Artificial intelligence ai usage control method, communication device, and storage medium

Abstract

Embodiments of the present disclosure provide an artificial intelligence (AI) usage control method, a communication device, and a storage medium. The method is performed by a terminal and includes stopping usage of an AI function for outputting a predicted result of wireless measurement if performance of the AI function meets a first condition.

Description

Artificial intelligence (AI) usage control methods, communication devices and storage media Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to a method for controlling the use of artificial intelligence (AI) functions, a communication device, and a storage medium. Background Technology

[0002] Machine learning algorithms are one of the most important methods for implementing artificial intelligence technology. Machine learning can build models using large amounts of training data, and these models can then predict events. In many fields, machine learning models can achieve very accurate predictions.

[0003] Summary of the Invention

[0004] This disclosure provides a method for controlling the use of artificial intelligence (AI), a communication device, and a storage medium.

[0005] According to a first aspect of the present disclosure, a method for controlling the use of AI is provided, wherein the method is executed by a terminal, the method comprising: stopping the use of the AI ​​function when the performance of the AI ​​function meets a first condition, the AI ​​function being used to output a prediction result of a wireless measurement.

[0006] According to a second aspect of the present disclosure, an AI usage control method is provided, wherein the method is executed by a first node, the method comprising: sending first information to a terminal, the first information being used to determine whether the performance of the AI ​​function meets a first condition for stopping the use of the AI ​​function.

[0007] According to a third aspect of the present disclosure, an AI usage control device is provided, wherein the device includes: a processing module configured to stop using the AI ​​function when the performance of the AI ​​function meets a first condition, wherein the AI ​​function is used to output a prediction result of wireless measurement and the AI ​​function is stopped when the performance of the AI ​​function meets the first condition.

[0008] According to a fourth aspect of the present disclosure, an AI usage control device is provided, wherein the device includes: a sending module configured to send first information to a terminal, the first information being used to determine whether the performance of the AI ​​function meets a first condition for stopping the use of the AI ​​function.

[0009] A communication system is provided according to a fifth aspect of the present disclosure, wherein the communication system includes: a terminal configured to perform the method described in any technical solution of the first aspect; and a network device configured to perform the method described in any technical solution of the second aspect.

[0010] According to a sixth aspect of the present disclosure, a communication device is provided, wherein the communication device includes: one or more processors; wherein the processors are configured to invoke instructions to cause the communication device to perform the method provided by any of the techniques described in the first to second aspects.

[0011] A storage medium is provided according to a seventh aspect of the present disclosure, wherein the storage medium stores instructions that, when executed on a communication device, cause the communication device to perform the method provided by any one of the first to second aspects.

[0012] According to an eighth aspect of the present disclosure, a program product is provided, wherein the program product includes a computer program, which, when executed by a communication device, enables the communication device to implement the method provided by any of the technical means of the first to second aspects.

[0013] The technical approach provided in this disclosure allows for the cessation of AI function usage when the performance of the AI ​​function meets a first condition. This reduces the problem of low AI function output accuracy and impact on terminal communication quality caused by continuing to use the AI ​​function when its performance is poor.

[0014] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the embodiments of this disclosure. Attached Figure Description

[0015] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of embodiments of this disclosure.

[0016] Figure 1A is a schematic diagram of the architecture of a communication system according to an exemplary embodiment;

[0017] Figure 1B is a schematic diagram illustrating the filtering of a measurement value according to an exemplary embodiment;

[0018] Figure 1C is a schematic diagram illustrating the filtering of a measurement value according to an exemplary embodiment;

[0019] Figure 2A is a flowchart illustrating an artificial intelligence (AI) usage control method according to an exemplary embodiment;

[0020] Figure 2B is a time-domain schematic diagram illustrating a measured value and a predicted value according to an exemplary embodiment;

[0021] Figure 3 is a flowchart illustrating an artificial intelligence (AI) usage control method according to an exemplary embodiment;

[0022] Figure 4A is a schematic diagram of the structure of a user equipment (UE) according to an exemplary embodiment;

[0023] Figure 4B is a schematic diagram of the structure of a network device according to an exemplary embodiment;

[0024] Figure 5A is a schematic diagram of the structure of a communication device according to an exemplary embodiment;

[0025] Figure 5B is a schematic diagram of the structure of a chip according to an exemplary embodiment. Detailed Implementation

[0026] This disclosure provides a method for controlling the use of artificial intelligence (AI), a communication device, a communication system, and a storage medium.

[0027] The first aspect provides a method for controlling the use of artificial intelligence (AI), wherein the method is executed by a terminal, and includes: stopping the use of the AI ​​function when the performance of the AI ​​function meets a first condition, wherein the AI ​​function is used to output the prediction results of wireless measurements.

[0028] Based on the above scheme, if the performance of the AI ​​function meets the first condition, the use of function A will be stopped, thereby reducing the problem of low output accuracy of the AI ​​function and affecting the communication quality of the terminal caused by continuing to use the AI ​​function when its performance is poor.

[0029] In some embodiments of the first aspect, the first condition includes one or more of the following: the first duration of the AI ​​function output prediction result is greater than the second duration; the data characteristics of the first data and the data characteristics of the second data are inconsistent, the first data is the input data of the AI ​​function; and the second data is the training data of the AI ​​function.

[0030] In the above scheme, the first condition can be one or more of the aforementioned conditions, which allows for flexible selection based on different application scenarios.

[0031] In some embodiments of the first aspect, the first duration includes one of the following: the time difference between the first output and the last input during a single prediction by the AI ​​function; and a third duration provided by the training node of the AI ​​function.

[0032] The above scheme provides an example of the first duration, but the actual implementation is not limited to the example above.

[0033] In some embodiments of the first aspect, the second duration is the remaining duration of the first timer.

[0034] The above scheme takes into account the triggering events associated with the first timer. By reducing the occurrence of the triggering events associated with the first timer, other unnecessary operations associated with the triggering events are reduced.

[0035] In some embodiments of the first aspect, the method further includes:

[0036] If the first result continuously satisfies the second condition within the timing range of the first timer, the first result is sent to the network device. The first result includes the measurement result and / or prediction result of the wireless measurement.

[0037] In the above scheme, the first result cannot continuously meet the second condition within the timing range of the first timer, i.e., the first result is sent to the network device. For example, the second condition can be the condition for the terminal to report the first result.

[0038] In some embodiments of the first aspect, the method further includes: measuring a reference signal to obtain a measurement result when a measurement result is required.

[0039] In the above scheme, due to the introduction of prediction results, measurement is only performed when reference signal measurement is required, which reduces the measurement overhead of the terminal.

[0040] In some embodiments of the first aspect, the data characteristics of the first data and the data characteristics of the second data are inconsistent, including one or more of the following: the first data is greater than or equal to a first threshold, and the first data input by the AI ​​function N consecutive times is greater than or equal to the first threshold; N is a positive integer, and the first data input by the AI ​​function within a fourth time period is continuously greater than or equal to the first threshold; the first data is less than or equal to a second threshold; the first data input by the AI ​​function M consecutive times is less than or equal to the second threshold, where M is a positive integer, and the first data input by the AI ​​function within a fifth time period is less than or equal to the second threshold. The above scheme provides various examples illustrating whether the first condition is met, and the specific implementation is not limited to the above examples.

[0041] In some embodiments of the first aspect, the first threshold is associated with the second data; and / or, the second threshold is associated with the second data.

[0042] In the above scheme, the first threshold and / or the second threshold are related to the second data. In other words, the first threshold and / or the second threshold reflect the data characteristics of the second data. Therefore, in this case, the first threshold and / or the second threshold can be used to determine whether the data characteristics of the first data and the second data are consistent, which has the advantage of being easy to implement.

