Information reporting method and apparatus, resource configuration method and apparatus, terminal, and base station

Abstract

The present application relates to the technical field of communications, and provides an information reporting method and apparatus, a resource configuration method and apparatus, a terminal, and a base station. The information reporting method comprises: a terminal receiving first configuration information from a base station, the first configuration information comprising an AI use case indication, different AI use case indications corresponding to different measurement resources; the terminal measuring a reference signal on a measurement resource corresponding to the AI use case indication, to obtain a measurement result; and the terminal performing reporting on the basis of the measurement result.

Description

Information reporting method and device, resource configuration method and device, terminal and base station

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese patent application No. 202310938613.9 filed on July 27, 2023, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present application relates to the field of communication technology, and more specifically, to an information reporting method and device, a resource configuration method and device, a terminal, and a base station. Background Art

[0004] In the New Radio (NR) system, more and more use cases are beginning to combine artificial intelligence (AI) to improve system performance. For example, at the physical layer, AI-based channel state information (CSI) compression and decompression are used to reduce air interface transmission overhead and improve the accuracy of CSI feedback information. Another example is AI-based beam management and AI-based positioning. However, AI-based reasoning is strongly correlated with data distribution, and the reasoning results of the AI ​​unit need to be monitored. At this stage, during the monitoring process, specific measurement resource configuration and measurement reporting configuration processes need to be designed for different AI use cases. When there are many AI use cases in the system, the implementation complexity is high. How to reduce the configuration complexity of measurement resources and reporting is a problem that needs to be solved.

[0005] Summary of the Invention

[0006] The present application provides an information reporting method and device, a resource configuration method and device, a terminal, and a base station, which can reduce the configuration complexity of measurement resources and reporting during the monitoring process of AI use cases or AI use case groups.

[0007] In a first aspect, a method for reporting information is provided, comprising:

[0008] The terminal receives first configuration information from the base station, where the first configuration information includes: an AI use case indication, where different AI use case indications correspond to respective measurement resources;

[0009] The terminal measures a reference signal on a measurement resource corresponding to the AI ​​use case indication to obtain a measurement result;

[0010] The terminal reports based on the measurement result.

[0011] In a second aspect, a resource configuration method is provided, comprising:

[0012] The base station sends first configuration information to the terminal, where the first configuration information includes: an AI use case indication, where different AI use case indications correspond to respective measurement resources;

[0013] The base station sends a reference signal to the terminal on the measurement resources corresponding to the AI ​​use case indication.

[0014] In a third aspect, an information reporting device is provided, comprising:

[0015] A receiving unit, configured to receive first configuration information from a base station, where the first configuration information includes: an artificial intelligence (AI) use case indication, where different AI use case indications correspond to respective measurement resources;

[0016] a processing unit, configured to measure a reference signal on a measurement resource corresponding to the AI ​​use case indication to obtain a measurement result;

[0017] A sending unit is configured to report based on the measurement result.

[0018] In a fourth aspect, a resource configuration device is provided, comprising:

[0019] A sending unit, configured to send first configuration information to a terminal, where the first configuration information includes: an artificial intelligence (AI) use case indication, where different AI use case indications correspond to respective measurement resources;

[0020] The sending unit is further configured to send a reference signal to the terminal on the measurement resources corresponding to the AI ​​use case indication.

[0021] In a fifth aspect, a terminal is provided, comprising a processor and a memory; wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method in the above-mentioned first aspect or its various implementation methods.

[0022] In the sixth aspect, a base station is provided, comprising a processor and a memory; wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method in the above-mentioned second aspect or its various implementation methods.

[0023] In a seventh aspect, an apparatus is provided for implementing the method described in any one of the first and second aspects above, or their respective implementations. Specifically, the apparatus includes a processor configured to retrieve and execute a computer program from a memory, causing a device equipped with the apparatus to perform the method described in any one of the first and second aspects above, or their respective implementations.

[0024] In an eighth aspect, a chip is provided for implementing the method described in any one of the first and second aspects above, or their respective implementations. Specifically, the chip includes a processor configured to load and execute a computer program from a memory, causing a device equipped with the chip to perform the method described in any one of the first and second aspects above, or their respective implementations.

[0025] In a ninth aspect, a computer-readable storage medium is provided for storing a computer program, which enables a computer to execute the method of any one of the first to second aspects or their respective implementations.

[0026] In a tenth aspect, a computer program product is provided, comprising computer instructions, which, when executed by a processor, implement the steps of the method in any one of the first to second aspects above or their respective implementations.

[0027] Through the above technical solution, the base station can configure different AI use case indications corresponding to their respective measurement resources, that is, the base station can configure measurement resources based on the AI ​​use case indication granularity. After that, the terminal can determine the corresponding measurement resources based on the AI ​​use case indication, which can avoid executing the measurement resource and reporting configuration process separately for different AI use cases. Therefore, the configuration complexity of measurement resources and reporting can be reduced during the monitoring process of AI use cases or AI use case groups. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for describing the embodiments of the present application. Obviously, the drawings described below are only some embodiments of the present application. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0029] FIG1 is a schematic diagram of a communication system architecture provided in an embodiment of the present application;

[0030] FIG2 is a schematic flow chart of an information reporting method provided according to an embodiment of the present application;

[0031] Figures 3 to 18 are schematic flow charts of AI use case monitoring according to embodiments of the present application;

[0032] FIG19 is a schematic flow chart of a resource configuration method according to an embodiment of the present application;

[0033] FIG20 is a schematic block diagram of an information reporting device according to an embodiment of the present application;

[0034] FIG21 is a schematic block diagram of a resource configuration device according to an embodiment of the present application;

[0035] FIG22 is a schematic block diagram of a communication device provided according to an embodiment of the present application;

[0036] FIG23 is a schematic block diagram of a device according to an embodiment of the present application;

[0037] Figure 24 is a schematic block diagram of a communication system provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0038] The following will describe the technical solutions in the embodiments of this application in conjunction with the drawings in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of the embodiments. With respect to the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0039] The terms used in the embodiments of the present application are only used to explain the specific embodiments of the present application and are not intended to limit the present application. The terms "first", "second", "third" and "fourth" in the specification and claims of the present application and the accompanying drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. In addition, the use of "and / or" in the specification and claims represents at least one of the connected objects, such as A and / or B and / or C, which means including 7 situations including single A, single B, single C, and both A and B exist, both B and C exist, both A and C exist, and both A, B and C exist.

[0040] It should be understood that the "indication" mentioned in the embodiments of this application can be a direct indication, an indirect indication, or an indication of an association. For example, "A indicates B" can mean that A directly indicates B, for example, B can obtain it through A; it can also mean that A indirectly indicates B, for example, A indicates C, and B can obtain it through C; it can also mean that there is an association between A and B.

[0041] In the description of the embodiments of the present application, the term "corresponding" may indicate a direct or indirect correspondence between the two, or an association relationship between the two, or a relationship between indication and being indicated, configuration and being configured, etc.

[0042] The technical solutions of the embodiments of the present application can be applied to various communication systems, such as: Long Term Evolution (LTE) system, Advanced Long Term Evolution (LTE-A) system, New Radio (NR) system, NR system evolution system, LTE on unlicensed spectrum (LTE-U) system, NR on unlicensed spectrum (NR-based access to unlicensed spectrum, NR-U) system, Non-Terrestrial Networks (NTN) system, Universal Mobile Telecommunication System (UMTS), Wireless Local Area Networks (WLAN), Internet of Things (IoT), Wireless Fidelity (WiFi), Fifth Generation Communication (5G) system, Sixth Generation Communication (6G) system or other evolved communication systems.

[0043] The communication system in the embodiments of the present application can be applied to licensed spectrum and / or unlicensed spectrum, wherein the unlicensed spectrum can also be considered as a shared spectrum, and the licensed spectrum can also be considered as a non-shared spectrum.

[0044] For example, a communication system 100 used in an embodiment of the present application may be as shown in FIG1 , and the communication system 100 may include a terminal device 110 and a network device 120. The network device 120 may provide communication coverage for a specific geographical area and may communicate with terminal devices within the coverage area. Specifically, for example, the terminal device 110 may also be referred to as a user equipment (UE), a terminal, or other similar names.

[0045] In some embodiments, the terminal device 110 can be a mobile phone, a tablet personal computer, a laptop computer, a notebook computer, a personal digital assistant (PDA), a handheld computer, a netbook, an ultra-mobile personal computer (UMPC), a mobile Internet device (MID), an augmented reality (AR), a virtual reality (VR) device, a robot, a wearable device, a flight vehicle, a vehicle user equipment (VUE), a shipborne device, a pedestrian user equipment (PUE), a smart home (home appliances with wireless communication capabilities, such as refrigerators, televisions, washing machines or furniture, etc.), a game console, a personal computer (PC), an ATM or a self-service machine, and other terminal-side devices. Wearable devices include: smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among them, vehicle-mounted equipment can also be called vehicle-mounted terminals, vehicle-mounted controllers, vehicle-mounted modules, vehicle-mounted components, vehicle-mounted chips, or vehicle-mounted units.

[0046] In some embodiments, the network device 120 may also be referred to as an access network device, a radio access network (RAN) device, a radio access network function, or a radio access network unit. The network device 120 may include a base station, a WLAN access point (AP), or a wireless fidelity (WiFi) node. Among them, the base station can be referred to as Node B (NB), Evolved Node B (eNB), the next generation Node B (gNB), New Radio Node B (NR Node B), access point, Relay Base Station (RBS), Serving Base Station (SBS), Base Transceiver Station (BTS), radio base station, radio transceiver, Basic Service Set (BSS), Extended Service Set (ESS), Home Node B (HNB), Home Evolved Node B (home evolved Node B), Transmission Reception Point (TRP) or other appropriate terms in the field. As long as the same technical effect is achieved, the base station is not limited to specific technical vocabulary. It should be noted that in the embodiment of the present application, only the base station in the NR system is used as an example for introduction, and the specific type of the base station is not limited.

[0047] In order to facilitate a better understanding of the embodiments of the present application, the technologies related to the present application are explained.

[0048] In mobile communication systems, artificial intelligence (AI) is increasingly being incorporated into use cases, such as AI-based CSI feedback compression at the physical layer, AI-based beam management, AI-based positioning, AI-based energy saving, and AI-based load balancing.

[0049] Given the uncertainty of the AI ​​unit's reasoning results, it's necessary to monitor the AI ​​unit's reasoning effectiveness in real time to determine whether to continue. For example, in AI-based beam prediction, all beam qualities measured by the UE are reported to the base station, which then determines the effectiveness of the AI ​​unit. In other words, the network node configures, starts, collects, and processes the monitoring data, while the UE is unaware of the monitoring data collection and considers it to be just a standard CSI report. While this solution offers good protocol compatibility, it significantly increases the amount of data that needs to be exchanged over the air interface.

[0050] In addition, there will be a large number of AI use cases in 6G in the future. If a specific monitoring process is designed for each AI use case, the 6G system design will become more complicated.

[0051] Based on the above problems, this application proposes an AI unit monitoring solution that can reduce the monitoring complexity of AI units.

[0052] To facilitate understanding of the technical solutions of the embodiments of the present application, the technical solutions of the present application are described in detail below through specific embodiments. The above related technologies can be combined arbitrarily with the technical solutions of the embodiments of the present application as optional solutions, and all of them fall within the scope of protection of the embodiments of the present application. The embodiments of the present application include at least part of the following contents.

[0053] FIG2 is a schematic flow chart of an information reporting method 200 according to an embodiment of the present application. As shown in FIG2 , the information reporting method 200 may include at least part of the following contents:

[0054] S210: The terminal receives first configuration information from a base station, where the first configuration information includes an AI use case indication, where different AI use case indications correspond to respective measurement resources.

[0055] S220, the terminal measures a reference signal on the measurement resource corresponding to the AI ​​use case indication, and obtains a measurement result;

[0056] S230: The terminal reports based on the measurement result.

[0057] It should be understood that FIG2 shows the steps or operations of the information reporting method 200, but these steps or operations are merely examples, and the embodiments of the present application may also perform other operations or variations of the operations in FIG2.

[0058] The AI ​​unit described in this application may also be referred to as an AI model, a machine learning (ML) model, an ML unit, an AI structure, an AI function, an AI feature, a machine learning model, a neural network, a neural network function, a neural network function, etc., or the AI ​​unit may also refer to a processing unit that can implement specific algorithms, formulas, processing procedures, capabilities, etc. related to AI, or the AI ​​unit may be a processing method, algorithm, function, module or unit for a specific data set, or the AI ​​unit may be a processing method, algorithm, function, module or unit running on AI / ML related hardware such as a graphics processing unit (GPU), a neural network processor (NPU), a tensor processing unit (TPU), an application-specific integrated circuit (ASIC), etc., and this application does not make specific limitations on this. Optionally, the specific data set includes the input and / or output of the AI ​​unit.

[0059] Optionally, the AI ​​unit can be identified by an AI unit identifier, which can also be called an AI model identifier, an AI structure identifier, an AI algorithm identifier, or an identifier of a specific data set associated with the AI ​​unit, or an identifier of a specific scenario, environment, channel feature, or device related to the AI / ML, or an identifier of a function, feature, capability, or module related to the AI / ML. This application does not make any specific limitations on this.

[0060] The base station described in the embodiment of the present application may also be referred to as an access network device or a network device, and the embodiment of the present application does not make any specific limitations on this.

[0061] In an embodiment of the present application, the base station can configure different AI use case indications corresponding to their respective measurement resources, that is, the base station can configure the measurement resources based on the AI ​​use case indication granularity. After that, the terminal can determine the corresponding measurement resources based on the first configuration information, which can avoid executing the measurement resource configuration and reporting configuration process separately for different AI use cases. Therefore, the configuration complexity of measurement resources and reporting can be reduced during the monitoring process of AI use cases or AI use case groups.

[0062] In an embodiment of the present application, the terminal can determine corresponding measurement resources for different AI use cases based on the first configuration information, and measure reference signals on the determined measurement resources. Furthermore, the terminal can report the measurement results, or the terminal can determine the monitoring results based on the measurement results and report the monitoring results, thereby realizing universal monitoring for different AI use case indications, avoiding the need to design specific monitoring processes for different AI use cases, and reducing the monitoring complexity of AI use cases or AI use case groups. Furthermore, compared to the base station side performing monitoring data collection, processing and monitoring (the base station performs monitoring data configuration, startup, data collection and data processing, the terminal does not perceive the monitoring data collection and processing, the terminal believes that it is just ordinary measurement and reporting, then the terminal needs to report a large amount of measurement data to support the monitoring data collection on the base station side, thereby greatly increasing the amount of reported data required by the terminal), in an embodiment of the present application, since the terminal perceives the monitoring process, it can avoid reporting some unnecessary data, thereby reducing the amount of data interacted with the air interface.

[0063] In some embodiments, the measurement resources corresponding to the AI ​​use case identifier can be configured through the first configuration information or other information. For example, the first configuration information is a reporting configuration, and the measurement resources corresponding to the AI ​​use case identifier can be configured through reference signal configuration information.

[0064] In the embodiments of the present application, universal monitoring for different AI use cases can be achieved, that is, forward compatibility can be achieved. For example, assuming that the current protocol supports AI use cases such as AI beam prediction and AI CSI prediction, then in the future, if there are new AI use cases such as AI mobility management, then the universal process can be reused and the corresponding parameters can be configured. There is no need to add an additional monitoring process specifically for AI mobility management.

[0065] In other words, in an embodiment of the present application, if a new AI use case appears, the monitoring of the new AI use case can be achieved by configuring the corresponding AI use case indication and measurement resource indication for the new AI use case in the first configuration information. Optionally, the first configuration information can also configure the corresponding measurement quantity, etc. for the new AI use case. In the related art, if the terminal is perceptually monitored, it is necessary to add a monitoring process specifically for the new AI use case based on the new AI use case. Among them, monitoring includes monitoring data acquisition (corresponding to measurement resource configuration) and monitoring data processing (corresponding to measurement quantity indication).

[0066] In an embodiment of the present application, the terminal is an inference device, or the base station is an inference device, or other devices or servers (such as third-party devices) are inference devices. This embodiment of the present application does not make specific limitations on this.

[0067] The reference signal described in the embodiments of the present application may include but is not limited to at least one of the following:

[0068] Synchronization Signal Block (SSB), Channel State Information Reference Signal (CSI-RS), Non-Zero Power Channel State Information-Reference Signal (NZP-CSI-RS).

