, a network coverage condition, and a network performance condition.
[00276] In a possible implementation, the network load condition includes at least one of a PRB utilization threshold and a user connection quantity threshold.
[00277] In a possible implementation, the network coverage condition includes at least one of the following: an RSRP threshold and a coverage rate threshold of the RSRP threshold in an area, an RSRQ threshold and a coverage rate threshold of the RSRQ threshold in the area, or an RSSINR threshold and a coverage rate threshold of the RSSINR threshold in the area.
[00278] In a possible implementation, the network performance condition includes at least one of the following: a handover success rate threshold, a data energy efficiency threshold, or a network slice energy efficiency threshold.
[00279] In a possible implementation, the transceiver module 1301 may further send training state information of the ML model to the second device, where the training state information indicates whether the ML model is trained, or whether the training on the ML model is performed based on at least one of a performance evaluation result of the ML model, the updated network state, and the updated training data.
[00280] In a possible implementation, the transceiver module 1301 may further send second information to the second device, where the second information includes at least one of the following: information indicating a training progress of the ML model; estimated training time of the training on the ML model; training execution duration of the ML model; training beginning time of the ML model; or training end time of the ML model.
[00281] When the communication apparatus is configured to implement the second device provided in this embodiment of this application, the communication apparatus may include the second device. In other words, the second device may include the transceiver module 1301 and the processing module 1302. The processing module 1302 may be configured to determine the first information, where the first information includes at least one of the first indication and the training condition of the ML model. The value range of the first indication includes the first value and the second value, where the first value indicates the first device to perform training on the ML model, the second value indicates the first device not to perform training on the ML model, and the value of the first indication is the first value. The transceiver module 1301 is configured to send the first information to the first device. The first device includes the model training producer, and the second device includes the model training consumer.
[00282] In a possible implementation, the transceiver module 1301 may be further configured to receive the training result of the ML model from the first device.
[00283] In a possible implementation, the first information includes the first indication, and the transceiver module 1301 may be further configured to receive the second indication from the first device. The second indication is used to notify the starting of the training on the ML model, indicates the second device to determine whether to perform training on the ML model, or indicates the second device to determine whether the first device performs training on the ML model.
[00284] In a possible implementation, the transceiver module 1301 may be further configured to receive the third indication from the first device, where the third indication is used to request the training control parameter of the ML model. The transceiver module 1301 may be further configured to send the training control parameter of the ML model to the first device, where the training control parameter of the ML model is used by the first device to perform training on the ML model.
[00285] In a possible implementation, the training control parameter of the ML model includes at least one of the identifier of the ML model, the type information of the ML model, the iteration times of the training on the ML model, the performance requirement of the ML model, the training time of the ML model, and the data used to train the ML model.
[00286] In a possible implementation, the data used to train the ML model includes at least one of the data source, the updated network state, and the updated training data.
[00287] In a possible implementation, the training condition of the ML model includes at least one of the network load condition, the network coverage condition, and the network performance condition.
[00288] In a possible implementation, the network load condition includes at least one of the PRB utilization threshold and the user connection quantity threshold.
[00289] In a possible implementation, the network coverage condition includes at least one of the following: the RSRP threshold and the coverage rate threshold of the RSRP threshold in the area, the RSRQ threshold and the coverage rate threshold of the RSRQ threshold in the area, and the RSSINR threshold and the coverage rate threshold of the RSSINR threshold in the area.
[00290] In a possible implementation, the network performance condition includes at least one of the handover success rate threshold, the data energy efficiency threshold, and the network slice energy efficiency threshold.
[00291] In a possible implementation, the transceiver module 1301 may further receive the training state information of the ML model from the first device, where the training state information indicates whether the ML model is trained, or the training state information indicates whether the ML model is trained based on at least one of the performance evaluation result of the ML model, the updated network state, and the updated training data.
[00292] In a possible implementation, the transceiver module 1301 may be further configured to receive the second information from the first device, where the second information includes at least one of the information indicating the training progress of the ML model, the estimated training time of the training on the ML model, the training execution duration of the ML model, the training beginning time of the ML model, or the training end time of the ML model.