[0043] In some embodiments of the first aspect, the method further includes:

[0044] Receive the first information sent by the first node. The first information is used to determine whether the performance of the AI ​​function meets the first condition.

[0045] Based on the above scheme, the terminal can easily obtain the first information on whether the first condition is met by receiving the first information.

[0046] In some embodiments of the first aspect, the first node includes a network device and / or a training node for AI functionality.

[0047] The second aspect provides a method for controlling the use of artificial intelligence (AI), wherein the method is executed by a first node and includes:

[0048] Send first information to the terminal. The first information is used to determine whether the performance of the AI ​​function meets the first condition for stopping the use of the AI ​​function.

[0049] In some embodiments of the second aspect, the first information is used to describe the data characteristics of the second data, which is training data for AI functions.

[0050] A third aspect provides an artificial intelligence (AI) usage control device, wherein the device includes: a processing module configured to stop using the AI ​​function when the performance of the AI ​​function meets a first condition, wherein the AI ​​function is used to output a prediction result of wireless measurement and the AI ​​function is stopped when the performance of the AI ​​function meets the first condition.

[0051] In some embodiments of the third aspect, the apparatus further includes:

[0052] The sending module is configured to send a first result to the network device if the first result continuously meets the second condition within the timing range of the first timer. The first result includes the measurement result and / or prediction result of the wireless measurement.

[0053] In some embodiments of the third aspect, the processing module is further configured to measure the reference signal to obtain the measurement result when a measurement result is required.

[0054] In some embodiments of the third aspect, the apparatus further includes:

[0055] The receiving module is configured to receive first information sent by the first node. The first information is used to determine whether the performance of the AI ​​function meets the first condition.

[0056] The fourth aspect provides an artificial intelligence (AI) usage control device, wherein the device includes: a sending module configured to send first information to a terminal, the first information being used to determine whether the performance of the AI ​​function meets a first condition for stopping the use of the AI ​​function. The fifth aspect provides a communication system, wherein the communication system includes: a terminal configured to execute the method provided by any technical solution of the first aspect; and a network device configured to execute the method provided by any technical solution of the second aspect.

[0057] In a sixth aspect, embodiments of this disclosure provide a program product, wherein the program product includes a computer program, which, when executed by a communication device, enables the communication device to perform the methods described in the optional implementations of the first to second aspects.

[0058] In a seventh aspect, embodiments of this disclosure provide a computer program that, when run on a computer, causes the computer to execute the artificial intelligence (AI) usage control method described in the optional implementations of the first to second aspects.

[0059] It is understood that the aforementioned first device, network device, communication system, program product, and computer program are all used to execute the methods provided in the embodiments of this disclosure. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0060] This disclosure provides a method for controlling the use of artificial intelligence (AI), a communication device, a communication system, and a storage medium. This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, removing some steps from a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementations in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with optional implementations of other embodiments.

[0061] In each of the disclosed embodiments, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of the embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0062] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.

[0063] In this embodiment of the disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the aforementioned," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular expression or a plural expression.

[0064] In the embodiments disclosed herein, "multiple" refers to two or more.

[0065] In some embodiments, the terms “at least one of”, “one or more”, “a plurality of”, “multiple”, etc., may be used interchangeably.

[0066] In some embodiments, the notation "at least one of A and B", "A and / or B", "A in one case, B in another", "A in one case, B in another", etc., may include the following technical methods depending on the situation: in some embodiments, A (A is executed regardless of B); in some embodiments, B (B is executed regardless of A); in some embodiments, execution is selected from A and B (A and B are selectively executed); in some embodiments, A and B (both A and B are executed). The same applies when there are more branches such as A, B, C, etc.

[0067] In some embodiments, the notation "A or B" may include the following technical methods, depending on the situation: in some embodiments, A (execution of A regardless of B); in some embodiments, B (execution of B regardless of A); in some embodiments, selective execution from A and B (A and B are selectively executed). The same applies when there are more branches such as A, B, C, etc.

[0068] The prefixes "first," "second," etc., used in the embodiments of this disclosure are merely for distinguishing different descriptive objects and do not impose restrictions on the position, order, priority, quantity, or content of the descriptive objects. The description of the descriptive objects is found in the claims or the context of the embodiments, and the use of prefixes should not constitute unnecessary restrictions. For example, if the descriptive object is a "field," the ordinal numbers preceding "field" in "first field" and "second field" do not restrict the position or order of the "fields." "First" and "second" do not restrict whether the "fields" they modify are in the same message, nor do they restrict the order of "first field" and "second field." Similarly, if the descriptive object is a "level," the ordinal numbers preceding "level" in "first level" and "second level" do not restrict the priority between "levels." Furthermore, the number of descriptive objects is not limited by ordinal numbers and can be one or more. For example, in "first device," the number of "devices" can be one or more. Furthermore, the objects modified by different prefixes can be the same or different. For example, if the object being described is "device", then "first device" and "second device" can be the same device or different devices, and their types can be the same or different. As another example, if the object being described is "information", then "first type of information" and "second type of information" can be the same information or different information, and their content can be the same or different.

[0069] In some embodiments, “including A,” “containing A,” “for indicating A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0070] In some embodiments, terms such as “…”, “determine…”, “in the case of…”, “when…”, “when…”, “if…”, etc. can be used interchangeably.

[0071] In some embodiments, the terms “greater than,” “greater than or equal to,” “not less than,” “more than,” “more than or equal to,” “not less than,” “higher than,” “higher than or equal to,” “not lower than,” and “above” can be used interchangeably, as can the terms “less than,” “less than or equal to,” “not greater than,” “less than,” “less than or equal to,” “not more than,” “lower than,” “lower than or equal to,” “not higher than,” and “below”.

[0072] In some embodiments, devices, etc., can be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. Terms such as “device”, “equipment”, “circuit”, “network element”, “node”, “function”, “unit”, “section”, “system”, “network”, “chip”, “chip system”, “entity”, and “subject” can be used interchangeably.

[0073] In some embodiments, "network" can be interpreted as network-side devices or network functions, such as access network devices and core network devices.

[0074] In some embodiments, the terms "access network device (AN device)," "radio access network device (RAN device)," "base station (BS)," "radio base station," "fixed station," "node," "access point," "transmission point (TP)," "reception point (RP)," "transmission / reception point (TRP)," "panel," "antenna panel," "antenna array," "cell," "macro cell," "small cell," "femto cell," "pico cell," "sector," "cell group," "serving node," "carrier," "component carrier," and "bandwidth part (BWP)" can be used interchangeably.

[0075] In some embodiments, the terms "UE (terminal)," "UE device (terminal device)," "user equipment (UE)," "user UE (user terminal)," "mobile station (MS)," "mobile UE (MT)," "subscriber station," "mobile unit," "subscriber unit," "wireless unit," "remote unit," "mobile device," "wireless device," "wireless communication device," "remote device," "mobile subscriber station," "access UE," "mobile UE," "wireless terminal," "remote UE," "handset," "user agent," "mobile client," and "client" can be used interchangeably.

[0076] In some embodiments, the access network device, core network device, or network device can be replaced by a UE. For example, embodiments of this disclosure can also be applied to structures where communication between the access network device, core network device, or network device and the UE is replaced by communication between multiple UEs (e.g., device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, the UE can also be configured to have all or some of the functions of the access network device. Furthermore, terms such as "uplink" and "downlink" can be replaced with terms corresponding to communication between UEs (e.g., "sidelink"). For example, uplink channel, downlink channel, etc., can be replaced with sidelink channel, and uplink link, downlink, etc., can be replaced with sidelink link.