[0069] In some embodiments, the first configuration information is reporting configuration information (such as CSI reporting configuration information), or the first configuration information is AI reference signal configuration information. Of course, the first configuration information may also be other configuration information, such as measurement reporting configuration information, which is not specifically limited in this embodiment of the present application.

[0070] In an embodiment of the present application, when the first configuration information is reporting configuration information (such as CSI reporting configuration information), the base station can reuse the reporting configuration information (such as CSI reporting configuration information) to reduce implementation complexity and reduce changes to the standard.

[0071] In an embodiment of the present application, when the first configuration information is AI reference signal configuration information, AI reference signals and AI reference signal configuration information dedicated to AI unit monitoring are introduced, and a monitoring configuration process can be constructed for different AI use cases. When a new AI use case appears in the network, the monitoring process of the new use case can be enabled by configuring the corresponding parameters, thereby achieving forward compatibility.

[0072] In some embodiments, the AI ​​use case indication includes but is not limited to one of the following:

[0073] AI use case identifier, AI use case group identifier.

[0074] The embodiments of the present application can implement monitoring of AI use cases (for example, monitoring some or all of the corresponding AI units for a specific AI use case), and can also implement monitoring of AI use case groups (for example, monitoring some or all of the corresponding AI units for a specific AI use case group), thereby improving monitoring performance.

[0075] In some embodiments, the AI ​​use case indicated by the AI ​​use case indication may include but is not limited to one of the following: beam prediction, CSI prediction, CSI compression recovery, terminal positioning, terminal energy saving, and beam selection.

[0076] In some embodiments, the AI ​​use case group indicated by the AI ​​use case indication may include one or more AI use cases, wherein the AI ​​use case in the AI ​​use case group may be one of the following: beam prediction, CSI prediction, CSI compression recovery, terminal positioning, terminal energy saving, and beam selection.

[0077] In some embodiments, when the AI ​​use case group indicated by the AI ​​use case indication includes multiple AI use cases, the terminal may measure the reference signal on the measurement resources corresponding to the AI ​​use case group, and perform monitoring-related reporting based on the measurement results, or perform monitoring based on the measurement results and report the monitoring results. That is, in this case, monitoring of multiple AI use cases within the AI ​​use case group can be achieved.

[0078] It should be noted that a "beam" can also be referred to as a "spatial filter", which is not limited in the embodiments of the present application.

[0079] In some embodiments, the AI ​​use case identifier indicated by the AI ​​use case indication in the first configuration information may be the identifier of a newly added AI use case, or the AI ​​use case group identifier indicated by the AI ​​use case indication in the first configuration information may be the identifier of a newly added AI use case group.

[0080] In some embodiments, the AI ​​use case identifier indicated by the AI ​​use case indication in the first configuration information may also be the identifier of an existing AI use case, or the AI ​​use case group identifier indicated by the AI ​​use case indication in the first configuration information may also be the identifier of an existing AI use case group.

[0081] For example, when it is necessary to update relevant information of an AI use case or an AI use case group (such as an identifier, measurement resources, measurement quantity, etc.), the AI ​​use case identifier indicated by the AI ​​use case indication in the first configuration information may also be the identifier of an existing AI use case, or the AI ​​use case group identifier indicated by the AI ​​use case indication in the first configuration information may also be the identifier of an existing AI use case group.

[0082] In some embodiments, the first configuration information further includes but is not limited to at least one of the following:

[0083] AI unit monitoring object, AI unit monitoring purpose, measurement quantity information monitored by the AI ​​unit, reference signal resource indication for AI unit monitoring, at least one AI use case indication corresponding to the measurement resource, and auxiliary information monitored by the AI ​​unit.

[0084] For example, the first configuration information configures measurement resources corresponding to CSI prediction, measurement resources corresponding to beam prediction, and measurement resources corresponding to terminal positioning, etc. The AI ​​use case indication included in the first configuration information indicates that the AI ​​use case includes at least one of CSI prediction, beam prediction, and terminal positioning.

[0085] In an embodiment of the present application, the base station may also configure at least one of the following through the first configuration information: an AI unit monitoring object, an AI unit monitoring purpose, measurement quantity information monitored by the AI ​​unit, a reference signal resource indication for AI unit monitoring, measurement resources corresponding to at least one AI use case indication, and auxiliary information monitored by the AI ​​unit; thereby, the terminal may obtain configuration-related information through the first configuration information to implement universal monitoring for different AI use case indications, thereby avoiding the need to design specific monitoring processes for different AI use cases, and reducing the monitoring complexity of AI use cases or AI use case groups.

[0086] In some embodiments, the AI ​​unit monitors objects including but not limited to one of the following:

[0087] AI unit ID, AI unit group ID, AI function ID, AI function group ID.

[0088] In an embodiment of the present application, when the first configuration information includes an AI unit monitoring object, the terminal can obtain the AI ​​unit monitoring object through the first configuration information, thereby performing monitoring based on the obtained AI unit monitoring object. That is, AI unit (such as the AI ​​use case indicated by the AI ​​use case indication or part or all AI units corresponding to the AI ​​use case group) monitoring can be implemented, or AI unit group (such as the AI ​​use case indicated by the AI ​​use case indication or part or all AI unit groups corresponding to the AI ​​use case group) monitoring can be implemented, or AI function (such as the AI ​​use case indicated by the AI ​​use case indication or part or all AI functions corresponding to the AI ​​use case group) monitoring can be implemented, or AI function group (such as the AI ​​use case indicated by the AI ​​use case indication or part or all AI function groups corresponding to the AI ​​use case group) monitoring can be implemented. Optionally, the terminal can also determine the monitoring measurement amount based on the AI ​​unit monitoring object, thereby saving the indication of the measurement amount.

[0089] In some embodiments, the AI ​​unit identifier can be: an AI model identifier, an AI structure identifier, an AI algorithm identifier, or the AI ​​unit identifier can be: an identifier of a specific data set associated with the AI ​​unit (for example, a training data set, an inference data set, a verification data set, a measurement data set for AI unit monitoring, etc.), or an identifier of a specific scenario (for example, a low-power scenario, a low-latency scenario, a high-speed mobile scenario, etc.), environment (for example, an urban microcell (Umi) environment, an urban macrocell (Uma) environment, etc.), channel characteristics (for example, line of sight (LOS), non-line of sight (NLOS), etc.), device (such as inference device, training device, verification device, monitoring device, etc.), or an identifier of a function, feature, capability or module related to the AI ​​unit. This application does not specifically limit this. In addition, the AI ​​unit group identifier is similar to the AI ​​unit identifier, except that the concept of "group" is introduced. For details, please refer to the relevant description of the AI ​​unit identifier, which will not be repeated here.

[0090] It should be noted that AI functions can be subsets of AI use cases. For example, the time-domain beam prediction use case can be subdivided into AI functions for 30 km / h and 60 km / h. For another example, for AI-based CSI compression, CSI prediction, beam management, and other use cases, the AI ​​functions can be: AI time-domain beam prediction for 30 km / h, or AI CSI prediction for 30 km / h.

[0091] Optionally, an AI use case may be associated with one or more AI units, that is, the AI ​​use case may be implemented based on reasoning of one or more AI units associated with the AI ​​use case.

[0092] Optionally, an AI use case may be associated with one or more AI unit groups, that is, the AI ​​use case may be inferred and implemented based on the one or more AI unit groups associated with the AI ​​use case.

[0093] Optionally, an AI use case may be associated with one or more AI functions, or an AI use case may be associated with one or more AI function groups.

[0094] For example, the AI ​​use case is beam prediction, and its associated AI functions may include at least one of the following: transmit beam prediction, receive beam prediction, and beam pair prediction.

[0095] For another example, the AI ​​use case is terminal positioning, and its associated AI functions may include at least one of the following: terminal positioning based on terminal implementation, terminal positioning based on terminal + network implementation, and terminal positioning based on network implementation.

[0096] For example, if the AI ​​use case is beam prediction, its associated AI functions can be defined from the following three aspects:

[0097] 1) Prediction objects: transmit beam quality, receive beam quality, and beam pair quality;

[0098] 2) Reasoning location: UE reasoning, base station reasoning, and UE and base station joint reasoning;

[0099] 3) Inference scenarios: for example, 30 km / h and 90 km / h.

[0100] In some embodiments, the AI ​​unit monitoring purpose includes but is not limited to one of the following:

[0101] Monitor one or more AI units that are active,

[0102] monitoring one or more AI units that are in a deactivated state,

[0103] Monitor one or more AI functions that are active,

[0104] One or more AI functions are monitored for being in a deactivated state.

[0105] In an embodiment of the present application, when the first configuration information includes the AI ​​unit monitoring purpose, the terminal can obtain the AI ​​unit monitoring purpose through the first configuration information, so that monitoring can be performed based on the obtained AI unit monitoring purpose. That is, one or more AI units in an activated state can be monitored, or one or more AI units in a deactivated state can be monitored, or one or more AI functions in an activated state can be monitored, or one or more AI functions in a deactivated state can be monitored. According to different monitoring purposes, the terminal can determine whether the measurement quantity used for monitoring is determined by itself or configured by the network. For example, if the monitoring purpose is to monitor one or more AI units in a deactivated state, the terminal can decide the monitoring measurement quantity by itself, and there is no need to report the monitoring measurement quantity, but only need to report the recommended AI unit list; for another example, if the monitoring purpose is to monitor one or more AI units in an activated state, the terminal uses the measurement quantity configured by the network for AI unit monitoring, and reports the measurement quantity or monitoring results.

[0106] In some embodiments, the measurement information monitored by the AI ​​unit includes but is not limited to at least one of the following:

[0107] a first measurement quantity, a second measurement quantity associated with the first measurement quantity, a default indication associated with the first measurement quantity, and a universal measurement quantity set identifier associated with the first measurement quantity;

[0108] The first measurement quantity is a measurement quantity monitored by the AI ​​unit.

[0109] In an embodiment of the present application, if the first configuration information includes measurement information monitored by the AI ​​unit, the terminal can obtain the measurement information monitored by the AI ​​unit through the first configuration information, thereby performing measurement based on the obtained measurement information monitored by the AI ​​unit and obtaining the measurement quantity monitored by the AI ​​unit (i.e., the first measurement quantity). In AI unit monitoring, the measurement quantity is used to indicate how data is processed to obtain a monitoring indicator.

[0110] Optionally, the first measurement quantity is one of the following: Top1 accuracy, cosine similarity squared. For example, the AI ​​use case is beam prediction, and the first measurement quantity is Top1 accuracy (for example, the Top1 accuracy can be determined based on Layer 1 Reference Signal Received Power (L1-RSRP) or Layer 3 Reference Signal Received Power (L3-RSRP)). For another example, the AI ​​use case is CSI compression, and the first measurement quantity is cosine similarity squared.

[0111] It should be noted that the probability that the beam with the highest beam quality inferred by the AI ​​unit is the same as the actual beam with the highest beam quality is the same. For each sample, if they are the same, it is 1, and if they are different, it is 0. The top 1 accuracy is calculated by taking the average of multiple samples.

[0112] For example, the measurement quantity information monitored by the AI ​​unit includes the first measurement quantity, that is, the base station may explicitly indicate the first measurement quantity through the first configuration information.

[0113] For example, the measurement quantity information monitored by the AI ​​unit includes a second measurement quantity associated with the first measurement quantity. That is, the terminal may determine the first measurement quantity based on the second measurement quantity.

[0114] Optionally, the second measurement quantity may be one or more intermediate measurement quantities, which is not limited in this embodiment of the present application.

[0115] Optionally, the association between the first measurement quantity and the second measurement quantity may be agreed upon by a protocol, or the association between the first measurement quantity and the second measurement quantity may be pre-configured by a network device (base station or core network function node). For example, the second measurement quantity is L1-RSRP or L3-RSRP, and the first measurement quantity is Top1 accuracy, which indicates the probability that the beam with the highest beam quality inferred by the AI ​​unit, as determined by L1-RSRP or L3-RSRP, is the same as the beam with the highest actual beam quality.

[0116] For example, the measurement quantity information monitored by the AI ​​unit includes a default indication associated with the first measurement quantity. That is, the terminal may determine the first measurement quantity based on the default indication.

[0117] Optionally, the association relationship between the first measurement quantity and the default indication may be agreed upon by a protocol, or the association relationship between the first measurement quantity and the default indication may be pre-configured by a network device (base station or core network function node).

[0118] For example, the measurement quantity information monitored by the AI ​​unit includes a universal measurement quantity set identifier associated with the first measurement quantity. That is, the terminal may determine the first measurement quantity based on the universal measurement quantity set identifier.

[0119] Optionally, the association relationship between the first measurement quantity and the universal measurement quantity set identifier may be agreed upon by a protocol, or the association relationship between the first measurement quantity and the universal measurement quantity set identifier may be pre-configured by a network device (base station or core network function node).

[0120] It should be noted that the universal measurement set may include some measurement quantities applicable to multiple AI use cases, or the universal measurement set may include some measurement quantities applicable to multiple AI units.

[0121] Optionally, the general measurement quantity set may be agreed upon by a protocol, or the general measurement quantity set may be pre-configured by a base station.

[0122] In some embodiments, the first measurement quantity may also be associated with the AI ​​unit identifier included in the AI ​​unit monitoring object. That is, the terminal may determine the first measurement quantity based on the AI ​​unit identifier included in the AI ​​unit monitoring object. In this case, the first configuration information may not include information about the measurement quantity monitored by the AI ​​unit.

[0123] Optionally, the association relationship between the first measurement quantity and the AI ​​unit identifier may be agreed upon by a protocol, or the association relationship between the first measurement quantity and the AI ​​unit identifier may be pre-configured by a network device (base station or core network function node). For example, when the AI ​​unit identifier is notified to the network by the inference device, the association relationship between the first measurement quantity and the AI ​​unit identifier may be pre-configured by the network device (base station or core network function node).

[0124] In some embodiments, the first measurement quantity may also be associated with the AI ​​unit group identifier included in the AI ​​unit monitoring object. That is, the terminal may determine the first measurement quantity based on the AI ​​unit group identifier included in the AI ​​unit monitoring object. In this case, the first configuration information may not include information about the measurement quantity monitored by the AI ​​unit.

[0125] Optionally, the association relationship between the first measurement quantity and the AI ​​unit group identifier may be agreed upon by a protocol, or the association relationship between the first measurement quantity and the AI ​​unit group identifier may be pre-configured by a network device (base station or core network function node).

[0126] In some embodiments, the first measurement quantity may also be associated with the AI ​​function identifier included in the AI ​​unit monitoring object. That is, the terminal may determine the first measurement quantity based on the AI ​​function identifier included in the AI ​​unit monitoring object. In this case, the first configuration information may not include information about the measurement quantity monitored by the AI ​​unit.

[0127] Optionally, the association relationship between the first measurement quantity and the AI ​​function identifier may be agreed upon by a protocol, or the association relationship between the first measurement quantity and the AI ​​function identifier may be pre-configured by a network device (base station or core network function node).

[0128] In some embodiments, the first measurement quantity may also be associated with the AI ​​function group identifier included in the AI ​​unit monitoring object. That is, the terminal may determine the first measurement quantity based on the AI ​​function group identifier included in the AI ​​unit monitoring object. In this case, the first configuration information may not include information about the measurement quantity monitored by the AI ​​unit.

[0129] Optionally, the association relationship between the first measurement quantity and the AI ​​function group identifier may be agreed upon by a protocol, or the association relationship between the first measurement quantity and the AI ​​function group identifier may be pre-configured by a network device (base station or core network function node).

[0130] In some embodiments, the first measurement quantity may also be associated with the AI ​​use case identifier included in the AI ​​use case indication, that is, the terminal may determine the first measurement quantity based on the AI ​​use case identifier included in the AI ​​use case indication. In this case, the first configuration information may not include measurement quantity information monitored by the AI ​​unit.

[0131] Optionally, the association relationship between the first measurement quantity and the AI ​​use case identifier may be agreed upon by a protocol, or the association relationship between the first measurement quantity and the AI ​​use case identifier may be pre-configured by a network device (base station or core network function node).

[0132] In some embodiments, the first measurement quantity may also be associated with the AI ​​use case group identifier included in the AI ​​use case indication. That is, the terminal may determine the first measurement quantity based on the AI ​​use case group identifier included in the AI ​​use case indication. In this case, the first configuration information may not include measurement quantity information monitored by the AI ​​unit.

