Misjudgment detection method and related product

Abstract

The embodiment of the invention discloses a misjudgment detection method and related products, and the method comprises the steps: predicting a monitoring target according to an artificial intelligence machine learning AIML model, and obtaining prediction information; monitoring the misjudged detection object to obtain first information; and according to the prediction information and the first information, determining whether misjudgment occurs in the AIML model. By adopting the method, whether the prediction of the AIML model has misjudgment or not can be effectively determined.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a misjudgment detection method and related products. Background Art

[0002] At present, the communication system has introduced AI (Artificial Intelligence) function. In the communication system, the prediction processing is performed through the AIML (Artificial Intelligence Machine Learning) model, and the accuracy of the prediction information obtained has a certain probability.

[0003] How to determine whether the AIML model's prediction is misjudged has become a hot topic in current research. Summary of the invention

[0004] The embodiments of the present application provide a misjudgment detection method and related products, which can effectively determine whether a misjudgment occurs in the prediction of an AIML model.

[0005] In order to solve the above technical problems, in a first aspect, an embodiment of the present application provides a misjudgment detection method, the method comprising:

[0006] According to the AIML model, the monitoring target is predicted to obtain prediction information;

[0007] Monitoring the misjudged detection object to obtain first information;

[0008] Determine whether the AIML model makes a misjudgment based on the prediction information and the first information.

[0009] In a second aspect, an embodiment of the present application provides a misjudgment detection method, the method comprising:

[0010] Sending second information to the terminal device, wherein the second information includes false positive detection indication information, and the false positive detection indication information is used to indicate the execution of false positive detection.

[0011] In a third aspect, an embodiment of the present application provides a communication device, the device comprising:

[0012] A prediction unit is used to predict the monitoring target according to the artificial intelligence machine learning AIML model to obtain prediction information;

[0013] A monitoring unit, configured to monitor the misjudged detection object and obtain first information;

[0014] A determination unit is used to determine whether the AIML model has a misjudgment based on the prediction information and the first information.

[0015] In a fourth aspect, an embodiment of the present application provides a communication device, the device comprising:

[0016] A generating unit, configured to generate second information, wherein the second information includes misjudgment detection indication information, and the misjudgment detection indication information is used to instruct to perform misjudgment detection;

[0017] A sending unit is used to send the second information to the terminal device.

[0018] In a fifth aspect, an embodiment of the present application provides a communication device, comprising a processor and a memory, wherein the processor and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is used to call the program instructions to execute the method as described in the first aspect, or to execute the method as described in the second aspect.

[0019] In a sixth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a computer, the method described in the first aspect is executed, or the method described in the second aspect is executed.

[0020] In a seventh aspect, an embodiment of the present application provides a chip, wherein the chip includes a processor, and the processor executes the method as described in the first aspect, or executes the method as described in the second aspect.

[0021] In an eighth aspect, an embodiment of the present application provides a chip module, the chip module comprising a transceiver component and a chip, the chip comprising a processor, the processor executing the method as described in the first aspect, or executing the method as described in the second aspect.

[0022] The implementation of the embodiments of the present application has the following beneficial effects: the present application performs misjudgment detection on the AIML model, and can determine whether misjudgment occurs in the prediction of the AIML model, which is beneficial for optimizing the AIML model to improve the reasoning performance of the AIML model and reduce the misjudgment rate of the AIML model. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A schematic diagram of a possible system architecture provided for an embodiment of the present application;

[0025] Figure 2 A flowchart of a possible misjudgment detection method provided in an embodiment of the present application;

[0026] Figure 3 A schematic diagram of various relevant times in a possible communication scenario provided in an embodiment of the present application;

[0027] Figure 4 A flowchart of a possible misjudgment detection method provided in an embodiment of the present application;

[0028] Figure 5 A flowchart of a possible misjudgment detection method provided in an embodiment of the present application;

[0029] Figure 6 A flowchart of a possible misjudgment detection method provided in an embodiment of the present application;

[0030] Figure 7 A flowchart of a possible misjudgment detection method provided in an embodiment of the present application;

[0031] Figure 8 A block diagram of the functional units of a possible communication device according to an embodiment of the present application;

[0032] Fig. 9 A block diagram of the functional units of a possible communication device according to an embodiment of the present application;

[0033] Fig.10 A schematic diagram of the structure of a possible communication device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0036] The specific embodiments of the present application are further described in detail below in conjunction with the accompanying drawings.

[0037] The terms "first" and "second" and the like in the specification, claims and drawings of this application are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices.

[0038] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0039] In the present application, "at least one (item)" means one or more, "more than one" means two or more, "at least two (items)" means two or three and more than three, and "and / or" is used to describe the corresponding relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0040] The following is an introduction to the system architecture of the embodiment of the present application:

[0041] See also Figure 1 , Figure 1 A schematic diagram of a possible system architecture provided in an embodiment of the present application. The system architecture may include one or more terminal devices 101. Optionally, the system architecture may also include one or more network devices 102. Figure 1 Take a terminal device 101 and a network device 102 as an example.

[0042] In an optional implementation manner, the communication system applied by the system architecture may, for example, include a Global System of Mobile communication (GSM) system, a Code Division Multiple Access (CDMA) system, a Wideband Code Division Multiple Access (WCDMA) system, a General Packet Radio Service (GPRS), a Long Term Evolution (LTE) system, an advanced long term evolution (LTE-A) system, a New Radio (NR) system, an evolution system of the NR system, an LTE-based access to unlicensed spectrum (LTE-U) system, an NR-based access to unlicensed spectrum (NR-U) system, a Universal Mobile Telecommunication System (UMTS), a next generation communication system or other communication systems, etc.

[0043] 1. Terminal equipment

[0044] Terminal equipment, also known as user equipment (UE), includes equipment that provides voice and / or data connectivity to users, such as a handheld device with wireless connection function, or a processing device connected to a wireless modem. The terminal device can communicate with a core network (CN) via a radio access network (RAN) to exchange voice and / or data with the radio access network. The terminal device may include a wireless terminal device, a mobile terminal device, a device-to-device communication (D2D) terminal device, a vehicle to everything (V2X) terminal device, a machine-to-machine / machine-type communications (M2M / MTC) terminal device, an Internet of Things (IoT) terminal device, a subscriber unit, a subscriber station, a mobile station, a remote station, an access point (AP), a remote terminal, an access terminal, a user terminal, a user agent, or a user equipment, etc. For example, it may include mobile phones (or "cellular" phones), computers with mobile terminal devices, portable, pocket-sized, handheld, and computer-built-in mobile devices, etc. For example, personal communication service (PCS) phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDA), and other devices. It also includes limited devices, such as devices with low power consumption, or devices with limited storage capacity, or devices with limited computing power, etc. For example, it includes information sensing devices such as barcodes, radio frequency identification (RFID), sensors, global positioning systems (GPS), laser scanners, etc.

[0045] 2. Network equipment

[0046] Network equipment includes nodes or devices that connect terminal equipment to a wireless network, which can be called access network equipment or base stations. Optionally, access network equipment includes, but is not limited to: a new generation base station (generation Node B, gNB), evolved node B (evolved node B, eNB), radio network controller (radio network controller, RNC), node B (node ​​B, NB), base station controller (base station controller, BSC), base transceiver station (base transceiver station, BTS), home base station (home evolved node B, HeNB) or (home node B, HNB)), baseband unit (baseBand unit, BBU), transmission and receiving point (transmitting and receiving point, TRP), transmission point (transmitting point, TP), or mobile switching center, etc. It should be noted that, Figure 1 The illustrated network device 102 is an access network device.

[0047] Optionally, the network device also includes a network element deployed in the core network, which can be referred to as a core network device ( Figure 1 Not shown). The core network may be, for example, an evolved packet core (EPC), a 5G core network (5Gcore network). The core network equipment may include, for example, an access and mobility management function (AMF) entity, a session management function (SMF) entity, a user plane function (UPF) entity, etc., which are not listed here one by one. Among them, the AMF entity may be responsible for the access management and mobility management of the terminal device; the SMF entity may be responsible for session management, such as user session establishment; the UPF entity may be a functional entity of the user plane, mainly responsible for connecting to the external network.

[0048] Optionally, the access network device can communicate with the terminal device, for example, the access network device can communicate with the terminal device through the air interface. Optionally, the access network device can communicate with the core network device, for example, the access network device can communicate with the core network device through the NG interface. Optionally, the core network device can communicate with the terminal device, for example, the core network device communicates with the terminal device through a non-access stratum (NAS) message. The above is only an example, and the access network device, the terminal device and / or the core network device can also communicate in other ways, and the communication method between the access network device, the terminal device and / or the core network device is not limited here.

[0049] For example, in Figure 1 In the system architecture shown, the terminal device 101 performs prediction processing through an AIML (Artificial Intelligence Machine Learning) model to obtain prediction information. Optionally, the terminal device 101 can perform misjudgment detection on the prediction of the AIML model according to the control of the network device 102. Optionally, the terminal device 101 can also perform misjudgment detection on the prediction of the AIML model according to local policies.

[0050] In order to better understand the solution provided by this application, the following is an introduction to the professional terms and technical terms involved in this application:

[0051] 1. AI model, AIML model information and AIML function information

[0052] The AI ​​model, also known as the AIML model, is used to implement a variety of functions. In the embodiment of the present application, the AIML model is used to implement the communication function.

