CN-121998125-A - Determination method, device, equipment, medium and product of AI model input information

Abstract

The application discloses a method, a device, equipment, a medium and a product for determining input information of an AI model. The method comprises the steps of receiving first information, determining measurement starting time according to the first information, and reporting second information to second equipment according to the measurement starting time and the first information, wherein the second information is used for generating AI model input information. According to the scheme, the second information for generating the AI model input information is determined according to the measurement starting time and the first information, so that the second information sent by different first devices meets a certain rule, the AI model input information generated by the second devices based on the second information has consistency, and the performance of the AI model is guaranteed.

Inventors

• ZHOU XIAOXING
• ZHAO RUI
• ZHENG SHILEI

Assignees

• 中信科智联科技有限公司

Dates

Publication Date

20260508

Application Date

20241108

Claims (17)

1. 1. A method for determining AI model input information, applied to a first device, the method comprising: Receiving first information; determining a measurement starting time according to the first information; And reporting second information to second equipment according to the measurement starting time and the first information, wherein the second information is used for generating AI model input information.
2. 2. The method of claim 1, wherein the measurement start time comprises at least one of: A time determined based on the symbol in which the reference signal is located; a time at which a sampling point is located adjacent to a time of the first path detected by the first device; A measurement start time configured by the second device; The boundary of a start symbol where a reference signal detected by first equipment is located; the time at which the first sampling point in the path information is located is detected.
3. 3. The method of claim 1, wherein the first information comprises at least one of: First offset information; reference signal configuration information; And the first indication information is used for indicating the determination mode of the measurement starting time.
4. 4. A method according to claim 3, characterized in that determining a measurement start time from the first information comprises at least one of: determining the measurement starting time according to the symbol of the reference signal determined by the reference signal configuration information; determining the measurement starting time according to the first offset information; Selecting target information for determining measurement starting time from the first information according to target parameters, and determining the measurement starting time based on the target information, wherein the target parameters are parameters provided by second equipment, preconfigured parameters or predefined parameters; And determining the measurement starting time by using a measurement starting time determining mode indicated by the first indication information.
5. 5. The method of claim 4, wherein determining the measurement start time using the measurement start time determination indicated by the first indication information comprises at least one of: when the first indication information indicates that the measurement starting time is determined based on the symbol starting time, determining the measurement starting time according to the symbol offset and/or the time slot offset in the reference signal configuration information; When the first indication information indicates that the measurement starting time is determined based on the detected first path, path detection is performed, and the measurement starting time is determined according to the detected time of the first path; Determining a measurement start time according to the first offset information when the first indication information indicates that the measurement start time is determined based on offset information configured by a second device; When the first indication information indicates that the measurement starting time is determined based on the symbol where the reference signal detected by the first device is located, determining the measurement starting time according to the boundary of the starting symbol where the reference signal detected by the first device is located; And when the first indication information indicates that the measurement starting time is determined based on the detection path information, determining the time of the first sampling point in the detection path information as the measurement starting time.
6. 6. The method of claim 1, wherein the second information comprises at least one of: AI model input-related information, wherein in a case where the AI model input-related information includes time information, the time information is offset time information based on a reference time; timestamp information, the timestamp information being associated with a reference signal; Quality indication information.
7. 7. The method of claim 6, wherein the reference time comprises at least one of: Reference time of uplink relative arrival time UL-RTOA; reference time of reference transmission and access point TRP; the subframe boundary where the reference signal is received is locally timed.
8. 8. A method for determining AI model input information, applied to a second device, the method comprising: transmitting first information to a first device, the first information being used to determine a measurement start time; And receiving second information sent by the first device, wherein the second information is generated based on the measurement starting time and the first information, and the second information is used for generating AI model input information.
9. 9. The method of claim 8, wherein the measurement start time comprises at least one of: A time determined based on the symbol in which the reference signal is located; a time at which a sampling point is located adjacent to a time of the first path detected by the first device; A measurement start time configured by the second device; The boundary of a start symbol where a reference signal detected by first equipment is located; the time at which the first sampling point in the path information is located is detected.
10. 10. The method of claim 8, wherein the first information comprises at least one of: First offset information; reference signal configuration information; And the first indication information is used for indicating the determination mode of the measurement starting time.
11. 11. The method of claim 8, wherein the second information comprises at least one of: AI model input-related information, wherein in a case where the AI model input-related information includes time information, the time information is offset time information based on a reference time; timestamp information, the timestamp information being associated with a reference signal; Quality indication information.
12. 12. The method of claim 11, wherein the reference time comprises at least one of: Reference time of UL-RTOA; a reference time for referencing TRP; the subframe boundary where the reference signal is received is locally timed.
13. 13. An AI model input information determination apparatus, characterized by being applied to a first device, comprising: The receiving module is used for receiving the first information; The determining module is used for determining the measurement starting time according to the first information sent by the second equipment; And the sending module is used for reporting second information to the second equipment according to the measurement starting time and the first information, wherein the second information is used for generating AI model input information.
14. 14. An AI-model-input-information determining apparatus, characterized by being applied to a second device, comprising: The device comprises a sending module, a measuring module and a measuring module, wherein the sending module is used for sending first information to first equipment, and the first information is used for determining measurement starting time; And the receiving module is used for receiving second information sent by the first equipment, the second information is generated based on the measurement starting time and the first information, and the second information is used for generating AI model input information.
15. 15. An AI model input information determination apparatus comprising a transceiver, a memory, a processor, and a computer program stored on the memory and running on the processor, wherein the processor, when executing the computer program, implements the AI model input information determination method of any one of claims 1 to 6, or implements the AI model input information determination method of any one of claims 7 to 12.
16. 16. A readable storage medium having stored thereon a program or instructions, which when executed by a processor, implements the AI model input information determination method of any one of claims 1 to 6, or implements the AI model input information determination method of any one of claims 7 to 12.
17. 17. A computer program product comprising computer instructions which, when executed by a processor, implement the AI model input information determination method of any of claims 1-6, or implement the AI model input information determination method of any of claims 7-12.