[0133] Optionally, the association relationship between the first measurement quantity and the AI ​​use case group identifier may be agreed upon by a protocol, or the association relationship between the first measurement quantity and the AI ​​use case group identifier may be pre-configured by a network device (base station or core network function node).

[0134] In some embodiments, the reference signal resource indication for AI unit monitoring includes but is not limited to at least one of the following: bandwidth information, resource density information, time domain resource information, predefined resource element (RE) mode identifier, default reference signal resource configuration information indication, universal reference signal resource configuration indication, and predefined reference signal resource configuration indication.

[0135] It should be noted that the default reference signal resource configuration information indication may mean that no reference signal resource indication for AI unit monitoring is carried, and the terminal may use the default value as the reference signal resource for AI unit monitoring.

[0136] In some embodiments, when the first configuration information includes measurement resources corresponding to the at least one AI use case indication, the AI ​​use case indicated by the at least one AI use case indication is an AI use case implemented by some or all AI units deployed by the inference device (terminal or base station), or the AI ​​use case group indicated by the at least one AI use case indication is an AI use case group implemented by some or all AI units deployed by the inference device (terminal or base station).

[0137] For example, the measurement resources corresponding to the at least one AI use case indication can be used for one or more measurements, that is, the measurement resources included in the first configuration information can be used for one or more measurements. Optionally, when the measurement resources corresponding to the at least one AI use case indication are used for multiple measurements, the base station can trigger or activate the current measurement resource through a MAC CE or DCI.

[0138] In some embodiments, the measurement resources corresponding to the at least one AI use case indication may also be configured in other ways, such as the measurement resources corresponding to the at least one AI use case indication may also be agreed upon by a protocol, or the measurement resources corresponding to the at least one AI use case indication may also be configured by other configuration information other than the first configuration information.

[0139] In some embodiments, when the first configuration information includes auxiliary information monitored by the AI ​​unit, the auxiliary information monitored by the AI ​​unit may include at least one of the following: an agent model, a reference data distribution, an inference result of the base station (the base station is an inference device), and a timestamp of the base station inference.

[0140] Optionally, the proxy model, also referred to as a reference model, is associated with the AI ​​use case identifier or AI use case group identifier indicated by the AI ​​use case indication, and network-side inference results can be inferred based on the proxy model. For example, the AI ​​use case is CSI compression and recovery, where CSI compression and recovery are achieved by compressing the channel into a data stream and decompressing the data stream into a channel. The decompression model is associated with the proxy model, meaning that the UE can infer the network-side data stream decompression result through the proxy model.

[0141] In an embodiment of the present application, when the first configuration information includes auxiliary information monitored by the AI ​​unit, the terminal can obtain the auxiliary information monitored by the AI ​​unit through the first configuration information, so that it can monitor based on the obtained auxiliary information monitored by the AI ​​unit and obtain monitoring results. By obtaining auxiliary information, the terminal enables the terminal side to collect complete monitoring data, and then processes the monitoring data according to the measurement quantity indication to obtain monitoring results. In a scenario where the base station participates in reasoning (including both the base station and the terminal participating in reasoning, or base station reasoning), if there is no auxiliary information, the terminal cannot obtain complete monitoring data, and thus cannot calculate the measurement quantity representing the monitoring indicator, or the monitoring result.

[0142] In some embodiments, the reference signal used for AI unit monitoring can be configured with reference to existing communication reference signals. Taking the RLM reference signal configuration as an example, the configuration method can be as follows:

[0143] That is, the reference signal used for AI unit monitoring may be SSB or CSI-RS.

[0144] In some embodiments, the reference signal used for AI unit monitoring can reuse existing communication reference signals. Taking the AI / ML monitoring reference signal configuration as an example, its configuration method can be as follows:

[0145] That is, the reference signal used for AI unit monitoring can be SSB or CSI-RS; and the AI ​​unit monitoring purpose includes but is not limited to one of the following: monitoring the AI / ML unit in the activated state, monitoring the AI / ML unit in the deactivated state.

[0146] In some embodiments, the first configuration information may be semi-statically configured or dynamically configured.

[0147] In some embodiments, the first configuration information may be carried by at least one of the following: Radio Resource Control (RRC) signaling, Media Access Control Control Element (MAC CE), and Downlink Control Information (DCI).

[0148] In some embodiments, before the terminal receives the first configuration information, the information reporting method 200 further includes: the terminal sending first information to the base station;

[0149] The first information is used to request the base station to perform AI unit monitoring configuration, and the first information includes but is not limited to at least one of the following:

[0150] AI use case identifier (such as the AI ​​use case identifier that the terminal requests to be monitored and configured), AI use case group identifier (such as the AI ​​use case group identifier that the terminal requests to be monitored and configured), auxiliary information, and request information for requesting auxiliary information for monitoring by the AI ​​unit.

[0151] In some embodiments, the first information is an AI unit monitoring configuration request, or the first information is a resource configuration request, or a reporting configuration request, or other similar request information, which is not limited in this embodiment of the present application.

[0152] Specifically, after receiving the first information, the base station sends the first configuration information to the terminal. That is, the first configuration information may be determined based on the first information.

[0153] That is, in this embodiment, the base station can determine the first configuration information based on the first information, thereby making the parameters included in the first configuration information more reasonable. Without the first information, the network side may not allocate the measurement resources and measurement quantities required for AI unit monitoring, resulting in the first configuration being unable to achieve the AI ​​unit measurement and monitoring effect. For example, insufficient measurement resource configuration may result in the inability to collect labeled data for comparison with model output. If the AI ​​use case identifier is unknown, it is impossible to configure reasonable monitoring indicators, such as the first measurement quantity.

[0154] In some embodiments, when the auxiliary information is included in the first information, the auxiliary information is used to indicate at least one of the following:

[0155] The resources monitored by the AI ​​unit are different from the resources the AI ​​unit reasons about;

[0156] AI unit monitoring purpose;

[0157] The AI ​​unit monitoring purpose is one of the following:

[0158] monitoring one or more AI units in a deactivated state;

[0159] monitoring one or more AI units in an activated state;

[0160] monitoring one or more AI functions that are in a deactivated state;

[0161] Monitor the active state of one or more AI functions.

[0162] In an embodiment of the present application, when auxiliary information is included in the first information, the base station can learn based on the obtained auxiliary information that: the resources monitored by the AI ​​unit are different from the resources inferred by the AI ​​unit, and / or the monitoring purpose of the AI ​​unit. The first configuration information can thus be determined based on the obtained auxiliary information. For example, when the resources monitored by the AI ​​unit are different from the resources inferred by the AI ​​unit, if there is no auxiliary information, it will result in insufficient measurement resource configuration, resulting in the inability to collect label data for comparison with the model output. For example, when the monitoring purpose of the AI ​​unit is to monitor one or more AI units in a deactivated state, then in the first configuration, the network default terminal will determine the measurement amount for monitoring by itself, and there is no need to indicate the measurement amount in the first configuration.

[0163] In some embodiments, the resources monitored by the AI ​​unit are different from the resources reasoned about by the AI ​​unit, including:

[0164] The resources monitored by the AI ​​unit are completely different from the resources reasoned about by the AI ​​unit (i.e., the resources monitored by the AI ​​unit do not overlap with the resources reasoned about by the AI ​​unit); or,

[0165] The resources monitored by the AI ​​unit partially overlap with the resources the AI ​​unit reasons about; or,

[0166] The resources monitored by the AI ​​unit cover the resources reasoned by the AI ​​unit; or,

[0167] The resources inferred by the AI ​​unit override the resources monitored by the AI ​​unit.

[0168] In some embodiments, if the auxiliary information is used to indicate: the AI ​​unit monitoring purpose is to monitor one or more AI units in a deactivated state, or the AI ​​unit monitoring purpose is to monitor one or more AI units in an activated state, or the AI ​​unit monitoring purpose is to monitor one or more AI functions in a deactivated state, or the AI ​​unit monitoring purpose is to monitor one or more AI functions in an activated state; the first configuration information may not carry the AI ​​unit monitoring purpose.

[0169] In some embodiments, the first information may be carried by at least one of the following:

[0170] RRC signaling, MAC CE, uplink control information (UCI).

[0171] In some embodiments, the information reporting method 200 further includes:

[0172] The terminal sends second information to the base station;

[0173] The second information is used to request the base station to perform AI unit monitoring, and the second information includes but is not limited to at least one of the following:

[0174] AI use case identifier (such as the AI ​​use case identifier that the terminal requests to monitor), AI use case group identifier (such as the AI ​​use case group identifier that the terminal requests to monitor), the purpose for which the terminal requests monitoring, and the reason why the terminal requests monitoring.

[0175] Specifically, the second information is sent by the terminal after receiving the first configuration information.

[0176] In an embodiment of the present application, the base station can trigger or initiate AI unit monitoring based on the second information, so that the base station can trigger AI unit monitoring in a timely manner, thereby avoiding the deterioration of AI unit reasoning performance and causing adverse effects on the network.

[0177] In some embodiments, the second information is an AI unit monitoring request, or the second information is a monitoring request, or other similar request information, which is not limited in this embodiment of the present application.

[0178] Specifically, after receiving the second information, the base station triggers the AI ​​unit monitoring through dynamic signaling (such as MAC CE or DCI).

[0179] In some embodiments, the purpose of the terminal requesting monitoring includes but is not limited to one of the following:

[0180] Monitor one or more AI units in an activated state, monitor one or more AI units in a deactivated state, monitor one or more AI functions in an activated state, and monitor one or more AI functions in a deactivated state.

[0181] In some embodiments, the reason why the terminal requests monitoring includes but is not limited to at least one of the following:

[0182] The AI ​​use case indicates that the reasoning of the corresponding AI unit is inaccurate, the terminal updates the activation status of one or more AI units, the terminal is preparing to activate one or more AI units in a deactivated state, the terminal detects a wireless link failure, and the terminal detects a deterioration in communication quality.

[0183] In some embodiments, when a first condition is met, the terminal sends the second information to the base station;

[0184] The first condition includes at least one of the following:

[0185] The AI ​​use case indicates that the reasoning of the corresponding AI unit is inaccurate, the terminal updates the activation status of one or more AI units, the terminal is preparing to activate one or more AI units in a deactivated state, the terminal detects a wireless link failure, and the terminal detects a deterioration in communication quality.

[0186] In an embodiment of the present application, when the first condition is met, the terminal sends the second information to the base station, which clarifies the conditions for the terminal to send the second information, thereby avoiding some unnecessary AI unit monitoring and also allowing timely AI unit monitoring when there is a potential risk of network performance deterioration.

[0187] In some embodiments, the AI ​​use case indicates that the reasoning of the corresponding AI unit is inaccurate, including:

[0188] The AI ​​use case indicates that the deviation between the inference result of the corresponding AI unit and the label data is greater than or equal to a threshold value of 1; or

[0189] During the first time period, the number of times that the inference result of the corresponding AI unit indicated by the AI ​​use case deviates from the label data by more than or equal to threshold value 1 or the probability is greater than or equal to threshold value 2; or

[0190] The AI ​​use case indicates that the distribution deviation of the input data of the corresponding AI unit during reasoning is greater than or equal to a threshold value of 3; or

[0191] The AI ​​use case indicates that the distribution deviation of the inference result data of the corresponding AI unit is greater than or equal to a threshold value of 4; or

[0192] During the second time period, the AI ​​use case indicates that the deviation between the inference result of the corresponding AI unit and the label data is less than or equal to the threshold value 5, or the probability is less than or equal to the threshold value 6.

[0193] For example, the terminal monitors that the communication quality deteriorates, including: the modulation and coding scheme (MCS) deteriorates compared to the block error rate (BLER) (MCS vs BLER deteriorates), for example, MCS vs BLER is less than or equal to a threshold value.

[0194] In some embodiments, the first condition is agreed upon by a protocol, or the first condition is pre-configured by a network device (base station or core network function node).

[0195] In some embodiments, the second information may be carried by at least one of the following:

[0196] RRC signaling, MAC CE, UCI.

[0197] In some embodiments, the information reporting method 200 further includes:

[0198] The terminal receives second configuration information sent by the base station; wherein the second configuration information is used to determine whether the reason for requesting monitoring is met, or the second configuration information is used to determine whether the first condition is met.

[0199] The second configuration information includes but is not limited to at least one of the following:

[0200] The first threshold value related to AI unit reasoning, the configuration indication corresponding to the wireless link failure, the measurement quantity related to communication quality monitoring, and the second threshold value related to communication quality monitoring.

[0201] In an embodiment of the present application, the terminal can obtain the threshold value related to the AI ​​unit reasoning (such as part or all of the above threshold values ​​1 to 6) through the second configuration information, thereby determining whether the reasoning of the AI ​​unit corresponding to the AI ​​use case indication is accurate. Alternatively, the terminal can obtain the configuration indication corresponding to the wireless link failure (such as the judgment indicator of the wireless link failure, measurement parameters, etc.) through the second configuration information, thereby determining whether the wireless link failure has occurred. Alternatively, the terminal can obtain the measurement quantity related to communication quality monitoring and the threshold value related to communication quality monitoring through the second configuration information, thereby determining whether the communication quality has deteriorated.

[0202] For example, the terminal may determine whether the reasoning of the AI ​​unit corresponding to the AI ​​use case indication is accurate based on a threshold value related to the reasoning of the AI ​​unit.

[0203] For example, the terminal may monitor whether a radio link failure occurs based on a configuration indication corresponding to the radio link failure (such as a judgment indicator of radio link failure, a measurement parameter, etc.).

[0204] For example, the terminal may perform measurement based on the measurement quantity related to the communication quality monitoring, and monitor whether the communication quality deteriorates based on the measurement result and the threshold value related to the communication quality monitoring.

[0205] In some embodiments, the second configuration information may be carried by at least one of the following:

[0206] RRC signaling, MAC CE, DCI.

[0207] In some embodiments, after the terminal receives the first configuration information, the information reporting method 200 further includes:

[0208] The terminal receives first indication information sent by the base station;

[0209] The first indication information is used to indicate the reporting configuration identifier monitored by the AI ​​unit, and the AI ​​use case indicates the corresponding measurement resources.

[0210] For example, the AI ​​unit monitoring reporting configuration identifier indicated by the first indication information can be used to obtain a pre-configured AI unit monitoring reporting configuration, so that the terminal can perform measurement reporting based on the obtained AI unit monitoring reporting configuration.

[0211] Specifically, after receiving the first indication information, the terminal obtains the reporting configuration monitored by the AI ​​unit, and measures the reference signal on the measurement resource corresponding to the AI ​​use case indication to obtain the measurement result.

[0212] In some embodiments, the first indication information may be carried by a MAC CE or a DCI. Specifically, for example, the first indication information is CSI-AssociatedReportConfigInfo.

[0213] Optionally, the measurement resources corresponding to the AI ​​use case indication indicated by the first indication information belong to the measurement resources associated with the AI ​​use case monitoring included in the first configuration information. For example, the base station activates part or all of the measurement resources associated with the AI ​​use case monitoring as the measurement resources corresponding to the AI ​​use case indication through the first indication information.

[0214] In an embodiment of the present application, the base station can trigger AI unit monitoring based on the first indication information, so that after receiving the first indication information, the terminal can measure the reference signal based on the content indicated by the first indication information to perform AI unit monitoring.

[0215] In some embodiments, in the above S230, the terminal reports based on the measurement result, including:

[0216] The terminal determines a first measurement amount based on the measurement result, and reports the first measurement amount to the base station, where the first measurement amount is a measurement amount monitored by the AI ​​unit (i.e., the terminal directly reports the first measurement amount, and the base station determines the monitoring result based on the first measurement amount reported by the terminal).

[0217] In an embodiment of the present application, the terminal reports a first measurement quantity to the base station, and the base station can determine a monitoring result based on the first measurement quantity reported by the terminal. In this embodiment, the terminal performs measurement and reporting, and the base station determines the monitoring result, that is, the terminal perceives the AI ​​unit monitoring process, which can avoid the terminal reporting some unnecessary data, thereby reducing the amount of data exchanged over the air interface. When the terminal does not perceive the AI ​​unit monitoring, the terminal needs to report a large amount of raw measurement data so that the network side can collect sufficient monitoring data to determine the monitoring result.