[0077] In some embodiments, the UE can be replaced by an access network device, a core network device, or a network device. In this case, it can also be configured such that the access network device, core network device, or network device has all or some of the functions of the UE.

[0078] In some embodiments, the acquisition of data, information, etc., may comply with the laws and regulations of the country where the location is situated.

[0079] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0080] Furthermore, each element, each row, or each column in the table of this disclosure can be implemented as an independent embodiment, and any combination of any element, any row, or any column can also be implemented as an independent embodiment.

[0081] Figure 1A is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure.

[0082] As shown in Figure 1A, the communication system 100 includes a terminal 101 and a network device 102. The network device 102 may include access network equipment and / or core network equipment. The terminal may also be referred to as a UE.

[0083] In some embodiments, terminal 101 includes, but is not limited to, at least one of the following: mobile phone, wearable device, Internet of Things device, car with communication function, smart car, tablet computer, computer with wireless transceiver function, virtual reality (VR) UE device, augmented reality (AR) UE device, wireless UE device in industrial control, wireless UE device in self-driving, wireless UE device in remote medical surgery, wireless UE device in smart grid, wireless UE device in transportation safety, wireless UE device in smart city, and wireless UE device in smart home.

[0084] In some embodiments, UE is also referred to as User Equipment (UE).

[0085] In some embodiments, the access network device may be a node or device that connects the UE to the wireless network. The access network device may include, but is not limited to, at least one of the following in a 5G communication system: evolved Node B (eNB), next generation eNB (ng-eNB), next generation Node B (gNB), node B (NB), home node B (HNB), home evolved node B (HeNB), radio backhaul device, radio network controller (RNC), base station controller (BSC), base transceiver station (BTS), base band unit (BBU), mobile switching center, base station in a 6G communication system, open RAN, cloud RAN, base station in other communication systems, and access node in a Wi-Fi system.

[0086] In some embodiments, the technical methods of this disclosure can be applied to the Open RAN architecture. In this case, the interfaces between or within access network devices involved in the embodiments of this disclosure can be transformed into internal interfaces of Open RAN. The processes and information interactions between these internal interfaces can be implemented by software or programs.

[0087] In some embodiments, the access network device may be composed of a central unit (CU) and a distributed unit (DU). The CU may also be called a control unit. The CU-DU structure can separate the protocol layer of the access network device. Some of the protocol layer functions are centrally controlled by the CU, while the remaining part or all of the protocol layer functions are distributed in the DU and centrally controlled by the CU. However, this is not the only possibility.

[0088] In some embodiments, the core network equipment can be a single device, including a first network element, or it can be multiple devices or a group of devices, each including a first network element. Network elements can be virtual or physical. The core network includes, for example, at least one of an Evolved Packet Core (EPC), a 5G Core Network (5GCN), and a Next Generation Core (NGC).

[0089] It is understood that the communication system described in this disclosure is for the purpose of more clearly illustrating the technical methods of this disclosure and does not constitute a limitation on the technical methods provided in this disclosure. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical methods provided in this disclosure are also applicable to similar technical problems.

[0090] The following embodiments of this disclosure can be applied to the communication system 100 shown in FIG1A, or to some of the main bodies, but are not limited thereto. The main bodies shown in FIG1A are illustrative. The communication system may include all or some of the main bodies in FIG1A, or it may include other main bodies outside of FIG1A. The number and form of each main body are arbitrary. The connection relationship between the main bodies is illustrative. The main bodies may not be connected or may be connected. The connection can be in any way, it can be a direct connection or an indirect connection, it can be a wired connection or a wireless connection.

[0091] The embodiments disclosed herein can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), Future Radio Access (FRA), New-Radio Access Technology (RAT), New Radio (NR), New radio access (NX), Future generation radio access (FX), Global System for Mobile communications (GSM), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), and IEEE 802.20, Ultra-Wideband (UWB), Bluetooth (a registered trademark), Public Land Mobile Network (PLMN) networks, Device-to-Device (D2D) systems, Machine-to-Machine (M2M) systems, Internet of Things (IoT) systems, Vehicle-to-Everything (V2X) systems, systems utilizing configuration methods of other resources, and next-generation systems extended from them, etc. Furthermore, multiple systems can be combined (e.g., LTE and NR can be combined).

[0092] Wireless communication networks can use AI for prediction and inference to improve system performance. Training AI models requires collecting a large amount of data, and the data requirements vary depending on the application scenario. Application scenarios can include mobile communication system processes such as beam management, channel state information (CSI) reporting, CSI compression, positioning, handover, mobility management and / or radio resource management.

[0093] During mobility operations, terminals can predict cell measurement results, handover target cells, or mobility events. Predicting future cell measurement results can be termed temporal prediction. Alternatively, predicting the measurement results of cells not yet measured can be termed spatial prediction. Mobility events include met measurement reporting conditions, handover failures, cell dwell time, and radio link failures.

[0094] In mobility management, the data used for model training can include measurement results from the serving cell, measurement results from the target cell, time, terminal location, source cell, and target cell, etc.

[0095] In the use and reasoning of AI, multiple AI models or AI functions may be needed for reasoning and prediction. An AI function implements a specific function and may include one or more AI models.

[0096] Within a measurement period, the terminal acquires the measurement values ​​of the reference signal during N measurement opportunities. It processes these measurement results to obtain a Reference Signal Received Power (RSRP) value; this processing is called L1 filtering. The measurement value obtained after L1 filtering is the measurement result after a Layer 1 (L1) filter (referred to as the L1 measurement result), which can be used to evaluate measurement reporting events and report them to the network.

[0097] There are various methods of L1 filtering, including but not limited to at least one of the following:

[0098] The average of the N measurements is used to obtain the L1 filtered value.

[0099] Select the strongest measurement result among N measurements as the value of the L1 filter;

[0100] The median measurement value among N measurements is selected as the L1 filter value. The method used depends on the device implementation. The measurement results of the serving cell or neighboring cells used in evaluating measurement events and reporting are obtained after filtering the terminal's Layer 1 (L1) measurement results through Layer 3 (L3) filtering. The L3 filter relationship is shown below:

[0101] Fn=(1-a)*Fn-1+a*Mn, where Mn is the L1 measurement result of this time; Fn is the measurement result after L3 filtering this time; and Fn-1 is the measurement result after L3 filtering in the previous time.

[0102] The quantity configuration is used to determine the parameter 'a' in the filter; different access technologies use different filter parameters.

[0103] It is worth noting that the above functional relationship is merely one example of L3 filtering, and the actual implementation is not limited to this example. There are at least two ways to obtain the time-domain measurement results:

[0104] Method 1: As shown in Figure 1B, L1 and / or L3 measurement results are obtained based on a sliding window. That is, the terminal performs L1 and / or L3 filtering for each L1 measurement result obtained, and obtains the L1 and / or L3 filtered measurement results.

[0105] Method 2: As shown in Figure 1C, L1 and / or L3 measurement results are obtained based on the measurement period. That is, the terminal performs L1 and / or L3 filtering after each measurement period to obtain the L1 and L3 filtered measurement results.

[0106] In methods 1 and 2, L1 filtering is applied to the actual measured values ​​to obtain L1 measurement results. L3 filtering is applied to methods 1 and 2 to obtain L3 measurement results.

[0107] The AI ​​function can predict other measurement results based on some of the measurement results, allowing the terminal to reduce the number of measurements and thus save energy. The terminal will perform measurements according to the network configuration, which includes the measurement object, report configuration, and quantity configuration.