[0053] The model information of AIML is used to identify the AIML model. The model information of AIML may be, for example, model identification information of the AIML model, and the model identification information may be, for example, a model identifier (Model ID). Different AIML models correspond to different model identification information.

[0054] The AIML function information is used to indicate the communication function of an untrained or trained AIML model. Optionally, the communication function may include, but is not limited to, at least one of the following:

[0055] Channel State Information (CSI) compression feedback,

[0056] Channel state information prediction,

[0057] Beam management,

[0058] position.

[0059] Optionally, the positioning may include direct positioning and / or indirect positioning, etc.

[0060] Among them, AIML model information and / or AIML function information can be used to indicate a specific AIML model and distinguish different AIML models.

[0061] II. Monitoring objectives and forecast information

[0062] In the embodiment of the present application, the prediction information is obtained by predicting the monitoring target according to the AIML model. Performing prediction processing according to the AIML model refers to performing model reasoning through the AIML model.

[0063] Optionally, the monitoring target may include but is not limited to at least one of the following information:

[0064] event,

[0065] Measurement information;

[0066] Measurement object.

[0067] Optionally, an event is Figure 1 Events related to communication services that may occur in the communication system architecture shown. The events may include, but are not limited to, at least one of the following events:

[0068] Beam Failure Detection (BFD),

[0069] Beam Failure Recovery (BFR),

[0070] Radio Link Failure (RLF),

[0071] Handover Failure (HOF).

[0072] Optionally, the measurement information refers to Figure 1 The information or parameters related to the communication service in the communication system architecture shown. The measurement information may include, but is not limited to, at least one of the following information:

[0073] The identification information of the cell,

[0074] The location information of the terminal device,

[0075] Signal quality information of the cell.

[0076] Optionally, the identification information of the cell may be, for example, a cell identifier (Cell ID) and / or a cell global identifier (Cell Global Identity, CGI), etc.

[0077] Optionally, the location of the terminal device may be, for example, Global Navigation Satellite System (GNSS) information.

[0078] Optionally, the signal quality information of the cell includes but is not limited to at least one of the following information:

[0079] Reference Signal Receiving Power (RSRP)

[0080] Reference Signal Receiving Quality (RSRQ),

[0081] Signal to Interference plus Noise Ratio (SINR).

[0082] Optionally, the measurement object refers to Figure 1 The objects in the communication system architecture shown are related to the communication service and are allowed to be measured. The measurement objects may include, but are not limited to, at least one of the following:

[0083] Community,

[0084] The cell's synchronization signal block (SSB),

[0085] The signal frequency of the cell,

[0086] Beam information of the cell.

[0087] In the embodiment of the present application, the prediction information may include but is not limited to at least one of the following information:

[0088] Prediction time,

[0089] The forecast conclusion that appears at the said forecast time,

[0090] predicted measurement information occurring at said predicted time,

[0091] Predicted probability.

[0092] Optionally, the prediction time refers to the predicted time when the prediction conclusion appears and / or the predicted time when the prediction measurement information appears.

[0093] Optionally, the prediction conclusion may include, but is not limited to, at least one of the following:

[0094] An event occurs at the predicted time.

[0095] The event will not occur at the predicted time,

[0096] Execute actions,

[0097] No action is performed.

[0098] Optionally, the event may be a communication event related to a communication service.

[0099] Optionally, the action may include, but is not limited to, performing a cell handover, etc. Optionally, the action may be determined to be performed or not performed according to at least one of the following information:

[0100] Prediction time,

[0101] The events in the prediction conclusion that occur at the prediction time,

[0102] Events in the forecast conclusion that will not occur at the forecast time,

[0103] The predicted measurement information.

[0104] Optionally, the predicted measurement information refers to predicted measurement information.

[0105] Optionally, the predicted probability may include but is not limited to at least one of the following predicted probabilities:

[0106] the probability of the predicted conclusion occurring at the predicted time,

[0107] The probability of the predicted measurement information occurring at the predicted time.

[0108] 3. False positive detection, false positive detection objects and first information

[0109] In a communication system, prediction processing is performed through an AIML model, and whether the prediction information obtained by the prediction is accurate has a certain probability. In an embodiment of the present application, misjudgment detection is performed on the prediction of the AIML model to determine whether the prediction of the AIML is correct.

[0110] In the embodiment of the present application, the misjudgment detection object is an object used to determine whether the AIML model has misjudged. Optionally, the misjudgment detection object may include but is not limited to at least one of the following:

[0111] AIML model,

[0112] Monitoring objectives,

[0113] Predictive information.

[0114] In the embodiment of the present application, the first information is obtained by monitoring the misjudged detection object. The first information is used to match the prediction information to determine whether the AIML model has misjudged. Optionally, the first information may include but is not limited to at least one of the following information:

[0115] Monitoring time,

[0116] The monitoring conclusions obtained during the monitoring period are:

[0117] The measurement information is obtained by monitoring during the monitoring time.

[0118] The monitoring time refers to the time when the monitoring conclusion is obtained and / or the time when the measurement information is obtained.

[0119] The monitoring conclusion may include, but is not limited to, at least one of the following:

[0120] An event is detected during the monitoring time.

[0121] No events were detected during the monitoring time.

[0122] The monitoring target meets the action execution conditions.

[0123] The monitoring target does not meet the action execution conditions.

[0124] Optionally, the action execution condition is a condition for triggering the execution of the action. The action execution conditions corresponding to different actions may be different or the same.

[0125] 4. Monitoring methods and action execution conditions

[0126] In the embodiments of the present application, the monitoring method refers to the actual method of monitoring the misjudged detection object. The monitoring method for the misjudged detection object may be, for example, a legacy method, also known as a legacy criterion. Among them, the legacy method refers to a monitoring method for monitoring the misjudged detection object that is traditional and / or specified in the standard. For example, the legacy method may be to perform neighboring cell measurements on the service cell where the terminal device has historically been located (i.e., the adjacent cell of the service cell where the terminal device is currently located), and the service cell where the terminal device has historically been located refers to the service cell where the terminal device is located before the cell switching action is performed. For another example, the traditional method may be a traditional RLF monitoring method, which is used to monitor whether RLF will occur in the service cell where the terminal device has historically been located. The traditional method also includes other monitoring methods, which are not limited here.

[0127] In the embodiment of the present application, the action execution condition may be, for example, a legacy execution condition. The legacy execution condition is a condition specified in the tradition and / or standard for triggering the execution of the action. For example, the legacy execution condition corresponding to the cell switching action is that the signal quality value (such as RSRP value, etc.) of the serving cell where the terminal device is located is lower than the signal quality threshold (such as RSRP threshold, etc.). The action execution condition is not limited here.

[0128] 5. Relaxation time range

[0129] The relaxation time range can be a continuous time range before and after a certain time (such as a certain moment, etc.) and / or one or more discrete time points before and after a certain time, which can be regarded as a time close to a certain time.

[0130] In the embodiment of the present application, the relaxation time range of the prediction time can be a continuous time range before and after the prediction time. Optionally, the time relaxation parameter can be used to determine the relaxation time range of the prediction time. Optionally, the time relaxation parameter can be a time relaxation threshold, also known as the matching time threshold delta, and the relaxation time range of the prediction time t1 is [t1-delta, t1+delta].

[0131] In the embodiments of the present application, the time relaxation parameter may come from a network device, or the time relaxation parameter may be set and maintained by the terminal device itself, or the time relaxation parameter may be obtained by other means, which is not limited here.

[0132] 6. Matching parameters

[0133] In the embodiment of the present application, the matching parameter is used to determine whether the predicted information matches the first information.

[0134] Optionally, the matching parameter may be specifically used to determine the degree of similarity between the first information and the predicted information, for example, the degree of similarity between the predicted measurement information and the measurement information included in the first information, or the degree of similarity between the predicted conclusion and the monitoring conclusion.

[0135] Optionally, the matching parameters can also be used to determine the correlation between the first information and the predicted information, for example, the correlation between the predicted measurement information and the monitoring conclusion, the correlation between the predicted conclusion and the measurement information included in the first information, and the correlation between the predicted conclusion and the predicted probability and the measurement information included in the first information.

[0136] Optionally, the matching parameter may be, for example, a matching threshold. The matching threshold may be, for example, a signal quality matching threshold. For example, the predicted measurement information appearing at the prediction time may be the predicted RSRP, the measurement information obtained by monitoring at the monitoring time may be the monitored RSRP, and the matching threshold may be the RSRP matching threshold; specifically, if the absolute value of the difference between the predicted RSRP and the monitored RSRP is greater than the RSRP matching threshold, it is determined that the predicted RSRP does not match the monitored RSRP, and thus it can be determined that the predicted information does not match the first information.

[0137] Optionally, the matching threshold may be, for example, a signal quality threshold. For example, the prediction conclusion is to execute an action, the action is to execute a cell switching action, the measurement information included in the first information is to monitor RSRP, the signal quality threshold is the RSRP threshold, and the action execution condition is that the RSRP of the cell signal is greater than the RSRP threshold, then the cell switching action is triggered, if the monitored RSRP is less than or equal to the RSRP threshold, that is, the action execution condition is not met, then it is determined that the monitored RSRP does not match the prediction conclusion of the execution action, so that it can be determined that the predicted information does not match the first information.