[0218] In some embodiments, in the above S230, the terminal reports based on the measurement result, including:

[0219] The terminal determines a monitoring result corresponding to the AI ​​use case indication based on the measurement result, and reports the monitoring result to the base station.

[0220] In an embodiment of the present application, the terminal determines the monitoring result corresponding to the AI ​​use case indication based on the measurement result, and reports the monitoring result to the base station. That is, in this embodiment, the terminal reports the final monitoring result, that is, the terminal perceives the AI ​​unit monitoring process, which can avoid the terminal reporting some unnecessary data, thereby reducing the amount of data exchanged over the air interface. In addition, compared to the terminal reporting the measurement amount, reporting the monitoring result can further reduce the amount of data reported by the terminal.

[0221] In some embodiments, in the above S230, the terminal reports based on the measurement result, including:

[0222] The terminal determines the monitoring result corresponding to the AI ​​use case indication based on the measurement result and the inference result and / or inference timestamp corresponding to the AI ​​use case indication provided by the base station, and reports the monitoring result to the base station.

[0223] In the embodiment of the present application, the base station (inference device) can provide an AI use case indicating the corresponding inference result and / or inference timestamp, so that the terminal can obtain complete monitoring data. Otherwise, the terminal side can only obtain label data and cannot collect complete monitoring data.

[0224] In some embodiments, the base station may provide the AI ​​use case provided to the terminal through the auxiliary information monitored by the AI ​​unit to indicate the corresponding inference result and / or inference timestamp.

[0225] In some embodiments, the terminal may carry the reported information through at least one of the following:

[0226] UCI, MAC CE, RRC signaling.

[0227] The following uses Examples 1 to 16 as examples to illustrate the technical solution of the present application.

[0228] In the first embodiment, the AI ​​use case is beam prediction, as shown in FIG3 , which may specifically include the following S1-1 to S1-5.

[0229] S1-1. The terminal receives first configuration information (such as measurement reporting configuration or CSI measurement reporting configuration) sent by the base station, where the first configuration information includes: an AI use case indication, a first measurement quantity, and measurement resources associated with the AI ​​use case monitoring; wherein the AI ​​use case indicated by the AI ​​use case indication is beam prediction, the first measurement quantity is a measurement quantity monitored by the AI ​​unit, and the first measurement quantity is a Top 1 accuracy rate of L1-RSRP (L1-RSRP is obtained by measuring the CSI reference signal, and the Top 1 accuracy rate of L1-RSRP is determined based on the measured L1-RSRP).

[0230] Optionally, the measurement resources associated with the AI ​​use case monitoring may reuse the measurement resources used during reasoning.

[0231] S1-2, the terminal receives first indication information sent by the base station, wherein the first indication information is used to indicate a reporting configuration identifier monitored by the AI ​​unit, and the AI ​​use case indicates corresponding measurement resources.

[0232] Optionally, the measurement resources corresponding to the AI ​​use case indication indicated by the first indication information belong to the measurement resources associated with the AI ​​use case monitoring included in the first configuration information. For example, the base station activates part or all of the measurement resources associated with the AI ​​use case monitoring as the measurement resources corresponding to the AI ​​use case indication through the first indication information.

[0233] Optionally, the first indication information may be carried by a MAC CE or a DCI. Specifically, for example, the first indication information is CSI-AssociatedReportConfigInfo.

[0234] S1-3, the base station sends a CSI reference signal on the measurement resource corresponding to the AI ​​use case indication.

[0235] S1-4, the terminal measures the L1-RSRP of the CSI reference signal on the measurement resource corresponding to the AI ​​use case indication, and processes to obtain the first measurement amount (ie, the Top1 accuracy of the L1-RSRP).

[0236] S1-5: The terminal reports the first measurement quantity (ie, the Top1 accuracy of L1-RSRP).

[0237] It should be noted that, in the above embodiment 1, the first measurement amount may also be the Top1 accuracy rate of L3-RSRP (L3-RSRP is obtained by measuring the CSI reference signal, and the Top1 accuracy rate of L3-RSRP is determined based on the measured L3-RSRP).

[0238] In the second embodiment, the AI ​​use case is CSI prediction, as shown in FIG4 , which may specifically include the following S2-1 to S2-5.

[0239] S2-1. The terminal receives first configuration information (such as measurement reporting configuration or CSI measurement reporting configuration) sent by the base station, wherein the first configuration information includes: an AI use case indication, a first measurement quantity, and measurement resources associated with the AI ​​use case monitoring; wherein the AI ​​use case indicated by the AI ​​use case indication is CSI prediction, the first measurement quantity is a measurement quantity monitored by the AI ​​unit, and the first measurement quantity is the square of the cosine similarity.

[0240] Optionally, the measurement resources associated with the AI ​​use case monitoring may reuse the measurement resources used during reasoning.

[0241] S2-2, the terminal receives first indication information sent by the base station, wherein the first indication information is used to indicate a reporting configuration identifier monitored by the AI ​​unit, and the AI ​​use case indicates corresponding measurement resources.

[0242] Optionally, the measurement resources corresponding to the AI ​​use case indication indicated by the first indication information belong to the measurement resources associated with the AI ​​use case monitoring included in the first configuration information. For example, the base station activates part or all of the measurement resources associated with the AI ​​use case monitoring as the measurement resources corresponding to the AI ​​use case indication through the first indication information.

[0243] Optionally, the first indication information may be carried by a MAC CE or a DCI. Specifically, for example, the first indication information is CSI-AssociatedReportConfigInfo.

[0244] S2-3, the base station sends a CSI reference signal on the measurement resource corresponding to the AI ​​use case indication.

[0245] S2-4, the terminal measures the CSI reference signal on the measurement resource corresponding to the AI ​​use case indication to obtain channel information, and processes it to obtain the first measurement value (i.e., the square of the cosine similarity).

[0246] S2-5: The terminal reports the first measurement value (ie, the square of the cosine similarity).

[0247] In the third embodiment, the AI ​​use case is CSI compression, as shown in FIG5 , which may specifically include the following S3-1 to S3-5.

[0248] S3-1. The terminal receives first configuration information (such as measurement reporting configuration or CSI measurement reporting configuration) sent by the base station, wherein the first configuration information includes: an AI use case indication, a first measurement quantity, measurement resources associated with the AI ​​use case monitoring, and auxiliary information monitored by the AI ​​unit; wherein the AI ​​use case indicated by the AI ​​use case indication is CSI prediction, the first measurement quantity is the measurement quantity monitored by the AI ​​unit, and the first measurement quantity is the square of the cosine similarity, and the auxiliary information monitored by the AI ​​unit is a proxy model.

[0249] Optionally, the measurement resources associated with the AI ​​use case monitoring may reuse the measurement resources used during reasoning.

[0250] S3-2, the terminal receives first indication information sent by the base station, wherein the first indication information is used to indicate the reporting configuration identifier monitored by the AI ​​unit, and the AI ​​use case indicates the corresponding measurement resources.

[0251] Optionally, the measurement resources corresponding to the AI ​​use case indication indicated by the first indication information belong to the measurement resources associated with the AI ​​use case monitoring included in the first configuration information. For example, the base station activates part or all of the measurement resources associated with the AI ​​use case monitoring as the measurement resources corresponding to the AI ​​use case indication through the first indication information.

[0252] Optionally, the first indication information may be carried by a MAC CE or a DCI. Specifically, for example, the first indication information is CSI-AssociatedReportConfigInfo.

[0253] S3-3, the base station sends a CSI reference signal on the measurement resource corresponding to the AI ​​use case indication.

[0254] S3-4, the terminal measures the CSI reference signal on the measurement resource corresponding to the AI ​​use case indication to obtain channel information, and determines the first measurement quantity (i.e., the square of the cosine similarity) according to the proxy model.

[0255] S3-5: The terminal reports the first measurement value (ie, the square of the cosine similarity).

[0256] It should be noted that in the above-mentioned embodiments 1 to 3, the inference device (i.e., the terminal) receives first configuration information (i.e., the measurement reporting configuration) from the base station, which includes an indication of a measurement quantity (i.e., the first measurement quantity) representing the monitored KPI, and may also include auxiliary information monitored by the AI ​​unit, such as a proxy model. The inference device (i.e., the terminal) collects data based on the associated measurement resource indication, processes the data based on the measurement quantity indication, calculates the first measurement quantity, and reports the first measurement quantity to the base station.

[0257] In the fourth embodiment, the AI ​​use case is beam prediction, as shown in FIG6 , which may specifically include the following S4-1 to S4-7.

[0258] S4-1. The terminal sends first information (such as an AI unit monitoring configuration request) to the base station. The first information is used to request the base station to perform AI unit monitoring configuration, and the first information includes:

[0259] The AI ​​use case identifier for which the terminal requests monitoring configuration: beam prediction;

[0260] Auxiliary information: The resources monitored by the AI ​​unit are different from the resources reasoned by the AI ​​unit.

[0261] Optionally, the first information may be sent by the UE to the network (eg, a base station) when the AI ​​unit is registered. For example, the first information may be carried in a UE capability report or an AI unit function report.

[0262] S4-2. The terminal receives first configuration information (such as measurement reporting configuration) sent by the base station, wherein the first configuration information includes: an AI use case indication, a first measurement quantity, and measurement resources associated with the AI ​​use case monitoring; wherein the AI ​​use case indicated by the AI ​​use case indication is beam prediction, the first measurement quantity is a measurement quantity monitored by the AI ​​unit, and the first measurement quantity is a Top1 accuracy rate of L1-RSRP (L1-RSRP is obtained by measuring a CSI reference signal, and the Top1 accuracy rate of L1-RSRP is determined based on the measured L1-RSRP).

[0263] Optionally, the measurement resources associated with the AI ​​use case monitoring may reuse the measurement resources used during reasoning.

[0264] S4-3, the terminal sends second information (such as an AI unit monitoring request) to the base station, where the second information is used to request the base station to perform AI unit monitoring, and the second information includes:

[0265] AI use case identification for terminal request monitoring: beam prediction.

[0266] Optionally, when the first condition is met, the terminal sends the second information to the base station;

[0267] The first condition includes at least one of the following:

[0268] The AI ​​use case indicates that the reasoning of the corresponding AI unit is inaccurate, the terminal updates the activation status of one or more AI units, the terminal is preparing to activate one or more AI units in a deactivated state, the terminal detects a wireless link failure, and the terminal detects a deterioration in communication quality.

[0269] S4-4, the terminal receives first indication information sent by the base station, wherein the first indication information is used to indicate the reporting configuration identifier monitored by the AI ​​unit, and the AI ​​use case indicates the corresponding measurement resources.

[0270] Optionally, the measurement resources corresponding to the AI ​​use case indication indicated by the first indication information belong to the measurement resources associated with the AI ​​use case monitoring included in the first configuration information. For example, the base station activates part or all of the measurement resources associated with the AI ​​use case monitoring as the measurement resources corresponding to the AI ​​use case indication through the first indication information.

[0271] Optionally, the first indication information may be carried by a MAC CE or a DCI. Specifically, for example, the first indication information is CSI-AssociatedReportConfigInfo.

[0272] S4-5, the base station sends a CSI reference signal on the measurement resource corresponding to the AI ​​use case indication.

[0273] S4-6, the terminal measures the CSI reference signal on the measurement resource corresponding to the AI ​​use case indication to obtain L1-RSRP, and then processes it to obtain the first measurement amount (i.e., the Top1 accuracy of L1-RSRP).

[0274] S4-7: The terminal reports the first measurement quantity (ie, the Top1 accuracy of L1-RSRP).

[0275] It should be noted that, in the above fourth embodiment, the first measurement amount may also be the Top1 accuracy rate of L3-RSRP (L3-RSRP is obtained by measuring the CSI reference signal, and the Top1 accuracy rate of L3-RSRP is determined based on the measured L3-RSRP).

[0276] In the fifth embodiment, the AI ​​use case is CSI prediction, as shown in FIG7 , which may specifically include the following S5-1 to S5-7.

[0277] S5-1. The terminal sends first information (such as an AI unit monitoring configuration request) to the base station. The first information is used to request the base station to perform AI unit monitoring configuration, and the first information includes:

[0278] The AI ​​use case identifier for which the terminal requests monitoring configuration: CSI prediction;

[0279] Auxiliary information: The resources monitored by the AI ​​unit are different from the resources reasoned by the AI ​​unit.

[0280] Optionally, the first information may be sent by the UE to the network (eg, a base station) when the AI ​​unit is registered. For example, the first information may be carried in a UE capability report or an AI unit function report.

[0281] S5-2, the terminal receives first configuration information (such as measurement reporting configuration or CSI measurement reporting configuration) sent by the base station, wherein the first configuration information includes: an AI use case indication, a first measurement quantity, and measurement resources associated with the AI ​​use case monitoring; wherein the AI ​​use case indicated by the AI ​​use case indication is CSI prediction, the first measurement quantity is a measurement quantity monitored by the AI ​​unit, and the first measurement quantity is the square of the cosine similarity.

[0282] Optionally, the measurement resources associated with the AI ​​use case monitoring may reuse the measurement resources used during reasoning.

[0283] S5-3, the terminal sends second information (such as an AI unit monitoring request) to the base station, where the second information is used to request the base station to perform AI unit monitoring, and the second information includes:

[0284] AI use case identification for terminal request monitoring: CSI prediction.

[0285] Optionally, when the first condition is met, the terminal sends the second information to the base station;

[0286] The first condition includes at least one of the following:

[0287] The AI ​​use case indicates that the reasoning of the corresponding AI unit is inaccurate, the terminal updates the activation status of one or more AI units, the terminal is preparing to activate one or more AI units in a deactivated state, the terminal detects a wireless link failure, and the terminal detects a deterioration in communication quality.

[0288] S5-4, the terminal receives first indication information sent by the base station, wherein the first indication information is used to indicate the reporting configuration identifier monitored by the AI ​​unit, and the AI ​​use case indicates the corresponding measurement resources.

[0289] Optionally, the measurement resources corresponding to the AI ​​use case indication indicated by the first indication information belong to the measurement resources associated with the AI ​​use case monitoring included in the first configuration information. For example, the base station activates part or all of the measurement resources associated with the AI ​​use case monitoring as the measurement resources corresponding to the AI ​​use case indication through the first indication information.

[0290] Optionally, the first indication information may be carried by a MAC CE or a DCI. Specifically, for example, the first indication information is CSI-AssociatedReportConfigInfo.

[0291] S5-5, the base station sends a CSI reference signal on the measurement resource corresponding to the AI ​​use case indication.

[0292] S5-6, the terminal measures the CSI reference signal on the measurement resource corresponding to the AI ​​use case indication to obtain channel information, and then processes it to obtain the first measurement value (i.e., the square of the cosine similarity).

[0293] S5-7: The terminal reports the first measurement value (ie, the square of the cosine similarity).

[0294] In the sixth embodiment, the AI ​​use case is CSI compression, as shown in FIG8 , which may specifically include the following S6-1 to S6-7.

[0295] S6-1. The terminal sends first information (such as an AI unit monitoring configuration request) to the base station. The first information is used to request the base station to perform AI unit monitoring configuration, and the first information includes:

[0296] The AI ​​use case identifier for which the terminal requests monitoring configuration: CSI compression;

[0297] Auxiliary information: The resources monitored by the AI ​​unit are different from the resources reasoned by the AI ​​unit.

[0298] Optionally, the first information may be sent by the UE to the network (eg, a base station) when the AI ​​unit is registered. For example, the first information may be carried in a UE capability report or an AI unit function report.

[0299] S6-2, the terminal receives first configuration information (such as measurement reporting configuration) sent by the base station, wherein the first configuration information includes: an AI use case indication, a first measurement quantity, measurement resources associated with the AI ​​use case monitoring, and auxiliary information monitored by the AI ​​unit; wherein the AI ​​use case indicated by the AI ​​use case indication is CSI compression, the first measurement quantity is the measurement quantity monitored by the AI ​​unit, and the first measurement quantity is the square of the cosine similarity, and the auxiliary information monitored by the AI ​​unit is a proxy model.

[0300] Optionally, the measurement resources associated with the AI ​​use case monitoring may reuse the measurement resources used during reasoning.

[0301] S6-3, the terminal sends second information (such as an AI unit monitoring request) to the base station, where the second information is used to request the base station to perform AI unit monitoring, and the second information includes:

[0302] AI use case identifier for terminal request monitoring: CSI compression.