[0108] The measurement object indicates the frequency or access technology to be measured. Different access technologies have their specific frequency ranges, and the measurement behavior of the UE differs depending on the access technology. For example, the technology may include, but is not limited to, New Radio (NR) and / or Long-term Evolution (LTE), and each measurement object is bound to a measurement object index identifier (measObject ID).

[0109] The reporting configuration indicates the type of reporting by the terminal, including periodic reporting and event-based reporting. It carries the reporting timer configuration. The reporting timer configuration can be used to run the reporting timer within the terminal. The running status of the reporting timer is used to trigger measurement reporting. Reporting timers may include, but are not limited to, T321, T322, and TTT (TimerToTrigger, TTT). Different reporting configurations can be used for measurement objects of different access technologies, and each reporting configuration is bound to a reporting configuration index identifier (reportconfig ID).

[0110] Event-based reporting configurations provide the following settings: the measurement that triggers the reporting. This measurement may include, but is not limited to, Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), or Signal to Interference plus Noise Ratio (SINR).

[0111] Threshold or bias.

[0112] The type of reported measurement results (measurements) includes RSRP, RSRQ, or SINR.

[0113] The terminal compares the relationship between signal measurement results of the serving cell or neighboring cells, or the relationship with a threshold. If the threshold requirement is met, the measurement result is triggered to be reported.

[0114] Event-based measurement reporting includes A1-A6, B1-B2, D1, and T1. A-series events are used for intra-system mobility management, while B-series events are used for inter-system mobility management. D1 and T1 are used for satellite system mobility management. The A-series reported events are shown below.

[0115] Event A1: The quality of the serving cell is better than the absolute threshold;

[0116] Event A2: The quality of the serving cell becomes worse than the absolute threshold;

[0117] Event A3: The quality offset of the neighboring cell is better than that of the primary cell (PCell) and / or the primary secondary cell (PSCell); this offset can be set by the network device, and for example, the offset is a positive number.

[0118] Event A4: The quality of the neighboring cell is better than the absolute threshold;

[0119] Event A5: The quality of the primary cell or the primary and secondary cells deteriorates below the absolute threshold d1, while the quality of the neighboring cells improves above another absolute threshold d2;

[0120] Event A6: The offset of the neighboring cell is better than that of the secondary cell. This offset can be set by the network device; for example, the offset is a positive number.

[0121] For each event, entry and exit conditions are defined separately. For cells that do not meet the measurement reporting conditions, the terminal evaluates the entry conditions for that cell. For cells that have already triggered measurement reporting, the terminal evaluates the exit conditions for that cell. Measurement reporting can be triggered when the entry conditions are met, or when the exit conditions are met continuously within the TTT duration.

[0122] If measurement results are predicted as shown in Figure 3, and the predicted results are obtained using the measurement results, some predicted results may be delayed due to processing delays in the AI ​​function. For example, the measurement result at time 2 may not be available until after time 5, because the AI ​​needs the measurement result at time 5 as input to obtain the predicted result at time 2. If the TTT (Time To Handling) times out at time 8, the UE will need to wait until time 11 to confirm and trigger measurement reporting, which will cause handover delays and may lead to handover failure.

[0123] If the data used to train an AI model is inconsistent with the input data used for prediction, the prediction accuracy will decrease. When training the AI, data with strong measurement results may be selected. However, during inference, the measurement results obtained by the user experience (UE) may be poor, which will reduce the AI's inference accuracy.

[0124] As shown in Figure 2A, this embodiment of the disclosure provides a method for controlling the use of AI functions, which can be executed by the communication system shown in Figure 1A. The method may include:

[0125] S2101: The first node sends the first information to the terminal.

[0126] In some embodiments, the first node may be a device different from the terminal. For example, the first node may be a network device, an application server, a training node for AI functions, and / or a service node for AI functions.

[0127] In some embodiments, the first node includes a network device and / or a training node for AI functions.

[0128] In some embodiments, the AI ​​function is used to output predictions for wireless measurements.

[0129] In some embodiments, wireless measurement includes, but is not limited to, various measurements of wireless signals. Exemplarily, the wireless measurement may include, but is not limited to, one or more of the following: beam measurement; cell measurement; positioning reference signal measurement.

[0130] In some embodiments, beam measurement can be used by the terminal to determine a good beam for communication with network devices based on the measurement results. Here, a good beam refers to a beam with signal quality above a threshold or optimal.

[0131] In some embodiments, cell measurement can be used to determine the serving cell or alternative serving cells based on the measurement results. For example, during cell handover or cell reselection, the measurement results of cell measurement can be used by network devices to select a target cell for cell handover or cell reselection for the terminal.

[0132] In some embodiments, in carrier aggregation or multi-connectivity (e.g., dual-connectivity) scenarios, cell measurements can also be used to determine the terminal's primary cell, secondary cell, or alternative cell. The alternative cell can subsequently be changed to the terminal's primary or secondary cell depending on the terminal's movement or the change in the wireless environment.

[0133] In some embodiments, the results of the wireless measurement can be used for Radio Resource Management (RRM). The results of the wireless measurement can be used for Radio Link Management (RLM).

[0134] In some embodiments, the first information is used to determine whether the performance of the AI ​​function meets a first condition for stopping the use of the AI ​​function.

[0135] In some embodiments, the first information is used to describe the data characteristics of the second data.

[0136] In some embodiments, the second data is training data for the AI ​​function. The first data may be data to be input into the AI ​​function.

[0137] In some embodiments, data characteristics include one or more of the following: data type; range of data values; mean of data; extreme values ​​of data; range of variance of data; range of standard deviation of data.

[0138] In AI applications related to wireless measurement, this data type may include floating-point numbers, integers, etc. For example, in AI applications related to wireless measurement, the data type may include the measured quantity.

[0139] In some embodiments, S2101 is an optional step, as the terminal obtains the first information when installing the AI ​​function, thus eliminating the need for repeated acquisition. In other embodiments, the AI ​​function may be an online AI function, where the terminal requests a server on the network side to assist in executing the AI ​​function; in this case, the terminal itself does not need to obtain the first information. Therefore, the terminal does not need to obtain the first information.

[0140] In some embodiments, the AI ​​functionality may be the ability to perform predictions of wireless measurements using one or more AI models.

[0141] In some embodiments, this AI function can be used to output prediction results corresponding to L1 measurement results.

[0142] In some embodiments, this AI function can be used to output prediction results corresponding to L3 measurement results.

[0143] In some embodiments, the AI ​​function can be used to output prediction results corresponding to L1 and / or L3 measurement results.

[0144] In some embodiments, the input to the AI ​​function may include: actual measurement results and / or prediction results from one or more moments in time for the AI ​​function.

[0145] S2102: The terminal determines whether the performance of the AI ​​function meets the first condition.

[0146] In some embodiments,

[0147] The first condition includes one or more of the following:

[0148] The first duration of the AI ​​function's predicted output is greater than the second duration;

[0149] The characteristics of the first data and the second data are inconsistent. The first data is the input data for the AI ​​function; the second data is the training data for the AI ​​function.

[0150] In some embodiments, the second duration may be a duration specified by the network device. In some embodiments, the second duration may be a duration agreed upon by the protocol.

[0151] In some embodiments, the second duration can be the timing duration of various timers. For example, the second duration can be the timing duration of a reporting timer. This reporting timer may include, but is not limited to, the aforementioned T321, T322, and / or TTT.

[0152] In other embodiments, the first timer is started according to the timer configuration, and if a trigger event is detected during the timing period of the first timer, the response measurement result or prediction result is reported.