[0138] In the embodiment of the present application, the matching parameters may come from the network device, or the matching parameters may be set and maintained by the terminal device itself, or the matching parameters may be obtained by other methods, which are not limited here.

[0139] 7. False positive detection indication information

[0140] The false positive detection indication information is used to instruct the execution of false positive detection. Optionally, the false positive detection indication information can be used to instruct the terminal device to execute false positive detection.

[0141] Optionally, the misjudgment detection indication information may include but is not limited to at least one of the following information:

[0142] Misjudgment detection time,

[0143] Misjudgment of the detected object.

[0144] Optionally, the false positive detection time is used to match the predicted time. When the predicted time matches the false positive detection time, it is determined to perform false positive detection. Optionally, when the predicted time matches the false positive detection time, it is determined to perform monitoring of the false positive detection object to obtain the first information.

[0145] Optionally, the false positive detection time may be a time range of the false positive detection. The matching of the predicted time with the false positive detection time may be that the predicted time is within the time range of the false positive detection.

[0146] In an embodiment of the present application, the false positive detection indication information may come from a network device, or the false positive detection indication information may be set and maintained by the terminal device itself, or the false positive detection indication information may be obtained by other means, which is not limited here.

[0147] 8. False positive detection configuration information

[0148] The false positive detection configuration information is configuration information for performing false positive detection. The false positive detection configuration information may include but is not limited to at least one of the following information:

[0149] First instruction information;

[0150] Second instruction information;

[0151] The third instruction information;

[0152] Measurement Gap.

[0153] The first indication information may be used to indicate prediction information for performing false positive detection. The second indication information may be used to indicate prediction information for not performing false positive detection. The third indication information may be used to indicate whether to allow measurement of false positive detection objects in different scenarios. The measurement gap is measurement time configuration information for performing false positive detection.

[0154] Optionally, the different scene is a scene that is different from the scene currently located by the terminal device. The different scene may be, for example but not limited to, a scene that is different from the scene currently located by the terminal device in at least one of the following information and / or objects:

[0155] Community,

[0156] The synchronization signal block of the cell,

[0157] The signal frequency of the cell,

[0158] Cell beam information,

[0159] Tracking Area (TA),

[0160] Registration Area (RA).

[0161] Exemplarily, the scenario in which the terminal device is located is cell 1 of signal frequency 1, and the different scenarios may be cell 2 of signal frequency 1 and / or cell 3 of signal frequency 2.

[0162] The above are only examples. A different scenario may also be a scenario in which other information related to the communication service and / or other objects related to the communication service are different from the scene in which the terminal device is currently located. The difference information and / or difference objects between the different scenario and the scene in which the terminal device is currently located are not limited here.

[0163] Exemplarily, the measurement gap can be used to measure the misjudged detection object of the different scene. For example, the terminal device can measure the misjudged detection object of the different scene within the configured measurement gap. Optionally, the time of the measurement gap configuration overlaps with the prediction time, and / or the time of the measurement gap configuration overlaps with the relaxation time range of the prediction time.

[0164] IX. Misjudged Record Indication and Misjudged Information

[0165] The misjudgment recording indication information is used to indicate recording of misjudgment information. Optionally, the misjudgment recording indication information may also indicate misjudgment information that needs to be recorded, and the misjudgment information that needs to be recorded may include but is not limited to at least one of the following information:

[0166] AIML model information,

[0167] AIML's functional information,

[0168] Misjudgment of instruction information,

[0169] Forecast information,

[0170] First information.

[0171] The terminal device may record the misjudgment information indicated by the misjudgment record indication information. Optionally, the misjudgment information may be presented in the form of a misjudgment report.

[0172] Optionally, the misjudgment indication information is used to indicate that the AIML model has a misjudgment. Optionally, the misjudgment indication information may be explicit indication information; for example, 1 bit of information is used to indicate whether the AIML model has a misjudgment; if the 1 bit of information is 1, it indicates that the AIML model has a misjudgment; if the 1 bit of information is 0, it indicates that the AIML model has not a misjudgment; or, if the 1 bit of information is 0, it indicates that the AIML model has a misjudgment; if the 1 bit of information is 1, it indicates that the AIML model has not a misjudgment. This is only an example, and the specific form of the explicit misjudgment indication information is not limited. Optionally, the misjudgment indication information may be implicit indication information. For example, if the misjudgment report includes AIML model information, AIML function information, prediction information, and the first information, it implicitly indicates that the AIML model has a misjudgment. This is only an example, and the specific form of the implicit misjudgment indication information is not limited.

[0173] 10. Second Information

[0174] The network device may control the terminal device to perform misjudgment detection processing through the second information. Optionally, the second information may include but is not limited to at least one of the following information:

[0175] False positive detection indication information,

[0176] Matching parameters,

[0177] Time relaxation parameter,

[0178] False positive detection configuration information,

[0179] Indication of misidentified records.

[0180] Exemplarily, the second information may be carried by at least one of the following messages:

[0181] Radio Resource Control (RRC) messages,

[0182] Downlink Control Information (DCI),

[0183] Medium Access Control Control Element (MAC CE),

[0184] System Information (SI),

[0185] Non-access stratum (NAS) message.

[0186] The following is a detailed introduction to the communication indication method and related products provided by this application:

[0187] See also Figure 2 , Figure 2 The following is a flow chart of a possible misjudgment detection method provided in an embodiment of the present application. Figure 2 As shown, the communication processing method includes the following steps 201 to 203. Optionally, the communication method may also include the following steps 204 to 206. Figure 2 The execution subject of the method shown can be a terminal device and a network device. Or, Figure 2 The execution subject of the method shown may be a chip or chip module in a terminal device and a chip or chip module in a network device. Figure 2 The following is an example of a terminal device and a network device. The execution subjects of the subsequent flow charts are similar and will not be described in detail.

[0188] 201. The terminal device predicts the monitoring target according to the AIML model to obtain prediction information.

[0189] 202. The terminal device monitors the misjudged detection object to obtain first information.

[0190] Optionally, the terminal device may monitor the misjudged detection object in a traditional manner to obtain the first information.

[0191] Optionally, when the terminal device determines that false positive detection needs to be performed, the terminal device triggers the execution of step 202 .

[0192] In an optional implementation manner, the terminal device may monitor the false positive detection object according to the false positive detection indication information to obtain the first information. Optionally, the false positive detection indication information may be set and maintained by the terminal device itself.

[0193] Optionally, the prediction information may include the prediction time, and the false positive detection indication information may include the false positive detection time; the step of monitoring the false positive detection object to obtain the first information includes: if the prediction time matches the false positive detection time, executing the step of monitoring the false positive detection object to obtain the first information.

[0194] Optionally, the false positive detection time may be set and maintained by the terminal device itself.

[0195] In an optional implementation manner, the terminal device may also monitor the false positive detection object according to the false positive detection configuration information to obtain the first information.

[0196] Optionally, the false positive detection configuration information includes first indication information, and the terminal device determines whether to perform false positive detection based on the first indication information and the prediction information. The first indication information is used to indicate the prediction information for performing false positive detection; if the prediction information obtained by step S201 belongs to the prediction information indicated by the first indication information, it is determined to perform false positive detection. Optionally, the first indication information may indicate that false positive detection is performed on the prediction information that meets certain conditions. For example, when the predicted measurement information is a signal quality value, the first indication information may indicate that false positive detection is performed if the information quality value is greater than a signal quality threshold.

[0197] Optionally, the false positive detection configuration information includes second indication information, and the terminal device determines whether to perform false positive detection based on the second indication information and the prediction information. The second indication information is used to indicate the prediction information for which false positive detection is not to be performed; if the prediction information obtained by step S201 belongs to the prediction information indicated by the second indication information, it is determined not to perform false positive detection. Optionally, the second indication information may indicate that false positive detection is to be performed on the prediction information that meets certain conditions. For example, when the predicted measurement information is a signal quality value, the second indication information may indicate that false positive detection is to be performed if the information quality value is less than or equal to the signal quality threshold.

[0198] Optionally, the false positive detection configuration information may be set and maintained by the terminal device itself.

[0199] 203. The terminal device determines whether the AIML model makes a misjudgment based on the prediction information and the first information.

[0200] In a possible implementation, determining whether the AIML model has a misjudgment based on the prediction information and the first information includes: if it is determined that the prediction information does not match the first information, determining that the AIML model has a misjudgment.

[0201] Optionally, determining whether the AIML model makes a misjudgment based on the prediction information and the first information further includes: if it is determined that the prediction information matches the first information, determining that the AIML model prediction is accurate.

[0202] In an optional implementation manner, the prediction information does not match the first information, including: at least one item of information included in the prediction information does not match at least one item of information included in the first information.

[0203] Optionally, the predicted information does not match the first information, which may be that the same type of information included in the predicted information and the first information respectively does not match, for example, the predicted conclusion does not match the monitoring conclusion, and / or, the predicted measurement information does not match the measurement information obtained by monitoring; and / or, it may also be that the predicted information and the first information respectively include different types of information mismatched, for example, the predicted conclusion does not match the measurement information obtained by monitoring, and / or, the predicted measurement information does not match the monitoring conclusion.