[0303] Optionally, when the first condition is met, the terminal sends the second information to the base station;

[0304] The first condition includes at least one of the following:

[0305] The AI ​​use case indicates that the reasoning of the corresponding AI unit is inaccurate, the terminal updates the activation status of one or more AI units, the terminal is preparing to activate one or more AI units in a deactivated state, the terminal detects a wireless link failure, and the terminal detects a deterioration in communication quality.

[0306] S6-4, the terminal receives first indication information sent by the base station, wherein the first indication information is used to indicate the reporting configuration identifier monitored by the AI ​​unit, and the AI ​​use case indicates the corresponding measurement resources.

[0307] Optionally, the measurement resources corresponding to the AI ​​use case indication indicated by the first indication information belong to the measurement resources associated with the AI ​​use case monitoring included in the first configuration information. For example, the base station activates part or all of the measurement resources associated with the AI ​​use case monitoring as the measurement resources corresponding to the AI ​​use case indication through the first indication information.

[0308] Optionally, the first indication information may be carried by a MAC CE or a DCI. Specifically, for example, the first indication information is CSI-AssociatedReportConfigInfo.

[0309] S6-5, the base station sends a CSI reference signal on the measurement resource corresponding to the AI ​​use case indication.

[0310] S6-6: The terminal measures the CSI reference signal on the measurement resource corresponding to the AI ​​use case indication to obtain channel information, and then determines the first measurement quantity (ie, the square of the cosine similarity) according to the proxy model.

[0311] S6-7: The terminal reports the first measurement value (ie, the square of the cosine similarity).

[0312] It should be noted that in the above-mentioned embodiments 4 to 6, the inference device (i.e., the terminal) sends the first information (such as an AI unit monitoring configuration request) to the base station before the RRC configuration, including: the AI ​​use case identifier for the terminal to request monitoring configuration, and may also include auxiliary information or auxiliary information request. The inference device (i.e., the terminal) receives the first configuration information (such as measurement reporting configuration) from the base station, including an indication of the measurement quantity (i.e., the first measurement quantity) that characterizes the monitoring KPI, and may also include auxiliary information monitored by the AI ​​unit, such as a proxy model. The inference device (i.e., the terminal) initiates the second information (such as a monitoring request) to the base station, including the reason for triggering the monitoring request, and may also include a characteristic identifier or a model identifier. The inference device (i.e., the terminal) collects data according to the associated measurement resource indication, processes the data according to the measurement quantity indication, calculates the first measurement quantity, and reports the first measurement quantity to the base station.

[0313] In the seventh embodiment, the AI ​​use case is beam prediction, and the AI ​​unit monitoring purpose is to monitor the AI ​​unit in the deactivated state, as shown in FIG9 , which may specifically include the following S7-1 to S7-7.

[0314] S7-1. The terminal sends first information (such as an AI unit monitoring configuration request) to the base station. The first information is used to request the base station to perform AI unit monitoring configuration, and the first information includes:

[0315] The AI ​​use case identifier for which the terminal requests monitoring configuration: beam prediction;

[0316] AI unit monitoring purpose: To monitor the AI ​​unit in deactivated state.

[0317] Optionally, the first information may be sent by the UE to the network (eg, a base station) when the AI ​​unit is registered. For example, the first information may be carried in a UE capability report or an AI unit function report.

[0318] S7-2, the terminal receives first configuration information (such as measurement reporting configuration) sent by the base station, wherein the first configuration information includes: an AI use case indication, a first measurement amount, and measurement resources associated with the AI ​​use case monitoring; wherein the AI ​​use case indicated by the AI ​​use case indication is beam prediction, the first measurement amount is a measurement amount monitored by the AI ​​unit, and the first measurement amount is an AI unit indication that meets the expected deactivated state.

[0319] Optionally, the measurement resources associated with the AI ​​use case monitoring may reuse the measurement resources used during reasoning.

[0320] S7-3, the terminal sends second information (such as an AI unit monitoring request) to the base station, where the second information is used to request the base station to perform AI unit monitoring, and the second information includes:

[0321] AI use case identification for terminal request monitoring: beam prediction.

[0322] Optionally, when the first condition is met, the terminal sends the second information to the base station;

[0323] The first condition includes at least one of the following:

[0324] The AI ​​use case indicates that the reasoning of the corresponding AI unit is inaccurate, the terminal updates the activation status of one or more AI units, the terminal is preparing to activate one or more AI units in a deactivated state, the terminal detects a wireless link failure, and the terminal detects a deterioration in communication quality.

[0325] S7-4, the terminal receives the first indication information sent by the base station, wherein the first indication information is used to indicate the reporting configuration identifier monitored by the AI ​​unit, and the corresponding measurement resources indicated by the AI ​​use case.

[0326] Optionally, the measurement resources corresponding to the AI ​​use case indication indicated by the first indication information belong to the measurement resources associated with the AI ​​use case monitoring included in the first configuration information. For example, the base station activates part or all of the measurement resources associated with the AI ​​use case monitoring as the measurement resources corresponding to the AI ​​use case indication through the first indication information.

[0327] Optionally, the first indication information may be carried by a MAC CE or a DCI. Specifically, for example, the first indication information is CSI-AssociatedReportConfigInfo.

[0328] S7-5, the base station sends a CSI reference signal on the measurement resource corresponding to the AI ​​use case indication.

[0329] S7-6, the terminal measures the CSI reference signal on the measurement resource corresponding to the AI ​​use case indication, and determines the first measurement quantity (ie, the AI ​​unit indication that meets the expected deactivated state).

[0330] S7-7, the terminal reports the first measurement quantity (ie, the AI ​​unit indication that meets the expected deactivation state).

[0331] It should be noted that in the above-mentioned embodiment seven, the inference device (i.e., the terminal) sends the first information (such as an AI unit monitoring configuration request) to the base station before the RRC configuration, including the AI ​​use case identifier, and may also include auxiliary information (including inactive model monitoring). The inference device (i.e., the terminal) receives the first configuration information (such as the measurement reporting configuration) from the base station, including the expected inactive model indication, or the recommended inactive model indication. The inference device (i.e., the terminal) initiates the second information (such as a monitoring request) to the base station, including the reason for triggering the monitoring request (inactive model monitoring), and may also include a feature identifier or a model identifier. The inference device (i.e., the terminal) collects data according to the associated measurement resource indication, determines the monitoring indicators by itself, determines the performance ranking of the deactivation model, and reports the recommended or expected deactivation model identifier to the base station.

[0332] In the eighth embodiment, the AI ​​use case is beam prediction, as shown in FIG10 , which may specifically include the following S8-1 to S8-5.

[0333] S8-1. The terminal receives first configuration information (such as measurement reporting configuration or CSI measurement reporting configuration) sent by the base station, wherein the first configuration information includes: an AI use case indication, a first measurement amount, and measurement resources associated with the AI ​​use case monitoring; wherein the AI ​​use case indicated by the AI ​​use case indication is beam prediction, the first measurement amount is the measurement amount monitored by the AI ​​unit, and the first measurement amount is the Top1 accuracy of L1-RSRP.

[0334] Optionally, the measurement resources associated with the AI ​​use case monitoring may reuse the measurement resources used during reasoning.

[0335] S8-2, the terminal receives first indication information sent by the base station, wherein the first indication information is used to indicate the reporting configuration identifier monitored by the AI ​​unit, and the AI ​​use case indicates the corresponding measurement resources.

[0336] Optionally, the measurement resources corresponding to the AI ​​use case indication indicated by the first indication information belong to the measurement resources associated with the AI ​​use case monitoring included in the first configuration information. For example, the base station activates part or all of the measurement resources associated with the AI ​​use case monitoring as the measurement resources corresponding to the AI ​​use case indication through the first indication information.

[0337] Optionally, the first indication information may be carried by a MAC CE or a DCI. Specifically, for example, the first indication information is CSI-AssociatedReportConfigInfo.

[0338] S8-3, the base station sends a CSI reference signal and auxiliary information monitored by the AI ​​unit on the measurement resources corresponding to the AI ​​use case indication, wherein the auxiliary information monitored by the AI ​​unit includes the inference result and / or inference timestamp corresponding to the AI ​​use case indication provided by the base station.

[0339] S8-4, the terminal measures the CSI reference signal on the measurement resource corresponding to the AI ​​use case indication to obtain L1-RSRP, and then determines the first measurement amount (i.e., the Top1 accuracy of L1-RSRP) based on the auxiliary information sent by the base station.

[0340] S8-5: The terminal reports the first measurement amount (ie, the Top1 accuracy of L1-RSRP).

[0341] It should be noted that, in the above-mentioned embodiment eight, the first measurement amount may also be the Top1 accuracy rate of L3-RSRP (L3-RSRP is obtained by measuring the CSI reference signal, and the Top1 accuracy rate of L3-RSRP is determined based on the measured L3-RSRP).

[0342] It should be noted that in the above-mentioned eighth embodiment, the terminal receives auxiliary information (base station inference result and timestamp) monitored by the AI ​​unit sent by the inference device (i.e., the base station). The terminal collects data according to the associated measurement resource indication, processes the data according to the measurement quantity indication, calculates the first measurement quantity, and reports the first measurement quantity to the base station.

[0343] In the ninth embodiment, the AI ​​use case is beam prediction, as shown in FIG11 , which may specifically include the following S9-1 to S9-5.

[0344] S9-1, the terminal receives first configuration information (such as AI monitoring reference signal configuration information) sent by the base station, wherein the first configuration information includes: an AI use case indication and a first measurement quantity; wherein the AI ​​use case indicated by the AI ​​use case indication is beam prediction, the first measurement quantity is the measurement quantity monitored by the AI ​​unit, and the first measurement quantity is the Top1 accuracy of L1-RSRP.

[0345] S9-2, the terminal receives first indication information sent by the base station, wherein the first indication information is used to indicate the reporting configuration identifier monitored by the AI ​​unit, and the AI ​​use case indicates the corresponding measurement resources.

[0346] Optionally, the first indication information may be carried by a MAC CE or a DCI. Specifically, for example, the first indication information is CSI-AssociatedReportConfigInfo.

[0347] S9-3, the base station sends an AI monitoring reference signal on the measurement resource corresponding to the AI ​​use case indication.

[0348] S9-4, the terminal measures the CSI reference signal on the measurement resource corresponding to the AI ​​use case indication to obtain L1-RSRP, and then processes it to obtain the first measurement amount (i.e., the Top1 accuracy of L1-RSRP).

[0349] S9-5: The terminal reports the first measurement amount (ie, the Top1 accuracy of L1-RSRP).

[0350] It should be noted that in the above-mentioned embodiment nine, the inference device (i.e., the terminal) receives the first configuration information (such as the AI ​​unit monitoring reference signal configuration) from the base station. The inference device receives a MACCE or DCI trigger from the base station, and the trigger signaling includes an AI use case identifier or a reporting configuration identifier (associated measurement quantity). The inference device receives the AI ​​use case monitoring reference signal. The inference device determines the first measurement quantity based on the AI ​​use case monitoring reference signal, or determines the first measurement quantity based on the AI ​​use case monitoring reference signal and the indicated measurement quantity, performs data collection and data processing, and calculates the first measurement quantity. The inference device reports the first measurement quantity.

[0351] It should be noted that, in the above-mentioned ninth embodiment, the first measurement amount may also be the Top1 accuracy rate of L3-RSRP (obtaining L3-RSRP by measuring the CSI reference signal, and determining the Top1 accuracy rate of L3-RSRP based on the measured L3-RSRP).

[0352] In the tenth embodiment, the AI ​​use case is CSI compression, as shown in FIG12 , which may specifically include the following S10 - 1 to S10 - 5 .

[0353] S10-1. The terminal receives first configuration information (such as AI monitoring reference signal configuration information) sent by the base station, wherein the first configuration information includes: an AI use case indication, a first measurement quantity, and auxiliary information monitored by the AI ​​unit; wherein the AI ​​use case indicated by the AI ​​use case indication is CSI compression, the first measurement quantity is a measurement quantity monitored by the AI ​​unit, the first measurement quantity is the square of the cosine similarity, and the auxiliary information monitored by the AI ​​unit is a proxy model.

[0354] S10-2, the terminal receives first indication information sent by the base station, wherein the first indication information is used to indicate a reporting configuration identifier monitored by the AI ​​unit, and the AI ​​use case indicates corresponding measurement resources.

[0355] Optionally, the first indication information may be carried by a MAC CE or a DCI. Specifically, for example, the first indication information is CSI-AssociatedReportConfigInfo.

[0356] S10-3, the base station sends an AI monitoring reference signal on the measurement resource corresponding to the AI ​​use case indication.

[0357] S10-4, the terminal measures the CSI reference signal on the measurement resource corresponding to the AI ​​use case indication to obtain channel information, and then determines the first measurement quantity (i.e., the square of the cosine similarity between the reconstructed channel and the measured channel) according to the proxy model.

[0358] S10-5: The terminal reports the first measurement value (ie, the square of the cosine similarity).

[0359] In the eleventh embodiment, the AI ​​use case is beam prediction, as shown in FIG13 , which may specifically include the following S11-1 to S11-5.

[0360] S11-1, the terminal receives first configuration information (such as AI monitoring reference signal configuration information) sent by the base station, wherein the first configuration information includes: an AI use case indication and a first measurement quantity; wherein the AI ​​use case indicated by the AI ​​use case indication is beam prediction, the first measurement quantity is a measurement quantity monitored by the AI ​​unit, and the first measurement quantity is the Top1 accuracy of L1-RSRP.

[0361] Optionally, the first configuration information further includes an indicator threshold, such as a threshold for Top 1 accuracy.

[0362] S11-2, the terminal receives first indication information sent by the base station, wherein the first indication information is used to indicate a reporting configuration identifier monitored by the AI ​​unit, and the AI ​​use case indicates corresponding measurement resources.

[0363] Optionally, the first indication information may be carried by a MAC CE or a DCI. Specifically, for example, the first indication information is CSI-AssociatedReportConfigInfo.

[0364] S11-3, the base station sends an AI monitoring reference signal on the measurement resource corresponding to the AI ​​use case indication.

[0365] S11-4, the terminal measures the CSI reference signal on the measurement resource corresponding to the AI ​​use case indication to obtain L1-RSRP, processes the first measurement quantity (i.e., the Top1 accuracy of L1-RSRP), and determines the monitoring result based on the first measurement quantity and the indicator threshold.

[0366] S11-5, the terminal reports the monitoring result (such as whether the AI ​​unit is valid or invalid).

[0367] It should be noted that in the above-mentioned embodiment eleven, the inference device (i.e., the terminal) receives the first configuration information (such as the AI ​​unit monitoring reference signal configuration) from the base station; the inference device receives a MACCE or DCI trigger from the base station, and the trigger signaling includes an AI use case identifier or a reporting configuration identifier (associated measurement quantity). The inference device receives the AI ​​use case monitoring reference signal; the inference device determines the measurement quantity for monitoring based on the AI ​​use case, or determines the first measurement quantity based on the AI ​​use case and the indicated measurement quantity, and collects and processes monitoring data. The inference device reports the AI ​​unit monitoring result (model validity or failure) based on pre-configured events.

[0368] It should be noted that, in the above embodiment eleven, the first measurement amount may also be the Top1 accuracy rate of L3-RSRP (L3-RSRP is obtained by measuring the CSI reference signal, and the Top1 accuracy rate of L3-RSRP is determined based on the measured L3-RSRP).

[0369] In the twelfth embodiment, the AI ​​use case is beam prediction, as shown in FIG14 , which may specifically include the following S12-1 to S12-5.

[0370] S12-1, the terminal receives first configuration information (such as AI monitoring reference signal configuration information) sent by the base station (inference device), wherein the first configuration information includes: an AI use case indication and a first measurement quantity; wherein the AI ​​use case indicated by the AI ​​use case indication is beam prediction, the first measurement quantity is a measurement quantity monitored by the AI ​​unit, and the first measurement quantity is the Top1 accuracy of L1-RSRP.

[0371] Optionally, the first configuration information further includes an indicator threshold, such as a threshold for Top 1 accuracy.

[0372] S12-2, the terminal receives first indication information sent by the base station, wherein the first indication information is used to indicate a reporting configuration identifier monitored by the AI ​​unit, and the AI ​​use case indicates corresponding measurement resources.

[0373] Optionally, the first indication information may be carried by a MAC CE or a DCI. Specifically, for example, the first indication information is CSI-AssociatedReportConfigInfo.