[0153] In some embodiments, after the first timer is started, one or more predictions of the AI ​​function are made during the first timer period, so that it can be determined whether the performance of the AI ​​function meets the first condition before determining periodically whether to continue using the AI ​​function or before each use of the AI ​​function.

[0154] In some embodiments, when determining whether the performance of the AI ​​function meets the first condition, the determination is based on whether the first duration of the AI ​​function is greater than the remaining duration of the first timer. If the first duration output by the AI ​​function is greater than the remaining duration of the first timer, the terminal will detect a trigger event associated with the first timer. Therefore, in this case, the performance of the AI ​​function can be considered to meet the first condition, and the use of the AI ​​function can be stopped in time to reduce the false detection of trigger events during the timing period of the first timer. If the first timer is a TTT (Time To Day) or similar device, unnecessary reporting during TTT operation can be reduced, and the interaction between the terminal and network devices can be reduced.

[0155] In some embodiments, the performance of an AI function can be determined by its output latency. Generally, the lower the output latency of an AI function, the more powerful its computational capabilities and the higher its output rate, thus having less impact on the use of the AI ​​function. In other words, the output latency of an AI function is negatively correlated with its output performance.

[0156] In some embodiments, the first timer may be a timer used by the terminal to determine whether to send wireless measurement results to the network device. Exemplarily, if the first result continuously satisfies the second condition within the timing range of the first timer, the terminal sends the first result to the network device, the first result including the measurement result and / or prediction result of the wireless measurement.

[0157] In some embodiments, the second condition is continuously satisfied, including but not limited to: the first result is obtained in a timely manner each time within the timing range of the first timer and the measurement quality indicated by the first result is greater than the threshold.

[0158] In some embodiments, the failure to continuously meet the second condition may include, but is not limited to:

[0159] The first result cannot be obtained in time within the timing range of the first timer;

[0160] Within the timing range of the first timer, one or more of the first results indicate that the measurement quality is less than or equal to the threshold.

[0161] In some embodiments, the first duration includes one of the following:

[0162] The time difference between the first output and the last input during an AI function's prediction process;

[0163] The third duration is provided by the training nodes of the AI ​​function.

[0164] In some embodiments, the first duration is related to the delay in the AI ​​function's output prediction result. For example, the first duration may be determined based on historical delay statistics of one or more output prediction results by the AI ​​function within the current time period.

[0165] In some embodiments, if the delay of the AI ​​function is the time difference between the first output and the last input in the time domain during a prediction process, the terminal can calculate or measure it based on the time difference between the time when its input is provided and the time when its output is acquired.

[0166] If the first duration of the AI ​​function is the third duration, the third duration can be dynamically requested from the training node, or it can be obtained from the application's package when the AI ​​function is installed.

[0167] In some embodiments, when measurement results are required, the terminal measures the reference signal to obtain the measurement results.

[0168] In some embodiments, the reference signal measured by the terminal includes, but is not limited to, one or more of the following:

[0169] Synchronization Signal / (Physical Broadcast Channel, PBCH) Block (SSB), Channel State Information-Reference Signal (CSI-RS), and / or Tracking Reference Signal (TRS), etc.

[0170] In some embodiments, the situations requiring measurement results include one or more of the following:

[0171] Not enough prediction results were obtained to serve as input parameters for AI functions;

[0172] Network equipment or protocol specifications indicate that the input parameters for AI functions cannot all be prediction results;

[0173] The terminal has just activated the AI ​​function;

[0174] There is a need to correct predictions using actual measurement results.

[0175] In some embodiments, the data characteristic can be understood as data features or data attributes, etc., describing the content of the data.

[0176] In some embodiments, the data characteristics of the first data and the data characteristics of the second data are inconsistent, including one or more of the following:

[0177] The first data point is greater than or equal to the first threshold.

[0178] The AI ​​function requires the first data input to be greater than or equal to a first threshold after N consecutive inputs; N is a positive integer.

[0179] The AI ​​function ensures that the first input data remains greater than or equal to the first threshold within the fourth time period.

[0180] The first data point is less than or equal to the second threshold;

[0181] The AI ​​function requires the first data input to be less than or equal to the second threshold for M consecutive inputs, where M is a positive integer.

[0182] The first data input within the fifth time period of the AI ​​function is less than or equal to the second threshold.

[0183] In some embodiments, the first threshold is associated with the second data; and / or, the second threshold is associated with the second data.

[0184] In some embodiments, the first threshold and / or the second threshold embody the data characteristics of the second data.

[0185] In some embodiments, the first threshold and / or the second threshold are determined based on the second data, for example, based on the data distribution characteristics of a plurality of second data.

[0186] In some embodiments, the first threshold may be determined based on the maximum values ​​of a plurality of second data. In other embodiments, the second threshold may be determined based on the minimum values ​​of a plurality of second data.

[0187] In some embodiments, the first threshold and the second threshold are not extreme values ​​of the plurality of second data, but rather two values ​​located between the maximum and minimum values ​​of the plurality of second data, depending on the distribution of the numerical magnitudes of the plurality of second data.

[0188] In some embodiments, the inconsistency between the data characteristics of the first data and the data characteristics of the second data may include, but is not limited to, the following special cases:

[0189] If the second data is less than the first threshold, the first data is greater than or equal to the first threshold.

[0190] If the second data point is less than the first threshold, the AI ​​function will input the first data point N consecutively, and the first data point will be greater than or equal to the first threshold; N is a positive integer.

[0191] If the second data is less than the first threshold, the AI ​​function will input the first data that is continuously greater than or equal to the first threshold within the fourth time period.

[0192] If the second data is greater than the second threshold, the first data is less than or equal to the second threshold.

[0193] If the second data point is greater than the second threshold, and the first data point input by the AI ​​function is less than or equal to the second threshold for M consecutive times, where M is a positive integer, or...

[0194] If the second data is greater than the second threshold, the first data input within the fifth duration of the AI ​​function is less than or equal to the second threshold.

[0195] In some embodiments, the first threshold, the second threshold, N and / or M may all be indicated by the first node.

[0196] In some embodiments, the first threshold, the second threshold, N and / or M can be determined by the terminal itself based on local policies or historical usage of AI functions.

[0197] In some embodiments, the first threshold, the second threshold, N and / or M can all be agreed upon by the protocol.

[0198] In some embodiments, there are many ways to determine whether the data characteristics of the first data and the data characteristics of the second data are consistent, and the specific implementation is not limited to any of the above methods.

[0199] In some embodiments, assuming the second data input during AI model training includes I type A measurements and P type B measurements, but the ratio of the two types of measurements in the first data to be input into the AI ​​model differs from the ratio of the two types of measurements in the second data, then the data characteristics of the first data and the second data can also be considered inconsistent. In some embodiments, the specific item for determining whether the first condition is met is selected according to different application scenarios. For example, if the current scenario requires latency sensitivity or high accuracy, then the first condition can be considered met if there is a second data point less than the first threshold or a second data point greater than the second threshold.

[0200] S2103: The performance of the AI ​​function meets the first condition; stop using the AI ​​function.

[0201] In some embodiments, if the performance of the AI ​​function meets a first condition, the predictive processing of wireless measurements by the AI ​​function is stopped.

[0202] In some embodiments, the first condition may include one or more sub-conditions.

[0203] In some embodiments, the sub-conditions for the prediction results corresponding to L3 measurement results and L1 measurement results are different. For example, the sub-condition corresponding to the L1 measurement result is the first sub-condition, and the sub-condition corresponding to the L3 measurement result is the second sub-condition. If the output performance of the AI ​​function and the L1 measurement result meets the first sub-condition, the AI ​​function stops predicting both the L1 and L3 measurement results. For example, if the output performance of the AI ​​function and the L3 measurement result meets the second sub-condition, the AI ​​function stops predicting the L3 measurement result.