[0204] Optionally, the predicted information does not match the first information, which may be that one item of information in the predicted information does not match one item of information in the first information, for example, the predicted conclusion does not match the monitoring conclusion, or the predicted measurement information does not match the measurement information obtained by monitoring; it may also be that one item of information in the predicted information does not match multiple items of information in the first information, or multiple items of information in the predicted information do not match one item of information in the first information, for example, the predicted conclusion does not match the monitoring time and the monitoring conclusion, or the predicted time, the predicted measurement information and the monitoring conclusion; it may also be that multiple items of information in the predicted information do not match multiple items of information in the first information, for example, the predicted time does not match the monitoring time, and the predicted conclusion does not match the monitoring conclusion. The above is only an example and does not limit the manner in which the predicted information does not match the first information.

[0205] In an optional implementation manner, the determining that the prediction information does not match the first information may include but is not limited to at least one of the following four methods:

[0206] Method 1: Determine, based on matching parameters, that the predicted information does not match the first information.

[0207] Optionally, the matching parameters may be set and maintained by the terminal device itself.

[0208] Mode 2: If the prediction conclusion is to execute the action, the monitoring time is earlier than the execution time of the action, and the monitoring conclusion is that the monitoring target meets the action execution condition, it is determined that the prediction information does not match the first information.

[0209] Optionally, if the prediction conclusion is to execute an action, the monitoring time is earlier than the execution time of the action, and the monitoring conclusion is that the monitoring target does not meet the action execution condition, then it is determined that the prediction information matches the first information, and then the action is executed at the execution time of the action.

[0210] Mode 3: If the prediction conclusion is to execute the action, the monitoring time is within the relaxation time range of the prediction time, and the monitoring conclusion is that the monitoring target does not meet the action execution condition, it is determined that the prediction information does not match the first information.

[0211] Optionally, if the prediction conclusion is to execute an action, the monitoring time is within the relaxation time range of the prediction time, and the monitoring conclusion is that the monitoring target meets the action execution condition, then it is determined that the prediction information matches the first information and the AIML model prediction is accurate.

[0212] Optionally, the relaxation time range of the prediction time may be determined according to a time relaxation parameter, and the time relaxation parameter may be set and maintained by the terminal device itself.

[0213] Mode 4: If the prediction conclusion is to execute the action, the monitoring time is the same as the prediction time, and the monitoring conclusion is that the monitoring target does not meet the action execution condition, it is determined that the prediction information does not match the first information.

[0214] Optionally, if the prediction conclusion is to execute an action, the monitoring time is the same as the prediction time, and the monitoring conclusion is that the monitoring target meets the action execution condition, then it is determined that the prediction information matches the first information and the AIML model prediction is accurate.

[0215] The action execution condition is a condition for triggering the execution of the action. The execution time of the action is determined according to the prediction information. Optionally, the execution time of the action is determined according to the prediction time and / or the prediction conclusion.

[0216] Among them, methods 2 to 4 are proposed for the scenario where the prediction conclusion is to execute an action. Methods 2 to 4 correspond to the situation where the prediction conclusion does not match the monitoring time and the monitoring conclusion. Method 2 is a method of matching the prediction information with the first information before the action is executed based on the execution time of the action, and methods 3 and 4 are methods of matching the prediction information with the first information after the action is executed based on the execution time of the action.

[0217] For a clearer explanation, see Figure 3 , Figure 3 A schematic diagram of various relevant times in a possible communication scenario provided in an embodiment of the present application. Figure 3 In FIG. 1 , t0 represents the time for executing step S201 to obtain the prediction information, t0-1 represents the execution time of the action, t1 represents the prediction time, and t2 and t3 represent two different monitoring times respectively. Figure 3 The related time shown is only applicable to the embodiment of the present application and does not limit the related time in other embodiments.

[0218] In Mode 2 to Mode 4, the terminal device determines the execution time of the action according to the predicted time and / or the predicted conclusion. Optionally, the predicted conclusion and / or the predicted measurement information appearing at the predicted time may have a negative impact on the terminal device's execution of communication-related services. Based on this, Figure 3 As shown, the execution time of the action determined by the terminal device is earlier than the predicted time, so as to avoid the negative impact on communication-related services at the predicted time in advance. Optionally, the execution time of the action determined by the terminal device can also be later than the predicted time, or the execution time of the action determined by the terminal device is the same as the predicted time.

[0219] Optionally, the terminal device sets and maintains a distance duration, which is used to indicate the length of the time interval between the execution time of the action and the predicted time, so that the terminal device can determine the execution time of the action based on the distance duration and the predicted time.

[0220] Optionally, the terminal device may set different distance durations for different actions, for example, a distance duration of 5 ms is set for action 1, and a distance duration of 7 ms is set for action 2.

[0221] Optionally, the terminal device can set a waiting time, and the terminal device executes the action after waiting for the waiting time. That is, the execution time of the action is the sum of the current time and the waiting time. Optionally, the current time can be the time when the prediction information is obtained by executing step 201, that is, Figure 3 t0 in .

[0222] Optionally, the terminal device may set different waiting time lengths for different actions, for example, a waiting time length of 5 ms is set for action 1, and a waiting time length of 3 ms is set for action 2.

[0223] like Figure 3 As shown, in method 2, when the monitoring conclusion is to execute an action, if before the execution time t0-1 of the action, it is monitored at the monitoring time t2 that the monitoring target satisfies the action execution condition, that is, the action can be triggered in advance before the execution time t0-1 of the action, then it is determined that the prediction information does not match the first information, and the AIML model makes a misjudgment detection; if before the execution time t0-1 of the action, it is monitored that the monitoring target does not satisfy the action execution condition, that is, the action will not be triggered in advance before the execution time t0-1 of the action, then it is determined that the prediction information matches the first information, and the AIML model predicts accurately.

[0224] In method 3, when the monitoring conclusion is to execute an action, after the action has been executed at the execution time t0-1 of the action, if it is monitored at the monitoring time t3 that the monitoring target does not meet the action execution conditions, and the monitoring time t3 is within the relaxation time range of the prediction time t1, it is determined that the prediction information does not match the first information, and the AIML model has a misjudgment detection; if it is monitored at the monitoring time t3 that the monitoring target meets the action execution conditions, and the monitoring time t3 is within the relaxation time range of the prediction time t1, it is determined that the prediction information matches the first information, and the AIML model prediction is accurate.

[0225] In method 4, when the monitoring conclusion is to execute an action, after the action has been executed at the execution time t0-1 of the action, if it is monitored at the prediction time t1 that the monitoring target does not meet the action execution conditions, then it is determined that the prediction information does not match the first information, and the AIML model makes a misjudgment detection; if it is monitored at the prediction time t1 that the monitoring target meets the action execution conditions, then it is determined that the prediction information matches the first information, and the AIML model prediction is accurate.

[0226] 204. If the terminal device determines that the AIML model has a misjudgment, it records the misjudgment information.

[0227] Optionally, the terminal device may record the misjudgment information according to the misjudgment record indication information, where the misjudgment record indication information indicates the misjudgment information to be recorded. Optionally, the misjudgment record indication information is set and maintained by the terminal device itself.

[0228] Optionally, the terminal device may also choose to record corresponding misjudgment information according to its own needs.

[0229] Optionally, the terminal device may also record all misjudgment information.

[0230] 205. The terminal device sends the misjudgment information to the network device.

[0231] Optionally, the misjudgment information is sent to the network device in the form of a misjudgment report.

[0232] Accordingly, the network device receives misjudgment information from the terminal device.

[0233] In an optional implementation, the terminal device may send the misjudgment information to the network device after successfully recording the misjudgment information.

[0234] In another optional implementation, after recording the misjudgment information, the terminal device sends recording indication information to the network device, and the recording indication information is used to indicate that the terminal device has recorded the misjudgment information. Optionally, the network device sends a misjudgment information request message to the terminal device according to the recording indication information, and the misjudgment information request message is used to request the misjudgment information recorded in the terminal device. The terminal device receives the misjudgment information request message, and sends the misjudgment information recorded by the terminal device to the terminal device according to the misjudgment information request message.

[0235] 206. The network device updates the AIML model according to the misjudgment information.

[0236] Optionally, the network device updates the AIML model based on the misjudgment information, including: determining at least one of the number of misjudgments of the AIML model and the frequency of misjudgments of the AIML model based on the misjudgment information; if the number of misjudgments of the AIML model reaches a misjudgment number threshold, and / or the frequency of misjudgments of the AIML model reaches a misjudgment frequency threshold, then updating the AIML model to optimize the AIML model and improve the prediction accuracy of the AIML model.

[0237] Before executing step S206, the network device may also record the misjudgment information for subsequent calling and analysis, and / or update the AIML model based on the recorded misjudgment information.

[0238] In the embodiments of the present application, regarding the AIML model, monitoring target, misjudgment detection indication information, misjudgment detection time, prediction information, prediction time, prediction conclusion, misjudgment detection configuration information, traditional method, misjudgment detection object, first information, monitoring time, monitoring conclusion, matching parameter, relaxation time range of prediction time, time relaxation parameter, action execution condition, misjudgment record indication information, misjudgment information, etc. and other existing in Figure 2 For the description of the professional terms and technical terms in the illustrated method embodiment, please refer to the introduction of the professional terms and technical terms mentioned above, which will not be repeated here.

