CN-122003930-A - Model selection method, first equipment, second equipment, device and system

Abstract

The disclosure provides a model selection method, a first device, a second device, a device and a system, wherein the method comprises the steps of conducting channel measurement based on a first signal, determining channel measurement data, wherein the first signal is a signal obtained when a sensing signal is received, selecting one second AI model matched with environment information from a plurality of second AI models, wherein each second AI model is used for conducting device positioning or beam management under different environments, and the environment information is the environment information determined based on the channel measurement data. The present disclosure improves reliability of device positioning, beam management, and usability of ISAC techniques.

Inventors

• ZHANG BOYUAN

Assignees

• 北京小米移动软件有限公司

Dates

Publication Date

20260508

Application Date

20240906

Claims (20)

1. A method of model selection, the method performed by a first device, comprising: Channel measurement is carried out based on a first signal, and channel measurement data is determined, wherein the first signal is a signal obtained when a sensing signal is received; Selecting one of a plurality of second artificial intelligence AI models, wherein each of the second AI models is used for device positioning or beam management in a different environment, and the environment information is determined based on the channel measurement data.
2. The method according to claim 1, wherein the method further comprises: And inputting the channel measurement data into a first AI model to acquire the environment information output by the first AI model.
3. The method according to claim 2, wherein the method further comprises: collecting sample channel measurement data corresponding to different environmental information; Inputting the sample channel measurement data into an initial AI model to obtain estimated environment information output by the initial AI model; Determining a loss function based on the difference between the estimated environmental information and the real environmental information; and training the initial AI model based on the loss function until the training is stopped when a stopping condition is met, so as to obtain the first AI model.
4. A method according to claim 3, wherein the stop condition comprises at least one of: The training cycle number is reached; The loss function is reduced to be within a fault tolerance range; The accuracy of the AI model after at least one training round reaches a first value.
5. The method according to any one of claims 2-4, further comprising: transmitting the environmental information to a second device; And receiving indication information sent by the second equipment, wherein the indication information is used for indicating the identification of the second AI model matched with the environment information.
6. The method according to claim 1, wherein the method further comprises: Transmitting the channel measurement data to a second device; And receiving indication information sent by the second equipment, wherein the indication information is used for indicating the identification of the second AI model matched with the environment information.
7. The method of claim 5 or 6, wherein said selecting one of the plurality of second artificial intelligence AI models that matches environmental information comprises: And selecting the second AI model indicated by the indication information from a plurality of second AI models.
8. The method of any of claims 2-4, wherein selecting one of the plurality of second artificial intelligence AI models that matches environmental information comprises: based on a correspondence between a second AI model and environmental information, one of the second AI models that matches the environmental information is selected among a plurality of the second AI models.
9. The method according to any of claims 1-8, wherein the context information is used to indicate at least one of: An environment type; scene type.
10. A method of model selection, the method performed by a second device, comprising: Selecting one of a plurality of second artificial intelligence AI models matched with environment information, wherein each of the second AI models is used for device positioning or beam management under different environments; And sending indication information to the first equipment, wherein the indication information is used for indicating the identification of the second AI model matched with the environment information.
11. The method according to claim 10, wherein the method further comprises: Receiving the channel measurement data sent by the first equipment; And inputting the channel measurement data into a first AI model to acquire the environment information output by the first AI model.
12. The method of claim 11, wherein the method further comprises: collecting sample channel measurement data corresponding to different environmental information; Inputting the sample channel measurement data into an initial AI model to obtain estimated environment information output by the initial AI model; Determining a loss function based on the difference between the estimated environmental information and the real environmental information; and training the initial AI model based on the loss function until the training is stopped when a stopping condition is met, so as to obtain the first AI model.
13. The method of claim 12, wherein the stop condition comprises at least one of: The training cycle number is reached; The loss function is reduced to be within a fault tolerance range; The accuracy of the AI model after at least one training round reaches a first value.
14. The method according to claim 10, wherein the method further comprises: and receiving the environment information sent by the first equipment.
15. The method according to any of claims 10-14, wherein the context information is used to indicate at least one of: An environment type; scene type.
16. A first device, comprising: The processing module is configured to perform channel measurement based on a first signal and determine channel measurement data, wherein the first signal is a signal obtained when a perception signal is received; The processing module is further configured to select one of a plurality of second artificial intelligence AI models that matches with environment information, wherein each of the second AI models is used for device positioning or beam management in a different environment, wherein the environment information is determined based on the channel measurement data.
17. A second device, comprising: A processing module configured to select one of a plurality of second artificial intelligence AI models that matches environmental information, wherein each of the second AI models is for device location or beam management in a different environment; And the receiving and transmitting module is configured to send indication information to the first equipment, wherein the indication information is used for indicating the identification of the second AI model matched with the environment information.
18. A communication device, characterized in that the device comprises a processor and a memory, the memory having stored therein a computer program, the processor executing the computer program stored in the memory to cause the device to perform the method according to any of claims 1-9 or 10-15.
19. A communication system, comprising: A third device for transmitting a perception signal; A first device configured to implement the method of any of claims 1-9; a second device configured to implement the method of any of claims 10-15.
20. A storage medium storing instructions that, when executed on a communication device, cause the communication device to perform the method of any one of claims 1-9 or 10-15.