[0204] Different sub-conditions are used to determine whether to use AI function based on L1 and L3 measurement results. This can maximize the use of AI function for wireless measurement processing and reduce the probability of poor prediction accuracy caused by continuing to use AI function with low performance.

[0205] Of course, the above are just examples. In some embodiments, the prediction of L1 measurement results and the prediction of L3 measurement results can be performed under the same conditions without distinction.

[0206] As shown in Figure 2B, this embodiment of the disclosure provides a method for controlling the use of AI functions, which can be executed by the communication system shown in Figure 1A. The method may include:

[0207] S2201: The first node sends the first information to the terminal.

[0208] For a description of the first node, terminal, and / or first information, please refer to the description of the corresponding embodiment in Figure 2A, which will not be repeated here.

[0209] Similarly, S2201 is an optional step, as the terminal obtains the first information when installing the AI ​​function, so there is no need to obtain it again. In other embodiments, the AI ​​function may be an online AI function, that is, the terminal requests the network-side server to help execute the AI ​​function. In this case, the terminal itself does not need to obtain the first information. Therefore, the terminal does not need to obtain the first information.

[0210] In some embodiments, the AI ​​functionality may be the ability to perform predictions of wireless measurements using one or more AI models.

[0211] In some embodiments, the first information can be used by the terminal to determine whether a first condition is met, and if the first condition is met, the use of the AI ​​function will be stopped. In some embodiments, the AI ​​function can be used to output the prediction result corresponding to the L1 measurement result. In some embodiments, the AI ​​function can be used to output the prediction result corresponding to the L3 measurement result. In some embodiments, the AI ​​function can be used to output the prediction result corresponding to the L1 and / or L3 measurement results. In some embodiments, the input to the AI ​​function may include: the actual measurement result and / or the prediction result of one or more time points of the AI ​​function.

[0212] S2202: The terminal determines whether the performance of the AI ​​function meets the first condition.

[0213] In some embodiments, the relevant descriptions of the AI ​​function and / or the first condition can be found in the embodiment corresponding to Figure 2A.

[0214] S2203: The performance of the AI ​​function does not meet the first condition for continued use of the AI ​​function.

[0215] In some embodiments, if the performance of the AI ​​function does not meet the first condition, the AI ​​function continues to be used for predictive processing of wireless measurements.

[0216] In some embodiments, if the performance of the AI ​​function does not meet the first condition, the AI ​​function continues to be used.

[0217] In some embodiments, if the performance of the AI ​​function does not meet the first condition, the AI ​​function may continue to be used until the specified task is completed or a stop instruction is received.

[0218] In some embodiments, if the performance of the AI ​​function does not meet the first condition, the AI ​​function continues to be used to perform predictive processing of wireless measurements.

[0219] In some embodiments, the first condition may include one or more sub-conditions.

[0220] In some embodiments, the sub-conditions for the prediction results corresponding to L3 measurement results and L1 measurement results are different. For example, the sub-condition corresponding to the L1 measurement result is the first sub-condition, and the sub-condition corresponding to the L3 measurement result is the second sub-condition. If the output performance of the AI ​​function and the L1 measurement result meets the first sub-condition, the AI ​​function stops predicting both the L1 and L3 measurement results. For example, if the output performance of the AI ​​function and the L3 measurement result meets the second sub-condition, the AI ​​function stops predicting the L3 measurement result.

[0221] If the output performance of the AI ​​function does not meet the first sub-condition, continue to use the AI ​​function to predict the L1 measurement results of wireless measurement.

[0222] If the output performance of the AI ​​function does not meet the first sub-condition and does not meet the second sub-condition, continue to use the AI ​​function to predict the L3 measurement results of wireless measurement.

[0223] If the output performance of the AI ​​function and the L3 measurement results meet the second sub-condition but the output performance of the AI ​​function does not meet the first sub-condition, stop the AI ​​function from predicting the L3 measurement results and continue to use the AI ​​function to predict the L1 measurement results.

[0224] In some embodiments, different sub-conditions are distinguished for L1 measurement results and L3 measurement results to determine whether AI function should be used. This can maximize the use of AI function for wireless measurement processing and reduce the probability of poor prediction accuracy caused by continuing to use AI function when its performance is low.

[0225] Of course, the above are just examples. In some embodiments, the prediction of L1 measurement results and the prediction of L3 measurement results can be performed under the same conditions without distinction.

[0226] This disclosure provides a method for stopping AI functions, enabling AI functions to stop working when performance is poor, thus avoiding performance degradation during switching or inference.

[0227] Option 1: The terminal determines to stop the AI ​​function if the first condition is met. The AI ​​function is used to predict measurement results.

[0228] As an example, the measurement results can be cell measurement results or beam measurement results.

[0229] Option 2: Based on Option 1, the first condition can be that the delay duration of the AI-predicted measurement result is greater than or equal to the second duration, and then the AI ​​function can be stopped.

[0230] Option 3: Based on Option 2, the delay duration is determined by any of the following:

[0231] a. The time difference between the first / earliest measurement result predicted by the AI ​​and the last / latest measurement result input by the AI.

[0232] b. The correspondence between AI functions and latency duration is determined by the network or by the node that provides AI model training.

[0233] As an example, the nodes for training the AI ​​model can be servers or network nodes.

[0234] Option 4: Based on option 2 or 3, the second duration is the remaining time of the distance timeout for the currently running TTT.

[0235] Option 5: Based on Option 1, the first condition can be that the input to the AI ​​function is inconsistent with the data used to train the AI ​​function.

[0236] Option 6: Based on Option 5, if the measurement results obtained by the terminal for input meet any of the following conditions, it is determined that the input to the AI ​​function is inconsistent with the data used to train the AI ​​function:

[0237] a. The measurement results used for input are below the threshold 1 for N consecutive times;

[0238] b. N consecutive measurement results used for input are higher than the threshold 2;

[0239] c. The measurement results used for input remain below the threshold 1 throughout the second time period;

[0240] d. The measurement results used for input during the second time period remain above the threshold 2.

[0241] Option 7: Based on Option 6, determine the parameters through the correspondence between AI functions and parameters. The parameters include the threshold, duration, and the value of N. The correspondence can be provided by the network or by the node providing AI model training.

[0242] Option 8: Based on Option 4, the measurement results used as input can be obtained from terminal measurements or predicted by AI.

[0243] To address the potential delays in prediction results and the decline in prediction accuracy of AI models when input data differs from training data, this disclosure proposes a method for stopping AI functions. This method aims to promptly halt the operation of AI functions when their performance is poor, thereby avoiding a decrease in switching or inference performance.

[0244] This disclosure provides a method for stopping AI functions, wherein the method is executed by a user device (terminal), and specifically includes the following steps:

[0245] Step A: Monitor the status of the AI ​​function, which may include: continuously monitoring the performance of the AI ​​function in predicting measurement results, including the accuracy and latency of the prediction.

[0246] Step B: Determine the conditions for stopping the AI ​​function, which may include: when a preset first condition is met, the terminal determines to stop the AI ​​function.

[0247] The first condition is related to the performance of AI functions, and may include, but is not limited to, the following situations:

[0248] a. The delay duration of the AI-predicted measurement result is greater than or equal to a preset second duration. Here, the delay duration refers to the time difference between the moment corresponding to the measurement result to be predicted and the moment the terminal actually obtains the predicted result.