[0239] In an embodiment of the present application, based on the local policy of the terminal device, the AIML model is subjected to misjudgment detection according to the prediction information obtained by the AIML model and the first information obtained by monitoring the misjudgment detection object, thereby effectively determining whether the AIML prediction has a misjudgment, and facilitating the optimization of the AIML model to improve the reasoning performance of the AIML model and reduce the misjudgment rate of the AIML model.

[0240] See also Figure 4 , Figure 4 The following is a flow chart of a possible misjudgment detection method provided in an embodiment of the present application. Figure 4 As shown, the communication processing method includes the following steps 301 to 304. Optionally, the communication processing method may also include the following steps 305 to 307. Figure 4 The execution subject of the method shown can be a terminal device and a network device. Or, Figure 4 The execution subject of the method shown may be a chip or chip module in a terminal device and a chip or chip module in a network device. Figure 3 The following is an example of a terminal device and a network device. The execution subjects of the subsequent flow charts are similar and will not be described in detail.

[0241] 301. The terminal device predicts the monitoring target according to the AIML model to obtain prediction information.

[0242] 302. The network device sends second information to the terminal device, where the second information includes false positive detection indication information, and the false positive detection indication information is used to instruct to perform false positive detection.

[0243] Correspondingly, the terminal device receives the second information from the network device.

[0244] Optionally, the second information further includes at least one of the following information:

[0245] Matching parameters,

[0246] Time relaxation parameter,

[0247] False positive detection configuration information,

[0248] Misjudgment of recorded indication information;

[0249] Among them, the matching parameter is used to determine whether the predicted information matches the first information, the time relaxation parameter is used to determine the relaxation time range of the predicted time, the false positive detection configuration information is the configuration information used to perform false positive detection, and the false positive recording indication information is used to indicate the recording of false positive information.

[0250] 303. The terminal device monitors the misjudged detection object to obtain first information.

[0251] Optionally, the terminal device triggers monitoring of the misjudgment detection object according to the misjudgment detection indication information to obtain the first information.

[0252] 304. The terminal device determines whether the AIML model has a misjudgment according to the prediction information and the first information.

[0253] 305. If the terminal device determines that the AIML model has a misjudgment, it records misjudgment information according to the misjudgment record indication information.

[0254] 306. The terminal device sends the misjudgment information to the network device.

[0255] 307. The network device updates the AIML model according to the misjudgment information.

[0256] For the description of steps 301, 303 to 307, please refer to Figure 2 The description of steps 201 to 206 of the method embodiment shown in FIG. 304 can be found in Figure 2 Description of step 203 of the method embodiment shown. In the embodiment of the present application, in mode 1, the matching parameter can come from the network device, that is, carried in the second information. In the embodiment of the present application, in mode 3, the relaxation time range of the prediction time can be determined according to the time relaxation parameter, and the time relaxation parameter can come from the network device, that is, carried in the second information.

[0257] It should be noted that step 302 can be executed before step 301, or step 302 can be executed after step 301, or step 302 can be executed simultaneously with step 301. The embodiment of the present application does not limit the relative execution order of step 301 and step 302. Step 302 only needs to be executed before step 303.

[0258] In the embodiment of the present application, the second information, matching parameters, misjudgment detection configuration information, misjudgment record indication information, and other information existing in Figure 4 For the description of the professional terms and technical terms in the illustrated method embodiment, please refer to the introduction of the professional terms and technical terms mentioned above, which will not be repeated here.

[0259] In an embodiment of the present application, based on the control of the network device, the AIML model is subjected to misjudgment detection according to the prediction information obtained by the AIML model and the first information obtained by monitoring the misjudgment detection object, thereby effectively determining whether the prediction of the AIML model has a misjudgment, and facilitating the optimization of the AIML model to improve the reasoning performance of the AIML model and reduce the misjudgment rate of the AIML model.

[0260] See also Figure 5 , Figure 5 The following is a flow chart of a possible misjudgment detection method provided in an embodiment of the present application. Figure 5 As shown, the communication processing method includes the following steps 401 to 408. Figure 5 The execution subject of the method shown can be a terminal device and a network device. Or, Figure 5 The execution subject of the method shown may be a chip or chip module in a terminal device and a chip or chip module in a network device. Figure 5 The following is an example of a terminal device and a network device. The execution subjects of the subsequent flow charts are similar and will not be described in detail.

[0261] 401. The terminal device predicts the RSRP value of the first cell of the first frequency f1 where the terminal device is located at time t0 according to AIML model 1 to obtain prediction information, wherein the prediction information includes the prediction time t1 and the predicted RSRP value m of the first cell, t1>t0.

[0262] Among them, according to the prediction of AIML model 1, the RSRP value of the first cell of the first frequency f1 at the prediction time t1 is n.

[0263] 402. The network device sends second information to the terminal device, where the second information includes a time range for misjudgment detection, an RSRP matching threshold x, a time relaxation threshold delta, and misjudgment record indication information.

[0264] Correspondingly, the terminal device receives the second information from the network device.

[0265] 403. If the terminal device determines that t1 is within the time range of the misjudgment detection, the terminal device monitors the RSRP value of the first cell to obtain first information, where the first information includes the monitoring time and the RSRP value n of the first cell monitored at the monitoring time;

[0266] Among them, the monitoring time is the relaxation time range of the predicted time obtained according to the time relaxation threshold delta, that is, [t1-delta, t1+delta]; n is the average RSRP value monitored within the relaxation time range of the predicted time, or n is the RSRP value monitored at any time within the relaxation time range of the predicted time.

[0267] 404. If the terminal device determines that the absolute value of the difference between m and n is greater than x, it determines that AIML model 1 has a misjudgment.

[0268] Among them, step 404 is a specific implementation of method 1.

[0269] 405. The terminal device records the misjudgment information according to the misjudgment recording indication information.

[0270] The misjudgment information includes model information of AIML model 1 and misjudgment indication information. Optionally, the misjudgment information may also include: prediction information and first information; wherein the prediction information in the misjudgment information includes: t1, f1, the cell identifier Cell1 of the first cell, RSRP=m; the first information in the misjudgment information includes: t1, f1, Cell1, RSRP=n.

[0271] 406. The terminal device sends a misjudgment report to the network device, where the misjudgment report includes misjudgment information.

[0272] Accordingly, the network device receives a misjudgment report from the terminal device.

[0273] 407. The network device records the misjudgment report, and determines the number of misjudgments and / or misjudgment frequency of the AIML model 1 according to the misjudgment report.

[0274] 408. The network device updates the AIML model 1 when the number of false positives of the AIML model 1 is greater than or equal to the false positive number threshold and / or the false positive frequency of the AIML model 1 is greater than or equal to the false positive frequency threshold.

[0275] It should be noted that step 402 can be executed before step 401, or step 402 can be executed after step 401, or step 402 can be executed simultaneously with step 401. The relative execution order of step 401 and step 402 is not limited. Step 402 only needs to be executed before step 403.

[0276] In an embodiment of the present application, based on the control of the network device, the AIML model is subjected to misjudgment detection according to the prediction information obtained by the AIML model and the first information obtained by monitoring the misjudgment detection object, thereby effectively determining whether the prediction of the AIML model has misjudgment, and facilitating the optimization of the AIML model to improve the reasoning performance of the AIML model and reduce the misjudgment rate of the AIML model.

[0277] See also Figure 6 , Figure 6 The following is a flow chart of a possible misjudgment detection method provided in an embodiment of the present application. Figure 6 As shown, the communication processing method includes the following steps 501 to 507. Figure 6 The execution subject of the method shown can be a terminal device and a network device. Or, Figure 6 The execution subject of the method shown may be a chip or chip module in a terminal device and a chip or chip module in a network device. Figure 6 The following is an example of a terminal device and a network device. The execution subjects of the subsequent flow charts are similar and will not be described in detail.

[0278] 501. At time t0, the terminal device predicts whether RLF occurs in the first cell of the first frequency f1 according to AIML model 2, and obtains prediction information, wherein the prediction information includes the prediction time t1 and the prediction that there is a 95% probability that the terminal device will experience RLF in the first cell, t1>t0.

[0279] According to the prediction of AIML model 2, there is a 95% probability that the terminal device will experience RLF in the first cell of the first frequency f1 at the predicted time t1.

[0280] 502. The terminal device determines to switch to the second cell of the first frequency f1 at the action execution time t2 according to the predicted time t1 and the predicted probability of 95% of the terminal device experiencing RLF in the first cell, t0<t2≤t1.

[0281] 503. The terminal device continues to monitor whether RLF occurs in the first cell according to the traditional RLF monitoring method, obtains first information, and determines that AIML model 2 has a misjudgment based on the first information; the first information includes that at the monitoring time t3, RLF is monitored to occur in the first cell, t0<t3<t2≤t1.

[0282] Among them, step 503 is a specific implementation of method 2.

[0283] 504. The terminal device records the misjudgment information, wherein the misjudgment information includes AIML model 2 model information and misjudgment indication information. Optionally, the misjudgment information may also include: prediction information and first information; wherein the prediction information in the misjudgment information includes: t1, f1, the cell identifier Cell1 of the first cell, and RLF; the first information in the misjudgment information includes: t3, f1, Cell1, RLF, and indication information of the early occurrence of RLF.

[0284] 505. The terminal device sends a misjudgment report to the network device, where the misjudgment report includes misjudgment information.

[0285] Accordingly, the network device receives a misjudgment report from the terminal device.

