CN-122003911-A - Information processing method and device, terminal equipment and network equipment

Abstract

The embodiment of the application provides an information processing method and device, terminal equipment and network equipment, wherein the method comprises the steps that the terminal equipment determines the number of CSI processing units occupied by first CSI reporting and a time window occupied by the CSI processing units; the first CSI report is an AI/ML-based CSI report.

Inventors

• CHEN WENHONG

Assignees

• OPPO广东移动通信有限公司

Dates

Publication Date

20260508

Application Date

20231011

Claims (20)

1. An information processing method, the method comprising: The terminal equipment determines the number of CSI processing units occupied by first Channel State Information (CSI) reporting and a time window occupied by the CSI processing units, wherein the first CSI reporting is based on AI/ML.
2. The method of claim 1, wherein the terminal device determines a number of CSI processing units occupied by the first CSI report based on one or more of: The first CSI reports the required reasoning times; The information content reported by the first CSI; The first model is used for reporting the first CSI; and the first CSI is reported.
3. The method of claim 2, wherein the determining, by the terminal device, the number of CSI processing units occupied by the first CSI report based on the number of inferences required for the first CSI report, comprises: The number of the CSI processing units occupied by the first CSI report is the product of the reasoning times required by the first CSI report and a first value, and the first value is the number of the CSI processing units required by the first model for carrying out one-time reasoning.
4. The method of claim 3, wherein, And the value of the first value is 1, or the first value is reported to network equipment by the terminal equipment through UE capability information.
5. The method of claim 4, wherein the UE capability information comprises one or more of: The terminal equipment comprises one or more AI/ML models supported by the terminal equipment, wherein each AI/ML model carries out reasoning on the number of CSI processing units which need to be occupied once; The terminal equipment comprises one or more model functions supported by the terminal equipment, wherein the AI/ML model corresponding to each model function performs reasoning on the number of CSI processing units required to be occupied once; The quantity of CSI processing units which are needed to be occupied by one reasoning for the feedback of the CSI information and one reasoning for the feedback of the model performance monitoring result respectively; and the first CSI report is used for CSI information feedback or model performance monitoring result feedback.
6. The method of any of claims 2-5, wherein the information content of the first CSI report comprises one or more of: compressed channel information, positioning information, beam information, and performance monitoring results of the first model.
7. The method according to any of claims 2-6, wherein the terminal device determines, based on the information content of the first CSI report, a number of CSI processing units occupied by the first CSI report, including one or more of: The quantity of the CSI processing units is a second value when the information content reported by the first CSI is positioning information, wherein the second value is a predefined value; The quantity of the CSI processing units is a third value when the information content reported by the first CSI is beam information, wherein the third value is a predefined value; Under the condition that the information content reported by the first CSI is compressed channel information, the number of the CSI processing units is a fourth value, and the fourth value is calculated based on the number of reference signal resources for CSI measurement; And when the information content reported by the first CSI is the performance monitoring result of the first model, the number of the CSI processing units is the number of times of reasoning by the terminal equipment based on the first model in the performance monitoring process, or is 0.
8. The method of any of claims 2-7, wherein the model information of the first model comprises one or more of: the type of neural network to which the first model applies; The number of layers of the neural network applied by the first model; The first model applies the structure of the neural network.
9. The method according to any of claims 2-8, wherein the use of the first CSI report comprises one or more of: the method is used for CSI information feedback; Performance monitoring for the first model; For online training of the first model.
10. The method according to any of claims 2-9, wherein the determining, by the terminal device, the number of CSI processing units occupied by the first CSI report based on the use of the first CSI report, comprises: under the condition that the first CSI is reported and used for CSI information feedback, the number of the CSI processing units is calculated based on the number of reference signal resources used for CSI measurement; Under the condition that the first CSI is reported to be used for performance monitoring of the first model, the quantity of the CSI processing units is the number of times that the terminal equipment performs reasoning based on the first model in the performance monitoring process; And under the condition that the first CSI reports on-line training for the first model, the quantity of the CSI processing units is the maximum quantity of the CSI processing units simultaneously supported by the terminal equipment.
11. The method of claim 1, wherein the first CSI report is used for online training of a first model, the first model is used for performing the first CSI report, the number of CSI processing units occupied by the first CSI report is determined based on a size of a data set used for the online training, or the number of CSI processing units occupied by the first CSI report is a maximum number of CSI processing units simultaneously supported by the terminal device.