[00293] In a possible implementation, when implementing a function of the first device, the transceiver module 1301 may be further configured to send a new data based machine learning ML training indication to the second device, where the new data based ML training indication indicates whether to perform training based on the updated training data of the ML model.
[00294] Optionally, the transceiver module 1301 may be further configured to receive the training control parameter of the ML model from the second device, where the training control parameter of the ML model is used by the communication apparatus to perform training on the ML model.
[00295] Optionally, the transceiver module 1301 may further send the second information to the second device, where the second information includes at least one of the following: the information indicating the training progress of the ML model; the estimated training time of the training on the ML model; the training execution duration of the ML model; the training beginning time of the ML model; or the training end time of the ML model.
[00296] Optionally, the information indicating the training progress of the ML model includes information indicating that the training on the ML model begins or information indicating that the training on the ML model ends.
[00297] Optionally, the transceiver module 1301 may further send the training state information of the ML model to the second device, where the training state information indicates running of the training on the ML model.
[00298] In a possible implementation, when implementing a function of the second device, the transceiver module 1301 may be further configured to receive the new data based machine learning ML training indication from the first device, where the new data based ML training indication indicates whether to perform training based on the updated training data of the ML model.
[00299] Optionally, the transceiver module 1301 may be further configured to send the training control parameter of the ML model to the first device, where the training control parameter of the ML model is used by the communication apparatus to perform training on the ML model.
[00300] Optionally, the transceiver module 1301 may be further configured to receive the second information from the first device, where the second information includes at least one of the following: the information indicating the training progress of the ML model; the estimated training time of the training on the ML model; the training execution duration of the ML model; the training beginning time of the ML model; or the training end time of the ML model.
[00301] Optionally, the information indicating the training progress of the ML model includes the information indicating that the training on the ML model begins or the information indicating that the training on the ML model ends.
[00302] Optionally, the transceiver module 1301 may be further configured to receive the training state information of the ML model from the first device, where the training state information indicates the running of the training on the ML model.
[00303] Based on the foregoing embodiments, an embodiment of this application further provides a communication apparatus. The device is configured to implement the communication method for machine learning model training in the foregoing figures. Refer to FIG. 14. A communication apparatus 1400 may include at least one of a transceiver 1401, a processor 1402, and a memory 1403. The transceiver 1401, the processor 1402, and the memory 1403 are connected to each other.
[00304] Optionally, the transceiver 1401, the processor 1402, and the memory 1403 are connected to each other via a bus 1404. The bus 1404 may be a peripheral component interconnect (peripheral component interconnect, PCI) bus, an extended industry standard architecture (extended industry standard architecture, EISA) bus, or the like. The bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of indication, the bus is represented by using only one bold line in FIG. 14. However, it does not indicate that there is only one bus or only one type of bus.
[00305] The transceiver 1401 is configured to receive and send data, to implement communication with another device. For example, the transceiver 1401 may be configured to perform a function of the transceiver module 1301.
[00306] Optionally, the transceiver may include a communication interface. The communication interface may be used for communication of the communication apparatus 1400. For example, the communication interface may be configured to implement, in a wired manner, a function of the transceiver module 1301 shown above.
[00307] The processor 1402 is configured to implement the communication method for machine learning model training in the foregoing figures. For details, refer to descriptions in the foregoing embodiments. For example, the processor 1402 may be configured to perform a function of the processing module 1302.
[00308] The memory 1403 is configured to store program instructions and the like. Specifically, the program instructions may include program code, and the program code includes computer operation instructions. The memory 1403 may include a random access memory (random access memory, RAM), or may further include a non-volatile memory (non-volatile memory), for example, at least one magnetic disk memory. The processor 1402 executes the program instructions stored in the memory 1403, to implement the foregoing function, and implement the communication method for machine learning model training provided in the foregoing embodiments.