[0374] S12-3, the base station sends an AI monitoring reference signal and auxiliary information monitored by the AI ​​unit on the measurement resources corresponding to the AI ​​use case indication, wherein the auxiliary information monitored by the AI ​​unit includes the inference result and / or inference timestamp corresponding to the AI ​​use case indication provided by the base station.

[0375] S12-4, the terminal measures the CSI reference signal on the measurement resource corresponding to the AI ​​use case indication to obtain L1-RSRP, and then determines the first measurement quantity (i.e., the Top1 accuracy of the L1-RSRP inferred by the base station) according to the auxiliary information monitored by the AI ​​unit, and determines the monitoring result based on the first measurement quantity and the indicator threshold.

[0376] S12-5, the terminal reports the monitoring result (such as whether the AI ​​unit is valid or invalid).

[0377] It should be noted that, in the above embodiment 12, the first measurement amount may also be the Top1 accuracy rate of L3-RSRP (obtaining L3-RSRP by measuring the CSI reference signal, and determining the Top1 accuracy rate of L3-RSRP based on the measured L3-RSRP).

[0378] In the thirteenth embodiment, the AI ​​use case is beam prediction, as shown in FIG15 , which may specifically include the following S13-1 to S13-7.

[0379] S13-1. The terminal (inference device) sends first information (e.g., an AI unit monitoring configuration request) to the base station. The first information is used to request the base station to perform AI unit monitoring configuration, and the first information includes:

[0380] The AI ​​use case identifier for which the terminal requests monitoring configuration: beam prediction.

[0381] Optionally, the first information may be sent by the UE to the network (eg, a base station) when the AI ​​unit is registered. For example, the first information may be carried in a UE capability report or an AI unit function report.

[0382] S13-2, the terminal receives first configuration information (such as AI monitoring reference signal configuration information) sent by the base station, wherein the first configuration information includes: an AI use case indication and a first measurement quantity; wherein the AI ​​use case indicated by the AI ​​use case indication is beam prediction, the first measurement quantity is a measurement quantity monitored by the AI ​​unit, and the first measurement quantity is the Top1 accuracy of L1-RSRP.

[0383] S13-3, the terminal sends second information (such as an AI unit monitoring request) to the base station, where the second information is used to request the base station to perform AI unit monitoring, and the second information includes:

[0384] AI use case identifier for terminal request monitoring: beam prediction; or

[0385] The AI ​​unit ID being monitored.

[0386] Optionally, when the first condition is met, the terminal sends the second information to the base station;

[0387] The first condition includes at least one of the following:

[0388] The AI ​​use case indicates that the reasoning of the corresponding AI unit is inaccurate, the terminal updates the activation status of one or more AI units, the terminal is preparing to activate one or more AI units in a deactivated state, the terminal detects a wireless link failure, and the terminal detects a deterioration in communication quality.

[0389] S13-4, the terminal receives first indication information sent by the base station, wherein the first indication information is used to indicate the reporting configuration identifier monitored by the AI ​​unit, and the AI ​​use case indicates the corresponding measurement resources.

[0390] Optionally, the first indication information may be carried by a MAC CE or a DCI. Specifically, for example, the first indication information is CSI-AssociatedReportConfigInfo.

[0391] S13-5, the base station sends an AI monitoring reference signal on the measurement resource corresponding to the AI ​​use case indication.

[0392] S13-6, the terminal measures the AI ​​monitoring reference signal on the measurement resource corresponding to the AI ​​use case indication to obtain L1-RSRP, and then processes it to obtain the first measurement quantity (i.e., the Top1 accuracy of L1-RSRP).

[0393] S13-7, the terminal reports the first measurement amount (ie, the Top1 accuracy of L1-RSRP).

[0394] It should be noted that, in the above-mentioned embodiment thirteen, the first measurement amount may also be the Top1 accuracy rate of L3-RSRP (obtaining L3-RSRP by measuring the CSI reference signal, and determining the Top1 accuracy rate of L3-RSRP based on the measured L3-RSRP).

[0395] In the fourteenth embodiment, the AI ​​use case is beam prediction, as shown in FIG16 , which may specifically include the following S14-1 to S14-7.

[0396] S14-1: The terminal (inference device) sends first information (e.g., an AI unit monitoring configuration request) to the base station. The first information is used to request the base station to perform AI unit monitoring configuration, and the first information includes:

[0397] The AI ​​use case identifier for which the terminal requests monitoring configuration: beam prediction.

[0398] Optionally, the first information may be sent by the UE to the network (eg, a base station) when the AI ​​unit is registered. For example, the first information may be carried in a UE capability report or an AI unit function report.

[0399] S14-2, the terminal receives first configuration information (such as AI monitoring reference signal configuration information) sent by the base station, wherein the first configuration information includes: an AI use case indication and a first measurement quantity; wherein the AI ​​use case indicated by the AI ​​use case indication is beam prediction, the first measurement quantity is a measurement quantity monitored by the AI ​​unit, and the first measurement quantity is the Top1 accuracy of L1-RSRP.

[0400] Optionally, the first configuration information further includes an indicator threshold, such as a threshold for Top 1 accuracy.

[0401] S14-3, the terminal sends second information (such as an AI unit monitoring request) to the base station, where the second information is used to request the base station to perform AI unit monitoring, and the second information includes:

[0402] AI use case identifier for terminal request monitoring: beam prediction; or

[0403] The AI ​​unit ID being monitored.

[0404] Optionally, when the first condition is met, the terminal sends the second information to the base station;

[0405] The first condition includes at least one of the following:

[0406] The AI ​​use case indicates that the reasoning of the corresponding AI unit is inaccurate, the terminal updates the activation status of one or more AI units, the terminal is preparing to activate one or more AI units in a deactivated state, the terminal detects a wireless link failure, and the terminal detects a deterioration in communication quality.

[0407] S14-4, the terminal receives first indication information sent by the base station, wherein the first indication information is used to indicate a reporting configuration identifier monitored by the AI ​​unit, and the AI ​​use case indicates corresponding measurement resources.

[0408] Optionally, the first indication information may be carried by a MAC CE or a DCI. Specifically, for example, the first indication information is CSI-AssociatedReportConfigInfo.

[0409] S14-5, the base station sends an AI monitoring reference signal on the measurement resource corresponding to the AI ​​use case indication.

[0410] S14-6, the terminal measures the AI ​​monitoring reference signal on the measurement resource corresponding to the AI ​​use case indication to obtain L1-RSRP, then processes to obtain the first measurement quantity (i.e., the Top1 accuracy of L1-RSRP), and determines the monitoring result based on the first measurement quantity and the indicator threshold.

[0411] S14-7, the terminal reports the monitoring result (such as whether the AI ​​unit is valid or invalid).

[0412] It should be noted that, in the above-mentioned embodiment 14, the first measurement amount may also be the Top1 accuracy rate of L3-RSRP (L3-RSRP is obtained by measuring the CSI reference signal, and the Top1 accuracy rate of L3-RSRP is determined based on the measured L3-RSRP).

[0413] In the fifteenth embodiment, the AI ​​use case is CSI compression, as shown in FIG17 , which may specifically include the following S15-1 to S15-7.

[0414] S15-1: The terminal (inference device) sends first information (e.g., an AI unit monitoring configuration request) to the base station. The first information is used to request the base station to perform AI unit monitoring configuration, and the first information includes:

[0415] The AI ​​use case identifier for which the terminal requests monitoring configuration: CSI compression.

[0416] Optionally, the first information may be sent by the UE to the network (eg, a base station) when the AI ​​unit is registered. For example, the first information may be carried in a UE capability report or an AI unit function report.

[0417] S15-2, the terminal receives first configuration information (such as measurement reporting configuration or CSI measurement reporting configuration) sent by the base station, wherein the first configuration information includes: an AI use case indication, a first measurement quantity, and auxiliary information monitored by the AI ​​unit; wherein the AI ​​use case indicated by the AI ​​use case indication is CSI compression, the first measurement quantity is the measurement quantity monitored by the AI ​​unit, and the first measurement quantity is the square of the cosine similarity, and the auxiliary information monitored by the AI ​​unit is a proxy model.

[0418] Optionally, the first configuration information further includes an indicator threshold, such as a threshold of the square of the cosine similarity.

[0419] S15-3, the terminal sends second information (such as an AI unit monitoring request) to the base station, where the second information is used to request the base station to perform AI unit monitoring, and the second information includes:

[0420] AI use case identifier requested by the terminal for monitoring: CSI compression; or

[0421] The AI ​​unit ID being monitored.

[0422] Optionally, when the first condition is met, the terminal sends the second information to the base station;

[0423] The first condition includes at least one of the following:

[0424] The AI ​​use case indicates that the reasoning of the corresponding AI unit is inaccurate, the terminal updates the activation status of one or more AI units, the terminal is preparing to activate one or more AI units in a deactivated state, the terminal detects a wireless link failure, and the terminal detects a deterioration in communication quality.

[0425] S15-4, the terminal receives first indication information sent by the base station, wherein the first indication information is used to indicate the reporting configuration identifier monitored by the AI ​​unit, and the AI ​​use case indicates the corresponding measurement resources.

[0426] Optionally, the first indication information may be carried by a MAC CE or a DCI. Specifically, for example, the first indication information is CSI-AssociatedReportConfigInfo.

[0427] S15-5, the base station sends an AI monitoring reference signal on the measurement resource corresponding to the AI ​​use case indication.

[0428] S15-6, the terminal measures the AI ​​monitoring reference signal on the measurement resource corresponding to the AI ​​use case indication to obtain channel information, then obtains the first measurement quantity (i.e., the square of the cosine similarity between the reconstructed channel and the measurement channel) according to the proxy model, and obtains a monitoring result based on the first measurement quantity and the indicator threshold.

[0429] S15-7, the terminal reports the monitoring result (such as whether the AI ​​unit is valid or invalid).

[0430] In the sixteenth embodiment, the AI ​​use case is beam prediction, and the AI ​​unit monitoring purpose is to monitor the AI ​​unit in the deactivated state, as shown in FIG18 , which may specifically include the following S16-1 to S16-7.

[0431] S16-1: The terminal (inference device) sends first information (e.g., an AI unit monitoring configuration request) to the base station. The first information is used to request the base station to perform AI unit monitoring configuration, and the first information includes:

[0432] The AI ​​use case identifier for which the terminal requests monitoring configuration: beam prediction;

[0433] AI unit monitoring purpose: To monitor the AI ​​unit in deactivated state.

[0434] Optionally, the first information may be sent by the UE to the network (eg, a base station) when the AI ​​unit is registered. For example, the first information may be carried in a UE capability report or an AI unit function report.

[0435] S16-2, the terminal receives the first configuration information (such as measurement reporting configuration) sent by the base station, wherein the first configuration information includes: AI use case indication, AI unit monitoring purpose; wherein, the AI ​​use case indicated by the AI ​​use case indication is beam prediction, and the AI ​​unit monitoring purpose is to monitor the AI ​​unit in the deactivated state.

[0436] S16-3, the terminal sends second information (such as an AI unit monitoring request) to the base station, where the second information is used to request the base station to perform AI unit monitoring, and the second information includes:

[0437] AI use case identifier for terminal request monitoring: beam prediction; or

[0438] The identifier of the monitored AI unit.

[0439] Optionally, the second information further includes:

[0440] AI unit monitoring purpose: To monitor the AI ​​unit in deactivated state.

[0441] Optionally, when the first condition is met, the terminal sends the second information to the base station;

[0442] The first condition includes at least one of the following:

[0443] The AI ​​use case indicates that the reasoning of the corresponding AI unit is inaccurate, the terminal updates the activation status of one or more AI units, the terminal is preparing to activate one or more AI units in a deactivated state, the terminal detects a wireless link failure, and the terminal detects a deterioration in communication quality.

[0444] S16-4, the terminal receives first indication information sent by the base station, wherein the first indication information is used to indicate the reporting configuration identifier monitored by the AI ​​unit, and the AI ​​use case indicates the corresponding measurement resources.

[0445] Optionally, the first indication information may be carried by a MAC CE or a DCI. Specifically, for example, the first indication information is CSI-AssociatedReportConfigInfo.

[0446] S16-5, the base station sends an AI monitoring reference signal on the measurement resource corresponding to the AI ​​use case indication.

[0447] S16-6: The terminal measures the AI ​​monitoring reference signal on the measurement resource corresponding to the AI ​​use case indication to determine the recommended AI unit indication of the deactivated state.

[0448] S16-7, the terminal reports the AI ​​unit indication of the recommended deactivation state.

[0449] It should be noted that in the above-mentioned embodiment 16, the inference device (i.e., the terminal) sends the first information (such as a monitoring configuration request) to the base station, including a use case identifier and auxiliary information (inactive model monitoring). The inference device (i.e., the terminal) receives the first configuration information (such as the AI ​​monitoring reference signal configuration) from the base station, which may also include the monitoring purpose (inactive model monitoring). The inference device sends a monitoring request to the base station, including a monitoring purpose of inactive model monitoring. The inference device receives the AI ​​use case monitoring reference signal; the inference device determines the monitoring indicators by itself, and decides on the recommended deactivated model or deactivated AI function to the base station.

[0450] The above, in combination with Figures 2 to 18, describes in detail the terminal side embodiment of the present application. The following, in combination with Figure 19, describes in detail the base station side embodiment of the present application. It should be understood that the base station side embodiment and the terminal side embodiment correspond to each other, and similar descriptions can refer to the terminal side embodiment.

[0451] FIG19 is a schematic flow chart of a resource configuration method 300 according to an embodiment of the present application. As shown in FIG19 , the resource configuration method 300 may include at least part of the following contents:

[0452] S310: The base station sends first configuration information to the terminal, where the first configuration information includes: an AI use case indication, where different AI use case indications correspond to respective measurement resources;

[0453] S320: The base station sends a reference signal to the terminal on the measurement resources corresponding to the AI ​​use case indication.

[0454] It should be understood that FIG19 shows the steps or operations of the resource configuration method 300, but these steps or operations are merely examples, and the embodiments of the present application may also perform other operations or variations of the operations in FIG19.

[0455] In some embodiments, the AI ​​use case indication includes one of the following:

[0456] AI use case identifier, AI use case group identifier.

[0457] In some embodiments, the first configuration information further includes at least one of the following:

[0458] AI unit monitoring object, AI unit monitoring purpose, measurement quantity information monitored by the AI ​​unit, reference signal resource indication for AI unit monitoring, at least one AI use case indication corresponding to the measurement resource, and auxiliary information monitored by the AI ​​unit.

[0459] In some embodiments, the AI ​​unit monitors one of the following:

[0460] AI unit ID, AI unit group ID, AI function ID, AI function group ID.

[0461] In some embodiments, the AI ​​unit monitoring purpose includes one of the following:

[0462] Monitor one or more AI units that are active,

[0463] monitoring one or more AI units that are in a deactivated state,

[0464] Monitor one or more AI functions that are active,

[0465] One or more AI functions are monitored for being in a deactivated state.

[0466] In some embodiments, the measurement information monitored by the AI ​​unit includes at least one of the following:

[0467] a first measurement quantity, a second measurement quantity associated with the first measurement quantity, a default indication associated with the first measurement quantity, and a universal measurement quantity set identifier associated with the first measurement quantity;

[0468] The first measurement quantity is a measurement quantity monitored by the AI ​​unit.

[0469] In some embodiments, the reference signal resource indication for AI unit monitoring includes at least one of the following:

[0470] Bandwidth information, resource density information, time domain resource information, predefined resource element RE pattern identifier, default reference signal resource configuration information indication, common reference signal resource configuration indication, predefined reference signal resource configuration indication.

[0471] In some embodiments, before the base station sends the first configuration information, the resource configuration method 300 further includes:

[0472] The base station receives first information from the terminal;

[0473] The first information is used to request the base station to perform AI unit monitoring configuration, and the first information includes at least one of the following:

[0474] The AI ​​use case identifier that the terminal requests to be monitored and configured, the AI ​​use case group identifier that the terminal requests to be monitored and configured, auxiliary information, and request information for requesting to configure auxiliary information monitored by the AI ​​unit.