[0286] 506. The network device records the misjudgment report, and determines the number of misjudgments and / or misjudgment frequency of AIML model 2 according to the misjudgment report.

[0287] 507. When the number of false positives of AIML model 2 is greater than or equal to the false positive number threshold, and / or when the false positive frequency of AIML model 2 is greater than or equal to the false positive frequency threshold, the network device updates the AIML model 2.

[0288] In an embodiment of the present application, based on the local policy of the terminal device, the AIML model is subjected to misjudgment detection according to the prediction information obtained by the AIML model and the first information obtained by monitoring the misjudgment detection object, thereby effectively determining whether the prediction of the AIML model has a misjudgment, and facilitating the optimization of the AIML model to improve the reasoning performance of the AIML model and reduce the misjudgment rate of the AIML model.

[0289] See also Figure 7 , Figure 7 The following is a flow chart of a possible misjudgment detection method provided in an embodiment of the present application. Figure 7 As shown, the communication processing method includes the following steps 601 to 609. Figure 7 The execution subject of the method shown can be a terminal device and a network device. Or, Figure 7 The execution subject of the method shown may be a chip or chip module in a terminal device and a chip or chip module in a network device. Figure 7 The following is an example of a terminal device and a network device. The execution subjects of the subsequent flow charts are similar and will not be described in detail.

[0290] 601. At time t0, the terminal device predicts whether RLF occurs in the first cell of the first frequency f1 according to AIML model 3, and obtains prediction information, wherein the prediction information includes the prediction time t1 and the prediction that there is a 95% probability that the terminal device will experience RLF in the first cell, t1>t0.

[0291] According to the prediction of AIML model 3, there is a 95% probability that the terminal device will experience RLF in the first cell of the first frequency f1 at the predicted time t1.

[0292] 602. The terminal device switches to the second cell of the first frequency f1 at time t2 according to the predicted time t1 and the predicted probability of 95% of the terminal device experiencing RLF in the first cell, t0<t2≤t1.

[0293] 603. The network device sends second information to the terminal device, where the second information includes a time range of false positive detection, a signal quality threshold, and false positive record indication information.

[0294] Correspondingly, the terminal device receives the second information from the network device.

[0295] 604. If the terminal device determines that t1 is within the time range of the false detection, it monitors the signal quality of the first cell to obtain first information, where the first information includes the monitoring time t1 and the signal quality q of the first cell monitored at the monitoring time t1.

[0296] 605. If the terminal device determines that q is greater than the signal quality threshold, it determines that AIML model 3 makes a misjudgment.

[0297] If the terminal device determines that q is greater than the signal quality threshold, it is determined that the terminal device will not have RLF in the first cell, thereby determining that AIML model 3 has a misjudgment.

[0298] Among them, step 605 is a specific implementation of method 3.

[0299] 606. The terminal device records the misjudgment information, wherein the misjudgment information includes AIML model 3 model information and misjudgment indication information. Optionally, the misjudgment information may also include: prediction information and first information; wherein the prediction information in the misjudgment information includes: t1, f1, the cell identifier Cell1 of the first cell, and RLF; the first information in the misjudgment information includes: t1, f1, Cell1, signal quality value = q, and indication information that RLF will not occur.

[0300] 607. The terminal device sends a misjudgment report to the network device, where the misjudgment report includes misjudgment information.

[0301] Correspondingly, the network device receives the misjudgment report.

[0302] 608. The network device records the misjudgment report, and determines the number of misjudgments and / or misjudgment frequency of the AIML model 3 according to the misjudgment report.

[0303] 609. When the number of misjudgments of AIML model 3 is greater than or equal to the number of misjudgments threshold, and / or when the misjudgment frequency of AIML model 1 is greater than or equal to the misjudgment frequency threshold, the network device updates the AIML model 3.

[0304] It should be noted that step 603 can be executed before step 601 and / or step 602, or step 603 can be executed after step 601 and / or step 602, or step 603 can be executed simultaneously with step 601 or step 602. The relative execution order of step 603 and steps 601 and 602 is not limited, as long as step 603 is executed before step 604.

[0305] In an embodiment of the present application, based on the control of the network device, the AIML model is subjected to misjudgment detection according to the prediction information obtained by the AIML model and the first information obtained by monitoring the misjudgment detection object, thereby effectively determining whether the prediction of the AIML model has misjudgment, and facilitating the optimization of the AIML model to improve the reasoning performance of the AIML model and reduce the misjudgment rate of the AIML model.

[0306] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the method side. It is understandable that in order to realize the above functions, the terminal equipment and the network equipment include hardware structures and / or software modules corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application.

[0307] The embodiment of the present application can divide the terminal device and the network device into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of a software program module. It should be noted that the division of the units in the embodiment of the present application is schematic, which is only a logical function division, and there may be other division methods in actual implementation.

[0308] See also Figure 8 , Figure 8The following is a block diagram of the functional units of a possible communication device 800 of an embodiment of the present application, and the communication device 800 can be applied to a terminal device. The communication device 800 includes: a prediction unit 801, a monitoring unit 802, and a determination unit 803. The prediction unit 801, the monitoring unit 802, and the determination unit 803 can be module units for processing signals, data, information, etc., and there is no specific limitation on this.

[0309] The communication device 800 may further include a storage unit for storing computer program codes or instructions executed by the communication device 800. The storage unit may be a memory.

[0310] In addition, it should be noted that the communication device 800 may be a chip or a chip module.

[0311] The prediction unit 801, the monitoring unit 802 and the determination unit 803 can be integrated in the processing unit. The processing unit can be a processor or a controller, for example, a central processing unit (CPU), a general processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It can implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processing unit can also be a combination that implements a computing function, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0312] In specific implementation, the prediction unit 801, the monitoring unit 802 and / or the determination unit 803 are used to execute any step executed by the terminal device in the above method embodiment.

[0313] The prediction unit 801 is used to predict the monitoring target according to the artificial intelligence machine learning AIML model to obtain prediction information;

[0314] The monitoring unit 802 is used to monitor the misjudged detection object to obtain first information;

[0315] The determination unit 803 is used to determine whether the AIML model has a misjudgment according to the prediction information and the first information.

[0316] In an optional implementation, the determination unit 803, in determining whether the AIML model has a misjudgment based on the prediction information and the first information, is specifically configured to determine that the AIML model has a misjudgment if it is determined that the prediction information does not match the first information.

[0317] In an optional implementation, the prediction information includes at least one of the following information:

[0318] Prediction time,

[0319] The forecast conclusion that appears at the said forecast time,

[0320] predicted measurement information occurring at said predicted time,

[0321] Prediction probability;

[0322] The predicted probability includes at least one of the following predicted probabilities:

[0323] the probability of the predicted conclusion occurring at the predicted time,

[0324] The probability of the predicted measurement information occurring at the predicted time;

[0325] The first information includes at least one of the following information:

[0326] Monitoring time,

[0327] The monitoring conclusions obtained during the monitoring period are:

[0328] Measurement information obtained during the monitoring time;

[0329] The prediction information does not match the first information, including:

[0330] At least one item of information included in the prediction information does not match at least one item of information included in the first information.

[0331] In an optional implementation, the communication device 800 further includes:

[0332] The receiving unit is used to receive second information from the network device before monitoring the false positive detection object to obtain the first information, wherein the second information includes false positive detection indication information, and the false positive detection indication information is used to indicate the execution of false positive detection.

[0333] Optionally, the receiving unit may be integrated into the processing unit.

[0334] In an optional implementation manner, the second information further includes at least one of the following information:

[0335] Matching parameters,

[0336] Time relaxation parameter,

[0337] False positive detection configuration information,

[0338] Misjudgment of recorded indication information;

[0339] Among them, the matching parameter is used to determine whether the predicted information matches the first information, the time relaxation parameter is used to determine the relaxation time range of the predicted time, the false positive detection configuration information is the configuration information used to perform false positive detection, and the false positive recording indication information is used to indicate the recording of false positive information.

[0340] In an optional implementation, the determining unit 803, in the aspect of determining that the predicted information does not match the first information, is specifically configured to determine that the predicted information does not match the first information if the predicted conclusion is to execute an action, the monitoring time is earlier than the execution time of the action, and the monitoring conclusion is that the monitoring target satisfies the action execution condition;

[0341] The execution time of the action is determined according to the predicted time and / or the predicted conclusion, and the action execution condition is a condition for triggering the execution of the action.

[0342] In an optional implementation, the determining unit 803, in the aspect of determining that the predicted information does not match the first information, is specifically configured to determine that the predicted information does not match the first information if the predicted conclusion is to execute an action, the monitoring time is within a relaxation time range of the predicted time, and the monitoring conclusion is that the monitoring target does not satisfy an action execution condition;

[0343] The action execution condition is a condition that triggers the execution of the action.

[0344] In an optional implementation, the determining unit 803, in the aspect of determining that the predicted information does not match the first information, is specifically configured to determine that the predicted information does not match the first information if the predicted conclusion is to execute an action, the monitoring time is the same as the predicted time, and the monitoring conclusion is that the monitoring target does not satisfy the action execution condition;

[0345] The action execution condition is a condition that triggers the execution of the action.

[0346] In an optional implementation, the determining unit 803, in the determining that the predicted information does not match the first information, is specifically configured to determine, based on a matching parameter, that the predicted information does not match the first information.