[00309] It should be understood that at least one of the communication module 1301 and the transceiver 1401 shown above may be configured to perform an action of sending information, a notification, or a message by the first device to the second device, or perform an action of receiving information, a notification, or a message by the second device from the first device, for example, perform any one of S201, S204, S205, S303, and S304. At least one of the communication module 1301 and the transceiver 1401 may be further configured to perform an action of sending information, a notification, or a message by the second device to the first device, or configured to perform an action of receiving information, a notification, or a message by the first device from the second device, for example, perform any one of S102, S202, and S301.
[00310] At least one of the processing module 1302 and the processor 1402 may be configured to perform a processing action of the first device or the second device. For example, the processing action of the first device includes S103, S203, and S302. The processing actions of the first device and the second device may further include triggering training on an ML model, generating information, a notification, or a message sent by at least one of the communication module 1301 and the transceiver 1401, or processing information, a notification, or a message received by at least one of the communication module 1301 and the transceiver 1401.
[00311] It should be further understood that in steps performed by at least one of the transceiver module 1301, the transceiver 1401, the processing module 1302, and the processor 1402, for related technical terms, nouns, action implementations, and the like, refer to descriptions of corresponding technical terms, nouns, and action implementations in FIG. 6 to FIG. 9 in the method embodiments of this application. For example, in an action of sending the second indication performed by the communication module 1301 and the transceiver 1401, for a meaning and a function of the second indication, refer to descriptions of S201 in FIG. 7 in this application. For another example, for an execution manner of performing training on the ML model based on the first information by at least one of the processing module 1302 and the processor 1402, refer to descriptions of S103 shown in FIG. 6, S203 shown in FIG. 7, and S302 shown in FIG. 8 in this application. No more examples are provided.
[00312] Based on the foregoing embodiments, an embodiment of this application further provides a communication method for machine learning model training. The method is implemented by a first device and a second device. The second device may be configured to send first information to the first device, and the first device may be configured to receive the first information from the second device, and perform training on an ML model based on the first information. For details of the method, refer to an implementation in this application.
[00313] Based on the foregoing embodiments, an embodiment of this application further provides a system. The system may include the foregoing first device and second device.
[00314] Based on the foregoing embodiments, an embodiment of this application further provides a computer program. When the computer program runs on a computer, the computer is enabled to perform the communication method for machine learning model training provided in the foregoing embodiments.
[00315] Based on the foregoing embodiments, an embodiment of this application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program. When the computer program is executed by a computer, the computer is enabled to perform the communication method for machine learning model training provided in the foregoing embodiments.
[00316] Based on the foregoing embodiments, an embodiment of this application further provides a chip. The chip is configured to read a computer program stored in a memory, to implement the communication method for machine learning model training provided in the foregoing embodiments. The chip may include a processor.
[00317] Based on the foregoing embodiments, an embodiment of this application provides a chip system. The chip system includes a processor, configured to support a computer apparatus in implementing a function related to at least one of the first device and the second device in the foregoing embodiments. In a possible design, the chip system further includes a memory, and the memory is configured to store a program and data that are necessary for the computer apparatus. The chip system may include a chip, or may include a chip and another discrete component.
[00318] In conclusion, an embodiment of this application provides a communication method for machine learning model training. In the method, a first device (for example, a model training producer) may train an ML model based on first information from a second device (for example, a model training consumer). The first information includes at least one of a first indication and a condition for starting the training on the ML model. Therefore, the training on the ML model performed by the first device is determined by the second device, or is based on the condition for starting the training on the ML model indicated by the second device. Therefore, a case in which the first device starts the training on the ML model when the training on the ML model does not need to be performed is avoided, so that a waste of resources is reduced.
[00319] A person skilled in the art should understand that embodiments of this application may be provided as a method, a system, or a computer program product. Therefore, this application may use a form of a hardware-only embodiment, a software-only embodiment, or an embodiment with a combination of software and hardware. In addition, this application may use a form of a computer program product implemented on one or more computer-usable storage media (including but not limited to a disk memory, a CD-ROM, an optical memory, and the like) that include computer-usable program code.