[0249] b. The accuracy of the AI ​​prediction results is lower than the preset accuracy threshold. Accuracy can be evaluated by comparing the difference between the predicted results and the actual measurement results, or by indicators such as confidence level.

[0250] c. Other conditions related to AI function performance, such as the number of consecutive failures of the AI ​​function exceeding a preset threshold.

[0251] Step C: Perform the shutdown operation for the AI ​​function. This step may specifically include: once it is determined that the conditions for stopping the AI ​​function are met, the terminal immediately stops the operation of the AI ​​function and may trigger the corresponding fault handling or recovery mechanism.

[0252] The following section uses cell measurement results or beam measurement results as the prediction object to illustrate the implementation process of the AI ​​function stopping method:

[0253] Option 1: The terminal determines to stop the AI ​​function if the first condition is met. Here, "AI function" specifically refers to the AI ​​model used to predict cell measurement results or beam measurement results.

[0254] Option 2: In the first condition, it is specifically stipulated that the AI ​​function will be stopped when the delay duration of the AI ​​predicting the measurement result is greater than or equal to the second duration. For example, if the preset second duration is T, and the terminal finds that the delay duration of the AI ​​predicting a certain measurement result exceeds T, then the terminal will stop using the AI ​​function for subsequent predictions.

[0255] Option 3: To accurately determine the delay duration, the terminal can use any of the following methods:

[0256] a. Record the time of the first / earliest measurement result predicted by the AI ​​and compare it with the time of the actual required measurement result to calculate the delay duration.

[0257] b. Alternatively, other more complex algorithms or mechanisms can be used to dynamically monitor and calculate latency.

[0258] In the above solution, timely shutdown of poorly performing AI functions can prevent performance degradation during switching or inference, thereby improving the stability and reliability of the communication system. This method can flexibly adapt to different application scenarios and performance requirements, precisely controlling the start and stop of AI functions through preset conditions. It reduces resource waste and performance loss caused by inaccurate AI predictions or excessive delays.

[0259] In summary, the AI ​​function stopping method provided in this disclosure can effectively solve the problems of delay in measurement result prediction and the decline in AI model prediction accuracy, thereby improving the overall performance of the communication system.

[0260] This disclosure also provides apparatus for implementing any of the above methods. For example, an apparatus is provided that includes units or modules for implementing the steps performed by the UE in any of the above methods. Alternatively, another apparatus is provided that includes units or modules for implementing the steps performed by a network device (e.g., an access network device, or a core network device) in any of the above methods.

[0261] It should be understood that the division of units or modules in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units or modules in the device can be implemented by a processor calling software: for example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of the units or modules in the above device. The processor can be, for example, a general-purpose processor, such as a Central Processing Unit (CPU) or a microprocessor, and the memory can be internal or external to the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits. The functionality of some or all of the units or modules can be achieved through the design of these hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC). The functionality of some or all of the units or modules is achieved through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a programmable logic device (PLD). Taking a field-programmable gate array (FPGA) as an example, it can include a large number of logic gates. The connection relationships between the logic gates are configured through a configuration file, thereby achieving the functionality of some or all of the units or modules. All units or modules of the above device can be implemented entirely through processor-called software, entirely through hardware circuits, or partially through processor-called software with the remaining parts implemented through hardware circuits.

[0262] In this disclosure, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a Central Processing Unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a type of microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. The logical relationships of the aforementioned hardware circuits are fixed or reconfigurable. For example, the processor is a hardware circuit implemented as an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a Neural Network Processing Unit (NPU), a Tensor Processing Unit (TPU), or a Deep Learning Processing Unit (DPU). Unit, DPU, etc.

[0263] As shown in Figure 4A, this embodiment of the present disclosure provides an AI usage control device, which includes:

[0264] The processing module 4101 is configured to stop using the AI ​​function when the performance of the AI ​​function meets a first condition. The AI ​​function is used to output the prediction results of wireless measurements.

[0265] In some embodiments, the AI ​​usage control device includes a receiving module and / or a transmitting module.

[0266] In some embodiments, the transmitting module and / or receiving module may correspond to the network interface and / or transceiver antenna of the AI's use control device.

[0267] In some embodiments, the processing module can be used by an AI usage control device to execute information processing-related steps in any artificial intelligence AI usage control method.

[0268] In some embodiments, the sending module can be used by the AI ​​usage control device to execute information sending-related steps in any AI usage control method.

[0269] In some embodiments, the receiving module can be used by the AI ​​usage control device to execute information transmission-related steps in any AI usage control method.

[0270] In some embodiments, the first condition includes one or more of the following:

[0271] The first duration of the AI ​​function's predicted output is greater than the second duration;

[0272] The data characteristics of the first data are inconsistent with those of the second data; the first data is the input data for the AI ​​function.

[0273] The second set of data consists of training data for the AI ​​function.

[0274] In some embodiments, the first duration includes one of the following:

[0275] The time difference between the first output and the last input during an AI function's prediction process;

[0276] The third duration is provided by the training nodes of the AI ​​function.

[0277] In some embodiments, the second duration is the remaining duration of the first timer.

[0278] In some embodiments, the sending module is configured to send a first result to a network device when the first result continuously satisfies a second condition within the timing range of a first timer. The first result includes measurement results and / or prediction results of wireless measurements.

[0279] In some embodiments, the processing module is further configured to measure the reference signal to obtain the measurement result when a measurement result is required.

[0280] In some embodiments, the apparatus further includes a receiving module configured to receive first information sent by a first node, the first information being used to determine whether the performance of the AI ​​function meets a first condition.

[0281] In some embodiments, the receiving module is configured to receive first information sent by the first node, the first information being used to determine whether the performance of the AI ​​function meets a first condition.

[0282] In some embodiments, the first node includes a network device and / or a training node for AI functions.

[0283] In some embodiments, the first data includes measurement data from the terminal and / or prediction data from AI functions.

[0284] As shown in Figure 4B, this embodiment of the present disclosure provides an AI usage control device, which includes:

[0285] The sending module 4201 is configured to send first information to the terminal, the first information being used to determine whether the performance of the AI ​​function meets the first condition for stopping the use of the AI ​​function.

[0286] In some embodiments, the AI ​​usage control device may further include a processing module and / or a receiving module. In some embodiments, the transmitting module and / or receiving module may correspond to a network interface and / or transceiver antenna of a network device. In some embodiments, the processing module may be used by the AI ​​usage control device to execute information processing-related steps in any AI usage control method. In some embodiments, the transmitting module may be used by the AI ​​usage control device to execute information transmission-related steps in any AI usage control method. In some embodiments, the receiving module may be used by the AI ​​usage control device to execute information transmission-related steps in any AI usage control method.

[0287] In some embodiments, the first information is used to describe the data characteristics of the second data, which is training data for the AI ​​function.

[0288] This disclosure also provides a communication device, which may include one or more processors; wherein the processors are configured to invoke instructions to cause the communication device to execute an artificial intelligence (AI) usage control method and / or an AI usage control method achievable in any of the foregoing embodiments.

[0289] In some embodiments, as shown in FIG5A and / or FIG5B, the communication device 8100 further includes one or more memories 8102 for storing instructions. Optionally, all or part of the memories 8102 may also be located outside the communication device 8100.

[0290] The communication device may be the aforementioned UE or network device. In some embodiments, the network device may be a primary node and / or a secondary node.

[0291] In some embodiments, the communication device 8100 further includes one or more transceivers 8103. When the communication device 8100 includes one or more transceivers 8103, the communication steps such as sending and receiving in the above method are performed by the transceivers 8103, and other steps are performed by the processor 8101.