[0347] In an optional implementation, the misjudgment detection indication information includes at least one of the following information:

[0348] Misjudgment detection time,

[0349] Misjudgment of detection object;

[0350] The monitoring of the misjudged detection object to obtain the first information includes:

[0351] If the predicted time matches the misjudgment detection time, the step of monitoring the misjudgment detection object to obtain the first information is performed.

[0352] In an optional implementation manner, the communication device 800 further includes:

[0353] A recording unit, configured to record misjudgment information according to the misjudgment recording indication information if it is determined that the AIML model has misjudgment;

[0354] The misjudgment record indication information indicates that the misjudgment information includes at least one of the following information:

[0355] The AIML model information,

[0356] The AIML function information,

[0357] Misjudgment of instruction information,

[0358] The prediction information,

[0359] The first information.

[0360] Optionally, the recording unit may be integrated into the processing unit.

[0361] In an optional implementation, the communication device 800 further includes:

[0362] A sending unit is used to send the misjudgment information to the network device after recording the misjudgment information.

[0363] Optionally, the sending unit may be integrated into the processing unit.

[0364] In an optional implementation, the misjudged detection object includes at least one of the following:

[0365] AIML model,

[0366] Monitoring objectives,

[0367] Predictive information.

[0368] Among them, the relevant content of this implementation method can refer to the relevant content of the above method embodiment. It will not be described in detail here. The embodiment of this application and the above method embodiment are based on the same concept, and the technical effects they bring are also the same. For the specific principles, please refer to the description of the above method embodiment, which will not be repeated here.

[0369] See also Fig. 9 , Fig. 9 The following is a block diagram of the functional units of a possible communication device 900 of an embodiment of the present application. The communication device 900 can be applied to a network device. The communication device 900 includes: a generating unit 901 and a sending unit 902. The generating unit 901 and the sending unit 902 can be a module unit for processing signals, data, information, etc., and there is no specific limitation on this.

[0370] The communication device 900 may further include a storage unit for storing computer program codes or instructions executed by the communication device 900. The storage unit may be a memory.

[0371] In addition, it should be noted that the communication device 900 may be a chip or a chip module.

[0372] The generating unit 901 and / or the sending unit 902 may be integrated in a processing unit. For the description of the processing unit, please refer to the above embodiments and will not be described in detail.

[0373] In specific implementation, the generating unit 901 and / or the sending unit 902 is used to execute any step executed by the network device in the above method embodiment.

[0374] The generating unit 901 is configured to generate second information, where the second information includes false positive detection indication information, where the false positive detection indication information is used to indicate the execution of false positive detection;

[0375] The sending communication unit is used to send the second information to the terminal device.

[0376] In an optional implementation manner, the second information further includes at least one of the following information:

[0377] Matching parameters,

[0378] Time relaxation parameter,

[0379] False positive detection configuration information,

[0380] Misjudgment of recorded indication information;

[0381] The matching parameter is used to determine whether the prediction information matches the first information, the time relaxation parameter is used to determine the relaxation time range of the prediction time, the false positive detection configuration information is configuration information for performing false positive detection, and the false positive recording indication information is used to indicate recording of false positive information;

[0382] The prediction information is obtained by predicting the monitoring target according to the artificial intelligence machine learning AIML model, and the first information is obtained by monitoring the misjudged detection object;

[0383] The prediction information includes at least one of the following information:

[0384] The predicted time,

[0385] The forecast conclusion that appears at the said forecast time,

[0386] predicted measurement information occurring at said predicted time,

[0387] Prediction probability;

[0388] The predicted probability includes at least one of the following predicted probabilities:

[0389] the probability of the predicted conclusion occurring at the predicted time,

[0390] The probability of the predicted measurement information occurring at the predicted time.

[0391] In an optional implementation, the communication device 900 further includes:

[0392] A receiving unit is used to receive misjudgment information from the terminal device after sending the second information to the terminal device.

[0393] Optionally, the receiving unit may be integrated into the processing unit.

[0394] In an optional implementation, the communication device 900 further includes:

[0395] An updating unit is used to update the AIML model according to the misjudgment information.

[0396] Optionally, the updating unit may be integrated in the processing unit.

[0397] In an optional implementation manner, the misjudgment record indication information indicates that the misjudgment information includes at least one of the following information:

[0398] The AIML model information,

[0399] The AIML function information,

[0400] Misjudgment of instruction information,

[0401] The prediction information,

[0402] The first information.

[0403] In an optional implementation, the misjudgment detection indication information includes at least one of the following information:

[0404] Misjudgment detection time,

[0405] Misjudgment of detection object;

[0406] Wherein, the misjudgment detection time is used to match the prediction time;

[0407] The misjudgment detection object includes at least one of the following:

[0408] AIML model,

[0409] Monitoring objectives,

[0410] Predictive information.

[0411] Among them, the relevant content of this implementation method can refer to the relevant content of the above method embodiment. It will not be described in detail here. The embodiment of this application and the above method embodiment are based on the same concept, and the technical effects they bring are also the same. For the specific principles, please refer to the description of the above method embodiment, which will not be repeated here.

[0412] See also Fig.10 , Fig.10 A possible communication device 1000 is provided in the embodiment of the present application, as shown in FIG. Fig.10 As shown, the communication device 1000 includes: a processor 1001 and a memory 1002, and the processor 1001 and the memory 1002 are connected to each other. Optionally, a communication interface (not shown) is also included. The memory 1002, the processor 1001 and the communication interface are connected via one or more communication buses. The communication interface is controlled by the processor 1001 to send and receive information.

[0413] The memory 1002 may include a read-only memory and a random access memory, and provides instructions and data to the processor 1001. A portion of the memory 1002 may also include a nonvolatile random access memory.

[0414] The communication interface is used to receive or send data.

[0415] The processor 1001 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, and optionally, the processor 1001 may also be any conventional processor, etc.

[0416] The communication device 1000 can be used to execute part or all of the functions of the terminal device in the above method embodiment, and / or, the communication device 1000 can be used to execute part or all of the functions of the network device in the above method embodiment.

[0417] When the communication device 1000 is used to perform part or all of the functions of the terminal device in the above method embodiment:

[0418] The memory 1002 is used to store a computer program 1003, wherein the computer program 1003 includes program instructions;

[0419] The processor 1001 is configured to execute the method executed by the terminal device in the above method embodiment when calling the program instruction.

[0420] When the communication device 1000 is used to perform part or all of the functions of the network device in the above method embodiment:

[0421] The memory 1002 is used to store a computer program 1003, wherein the computer program 1003 includes program instructions;

[0422] The processor 1001 is configured to execute the method executed by the network device in the above method embodiment when calling the program instruction.

[0423] What needs to be explained is: Fig.10 For the contents not mentioned in the corresponding embodiments and the specific implementation methods of each step, please refer to the contents of the above method embodiments and will not be repeated here.

[0424] Exemplarily, an embodiment of the present invention further provides a possible computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a computer, for example, when the program instructions are executed by a processor or a computer, the method flow of the method embodiment executed by the above-mentioned terminal device and / or network device will be implemented. The specific implementation of the terminal device and / or the network device can refer to the description of the relevant content of the aforementioned embodiment, which will not be repeated here. It can be understood that the computer storage medium here can include both the built-in storage medium in the terminal device and / or the network device, and of course, can also include the extended storage medium supported by the terminal device and / or the network device. The computer storage medium provides a storage space, which stores the operating system of the terminal device and / or the network device. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer storage medium here can be a high-speed RAM memory, or a non-volatile memory (Non-Volatile Memory), such as at least one disk storage, or Flash (flash memory); optionally, it can also be at least one computer storage medium located away from the aforementioned processor. The specific implementation of the terminal device and / or the network device can refer to the description of the relevant content of the aforementioned method embodiment, which will not be repeated here.

[0425] Exemplarily, the embodiment of the present application further provides a possible chip, the chip includes a processor, the processor is used to execute the relevant steps executed by the terminal device in the above method embodiment, or the processor is used to execute the relevant steps executed by the network device in the above method embodiment. The specific implementation of the terminal device and / or the network device can refer to the description of the relevant content of the above method embodiment, which is not repeated here.

[0426] In an optional embodiment, the chip also includes at least one first memory and at least one second memory; the at least one first memory and the first processor are interconnected via lines, the at least one first memory and the second processor are interconnected via lines, and the first memory stores instructions; the at least one second memory and the first processor are interconnected via lines, the at least one second memory and the second processor are interconnected via lines, and the second memory stores data that need to be stored in the above method embodiment.

[0427] Exemplarily, an embodiment of the present application further provides a possible chip module, the chip module includes a transceiver component and a chip, the chip includes a processor, the processor is used to execute the relevant steps executed by the terminal device in the above method embodiment, or the processor is used to execute the relevant steps executed by the network device in the above method embodiment. Optionally, the chip may also include a memory and a computer program or instruction stored on the memory, and the processor executes the computer program or instruction to implement the steps described in the above method embodiment. The specific implementation of the terminal device and / or the network device can refer to the description of the relevant content of the above method embodiment, which will not be repeated here.

[0428] In an optional implementation, the chip and the transceiver component are interconnected via a line; through the transceiver component, the chip module can exchange data with other chip modules, other terminals, servers and other modules or devices.