[00320] This application is described with reference to the flowcharts and / or block diagrams of the method, the device (system), and the computer program product according to embodiments of this application. It should be understood that computer program instructions may be used to implement each process and / or each block in the flowcharts and / or the block diagrams and a combination of a process and / or a block in the flowcharts and / or the block diagrams. These computer program instructions may be provided for a general-purpose computer, a dedicated computer, an embedded processor, or a processor of any other programmable data processing device to generate a machine, so that the instructions executed by a computer or a processor of any other programmable data processing device generate an apparatus for implementing a specific function in one or more processes in the flowcharts and / or in one or more blocks in the block diagrams.
[00321] These computer program instructions may be stored in a computer-readable memory that can indicate the computer or any other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate an artifact that includes an instruction apparatus. The instruction apparatus implements a specific function in one or more processes in the flowcharts and / or in one or more blocks in the block diagrams.
[00322] The computer program instructions may alternatively be loaded onto a computer or another programmable data processing device, so that a series of operations and steps are performed on the computer or another programmable device, to generate computer-implemented processing. Therefore, the instructions executed on the computer or the another programmable device provide steps for implementing a specific function in one or more procedures in the flowcharts and / or in one or more blocks in the block diagrams.
[00323] It is clear that a person skilled in the art can make various modifications and variations to embodiments of this application without departing from the scope of embodiments of this application. This application is intended to cover these modifications and variations provided that they fall within the scope of protection defined by the following claims and their equivalent technologies.
[00324] In this application, "a plurality of means two or more than two. "And / or" describes an association relationship between associated objects, and represents that three relationships may exist. For example, A and / or B may represent the following cases: Only A exists, both A and B exist, and only B exists, where A and B may be singular or plural. In the text descriptions of this 5 application, the character " / " generally indicates an "or" relationship between the associated objects. In a formula in this application, the character " / " indicates a "division" relationship between the associated objects. "Including at least one of A, B, or C" may represent the following cases: including A, including B, including C, including A and B, including A and C, including B and C, and including A, B, and C. 10
[00325] It may be understood that various numbers in embodiments of this application are merely used for differentiation for ease of description, and are not used to limit the scope of embodiments of this application. The sequence numbers of the foregoing processes do not mean execution sequences, and the execution sequences of the processes should be determined based on functions and internal logic of the processes. 15
Claims
1. A communication method for machine learning model training, comprising:receiving, by a first device, first information from a second device, wherein the first information comprises at least one of a first indication and a training condition of a machine learning ML model; a value range of the first indication comprises a first value and a second value, wherein the first value indicates the first device to perform training on the ML model, and the second value indicates the first device not to perform training on the ML model; and a value of the first indication is the first value; andperforming, by the first device, training on the ML model based on the first information.
2. The method according to claim 1, wherein the first information comprises the first indication, and the method further comprises:starting, by the first device, the training on the ML model; andsending, by the first device, a second indication to the second device, wherein the second indication is used to notify the starting of the training on the ML model.
3. The method according to claim 1 or 2, wherein the method further comprises:sending, by the first device, a third indication to the second device, wherein the third indication is used to request a training control parameter of the ML model; andreceiving, by the first device, the training control parameter of the ML model from the second device, wherein the training control parameter of the ML model is used by the first device to perform training on the ML model.
4. The method according to claim 3, wherein the training control parameter of the ML model comprises at least one of the following:an identifier of the ML model;type information of the ML model;iteration times of the training on the ML model;a performance requirement of the ML model;training time of the ML model; ordata used to train the ML model.
5. The method according to claim 4, wherein the data used to train the ML model comprises at least one of the following: a data source, an updated network state, and updated training data.
6. The method according to any one of claims 1 to 5, wherein the training condition of the ML model comprises at least one of the following: a network load condition, a network coverage condition, and a network performance condition.
7. The method according to claim 6, wherein the network load condition comprises at least one of the following:a physical resource block PRB utilization threshold; ora user connection quantity threshold.