[0292] In some embodiments, a transceiver may include a receiver and a transmitter, which may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, etc., may be used interchangeably; the terms transmitter, transmitting unit, transmitter, transmitting circuit, etc., may be used interchangeably; and the terms receiver, receiving unit, receiver, receiving circuit, etc., may be used interchangeably.

[0293] Optionally, the communication device 8100 further includes one or more interface circuits 8104, which are connected to the memory 8102. The interface circuits 8104 can be used to receive signals from the memory 8102 or other devices, and can be used to send signals to the memory 8102 or other devices. For example, the interface circuits 8104 can read instructions stored in the memory 8102 and send the instructions to the processor 8101.

[0294] The communication device 8100 described in the above embodiments may be a network device or a UE, but the scope of the communication device 8100 described in this disclosure is not limited thereto, and the structure of the communication device 8100 may not be limited by FIG. 5A. The communication device may be a standalone device or may be part of a larger device. For example, the communication device may be: (1) a standalone integrated circuit IC, or chip, or chip system or subsystem; (2) a collection of one or more ICs, optionally, the IC collection may also include storage components for storing data and programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, UE device, smart UE device, cellular phone, wireless device, handheld device, mobile unit, vehicle device, network device, cloud device, artificial intelligence device, etc.; (6) others, etc.

[0295] Figure 5B is a schematic diagram of the structure of chip 8200 provided in an embodiment of this disclosure. For cases where the communication device 8100 can be a chip or a chip system, please refer to the schematic diagram of the structure of chip 8200 shown in Figure 5B, but it is not limited thereto.

[0296] Chip 8200 includes one or more processors 8201, which are used to invoke instructions to cause chip 8200 to execute any of the above-mentioned artificial intelligence (AI) usage control methods.

[0297] In some embodiments, chip 8200 further includes one or more interface circuits 8202 connected to memory 8203. Interface circuits 8202 can be used to receive signals from memory 8203 or other devices, and can also be used to send signals to memory 8203 or other devices. For example, interface circuit 8202 can read instructions stored in memory 8203 and send those instructions to processor 8201. Optionally, terms such as interface circuit, interface, transceiver pin, and transceiver can be used interchangeably.

[0298] In some embodiments, chip 8200 further includes one or more memories 8203 for storing instructions. Optionally, all or part of the memories 8203 may be located outside of chip 8200.

[0299] This disclosure also provides a storage medium storing instructions that, when executed on a communication device 8100, cause the communication device 8100 to perform any of the methods described above. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but it can also be a storage medium readable by other devices. Optionally, the storage medium can be a non-transitory storage medium, but it can also be a temporary storage medium.

[0300] This disclosure also provides a program product, which, when executed by a communication device 8100, causes the communication device 8100 to execute any of the above-mentioned artificial intelligence (AI) usage control methods. Optionally, the program product is a computer program product.

[0301] This disclosure also provides a computer program that, when run on a computer, causes the computer to execute any of the above-described artificial intelligence (AI) usage control methods.

[0302] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the embodiments of this disclosure that follow the general principles of the embodiments of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the embodiments of this disclosure are indicated by the following claims.

[0303] It should be understood that the embodiments disclosed herein are not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from their scope. The scope of the embodiments disclosed herein is limited only by the appended claims.

Claims

1. A method for controlling the use of artificial intelligence (AI), wherein, The method, executed by a terminal, includes: If the performance of the AI ​​function meets the first condition, the use of the AI ​​function, which is used to output the prediction results of wireless measurement, shall be stopped.

2. The method according to claim 1, wherein, The first condition includes one or more of the following: The first duration of the AI ​​function's output prediction result is greater than the second duration; The data characteristics of the first data and the second data are inconsistent. The first data is the input data of the AI ​​function; the second data is the training data of the AI ​​function.

3. The method according to claim 2, wherein, The first duration includes one of the following: The time difference between the first output and the last input during a single prediction process of the AI ​​function; The third duration is provided by the training node of the AI ​​function.

4. The method according to claim 2 or 3, wherein, The second duration is the remaining duration of the first timer.

5. The method according to claim 4, wherein, The method further includes: sending the first result to the network device if the first result continuously satisfies the second condition within the timing range of the first timer, wherein the first result includes the measurement result and / or prediction result of the wireless measurement.

6. The method according to claim 5, wherein, The method further includes: When the measurement result is required, the measurement reference signal is measured to obtain the measurement result.

7. The method according to claim 2, wherein, The data characteristics of the first data and the data characteristics of the second data are inconsistent, including one or more of the following: The first data is greater than or equal to the first threshold. The AI ​​function inputs the first data N times consecutively, and the result is greater than or equal to the first threshold; where N is a positive integer. The AI ​​function inputs the first data that is continuously greater than or equal to the first threshold within a fourth time period; The first data is less than or equal to the second threshold; The AI ​​function inputs the first data M times consecutively, and the result is less than or equal to the second threshold, where M is a positive integer. The first data input within the fifth time period of the AI ​​function is less than or equal to the second threshold.

8. The method according to claim 7, wherein, The first threshold is related to the second data; and / or, the second threshold is related to the second data.

9. The method according to any one of claims 1 to 7, wherein, The method further includes: Receive first information sent by the first node, the first information being used to determine whether the performance of the AI ​​function meets the first condition.

10. The method according to claim 9, wherein, The first node includes network devices and / or training nodes for the AI ​​function.

11. The method according to any one of claims 1 to 10, wherein, The first data includes the measurement data of the terminal and / or the prediction data of the AI ​​function.

12. A method for controlling the use of artificial intelligence (AI), wherein, Executed by the first node, the method includes: Send first information to the terminal, the first information being used to determine whether the performance of the AI ​​function meets the first condition for stopping the use of the AI ​​function.

13. The method according to claim 12, wherein, The first information is used to describe the data characteristics of the second data, which is the training data for the AI ​​function.

14. A control device for the use of artificial intelligence (AI), wherein, The device includes: The processing module is configured to stop using the AI ​​function when the performance of the AI ​​function meets a first condition, wherein the AI ​​function is used to output the prediction result of the wireless measurement.

15. The apparatus according to claim 14, wherein, The device further includes: The sending module is configured to send the first result to the network device if the first result continuously meets the second condition within the timing range of the first timer, wherein the first result includes the measurement result and / or prediction result of the wireless measurement.

16. The apparatus according to claim 14 or 15, wherein, The processing module is further configured to measure a reference signal to obtain the measurement result when the measurement result is required.

17. The apparatus according to any one of claims 14 to 16, wherein, The device further includes: The receiving module is configured to receive first information sent by the first node, the first information being used to determine whether the performance of the AI ​​function meets the first condition.

18. A control device for the use of artificial intelligence (AI), wherein, The device includes: The sending module is configured to send first information to the terminal, the first information being used to determine whether the performance of the AI ​​function meets a first condition for stopping the use of the AI ​​function.

19. A communication system, wherein, The communication system includes: The terminal is configured to execute the AI ​​usage control method according to any one of claims 1 to 11; A network device is configured to perform the AI ​​usage control method as described in claim 12 or 13.

20. A communication device, wherein, The communication device includes: One or more processors; The processor is configured to invoke instructions to cause the communication device to perform the method of any one of claims 1 to 11 or 12 to 13.

21. A storage medium, wherein, The storage medium stores instructions that, when executed on a communication device, cause the communication device to perform any one of the artificial intelligence (AI) usage control methods according to claims 1 to 11 or 12 to 13.

22. A program product, wherein, The program product includes a computer program that, when executed by a communication device, enables the communication device to implement the method of any one of claims 1 to 11 or 12 to 13.

Images