Description

Model selection method, first equipment, second equipment, device and system Technical Field The present disclosure relates to the field of communications, and in particular, to a method, a first device, a second device, an apparatus, and a system for model selection. Background Communication awareness Integration (ISAC) is one of the very important research directions in wireless Communication. The sense-of-general integrated technology is beneficial to realizing various application services such as detection, positioning and tracking, environment reconstruction, target imaging, gesture and gesture recognition and the like. Disclosure of Invention In order to improve availability of ISAC technology, embodiments of the present disclosure provide a method, a first device, a second device, an apparatus, and a system for model selection. According to a first aspect of embodiments of the present disclosure, there is provided a model selection method, performed by a first device, comprising: Channel measurement is carried out based on a first signal, and channel measurement data is determined, wherein the first signal is a signal obtained when a sensing signal is received; Selecting one of a plurality of second artificial intelligence AI models matched with environment information, wherein each of the second AI models is used for device positioning or beam management under different environments, and the environment information is based on the channel measurement data. According to a second aspect of embodiments of the present disclosure, there is provided a model selection method, the method performed by a second device, comprising: Selecting one of a plurality of second artificial intelligence AI models matched with environment information, wherein each of the second AI models is used for device positioning or beam management under different environments; And sending indication information to the first equipment, wherein the indication information is used for indicating the identification of the second AI model matched with the environment information. According to a third aspect of embodiments of the present disclosure, there is provided a first apparatus comprising: The processing module is configured to perform channel measurement based on a first signal and determine channel measurement data, wherein the first signal is a signal obtained when a perception signal is received; The processing module is further configured to select one of a plurality of second artificial intelligence AI models that matches with environment information, wherein each of the second AI models is used for device positioning or beam management in a different environment, wherein the environment information is determined based on the channel measurement data. According to a fourth aspect of embodiments of the present disclosure, there is provided a second device comprising: A processing module configured to select one of a plurality of second artificial intelligence AI models that matches environmental information, wherein each of the second AI models is for device location or beam management in a different environment; And the receiving and transmitting module is configured to send indication information to the first equipment, wherein the indication information is used for indicating the identification of the second AI model matched with the environment information. According to a fifth aspect of embodiments of the present disclosure, there is provided a communication apparatus comprising a processor and a memory, the memory having stored therein a computer program, the processor executing the computer program stored in the memory to cause the apparatus to perform the method of any one of the first or second aspects. According to a sixth aspect of embodiments of the present disclosure, there is provided a communication system comprising: A third device for transmitting a perception signal; A first device configured to implement the method of any of the first aspects; A second device configured to implement the method of any of the second aspects. According to a seventh aspect of embodiments of the present disclosure, there is provided a storage medium storing instructions that, when executed on a communication device, cause the communication device to perform the method of any one of the first or second aspects. According to an eighth aspect of embodiments of the present disclosure, there is provided a computer program product comprising a computer program for implementing the method of any one of the first or second aspects when the computer program is executed by a processor. In the embodiment of the disclosure, the first device may select one second AI model matched with the environment information from a plurality of second AI models, and each second AI model may perform device positioning or beam management in different environments, thereby improving reliability of device positioning and beam management and usability of ISAC