[0475] In some embodiments, the auxiliary information is used to indicate at least one of the following:

[0476] The resources monitored by the AI ​​unit are different from the resources the AI ​​unit reasons about;

[0477] AI unit monitoring purpose;

[0478] The AI ​​unit monitoring purpose is one of the following:

[0479] monitoring one or more AI units in a deactivated state;

[0480] monitoring one or more AI units in an activated state;

[0481] monitoring one or more AI functions that are in a deactivated state;

[0482] Monitor the active state of one or more AI functions.

[0483] In some embodiments, after the base station sends the first configuration information, the resource configuration method 300 further includes:

[0484] The base station receives second information from the terminal;

[0485] The second information is used to request the base station to perform AI unit monitoring, and the second information includes at least one of the following:

[0486] AI use case identifier, AI use case group identifier, the purpose for which the terminal requests monitoring, and the reason why the terminal requests monitoring.

[0487] In some embodiments, the purpose for which the terminal requests monitoring includes one of the following:

[0488] Monitor one or more AI units in an activated state, monitor one or more AI units in a deactivated state, monitor one or more AI functions in an activated state, and monitor one or more AI functions in a deactivated state.

[0489] In some embodiments, the reason why the terminal requests monitoring includes at least one of the following:

[0490] The AI ​​use case indicates that the reasoning of the corresponding AI unit is inaccurate, the terminal updates the activation status of one or more AI units, the terminal is preparing to activate one or more AI units in a deactivated state, the terminal detects a wireless link failure, and the terminal detects a deterioration in communication quality.

[0491] In some embodiments, the second information is sent by the terminal when the first condition is met;

[0492] The first condition includes at least one of the following:

[0493] The AI ​​use case indicates that the reasoning of the corresponding AI unit is inaccurate, the terminal updates the activation status of one or more AI units, the terminal is preparing to activate one or more AI units in a deactivated state, the terminal detects a wireless link failure, and the terminal detects a deterioration in communication quality.

[0494] In some embodiments, the resource configuration method 300 further includes:

[0495] The base station sends second configuration information to the terminal;

[0496] The second configuration information includes at least one of the following:

[0497] The first threshold value related to AI unit reasoning, the configuration indication corresponding to the wireless link failure, the measurement quantity related to communication quality monitoring, and the second threshold value related to communication quality monitoring.

[0498] In some embodiments, after the base station sends the first configuration information, the resource configuration method 300 further includes:

[0499] The base station sends first indication information to the terminal;

[0500] The first indication information is used to indicate the reporting configuration identifier monitored by the AI ​​unit, and the AI ​​use case indicates the corresponding measurement resources.

[0501] In some embodiments, after the base station sends a reference signal to the terminal on the measurement resource corresponding to the AI ​​use case indication, the resource configuration method 300 further includes:

[0502] receiving, by the base station, information reported by the terminal based on the reference signal;

[0503] The information reported by the terminal and received by the base station includes one of the following: a first measurement quantity corresponding to the AI ​​use case indication, and a monitoring result corresponding to the AI ​​use case indication;

[0504] The first measurement quantity is a measurement quantity monitored by the AI ​​unit.

[0505] In some embodiments, the resource configuration method 300 further includes:

[0506] The base station provides the terminal with an inference result and / or an inference timestamp corresponding to the AI ​​use case indication;

[0507] Among them, the monitoring result corresponding to the AI ​​use case indication received by the base station corresponds to the inference result and / or inference timestamp.

[0508] In some embodiments, different AI use cases correspond to the same measurement resources, or different AI use cases correspond to different measurement resources.

[0509] In some embodiments, the first configuration information is reporting configuration information, or the first configuration information is AI reference signal configuration information.

[0510] Therefore, in an embodiment of the present application, the base station can configure different AI use case indications corresponding to their respective measurement resources, that is, the base station can configure the measurement resources based on the AI ​​use case indication granularity. After that, the terminal can determine the corresponding measurement resources based on the AI ​​use case indication, which can avoid executing the measurement resource and reporting configuration process separately for different AI use cases. Thus, the configuration complexity of measurement resources and reporting can be reduced during the monitoring process of AI use cases or AI use case groups.

[0511] The above text, in combination with Figures 2 to 19, describes in detail the method embodiment of the present application. The following text, in combination with Figures 20 to 21, describes in detail the device embodiment of the present application. It should be understood that the device embodiment and the method embodiment correspond to each other, and similar descriptions can refer to the method embodiment.

[0512] Figure 20 shows a schematic block diagram of an information reporting device 400 according to an embodiment of the present application. As shown in Figure 20, the information reporting device 400 includes:

[0513] The receiving unit 410 is configured to receive first configuration information from a base station, where the first configuration information includes: an artificial intelligence (AI) use case indication, where different AI use case indications correspond to respective measurement resources;

[0514] The processing unit 420 is configured to measure a reference signal on a measurement resource corresponding to the AI ​​use case indication to obtain a measurement result;

[0515] The sending unit 430 is configured to report based on the measurement result.

[0516] In some embodiments, the AI ​​use case indication includes one of the following:

[0517] AI use case identifier, AI use case group identifier.

[0518] In some embodiments, the first configuration information further includes at least one of the following:

[0519] AI unit monitoring object, AI unit monitoring purpose, measurement quantity information monitored by the AI ​​unit, reference signal resource indication for AI unit monitoring, at least one AI use case indication corresponding to the measurement resource, and auxiliary information monitored by the AI ​​unit.

[0520] In some embodiments, the AI ​​unit monitoring object includes one of the following: an AI unit identifier, an AI unit group identifier, an AI function identifier, an AI function group identifier; and / or,

[0521] The AI ​​unit monitoring purpose includes one of the following: monitoring one or more AI units in an activated state, monitoring one or more AI units in a deactivated state, monitoring one or more AI functions in an activated state, monitoring one or more AI functions in a deactivated state; and / or,

[0522] The measurement quantity information monitored by the AI ​​unit includes at least one of the following: a first measurement quantity, a second measurement quantity associated with the first measurement quantity, a default indication associated with the first measurement quantity, and a universal measurement quantity set identifier associated with the first measurement quantity; wherein the first measurement quantity is the measurement quantity monitored by the AI ​​unit; and / or,

[0523] The reference signal resource indication for AI unit monitoring includes at least one of the following: bandwidth information, resource density information, time domain resource information, a predefined resource element RE pattern identifier, a default reference signal resource configuration information indication, a common reference signal resource configuration indication, and a predefined reference signal resource configuration indication.

[0524] In some embodiments, before the information reporting device 400 receives the first configuration information, the sending unit 430 is further configured to send the first information to the base station;

[0525] The first information is used to request the base station to perform AI unit monitoring configuration, and the first information includes at least one of the following:

[0526] AI use case identifier, AI use case group identifier, auxiliary information, and request information for configuring auxiliary information monitored by the AI ​​unit.

[0527] In some embodiments, the auxiliary information is used to indicate at least one of the following:

[0528] The resources monitored by the AI ​​unit are different from the resources the AI ​​unit reasons about;

[0529] AI unit monitoring purpose;

[0530] The AI ​​unit monitoring purpose is one of the following:

[0531] monitoring one or more AI units in a deactivated state;

[0532] monitoring one or more AI units in an activated state;

[0533] monitoring one or more AI functions that are in a deactivated state;

[0534] Monitor the active state of one or more AI functions.

[0535] In some embodiments, after the information reporting device 400 receives the first configuration information, the sending unit 430 is further configured to send second information to the base station;

[0536] The second information is used to request the base station to perform AI unit monitoring, and the second information includes at least one of the following:

[0537] AI use case identifier, AI use case group identifier, the purpose for which the information reporting device 400 requests monitoring, and the reason why the information reporting device 400 requests monitoring.

[0538] In some embodiments, the purpose of the monitoring request by the information reporting device 400 includes one of the following: monitoring one or more AI units in an activated state, monitoring one or more AI units in a deactivated state, monitoring one or more AI functions in an activated state, monitoring one or more AI functions in a deactivated state; and / or,

[0539] The reasons why the information reporting device 400 requests monitoring include at least one of the following: the AI ​​use case indicates that the reasoning of the corresponding AI unit is inaccurate, the information reporting device 400 updates the activation status of one or more AI units, the information reporting device 400 is preparing to activate one or more AI units in a deactivated state, the information reporting device 400 detects a wireless link failure, and the information reporting device 400 detects a deterioration in communication quality.

[0540] In some embodiments, the sending unit 430 is specifically configured to:

[0541] When the first condition is met, sending the second information to the base station;

[0542] The first condition includes at least one of the following:

[0543] The AI ​​use case indicates that the reasoning of the corresponding AI unit is inaccurate, the information reporting device 400 updates the activation status of one or more AI units, the information reporting device 400 is ready to activate one or more AI units in a deactivated state, the information reporting device 400 detects a wireless link failure, and the information reporting device 400 detects a deterioration in communication quality.

[0544] In some embodiments, the receiving unit 410 is further configured to receive second configuration information from the base station;

[0545] The second configuration information includes at least one of the following:

[0546] The first threshold value related to AI unit reasoning, the configuration indication corresponding to the wireless link failure, the measurement quantity related to communication quality monitoring, and the second threshold value related to communication quality monitoring.

[0547] In some embodiments, after the information reporting device 400 receives the first configuration information, the receiving unit 410 is further configured to receive first indication information sent by the base station;

[0548] The first indication information is used to indicate the reporting configuration identifier monitored by the AI ​​unit, and the AI ​​use case indicates the corresponding measurement resources.

[0549] In some embodiments, the sending unit 430 is specifically configured to determine a first measurement amount based on the measurement result, and report the first measurement amount to the base station, wherein the first measurement amount is a measurement amount monitored by the AI ​​unit; or

[0550] The processing unit 420 is further configured to determine a monitoring result corresponding to the AI ​​use case indication based on the measurement result, and the sending unit 430 is specifically configured to report the monitoring result to the base station; or,

[0551] The processing unit 420 is also used to determine the monitoring result corresponding to the AI ​​use case indication based on the measurement result and the inference result and / or inference timestamp corresponding to the AI ​​use case indication provided by the base station, and the sending unit 430 is specifically used to report the monitoring result to the base station.

[0552] In some embodiments, different AI use cases correspond to the same measurement resources, or different AI use cases correspond to different measurement resources.

[0553] In some embodiments, the first configuration information is reporting configuration information, or the first configuration information is AI reference signal configuration information.

[0554] In some embodiments, the sending unit and the receiving unit may be a communication interface or a transceiver, or an input / output interface of a communication chip or a system on chip.

[0555] It should be understood that the information reporting device 400 according to the embodiment of the present application may correspond to the terminal in the embodiment of the method of the present application, and the above-mentioned and other operations and / or functions of each unit in the information reporting device 400 are respectively for realizing the corresponding processes of the terminal in the method 200 shown in Figure 2. For the sake of brevity, they will not be repeated here.

[0556] FIG21 shows a schematic block diagram of a resource configuration device 500 according to an embodiment of the present application. As shown in FIG21 , the resource configuration device 500 includes:

[0557] A sending unit 510 is configured to send first configuration information to a terminal, where the first configuration information includes: an artificial intelligence (AI) use case indication, where different AI use case indications correspond to respective measurement resources;

[0558] The sending unit 510 is further configured to send a reference signal to the terminal on the measurement resources corresponding to the AI ​​use case indication.

[0559] In some embodiments, the AI ​​use case indication includes one of the following:

[0560] AI use case identifier, AI use case group identifier.

[0561] In some embodiments, the first configuration information further includes at least one of the following:

[0562] AI unit monitoring object, AI unit monitoring purpose, measurement quantity information monitored by the AI ​​unit, reference signal resource indication for AI unit monitoring, at least one AI use case indication corresponding to the measurement resource, and auxiliary information monitored by the AI ​​unit.

[0563] In some embodiments, the AI ​​unit monitoring object includes one of the following: an AI unit identifier, an AI unit group identifier, an AI function identifier, an AI function group identifier; and / or,

[0564] The AI ​​unit monitoring purpose includes one of the following: monitoring one or more AI units in an activated state, monitoring one or more AI units in a deactivated state, monitoring one or more AI functions in an activated state, monitoring one or more AI functions in a deactivated state; and / or,

[0565] The measurement quantity information monitored by the AI ​​unit includes at least one of the following: a first measurement quantity, a second measurement quantity associated with the first measurement quantity, a default indication associated with the first measurement quantity, and a universal measurement quantity set identifier associated with the first measurement quantity; wherein the first measurement quantity is the measurement quantity monitored by the AI ​​unit; and / or,

[0566] The reference signal resource indication for AI unit monitoring includes at least one of the following: bandwidth information, resource density information, time domain resource information, a predefined resource element RE pattern identifier, a default reference signal resource configuration information indication, a common reference signal resource configuration indication, and a predefined reference signal resource configuration indication.

[0567] In some embodiments, before the resource configuration apparatus 500 sends the first configuration information, the resource configuration apparatus 500 further includes:

[0568] The receiving unit 520 is configured to receive first information from the terminal;

[0569] The first information is used to request the resource configuration device 500 to perform AI unit monitoring configuration, and the first information includes at least one of the following:

[0570] AI use case identifier, AI use case group identifier, auxiliary information, and request information for configuring auxiliary information monitored by the AI ​​unit.

[0571] In some embodiments, the auxiliary information is used to indicate at least one of the following:

[0572] The resources monitored by the AI ​​unit are different from the resources the AI ​​unit reasons about;

[0573] AI unit monitoring purpose;

[0574] The AI ​​unit monitoring purpose is one of the following:

[0575] monitoring one or more AI units in a deactivated state;

[0576] monitoring one or more AI units in an activated state;

[0577] monitoring one or more AI functions that are in a deactivated state;

[0578] Monitor the active state of one or more AI functions.

[0579] In some embodiments, after the resource configuration apparatus 500 sends the first configuration information, the receiving unit 520 is further configured to receive second information from the terminal;

[0580] The second information is used to request the resource configuration device 500 to perform AI unit monitoring, and the second information includes at least one of the following:

[0581] AI use case identifier, AI use case group identifier, the purpose for which the terminal requests monitoring, and the reason why the terminal requests monitoring.

[0582] In some embodiments, the purpose of the terminal requesting monitoring includes one of the following: monitoring one or more AI units in an activated state, monitoring one or more AI units in a deactivated state, monitoring one or more AI functions in an activated state, and monitoring one or more AI functions in a deactivated state; and / or,

[0583] The reason why the terminal requests monitoring includes at least one of the following: the AI ​​use case indicates that the reasoning of the corresponding AI unit is inaccurate, the terminal updates the activation status of one or more AI units, the terminal is preparing to activate one or more AI units in a deactivated state, the terminal detects a wireless link failure, and the terminal detects a deterioration in communication quality.

[0584] In some embodiments, the sending unit 510 is further configured to send second configuration information to the terminal;

[0585] The second configuration information includes at least one of the following:

[0586] Thresholds related to AI unit reasoning, configuration instructions corresponding to wireless link failures, measurement quantities related to communication quality monitoring, and thresholds related to communication quality monitoring.

[0587] In some embodiments, after the resource configuration device 500 sends the first configuration information, the sending unit 510 is further configured to send first indication information to the terminal;

[0588] The first indication information is used to indicate the reporting configuration identifier monitored by the AI ​​unit, and the AI ​​use case indicates the corresponding measurement resources.

[0589] In some embodiments, after the resource configuration device 500 sends a reference signal to the terminal on the measurement resource corresponding to the AI ​​use case indication, the receiving unit 520 is further configured to receive information reported by the terminal based on the reference signal;

[0590] The information reported by the terminal and received by the resource configuration device 500 includes one of the following: a first measurement quantity corresponding to the AI ​​use case indication, and a monitoring result corresponding to the AI ​​use case indication;

[0591] The first measurement quantity is a measurement quantity monitored by the AI ​​unit.

[0592] In some embodiments, the sending unit 510 is further configured to provide the terminal with an inference result and / or an inference timestamp corresponding to the AI ​​use case indication;

[0593] Among them, the monitoring result corresponding to the AI ​​use case indication received by the resource configuration device 500 corresponds to the reasoning result and / or reasoning timestamp.

[0594] In some embodiments, different AI use cases correspond to the same measurement resources, or different AI use cases correspond to different measurement resources.

[0595] In some embodiments, the first configuration information is reporting configuration information, or the first configuration information is AI reference signal configuration information.

[0596] In some embodiments, the sending unit and the receiving unit may be a communication interface or a transceiver, or an input / output interface of a communication chip or a system on chip.

