CN-122002363-A - Measurement reporting method and user equipment

Abstract

The present disclosure provides a measurement reporting method and a user equipment. The measurement report method comprises the steps that User Equipment (UE) receives a measurement configuration Radio Resource Control (RRC) message which is sent by a network side and contains Radio Resource Management (RRM) measurement used for assisting an artificial intelligent AI/Machine Learning (ML) model, the received measurement configuration is stored in one UE variable, and model-assisted measurement prediction, evaluation and reporting processes are executed based on the stored measurement configuration, wherein the measurement report process is triggered if the time difference between the occurrence time of one predicted measurement event and the occurrence time of the same measurement event in a predicted measurement report sent to the network side last time is larger than a first threshold value in the measurement configuration and the measurement event is associated to the same cell.

Inventors

• CHANG NINGJUAN
• LIU RENMAO

Assignees

• 夏普株式会社

Dates

Publication Date

20260508

Application Date

20241107

Claims (10)

1. 1. A measurement reporting method performed by a user equipment UE, comprising: The User Equipment (UE) receives a measurement configuration Radio Resource Control (RRC) message which is sent by a network side and contains Radio Resource Management (RRM) measurement for assisting an Artificial Intelligence (AI)/Machine Learning (ML) model; in the measurement configuration, one or more of the following information is included: first information indicating whether the type of the RRM measurement model is direct or indirect; second information for enabling a mechanism for determining whether to trigger a measurement reporting procedure based on the predicted time of occurrence of the measurement event; the third information indicates a time threshold value and is used for judging whether to trigger a measurement reporting process or not based on the predicted time of occurrence of a measurement event and the third information; Fourth information for enabling a mechanism for determining whether to trigger a measurement reporting procedure based on the predicted probability of occurrence of the measurement event; Fifth information, which indicates a percentage threshold value, is used for judging whether to trigger a measurement reporting process or not based on the predicted probability of occurrence of the measurement event and the fifth information by the UE; And Saving the received measurement configuration to a UE variable, and Model-assisted measurement prediction, assessment, and reporting processes are performed based on the saved measurement configuration.
2. 2. The measurement reporting method of claim J, wherein, The measurement configuration refers to a configuration associated with the RRM measurement prediction assisted by the model or an input information or output configuration of the model, and comprises one or more of a measurement identifier, a measurement object, a measurement report configuration, a measurement reference cell, a measurement window size, a prediction window size, a model identifier, and the like.
3. 3. The measurement reporting method of claim 1, wherein, The direct output of the model in the indirect prediction model is used for predicting the signal quality of a measured cell at a future moment, and indirectly obtaining the information of whether a measurement event occurs at the moment or not based on the signal quality and the measurement event configuration, wherein the output of the model in the direct prediction model is the probability of occurrence of the measurement event at the future moment or time period.
4. 4. The measurement reporting method of claim 1, wherein, The fifth information is a threshold value or a hysteresis parameter.
5. 5. The measurement reporting method of claim 1, wherein, The performing model-assisted measurement prediction and assessment includes: And if the time difference between the predicted time of occurrence of one measurement event and the time of occurrence of the same measurement event in the predicted measurement report sent to the network side last time by the UE is greater than or equal to a first threshold value, and the measurement event is associated to the same cell or the same group of cells, triggering a measurement reporting process.
6. 6. The measurement reporting method of claim 1, wherein, The performing model-assisted measurement prediction and assessment includes: And if the signal quality measured value of the measured cell corresponding to the predicted measurement event and the signal quality of the measured cell in the predicted measurement report sent to the network side last time exceed or are equal to a second threshold value, triggering a measurement reporting process by the UE.
7. 7. The measurement reporting method of claim 1, wherein, The performing model-assisted measurement prediction and assessment includes: If the difference between the predicted probability of occurrence of one measurement event and one threshold value TH1 is greater than or equal to the other threshold value TH2, the entry condition of the measurement event is considered to be satisfied.
8. 8. The measurement reporting method of claim 1, wherein, The performing model-assisted measurement prediction and assessment includes: If the sum of the predicted probability of occurrence of one measurement event and one threshold value TH3 is smaller than or equal to the other threshold value TH4, the leaving condition of the measurement event is considered to be satisfied.
9. 9. The measurement reporting method of claim 1, wherein, The execution model assisted measurement prediction and assessment is performed on a measurement identity, or a measurement object, or a measured cell or a measured event.
10. 10. A user equipment, UE, comprising: processor, and A memory storing instructions; wherein the instructions, when executed by the processor, perform the measurement reporting method according to any one of claims 1 to 9.