8. The method according to claim 6 or 7, wherein the network coverage condition comprises at least one of the following:a reference signal received power RSRP threshold and a coverage rate threshold of the RSRP threshold in an area;a reference signal received quality RSRQ threshold and a coverage rate threshold of the RSRQ threshold in an area; ora reference signal signal to interference plus noise ratio RSSINR threshold and a coverage rate threshold of the RSSINR threshold in an area.
9. The method according to any one of claims 6 to 8, wherein the network performance condition comprises at least one of the following:a handover success rate threshold;a data energy efficiency threshold; ora network slice energy efficiency threshold.
10. The method according to any one of claims 1 to 9, wherein the method further comprises: sending, by the first device, training state information of the ML model to the second device, wherein the training state information indicates:whether the ML model has been trained; orwhether the ML model is trained based on at least one of a performance evaluation result of the ML model, the updated network state, and the updated training data.
11. The method according to any one of claims 1 to 10, wherein the method further comprises: sending, by the first device, second information to the second device, wherein the second information comprises at least one of the following:information indicating a training progress of the ML model;estimated training time of the training on the ML model;training execution duration of the ML model;training beginning time of the ML model; ortraining end time of the ML model.
12. A communication method for machine learning model training, comprising:determining, by a second device, first information, wherein the first information comprises at least one of a first indication and a training condition of a machine learning ML model; a value range of the first indication comprises a first value and a second value, wherein the first valueindicates a first device to perform training on the ML model, and the second value indicates the first device not to perform training on the ML model; and a value of the first indication is the first value; andsending, by the second device, the first information to the first device.
13. The method according to claim 12, wherein the first information comprises the first indication, and the method further comprises:receiving, by the second device, a second indication from the first device, wherein the second indication is used to notify starting of the training on the ML model.
14. The method according to claim 12 or 13, wherein the method further comprises:receiving, by the second device, a third indication from the first device, wherein the third indication is used to request a training control parameter of the ML model; andsending, by the second device, the training control parameter of the ML model to the first device, wherein the training control parameter of the ML model is used by the first device to perform training on the ML model.
15. The method according to claim 14, wherein the training control parameter of the ML model comprises at least one of the following:an identifier of the ML model;type information of the ML model;iteration times of the training on the ML model;a performance requirement of the ML model;training time of the ML model; ordata used to train the ML model.
16. The method according to claim 15, wherein the data used to train the ML model comprises at least one of the following: a data source, an updated network state, and updated training data.
17. The method according to any one of claims 12 to 16, wherein the training condition of the ML model comprises at least one of the following: a network load condition, a network coverage condition, and a network performance condition.
18. The method according to claim 17, wherein the network load condition comprises at least one of the following:a physical resource block PRB utilization threshold; ora user connection quantity threshold.
19. The method according to claim 17 or 18, wherein the network coverage condition comprises at least one of the following:a reference signal received power RSRP threshold and a coverage rate threshold of the RSRP threshold in an area;a reference signal received quality RSRQ threshold and a coverage rate threshold of the RSRQ threshold in an area; ora reference signal signal to interference plus noise ratio RSSINR threshold and a coverage rate threshold of the RSSINR threshold in an area.
20. The method according to any one of claims 17 to 19, wherein the network performance condition comprises at least one of the following:a handover success rate;data energy efficiency; ornetwork slice energy efficiency.
21. The method according to any one of claims 12 to 20, wherein the method further comprises:receiving, by the second device, training state information of the ML model from the first device, wherein the training state information indicates:whether the ML model has been trained; orwhether the ML model is trained based on at least one of a performance evaluation result of the ML model, the updated network state, and the updated training data.
22. The method according to any one of claims 12 to 21, wherein the method further comprises:receiving, by the second device, second information from the first device, wherein the second information comprises at least one of the following:information indicating a training progress of the ML model;estimated training time of the training on the ML model;training execution duration of the ML model;training beginning time of the ML model; ortraining end time of the ML model.