12. The method of any of claims 1-11, wherein the determining a time window occupied by the CSI processing unit comprises: And under the condition that the first CSI reports are used for the feedback of the CSI information and/or the feedback of the performance monitoring result of the first model, the time window occupied by the CSI processing unit is determined based on the periodic configuration of the first CSI report, wherein the periodic configuration of the first CSI report is configured by the network equipment.
13. The method of any of claims 1-11, wherein the determining a time window occupied by the CSI processing unit comprises: In the case where the first CSI is used for performance monitoring of the first model and the terminal device does not report the performance monitoring result, The time window starts from a first time domain symbol of a first reference signal resource to K1 time domain symbols after a last time domain symbol, wherein the first reference signal resource is a reference signal resource for channel measurement reported by the first CSI; Or the time window starts from the last time domain symbol carrying the first signaling to last K2 time domain symbols, wherein the first signaling is used for triggering the first CSI to report; and K1 and/or K2 are predefined values.
14. The method of any of claims 1-11, wherein the determining a time window occupied by the CSI processing unit comprises: In case the first CSI reports online training for the first model, The time window starts from the last time domain symbol carrying the first signaling until the terminal equipment completes the updating of the first model based on online training; Or the time window starts from the last time domain symbol carrying a first signaling, until the terminal equipment sends a second CSI report to the network equipment based on the updated first model, wherein the updated first model is obtained based on the online training process, and the first signaling is used for triggering the first CSI report.
15. The method of any one of claims 1-14, wherein the method further comprises: The terminal equipment determines the number of the currently available CSI processing units based on the number of the currently occupied CSI processing units and the maximum number of the CSI processing units simultaneously supported by the terminal equipment; The terminal equipment determines whether to perform the first CSI reporting related CSI measurement and reporting based on the number of the CSI processing units occupied by the first CSI reporting, the time window occupied by the CSI processing units and the number of the currently available CSI processing units.
16. The method of claim 15, wherein the determining, by the terminal device, whether to perform CSI measurement and reporting related to the first CSI report based on a number of CSI processing units occupied by the first CSI report, a time window occupied by the CSI processing units, and the number of currently available CSI processing units comprises: If the number of the CSI processing units occupied by the first CSI reporting does not exceed the number of the currently available CSI processing units in the time window, the terminal equipment performs CSI measurement and reporting related to the first CSI reporting; If the number of the first CSI reports is one, in the time window, if the number of CSI processing units occupied by the first CSI report exceeds the number of currently available CSI processing units, the terminal device determines that CSI measurement and reporting related to the first CSI report are not performed; If the number of the first CSI is more than one, in the time window, if the number of CSI processing units occupied by the first CSI reports exceeds the number of currently available CSI processing units, the terminal device only performs CSI measurement and reporting related to M first CSI reports with highest priority among the first CSI reports; And M is the maximum value of the quantity of the CSI processing units occupied by M first CSI reports with the highest priority in the first CSI reports, wherein the quantity of the CSI processing units occupied by the M first CSI reports does not exceed the quantity of the currently available CSI processing units.
17. The method of any one of claims 1-16, wherein the method further comprises: The terminal equipment determines the number of the currently occupied CSI processing units based on the number of the occupied CSI processing units reported by the first CSI and a time window occupied by the CSI processing units; The terminal equipment determines the number of the currently available CSI processing units based on the number of the currently occupied CSI processing units and the maximum number of the CSI processing units simultaneously supported by the terminal equipment; And the terminal equipment determines whether to perform CSI measurement and reporting related to third CSI reporting based on the number of the currently available CSI processing units, wherein the priority of the third CSI reporting is lower than that of the first CSI reporting, or the third CSI reporting is the CSI reporting triggered after the first CSI reporting.
18. The method of any of claims 1-17, wherein the first CSI report is used to trigger performance monitoring of the first model, the method further comprising: And if the number of the currently available CSI processing units is smaller than the number of the CSI processing units required for performance monitoring of the first model in the time window, the terminal equipment determines not to monitor the performance of the first model.
19. The method of any of claims 1-18, wherein the first CSI report is to trigger online training of the first model, the method further comprising: And if the number of the available CSI processing units is smaller than the number of the CSI processing units required by the online training of the first model in the time window, the terminal equipment determines not to conduct the online training of the first model.
20. The method according to claim 16 or 17, wherein, The priority of the CSI report for triggering the terminal equipment to perform the online training of the first model is higher than that of the CSI report based on the CSI information obtained by the first model; and/or the number of the groups of groups, And the priority of the CSI reporting for the performance monitoring of the first model is higher than that of the CSI reporting based on the CSI information obtained by the first model.