Description

Measurement reporting method and user equipment Technical Field The present disclosure relates to the field of wireless communication technologies, and more particularly, to a measurement reporting method and a corresponding user equipment. Background Artificial intelligence/machine learning (ARTIFICIAL INTELLIGENCE/MACHINE LEARNING, AI/ML) is an important revolution in the fields of computer science and data processing. AI/ML generally refers to processes and algorithms that can simulate human intelligence, and through collection, analysis, learning, and derivation of existing data, the goal of solving problems in various fields is achieved. At the 3GPP ran general at 9 of 2024, a research project concerning the application of artificial intelligence/machine learning (AI/ML) in NR mobility (NR mobility) was approved (see 3GPP non-patent document RP-242393). The study focused on air interface mobility enhancement in radio resource control (Radio Resource Connection, RRC) connected state, which refers to a change of primary cell (PRIMARY CELL, PCELL) in NR system. The issue study and evaluation of the benefits and gains of AI/ML assisted network side triggered layer 3 handover mobility mainly considers the following aspects: AI/ML-based radio resource management (Radio Resource Management, RRM) Measurement and event prediction. This includes cell-level measurement predictions including intra-frequency (intra-ffequency) and inter-frequency (inter-frequency), radio link failure (Radio Link Failure, RLF) predictions, and handover failure predictions, among others. Study the necessity and benefits for UE assistance information in the network side model. AI/ML assisted mobility impact on 3GPP specifications. In the prior art of the NR system, the UE performs measurement for RRM and reports the obtained measurement result to the network based on a reporting configuration (e.g., measurement event) configured by the network side, and the network side performs mobility management and decision of the RRC connected state based on the received measurement result actually performed by the UE. The present disclosure aims to solve the problem of AI/ML-based measurement configuration or measurement reporting in NR networks, and further to solve the problem of how to reduce unnecessary reporting of UE-predicted measurement results in a system that enables AI/ML-assisted RRM measurement. Disclosure of Invention The main objective of the present disclosure is to provide a measurement reporting method and a user equipment to reduce the problem of unnecessary reporting of measurement results predicted by a UE in a system that enables AI/ML-assisted RRM measurement. According to a first aspect of the present disclosure, there is provided a measurement reporting method, including a user equipment UE receiving a measurement configuration radio resource control RRC message including a RRM measurement for artificial intelligence AI/machine learning ML model assistance sent by a network side, the measurement configuration including one or more of first information indicating whether a type of RRM measurement model is direct or indirect, second information enabling a mechanism for determining whether to trigger a measurement reporting procedure based on a predicted time of occurrence of a measurement event, third information indicating a time threshold for determining whether to trigger the measurement reporting procedure based on a predicted time of occurrence of a measurement event and the third information, fourth information enabling a mechanism for determining whether to trigger the measurement reporting procedure based on a predicted probability of occurrence of a measurement event, fifth information indicating a percentage threshold for determining whether to trigger the measurement reporting procedure based on a predicted probability of occurrence of a measurement event and the fifth information, and storing the measurement configuration received by the UE and performing the measurement reporting procedure based on the predicted measurement configuration and the stored evaluation parameters. In the measurement report method of the first aspect, the measurement configuration refers to configuration associated with RRM measurement prediction assisted by a model or input information of the model, and includes one or more of measurement identifier, measurement object, measurement report configuration, measurement reference cell, observation window size, prediction window size, model identifier, and the like. In the measurement report method of the first aspect, the direct output of the model in the indirect prediction model predicts the signal quality of the measured cell at a time in the future, and then indirectly obtains whether a measurement event occurs at the time based on the signal quality and the measurement event configuration, and the output of the model in the direct prediction model is the probability of occurrence of