23. A first device for machine learning model training, comprising:a transceiver module, configured to receive first information from a second device, wherein the first information comprises at least one of a first indication and a training condition of a machine learning ML model; a value range of the first indication comprises a first value and a second value, wherein the first value indicates the first device to perform training on the ML model, and the second value indicates the first device not to perform training on the ML model; and a value of the first indication is the first value; anda processing module, configured to perform training on the ML model based on the first information.
24. The first device according to claim 23, wherein the first information comprises the firstindication, and the processing module is further configured to:start the training on the ML model; andthe transceiver module is further configured to:send a second indication to the second device, wherein the second indication is used to notify the starting of the training on the ML model.
25. The first device according to claim 23 or 24, wherein the transceiver module is further configured to:send a third indication to the second device, wherein the third indication is used to request a training control parameter of the ML model; andreceive the training control parameter of the ML model from the second device, wherein the training control parameter of the ML model is used by the first device to perform training on the ML model.
26. The first device according to claim 25, wherein the training control parameter of the ML model comprises at least one of the following:an identifier of the ML model;type information of the ML model;iteration times of the training on the ML model;a performance requirement of the ML model;training time of the ML model; ordata used to train the ML model.
27. The first device according to claim 26, wherein the data used to train the ML model comprises at least one of the following: a data source, an updated network state, and updated training data.
28. The first device according to any one of claims 23 to 27, wherein the training condition of the ML model comprises at least one of the following: a network load condition, a network coverage condition, and a network performance condition.
29. The first device according to claim 28, wherein the network load condition comprises at least one of the following:a physical resource block PRB utilization threshold; ora user connection quantity threshold.
30. The first device according to claim 28 or 29, wherein the network coverage condition comprises at least one of the following:a reference signal received power RSRP threshold and a coverage rate threshold of the RSRP threshold in an area;a reference signal received quality RSRQ threshold and a coverage rate threshold of theRSRQ threshold in an area; ora reference signal signal to interference plus noise ratio RSSINR threshold and a coverage rate threshold of the RSSINR threshold in an area.
31. The first device according to any one of claims 28 to 30, wherein the network performance condition comprises at least one of the following:a handover success rate threshold;a data energy efficiency threshold; ora network slice energy efficiency threshold.
32. The first device according to any one of claims 23 to 31, wherein the transceiver module is further configured to:send training state information of the ML model to the second device, wherein the training state information indicates:whether the ML model has been trained; orwhether the ML model is trained based on at least one of a performance evaluation result of the ML model, the updated network state, and the updated training data.
33. The first device according to any one of claims 23 to 32, wherein the transceiver module is further configured to:send second information to the second device, wherein the second information comprises at least one of the following:information indicating a training progress of the ML model;estimated training time of the training on the ML model;training execution duration of the ML model;training beginning time of the ML model; ortraining end time of the ML model.
34. A second device for machine learning model training, comprising:a processing module, configured to determine first information, wherein the first information comprises at least one of a first indication and a training condition of a machine learning ML model; a value range of the first indication comprises a first value and a second value, wherein the first value indicates the first device to perform training on the ML model, and the second value indicates the first device not to perform training on the ML model; and a value of the first indication is the first value; anda transceiver module, configured to send the first information to the first device.
35. The second device according to claim 34, wherein the first information comprises the first indication, and the transceiver module is further configured to:receive a second indication from the first device, wherein the second indication is used tonotify starting of the training on the ML model.
36. The second device according to claim 34 or 35, wherein the transceiver module is further configured to:receive a third indication from the first device, wherein the third indication is used to request a training control parameter of the ML model; andsend the training control parameter of the ML model to the first device, wherein the training control parameter of the ML model is used by the first device to perform training on the ML model.
37. The second device according to claim 36, wherein the training control parameter of the ML model comprises at least one of the following:an identifier of the ML model;type information of the ML model;iteration times of the training on the ML model;a performance requirement of the ML model;training time of the ML model; ordata used to train the ML model.