Description

Determination method, device, equipment, medium and product of AI model input information Technical Field The present application relates to the field of communications technologies, and in particular, to a method, an apparatus, a device, a medium, and a product for determining AI model input information. Background In the research of the artificial intelligence (ARTIFICIAL INTELLIGENCE, AI)/machine learning (MACHINE LEARNING, ML) and air interface combination technology, the AI technology can be used for solving some complex problems in communication, and the purpose of solving the corresponding problems is achieved by deploying AI models with corresponding functions in a terminal or network side equipment. However, at present, the AI model input information provided by each device is not consistent, so that the AI model has poor performance. Disclosure of Invention The application provides a method, a device, equipment, a medium and a product for determining input information of an AI model, which solve the problem of poor performance of the AI model caused by the fact that the input information of the AI model is not consistent at present. In a first aspect, an embodiment of the present application provides a method for determining AI model input information, applied to a first device, where the method includes: Receiving first information; determining a measurement starting time according to the first information; And reporting second information to second equipment according to the measurement starting time and the first information, wherein the second information is used for generating AI model input information. Wherein the measurement start time includes at least one of: A time determined based on the symbol in which the reference signal is located; a time at which a sampling point is located adjacent to a time of the first path detected by the first device; A measurement start time configured by the second device; The boundary of a start symbol where a reference signal detected by first equipment is located; the time at which the first sampling point in the path information is located is detected. Wherein the first information includes at least one of: First offset information; reference signal configuration information; And the first indication information is used for indicating the determination mode of the measurement starting time. Wherein determining a measurement start time based on the first information comprises at least one of: determining the measurement starting time according to the symbol of the reference signal determined by the reference signal configuration information; determining the measurement starting time according to the first offset information; Selecting target information for determining measurement starting time from the first information according to target parameters, and determining the measurement starting time based on the target information, wherein the target parameters are parameters provided by second equipment, preconfigured parameters or predefined parameters; And determining the measurement starting time by using a measurement starting time determining mode indicated by the first indication information. Wherein the measurement start time determining method indicated by the first indication information is used for determining the measurement start time, and the method comprises at least one of the following steps: when the first indication information indicates that the measurement starting time is determined based on the symbol starting time, determining the measurement starting time according to the symbol offset and/or the time slot offset in the reference signal configuration information; When the first indication information indicates that the measurement starting time is determined based on the detected first path, path detection is performed, and the measurement starting time is determined according to the detected time of the first path; Determining a measurement start time according to the first offset information when the first indication information indicates that the measurement start time is determined based on offset information configured by a second device; When the first indication information indicates that the measurement starting time is determined based on the symbol where the reference signal detected by the first device is located, determining the measurement starting time according to the boundary of the starting symbol where the reference signal detected by the first device is located; And when the first indication information indicates that the measurement starting time is determined based on the detection path information, determining the time of the first sampling point in the detection path information as the measurement starting time. Wherein the second information includes at least one of: AI model input-related information, wherein in a case where the AI model input-related information includes time information, the time informat