Description

Information processing method and device, terminal equipment and network equipment Technical Field The embodiment of the application relates to the technical field of mobile communication, in particular to an information processing method and device, terminal equipment and network equipment. Background In view of the great success of artificial intelligence (ARTIFICIAL INTELLIGENCE, AI)/machine learning (MACHINE LEARNING, ML) technology in computer vision, natural language processing, etc., the communication field begins to attempt to seek new technical ideas by using AI/ML technology to solve the technical problems limited by the conventional method. The reporting of channel state Information (CHANNEL STATE Information, CSI) based on AI/ML takes into account that the CSI is compressed at the transmitting end by using an encoder in the AI/ML model and is reconstructed at the receiving end by using a decoder of the AI/ML model. The scheme based on AI/ML utilizes the nonlinear fitting capability of the neural network to carry out compression feedback on the CSI, so that the compression efficiency and the feedback precision can be greatly improved. The terminal device may report CSI based on CSI reporting configuration indicated by the network device. The terminal equipment needs to occupy a certain CSI processing unit for carrying out one time of CSI reporting. However, the computing/processing resources of the terminal device are limited, and there is no clear method at present how to determine the CSI processing unit occupied by the CSI reporting based on the AI/ML model according to the computing/processing complexity, so that the processing capability of the terminal device is utilized to the maximum in the computing capability range of the terminal device for CSI reporting. Disclosure of Invention The embodiment of the application provides an information processing method and device, terminal equipment and network equipment. In a first aspect, an information processing method provided by an embodiment of the present application includes: the terminal equipment determines the quantity of CSI processing units occupied by first CSI reporting and a time window occupied by the CSI processing units, wherein the first CSI reporting is based on AI/ML. In a second aspect, an information processing method provided by an embodiment of the present application includes: The network equipment determines the number of CSI processing units occupied by first CSI reporting and a time window occupied by the CSI processing units, wherein the first CSI reporting is based on AI/ML. In a third aspect, an information processing apparatus provided in an embodiment of the present application is applied to a terminal device, and includes: The system comprises a first determining unit, a second determining unit and a first judging unit, wherein the first determining unit is configured to determine the number of CSI processing units occupied by first Channel State Information (CSI) reporting and a time window occupied by the CSI processing units, and the first CSI reporting is based on AI/ML (advanced technology/media line) reporting. In a fourth aspect, an information processing apparatus provided by an embodiment of the present application is applied to a network device, and includes: The system comprises a first determining unit, a second determining unit and a first reporting unit, wherein the first determining unit is configured to determine the number of CSI processing units occupied by first Channel State Information (CSI) reporting and a time window occupied by the CSI processing units, and the first CSI reporting is based on AI/ML (advanced technology/media line) reporting. In a fifth aspect, an embodiment of the present application provides a terminal device, where the terminal device includes a processor and a memory. The memory is configured to store computer executable instructions, and the processor is coupled to the memory, and configured to implement the information processing method of the first aspect by executing the computer executable instructions. In a sixth aspect, a network device provided by an embodiment of the present application includes a processor and a memory. The memory is configured to store computer executable instructions, and the processor is coupled to the memory, and configured to implement the information processing method of the second aspect by executing the computer executable instructions. In a seventh aspect, an embodiment of the present application provides a chip for implementing the information processing method of the first aspect or the second aspect. Specifically, the chip includes a processor for calling and running a computer program from a memory, so that a device mounted with the chip performs the information processing method of the first aspect or the second aspect. In an eighth aspect, an embodiment of the present application provides a computer readable storage medium storing