38. The second device according to claim 37, wherein the data used to train the ML model comprises at least one of the following: a data source, an updated network state, and updated training data.
39. The second device according to any one of claims 34 to 38, wherein the training condition of the ML model comprises at least one of the following: a network load condition, a network coverage condition, and a network performance condition.
40. The second device according to claim 39, wherein the network load condition comprises at least one of the following:a physical resource block PRB utilization threshold; ora user connection quantity threshold.
41. The second device according to claim 39 or 40, wherein the network coverage condition comprises at least one of the following:a reference signal received power RSRP threshold and a coverage rate threshold of the RSRP threshold in an area;a reference signal received quality RSRQ threshold and a coverage rate threshold of the RSRQ threshold in an area; ora reference signal signal to interference plus noise ratio RSSINR threshold and a coverage rate threshold of the RSSINR threshold in an area.
42. The second device according to any one of claims 39 to 41, wherein the network performance condition comprises at least one of the following:a handover success rate;data energy efficiency; ornetwork slice energy efficiency.
43. The second device according to any one of claims 34 to 42, wherein the transceiver module is further configured to:receive training state information of the ML model from the first device, wherein the training state information indicates:whether the ML model has been trained; orwhether the ML model is trained based on at least one of a performance evaluation result of the ML model, the updated network state, and the updated training data.
44. The second device according to any one of claims 34 to 43, wherein the transceiver module is further configured to:receive second information from the first device, wherein the second information comprises at least one of the following:information indicating a training progress of the ML model;estimated training time of the training on the ML model;training execution duration of the ML model;training beginning time of the ML model; ortraining end time of the ML model.
45. A communication method for machine learning model training, comprising:sending, by a first device, a new data based machine learning ML training indication to a second device, wherein the new data based ML training indication indicates whether training is performed based on updated training data of an ML model.
46. The method according to claim 45, wherein the method further comprises:receiving, by the first device, a training control parameter of the ML model from the second device, wherein the training control parameter of the ML model is used by the first device to perform training on the ML model.
47. The method according to claim 45 or 46, wherein the method further comprises:sending, by the first device, second information to the second device, wherein the second information comprises at least one of the following:information indicating a training progress of the ML model;estimated training time of the training on the ML model;training execution duration of the ML model;training beginning time of the ML model; ortraining end time of the ML model.
48. The method according to claim 47, wherein the information indicating the training progress of the ML model comprises information indicating that the training on the ML model begins or information indicating that the training on the ML model is finished.
49. The method according to any one of claims 45 to 48, wherein the method further comprises:sending, by the first device, training state information of the ML model to the second device, wherein the training state information indicates running of the training on the ML model.
50. A communication method for machine learning model training, comprising:receiving, by a second device, a new data based machine learning ML training indication from a first device, wherein the new data based ML training indication indicates whether training is performed based on updated training data of an ML model.
51. The method according to claim 50, wherein the method further comprises:sending, by the second device, the training control parameter of the ML model to the first device, wherein the training control parameter of the ML model is used by the first device to perform training on the ML model.
52. The method according to claim 50 or 51, wherein the method further comprises:receiving, by the second device, second information from the first device, wherein the second information comprises at least one of the following:information indicating a training progress of the ML model;estimated training time of the training on the ML model;training execution duration of the ML model;training beginning time of the ML model; ortraining end time of the ML model.
53. The method according to claim 52, wherein the information indicating the training progress of the ML model comprises information indicating that the training on the ML model begins or information indicating that the training on the ML model is finished.
54. The method according to any one of claims 50 to 53, wherein the method further comprises:receiving, by the second device, training state information of the ML model from the first device, wherein the training state information indicates running of the training on the ML model.
55. A communication apparatus for machine learning model training, comprising:a communication module, configured to send a new data based machine learning ML training indication to a second device, wherein the new data based ML training indication indicates whether training is performed based on updated training data of an ML model.
56. The apparatus according to claim 55, wherein the communication module is furtherconfigured to:receive a training control parameter of the ML model from the second device, wherein the training control parameter of the ML model is used by the communication apparatus to perform training on the ML model.