[0429] The various devices and products described in the above embodiments include modules / units, which may be software modules / units or hardware modules / units, or may be partially software modules / units and partially hardware modules / units. For example, for each device or product that applies to or integrates a chip, each module / unit contained therein can be implemented in the form of hardware such as circuits, or at least some modules / units can be implemented in the form of software programs, which run on the integrated processor inside the chip, and the remaining modules / units can be implemented in the form of hardware such as circuits; for each device or product that applies to or integrates a chip module, each module / unit contained therein can be implemented in the form of hardware such as circuits, and different modules / units can be located in the same part of the chip module (for example, a chip, a circuit module, etc.) or in different components, at least some / units can be implemented in the form of software programs, which run on the integrated processor inside the chip module, and the remaining modules / units can be implemented in the form of hardware such as circuits; for each device or product that applies to or integrates a terminal, the modules / units contained therein can be implemented in the form of hardware such as circuits, and different modules / units can be located in the same component (for example, a chip, a circuit module, etc.) or in different components in the terminal, or at least some modules / units can be implemented in the form of software programs, which run on the integrated processor inside the terminal, and the remaining modules / units can be implemented in the form of hardware such as circuits.

[0430] The steps of the method or algorithm described in the embodiment of the present application can be implemented in a hardware manner, or can be implemented by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory (random access memory, RAM), flash memory, read-only memory (read-only memory, ROM), erasable programmable read-only memory (erasable programmable ROM, EPROM), electrically erasable programmable read-only memory (electrically EPROM, EEPROM), registers, hard disks, mobile hard disks, read-only compact disks (CD-ROMs) or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application specific integrated circuit (application specific integrated circuit, ASIC). In addition, the ASIC can be located in a user device or a network device. Of course, the processor and the storage medium can also be present in a user device or a network device as discrete components.

[0431] Those skilled in the art should be aware that in one or more of the above examples, the functions described in the embodiments of the present application can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiments of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server, or data center to another website site, computer, server, or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital video disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0432] The specific implementation methods described above further explain in detail the purpose, technical solutions and beneficial effects of the embodiments of the present application. It should be understood that the above description is only the specific implementation method of the embodiments of the present application and is not used to limit the protection scope of the embodiments of the present application. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solutions of the embodiments of the present application should be included in the protection scope of the embodiments of the present application.

Claims

1. A method for detecting misjudgment, characterized in that: The method comprises: According to the AIML model, the monitoring target is predicted to obtain prediction information; Monitoring the misjudged detection object to obtain first information; Determine whether the AIML model makes a misjudgment based on the prediction information and the first information.

2. The method according to claim 1, characterized in that The determining, based on the prediction information and the first information, whether the AIML model makes a misjudgment includes: If it is determined that the predicted information does not match the first information, it is determined that the AIML model has made a misjudgment.

3. The method according to claim 2, characterized in that The prediction information includes at least one of the following information: Prediction time, The forecast conclusion that appears at the said forecast time, predicted measurement information occurring at said predicted time, Prediction probability; The predicted probability includes at least one of the following predicted probabilities: the probability of the predicted conclusion occurring at the predicted time, The probability of the predicted measurement information occurring at the predicted time; The first information includes at least one of the following information: Monitoring time, The monitoring conclusions obtained during the monitoring period are: Measurement information obtained during the monitoring time; The prediction information does not match the first information, including: At least one item of information included in the prediction information does not match at least one item of information included in the first information.

4. The method according to claim 3, characterized in that Before monitoring the misjudged detection object and obtaining the first information, the method further includes: Second information is received from a network device, where the second information includes false positive detection indication information, where the false positive detection indication information is used to instruct execution of false positive detection.

5. The method according to claim 4, characterized in that The second information also includes at least one of the following information: Matching parameters, Time relaxation parameter, False positive detection configuration information, Misjudgment of recorded indication information; Among them, the matching parameter is used to determine whether the predicted information matches the first information, the time relaxation parameter is used to determine the relaxation time range of the predicted time, the false positive detection configuration information is the configuration information used to perform false positive detection, and the false positive recording indication information is used to indicate the recording of false positive information.

6. The method according to any one of claims 3 to 5, characterized in that The determining that the prediction information does not match the first information includes: If the prediction conclusion is to execute an action, the monitoring time is earlier than the execution time of the action, and the monitoring conclusion is that the monitoring target satisfies the action execution condition, then it is determined that the prediction information does not match the first information; The execution time of the action is determined according to the predicted time and / or the predicted conclusion, and the action execution condition is a condition for triggering the execution of the action.

7. The method according to any one of claims 3 to 5, characterized in that The determining that the prediction information does not match the first information includes: If the prediction conclusion is to execute an action, the monitoring time is within the relaxation time range of the prediction time, and the monitoring conclusion is that the monitoring target does not meet the action execution condition, then it is determined that the prediction information does not match the first information; The action execution condition is a condition that triggers the execution of the action.

8. The method according to any one of claims 3 to 5, characterized in that The determining that the prediction information does not match the first information includes: If the prediction conclusion is to execute an action, the monitoring time is the same as the prediction time, and the monitoring conclusion is that the monitoring target does not meet the action execution condition, then it is determined that the prediction information does not match the first information; The action execution condition is a condition that triggers the execution of the action.

9. The method according to any one of claims 2 to 5, characterized in that The determining that the prediction information does not match the first information includes: According to the matching parameter, it is determined that the predicted information does not match the first information.

10. The method according to claim 4 or 5, characterized in that The misjudgment detection indication information includes at least one of the following information: Misjudgment detection time, Misjudgment of detection object; The monitoring of the misjudged detection object to obtain the first information includes: If the predicted time matches the misjudgment detection time, the step of monitoring the misjudgment detection object to obtain the first information is performed.

11. The method according to claim 5, characterized in that The method further comprises: If it is determined that the AIML model has a misjudgment, recording misjudgment information according to the misjudgment recording indication information; The misjudgment record indication information indicates that the misjudgment information includes at least one of the following information: The AIML model information, The AIML function information, Misjudgment of indication information, The prediction information, The first information.

12. The method according to claim 11, characterized in that After recording the misjudgment information, the method further includes: The misjudgment information is sent to the network device.

13. The method according to any one of claims 1 to 12, characterized in that The misjudgment detection object includes at least one of the following: AIML model, Monitoring objectives, Predictive information.

14. A method for detecting misjudgment, characterized in that: The method comprises: Sending second information to the terminal device, wherein the second information includes false positive detection indication information, and the false positive detection indication information is used to indicate the execution of false positive detection.

15. The method according to claim 14, characterized in that The second information also includes at least one of the following information: Matching parameters, Time relaxation parameter, False positive detection configuration information, Misjudgment of recorded indication information; The matching parameter is used to determine whether the prediction information matches the first information, the time relaxation parameter is used to determine the relaxation time range of the prediction time, the false positive detection configuration information is configuration information for performing false positive detection, and the false positive recording indication information is used to indicate recording of false positive information; The prediction information is obtained by predicting the monitoring target according to the artificial intelligence machine learning AIML model, and the first information is obtained by monitoring the misjudged detection object; The prediction information includes at least one of the following information: The predicted time, The forecast conclusion that appears at the said forecast time, predicted measurement information occurring at said predicted time, Prediction probability; The predicted probability includes at least one of the following predicted probabilities: the probability of the predicted conclusion occurring at the predicted time, The probability of the predicted measurement information occurring at the predicted time.

16. The method according to claim 14 or 15, characterized in that After sending the second information to the terminal device, the method further includes: Receive misjudgment information from the terminal device.

17. The method according to claim 16, characterized in that The method further comprises: The AIML model is updated according to the misjudgment information.

18. The method according to claim 15, characterized in that The misjudgment record indication information indicates that the misjudgment information includes at least one of the following information: The AIML model information, The AIML function information, Misjudgment of instruction information, The prediction information, The first information.

19. The method according to any one of claims 14 to 18, characterized in that The misjudgment detection indication information includes at least one of the following information: Misjudgment detection time, Misjudgment of detection object; Wherein, the misjudgment detection time is used to match the prediction time; The misjudgment detection object includes at least one of the following: AIML model, Monitoring objectives, Predictive information.

20. A communication device, characterized in that: The device comprises: A prediction unit is used to predict the monitoring target according to the artificial intelligence machine learning AIML model to obtain prediction information; A monitoring unit, configured to monitor the misjudged detection object and obtain first information; A determination unit is used to determine whether the AIML model has a misjudgment based on the prediction information and the first information.

21. A communication device, characterized in that: The device comprises: A generating unit, configured to generate second information, wherein the second information includes misjudgment detection indication information, and the misjudgment detection indication information is used to instruct to perform misjudgment detection; A sending unit is used to send the second information to the terminal device.

22. A communication device, characterized in that: The invention comprises a processor and a memory, wherein the processor and the memory are connected to each other, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is used to call the program instructions to execute the method as claimed in any one of claims 1 to 13, or to execute the method as claimed in any one of claims 14 to 19.

23. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a computer, the method according to any one of claims 1 to 13 is executed, or the method according to any one of claims 14 to 19 is executed.

24. A chip, characterized in that: The chip includes a processor, and the processor executes the method according to any one of claims 1 to 13, or executes the method according to any one of claims 14 to 19.

25. A chip module, characterized in that: The chip module includes a transceiver component and a chip, the chip includes a processor, and the processor executes the method according to any one of claims 1 to 13, or executes the method according to any one of claims 14 to 19.

Images