[0597] It should be understood that the resource configuration device 500 according to the embodiment of the present application may correspond to the base station in the method embodiment of the present application, and the above-mentioned and other operations and / or functions of each unit in the resource configuration device 500 are respectively for realizing the corresponding processes of the base station in the method 300 shown in Figure 19. For the sake of brevity, they will not be repeated here.

[0598] Figure 22 is a schematic structural diagram of a communication device 600 provided in an embodiment of the present application. The communication device 600 shown in Figure 22 includes a processor 610, which can call and run a computer program from a memory to implement the method in the embodiment of the present application.

[0599] In some embodiments, as shown in FIG22 , the communication device 600 may further include a memory 620. The processor 610 may call and execute a computer program from the memory 620 to implement the method in the embodiment of the present application.

[0600] The memory 620 may be a separate device independent of the processor 610 , or may be integrated into the processor 610 .

[0601] In some embodiments, as shown in FIG. 22 , the communication device 600 may further include a transceiver 630 , and the processor 610 may control the transceiver 630 to communicate with other devices. Specifically, the transceiver 630 may send information or data to other devices, or receive information or data sent by other devices.

[0602] The transceiver 630 may include a transmitter and a receiver. The transceiver 630 may further include an antenna, and the number of antennas may be one or more.

[0603] In some embodiments, the processor 610 may implement the functions of a processing unit in a terminal, or the processor 610 may implement the functions of a processing unit in a base station, which will not be described in detail here for the sake of brevity.

[0604] In some embodiments, the transceiver 630 may implement the functions of a transmitting unit and a receiving unit in the terminal, which will not be described in detail here for the sake of brevity.

[0605] In some embodiments, the transceiver 630 may implement the functions of a transmitting unit and a receiving unit in a base station, which will not be described in detail here for the sake of brevity.

[0606] In some embodiments, the communication device 600 may specifically be a base station in an embodiment of the present application, and the communication device 600 may implement the corresponding processes implemented by the base station in each method in the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0607] In some embodiments, the communication device 600 may specifically be a terminal in an embodiment of the present application, and the communication device 600 may implement the corresponding processes implemented by the terminal in each method in the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0608] Figure 23 is a schematic structural diagram of an apparatus according to an embodiment of the present application. The apparatus 700 shown in Figure 23 includes a processor 710, which can call and execute a computer program from a memory to implement the method according to the embodiment of the present application.

[0609] In some embodiments, as shown in FIG23 , the apparatus 700 may further include a memory 720. The processor 710 may call and execute a computer program from the memory 720 to implement the method in the embodiment of the present application.

[0610] The memory 720 may be a separate device independent of the processor 710 , or may be integrated into the processor 710 .

[0611] In some embodiments, the processor 710 may implement the functions of a processing unit in a terminal, or the processor 710 may implement the functions of a processing unit in a base station, which will not be described in detail here for the sake of brevity.

[0612] In some embodiments, the apparatus 700 may further include an input interface 730. The processor 710 may control the input interface 730 to communicate with other devices or chips, and specifically, may obtain information or data sent by other devices or chips. Optionally, the processor 710 may be located inside or outside the chip.

[0613] In some embodiments, the input interface 730 may implement the function of a receiving unit in a terminal, or the input interface 730 may implement the function of a receiving unit in a base station.

[0614] In some embodiments, the apparatus 700 may further include an output interface 740. The processor 710 may control the output interface 740 to communicate with other devices or chips, specifically, to output information or data to other devices or chips. Optionally, the processor 710 may be located inside or outside the chip.

[0615] In some embodiments, the output interface 740 may implement the function of a transmitting unit in a terminal device, or the output interface 740 may implement the function of a transmitting unit in a base station.

[0616] In some embodiments, the device can be applied to the base station in the embodiments of the present application, and the device can implement the corresponding processes implemented by the base station in each method of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0617] In some embodiments, the device can be applied to the terminal in the embodiments of the present application, and the device can implement the corresponding processes implemented by the terminal in each method of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0618] In some embodiments, the device mentioned in the embodiments of the present application may also be a chip, such as a system-on-chip, a system-on-chip, a chip system, or a system-on-chip chip.

[0619] FIG24 is a schematic block diagram of a communication system 800 provided in an embodiment of the present application. As shown in FIG24 , the communication system 800 includes a terminal 810 and a base station 820.

[0620] Among them, the terminal 810 can be used to implement the corresponding functions implemented by the terminal in the above method, and the base station 820 can be used to implement the corresponding functions implemented by the base station in the above method. For the sake of brevity, they are not repeated here.

[0621] It should be understood that the processor of the embodiments of the present application may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiment can be completed by hardware integrated logic circuits in the processor or software instructions. The above processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The various methods, steps, and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of the present application can be directly implemented as a hardware decoding processor, or can be implemented by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0622] It is understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. It should be noted that the memory described herein is intended to include but is not limited to these and any other suitable types of memory.

[0623] It should be understood that the above-mentioned memories are exemplary but not restrictive. For example, the memories in the embodiments of the present application may also be static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM RAM (DR RAM), etc. In other words, the memories in the embodiments of the present application are intended to include, but are not limited to, these and any other suitable types of memories.

[0624] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0625] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0626] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0627] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0628] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0629] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. In view of this understanding, the technical solution of the present application, or the part that contributes to the relevant technology or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0630] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. An information reporting method, comprising: The terminal receives first configuration information from the base station, where the first configuration information includes: an artificial intelligence (AI) use case indication, where different AI use case indications correspond to respective measurement resources; The terminal measures a reference signal on a measurement resource corresponding to the AI ​​use case indication to obtain a measurement result; The terminal reports based on the measurement result.

2. The method according to claim 1, wherein: The AI ​​use case indication includes one of the following: AI use case identifier, AI use case group identifier.

3. The method according to claim 1 or 2, wherein: The first configuration information also includes at least one of the following: AI unit monitoring object, AI unit monitoring purpose, measurement quantity information monitored by the AI ​​unit, reference signal resource indication used for AI unit monitoring, at least one AI use case indication corresponding to the measurement resources, and auxiliary information monitored by the AI ​​unit.

4. The method according to claim 3, wherein: The AI ​​unit monitoring object includes one of the following: an AI unit identifier, an AI unit group identifier, an AI function identifier, an AI function group identifier; and / or, The AI ​​unit monitoring purpose includes one of the following: monitoring one or more AI units in an activated state, monitoring one or more AI units in a deactivated state, monitoring one or more AI functions in an activated state, monitoring one or more AI functions in a deactivated state; and / or, The measurement quantity information monitored by the AI ​​unit includes at least one of the following: a first measurement quantity, a second measurement quantity associated with the first measurement quantity, a default indication associated with the first measurement quantity, and a common measurement quantity set identifier associated with the first measurement quantity; wherein the first measurement quantity is a measurement quantity monitored by the AI ​​unit; and / or, The reference signal resource indication for AI unit monitoring includes at least one of the following: bandwidth information, resource density information, time domain resource information, a predefined resource element RE pattern identifier, a default reference signal resource configuration information indication, a common reference signal resource configuration indication, and a predefined reference signal resource configuration indication.

5. The method according to any one of claims 1 to 4, wherein: Before the terminal receives the first configuration information, the method further includes: The terminal sends first information to the base station; The first information is used to request the base station to perform AI unit monitoring configuration, and the first information includes at least one of the following: AI use case identifier, AI use case group identifier, auxiliary information, and request information for requesting auxiliary information monitored by the AI ​​unit.

6. The method according to claim 5, wherein: The auxiliary information is used to indicate at least one of the following: The resources monitored by the AI ​​unit are different from the resources that the AI ​​unit reasons about; AI unit monitoring purpose; The monitoring purpose of the AI ​​unit is one of the following: monitoring one or more AI units in a deactivated state; monitoring one or more AI units in an activated state; monitoring one or more AI functions in a deactivated state; Monitor one or more AI functions that are active.

7. The method according to any one of claims 1 to 6, wherein: After the terminal receives the first configuration information, the method further includes: The terminal sends second information to the base station; The second information is used to request the base station to perform AI unit monitoring, and the second information includes at least one of the following: AI use case identifier, AI use case group identifier, the purpose of the terminal requesting monitoring, and the reason why the terminal requests monitoring.

8. The method according to claim 7, wherein: The purpose of the terminal requesting monitoring includes one of the following: monitoring one or more AI units in an activated state, monitoring one or more AI units in a deactivated state, monitoring one or more AI functions in an activated state, and monitoring one or more AI functions in a deactivated state; and / or, The reason why the terminal requests monitoring includes at least one of the following: the AI ​​use case indicates that the reasoning of the corresponding AI unit is inaccurate, the terminal updates the activation status of one or more AI units, the terminal is preparing to activate one or more AI units in a deactivated state, the terminal monitors a wireless link failure, and the terminal monitors a deterioration in communication quality.

9. The method according to claim 7 or 8, wherein: The terminal sending second information to the base station includes: When the first condition is met, the terminal sends the second information to the base station; The first condition includes at least one of the following: The AI ​​use case indicates that the reasoning of the corresponding AI unit is inaccurate; The terminal updates the activation status of one or more AI units; The terminal is ready to activate one or more AI units in a deactivated state; The terminal detects that the wireless link fails; The terminal detects that the communication quality has deteriorated.

10. The method according to claim 8 or 9, further comprising: The terminal receives second configuration information from the base station; The second configuration information includes at least one of the following: The first threshold value related to AI unit reasoning, the configuration indication corresponding to the wireless link failure, the measurement quantity related to communication quality monitoring, and the second threshold value related to communication quality monitoring.

11. The method according to any one of claims 1 to 10, wherein: After the terminal receives the first configuration information, the method further includes: The terminal receives first indication information from the base station; Among them, the first indication information is used to indicate the reporting configuration identifier monitored by the AI ​​unit, and the AI ​​use case indicates the corresponding measurement resources.

12. The method according to any one of claims 1 to 11, wherein: The terminal reports based on the measurement result, including: The terminal determines a first measurement amount based on the measurement result, and reports the first measurement amount to the base station, wherein the first measurement amount is a measurement amount monitored by the AI ​​unit; or, The terminal determines, based on the measurement result, a monitoring result corresponding to the AI ​​use case indication, and reports the monitoring result to the base station; or, The terminal determines the monitoring result corresponding to the AI ​​use case indication based on the measurement result and the inference result and / or inference timestamp corresponding to the AI ​​use case indication provided by the base station, and reports the monitoring result to the base station.

13. The method according to any one of claims 1 to 12, wherein: The first configuration information is reporting configuration information, or the first configuration information is AI reference signal configuration information.

14. A resource allocation method, comprising: The base station sends first configuration information to the terminal, where the first configuration information includes: an artificial intelligence AI use case indication, where different AI use case indications correspond to respective measurement resources; The base station sends a reference signal to the terminal on the measurement resources corresponding to the AI ​​use case indication.

15. The method according to claim 14, wherein: The AI ​​use case indication includes one of the following: AI use case identifier, AI use case group identifier.

16. The method according to claim 14 or 15, wherein: The first configuration information also includes at least one of the following: AI unit monitoring object, AI unit monitoring purpose, measurement quantity information monitored by the AI ​​unit, reference signal resource indication used for AI unit monitoring, at least one AI use case indication corresponding to the measurement resources, and auxiliary information monitored by the AI ​​unit.

17. The method according to claim 16, wherein: The AI ​​unit monitoring object includes one of the following: an AI unit identifier, an AI unit group identifier, an AI function identifier, an AI function group identifier; and / or, The AI ​​unit monitoring purpose includes one of the following: monitoring one or more AI units in an activated state, monitoring one or more AI units in a deactivated state, monitoring one or more AI functions in an activated state, monitoring one or more AI functions in a deactivated state; and / or, The measurement quantity information monitored by the AI ​​unit includes at least one of the following: a first measurement quantity, a second measurement quantity associated with the first measurement quantity, a default indication associated with the first measurement quantity, and a common measurement quantity set identifier associated with the first measurement quantity; wherein the first measurement quantity is a measurement quantity monitored by the AI ​​unit; and / or, The reference signal resource indication for AI unit monitoring includes at least one of the following: bandwidth information, resource density information, time domain resource information, a predefined resource element RE pattern identifier, a default reference signal resource configuration information indication, a common reference signal resource configuration indication, and a predefined reference signal resource configuration indication.

18. The method according to any one of claims 14 to 17, wherein: Before the base station sends the first configuration information, the method further includes: The base station receives first information from the terminal; The first information is used to request the base station to perform AI unit monitoring configuration, and the first information includes at least one of the following: AI use case identifier, AI use case group identifier, auxiliary information, and request information for requesting auxiliary information monitored by the AI ​​unit.

19. The method according to claim 18, wherein: The auxiliary information is used to indicate at least one of the following: The resources monitored by the AI ​​unit are different from the resources that the AI ​​unit reasons about; AI unit monitoring purpose; The monitoring purpose of the AI ​​unit is one of the following: monitoring one or more AI units in a deactivated state; monitoring one or more AI units in an activated state; monitoring one or more AI functions in a deactivated state; Monitor one or more AI functions that are active.

20. The method according to any one of claims 14 to 19, wherein: After the base station sends the first configuration information, the method further includes: The base station receives second information from the terminal; The second information is used to request the base station to perform AI unit monitoring, and the second information includes at least one of the following: AI use case identifier, AI use case group identifier, the purpose of the terminal requesting monitoring, and the reason why the terminal requests monitoring.

21. The method according to claim 20, wherein: The purpose of the terminal requesting monitoring includes one of the following: monitoring one or more AI units in an activated state, monitoring one or more AI units in a deactivated state, monitoring one or more AI functions in an activated state, and monitoring one or more AI functions in a deactivated state; and / or, The reason why the terminal requests monitoring includes at least one of the following: the AI ​​use case indicates that the reasoning of the corresponding AI unit is inaccurate, the terminal updates the activation status of one or more AI units, the terminal is preparing to activate one or more AI units in a deactivated state, the terminal monitors a wireless link failure, and the terminal monitors a deterioration in communication quality.

22. The method according to claim 21, further comprising: The base station sends second configuration information to the terminal; The second configuration information includes at least one of the following: The first threshold value related to AI unit reasoning, the configuration indication corresponding to the wireless link failure, the measurement quantity related to communication quality monitoring, and the second threshold value related to communication quality monitoring.

23. The method according to any one of claims 14 to 22, wherein: After the base station sends the first configuration information, the method further includes: The base station sends first indication information to the terminal; Among them, the first indication information is used to indicate the reporting configuration identifier monitored by the AI ​​unit, and the AI ​​use case indicates the corresponding measurement resources.

24. The method according to any one of claims 14 to 23, wherein: After the base station sends a reference signal to the terminal on the measurement resource corresponding to the AI ​​use case indication, the method further includes: receiving, by the base station, information reported by the terminal based on the reference signal; The information reported by the terminal and received by the base station includes one of the following: a first measurement amount corresponding to the AI ​​use case indication, and a monitoring result corresponding to the AI ​​use case indication; The first measurement quantity is a measurement quantity monitored by the AI ​​unit.

25. The method according to claim 24, further comprising: The base station provides the terminal with an inference result and / or an inference timestamp corresponding to the AI ​​use case indication; Among them, the monitoring result corresponding to the AI ​​use case indication received by the base station corresponds to the reasoning result and / or reasoning timestamp.

26. The method according to any one of claims 14 to 25, wherein: The first configuration information is reporting configuration information, or the first configuration information is AI reference signal configuration information.

27. An information reporting device, comprising: A receiving unit, configured to receive first configuration information from a base station, where the first configuration information includes: an artificial intelligence (AI) use case indication, where different AI use case indications correspond to respective measurement resources; A processing unit, configured to measure a reference signal on a measurement resource corresponding to the AI ​​use case indication to obtain a measurement result; A sending unit is used to report based on the measurement result.

28. A resource allocation device, comprising: A sending unit, configured to send first configuration information to a terminal, wherein the first configuration information includes: an artificial intelligence (AI) use case indication, where different AI use case indications correspond to respective measurement resources; The sending unit is further used to send a reference signal to the terminal on the measurement resources corresponding to the AI ​​use case indication.

29. A terminal, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the method according to any one of claims 1 to 13 when executed by the processor.

30. A base station, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the method according to any one of claims 14 to 26 when executed by the processor.

31. A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the computer program implements the steps in the method as claimed in any one of claims 1 to 13; or implements the steps in the method as claimed in any one of claims 14 to 26.

Images