57. The apparatus according to claim 55 or 56, wherein the communication module is further configured to:send second information to the second device, wherein the second information comprises at least one of the following:information indicating a training progress of the ML model;estimated training time of the training on the ML model;training execution duration of the ML model;training beginning time of the ML model; ortraining end time of the ML model.
58. The apparatus according to claim 57, wherein the information indicating the training progress of the ML model comprises information indicating that the training on the ML model begins or information indicating that the training on the ML model is finished.
59. The apparatus according to any one of claims 55 to 58, wherein the communication module is further configured to:send training state information of the ML model to the second device, wherein the training state information indicates running of the training on the ML model.
60. A communication apparatus for machine learning model training, comprising:a communication module, configured to receive a new data based machine learning ML training indication from a first device, wherein the new data based ML training indication indicates whether training is performed based on updated training data of an ML model.
61. The apparatus according to claim 60, wherein the communication module is further configured to:send a training control parameter of the ML model to the first device, wherein the training control parameter of the ML model is used by the first device to perform training on the ML model.
62. The apparatus according to claim 60 or 61, wherein the communication module is further configured to:receive second information from the first device, wherein the second information comprises at least one of the following:information indicating a training progress of the ML model;estimated training time of the training on the ML model;training execution duration of the ML model;training beginning time of the ML model; ortraining end time of the ML model.
63. The apparatus according to claim 62, wherein the information indicating the training progress of the ML model comprises information indicating that the training on the ML model begins or information indicating that the training on the ML model is finished.
64. The apparatus according to any one of claims 60 to 63, wherein the communication module is further configured to:receive training state information of the ML model from the first device, wherein the training state information indicates running of the training on the ML model.
65. A computer-readable storage medium, wherein the computer-readable storage medium is configured to store a computer program, and when the computer program runs on a computer, the computer is enabled to perform the method according to any one of claims 1 to 11, the method according to any one of claims 12 to 22, the method according to any one of claims 45 to 49, or the method according to any one of claims 50 to 54.
66. A computer program product, wherein when the computer program product runs on a computer, the computer is enabled to perform the method according to any one of claims 1 to 11, the method according to any one of claims 12 to 22, the method according to any one of claims 45 to 49, or the method according to any one of claims 50 to 54.
67. A communication system, comprising the first device according to any one of claims 23 to 33, and the second device according to any one of claims 34 to 44; orcomprising the communication apparatus according to any one of claims 55 to 59 and the communication apparatus according to any one of claims 60 to 64.
68. A communication method, comprising:sending, by a second device, first information to a first device, wherein the first information comprises at least one of a first indication and a training condition of a machine learning ML model; a value range of the first indication comprises a first value and a second value, wherein the first value indicates the first device to perform training on the ML model, and the second value indicates the first device not to perform training on the ML model; and a value of the first indication is the first value; andperforming, by the first device, training on the ML model based on the first information.
69. A communication method, comprising:sending, by a first device, a new data based machine learning ML training indication to a second device, wherein the new data based ML training indication indicates whether training is performed based on updated training data of an ML model; andreceiving, by the second device, the new data based machine learning ML training indicationfrom the first device.
70. A communication apparatus, comprising a processor, configured to execute a computer program or instructions stored in a memory, to implement the method according to any one of claims 1 to 11, the method according to any one of claims 12 to 22, the method according to any 5 one of claims 45 to 49, or the method according to any one of claims 50 to 54.
71. The communication apparatus according to claim 70, further comprising the memory and / or a transceiver, wherein the transceiver is used by the communication apparatus to perform receiving and / or sending.
72. A communication apparatus, configured to perform an action in the method according to 10 any one of claims 1 to 11, or an action in the method according to any one of claims 12 to 22 or claims 45 to 54.
73. A chip, comprising a processor, configured to perform an action in the method according to any one of claims 1 to 11, or an action in the method according to any one of claims 12 to 22 or claims 45 to 54.15