Monitoring management method, apparatus, terminal, network device, program product and medium

Abstract

The present disclosure relates to the field of wireless technology. Provided are a monitoring management method, an apparatus, a terminal, a network device, a program product and a medium. The method comprises: receiving first information sent by a network device, the first information being used for configuring information related to monitoring management of models and / or functions; and sending second information to the network device, the second information comprising at least one of the following: a model identifier or index of at least one candidate model, a function identifier or index of at least one candidate function, a first beam set of at least one candidate model, a first beam set of at least one candidate function, first request information used for requesting the network device to configure a first beam set of a first model, and second request information used for requesting the network device to configure a first beam set of a first function.

Description

Monitoring management method and device, terminal, network equipment, program product and medium

[0001] Cross-reference to related applications

[0002] The present disclosure claims priority to Chinese Patent Application No. 202410857086.3, filed on June 28, 2024 in China, the entire contents of which are incorporated herein by reference. TECHNICAL FIELD

[0003] The present disclosure relates to the field of wireless technology, and particularly refers to a monitoring management method, device, terminal, network equipment, program product and medium. BACKGROUND

[0004] As shown in FIG. 1, artificial intelligence (AI) and machine learning (ML) acquire a large amount of available data (including data collected by terminals and network sides), rely on machine learning algorithms for model training, and then use the obtained model to drive the behavior decision of the 5th Generation Mobile Communication Technology (5G) network intelligentization and automation.

[0005] The 3rd Generation Partnership Project (3GPP) air interface AI researches the AI / ML basic framework, including the whole process of AI / ML model life cycle management, such as data collection, model training, model management / control (including model activation, deactivation, selection, switching, fallback), model inference, model transfer / delivery, model identification, model monitoring, and user equipment (UE, also called terminal) capability.

[0006] However, the current standard only discusses the concept of AI model monitoring and management, and does not discuss and define in detail the specific interaction process between the terminal and the network during model monitoring and model management. SUMMARY

[0007] The object of the present disclosure is to provide a monitoring management method, device, terminal, network device, program product and medium, which solves the problem that there is currently a lack of definition of the specific interaction process between the terminal and the network during model monitoring and model management.

[0008] To achieve the above object, the embodiments of the present disclosure provide a monitoring management method applied to a terminal, comprising:

[0009] receiving first information sent by a network device, the first information being used for configuring information related to the supervision of a model and / or a function;

[0010] sending second information to the network device;

[0011] The second information comprises at least one of the following:

[0012] a model identifier or index of at least one candidate model;

[0013] a function identifier or index of at least one candidate function;

[0014] a first beam set of the at least one candidate model;

[0015] a first beam set of the at least one candidate function;

[0016] first request information for requesting the network device to configure a first beam set of a first model;

[0017] second request information for requesting the network device to configure a first beam set of a first function.

[0018] Optionally, the method further comprises at least one of the following:

[0019] receiving management decision information sent by the network device;

[0020] receiving configuration information of the first beam set of the first model sent by the network device;

[0021] receiving configuration information of the first beam set of the first function sent by the network device.

[0022] Optionally, the management decision information comprises at least one of the following:

[0023] a model identifier or index of at least one second model;

[0024] a function identifier or index of at least one second function;

[0025] a first activation indication for instructing the terminal to activate at least one second model;

[0026] a second activation indication for instructing the terminal to activate at least one second function;

[0027] a third activation indication for instructing the terminal to deactivate at least one third model;

[0028] a fourth activation indication for instructing the terminal to deactivate at least one third function;

[0029] a first switching indication for instructing the terminal to switch to the second model;

[0030] a second switching indication for instructing the terminal to switch to the second function;

[0031] a condition for applying the second model;

[0032] a condition for applying the second function;

[0033] first fallback indication information for instructing the terminal to fallback to a non-artificial intelligence operation;

[0034] second fallback indication information for instructing the terminal to fallback to a preset model;

[0035] third fallback indication information for instructing the terminal to fallback to a preset function.

[0036] Optionally, the second information further comprises at least one of the following:

[0037] a performance index of the third model;

[0038] a performance index of the third function;

[0039] a list of available candidate models;

[0040] a list of available candidate functions;

[0041] a performance index of at least one candidate model;

[0042] a performance index of at least one candidate function;

[0043] key information of at least one candidate model;

[0044] key information of at least one candidate function;

[0045] model fallback indication information;

[0046] function fallback indication information;

[0047] condition information of the terminal.

[0048] Optionally, the first information comprises at least one of the following:

[0049] measurement configuration information;

[0050] a performance indicator that the terminal needs to monitor;

[0051] a Key Performance Indicator (KPI) that the terminal needs to monitor;

[0052] first indication information, used to indicate that the first information is used for model monitoring and / or function monitoring;

[0053] second indication information, used to indicate periodic information of the terminal reporting the second information;

[0054] third indication information, used to indicate whether the terminal needs to report the performance indicator and / or the KPI;

[0055] fourth indication information, used to indicate whether the terminal is allowed to report management suggestion information;

[0056] a model and / or a function supported by the network device;

[0057] a second beam set corresponding to the model supported by the network device;

[0058] a second beam set corresponding to the function supported by the network device;

[0059] a configuration supported by the network device;

[0060] fifth indication information, used to indicate whether the terminal needs to report a management result;

[0061] an event triggering the terminal to perform model management and / or function management;

[0062] an event triggering the terminal to report the second information;

[0063] sixth indication information, used to indicate that the terminal reports the management result.

[0064] To achieve the above purpose, an embodiment of the present disclosure provides a monitoring management method, applied to a network device, comprising:

[0065] sending first information to a terminal, the first information being used to configure information related to supervision of a model and / or a function;

[0066] receiving second information sent by the terminal;

[0067] The second information includes at least one of the following:

[0068] a model identifier or index of at least one candidate model;

[0069] a function identifier or index of at least one candidate function;

[0070] a first beam set of the at least one candidate model;

[0071] a first beam set of the at least one candidate function;

[0072] first request information for requesting the network device to configure a first beam set of a first model;

[0073] second request information for requesting the network device to configure a first beam set of a first function.

[0074] Optionally, the method further comprises at least one of the following:

[0075] determining at least one second model from the at least one candidate model, and sending management decision information to the terminal;

[0076] determining at least one second function from the at least one candidate function, and sending management decision information to the terminal;

[0077] sending configuration information of the first beam set of the first model to the terminal;

[0078] sending configuration information of the first beam set of the first function to the terminal.

[0079] Optionally, the management decision information comprises at least one of the following:

[0080] a model identifier or index of at least one second model;

[0081] a function identifier or index of at least one second function;

[0082] a first activation indication for instructing the terminal to activate at least one second model;

[0083] a second activation indication for instructing the terminal to activate at least one second function;

[0084] a third activation indication for instructing the terminal to deactivate at least one third model;

[0085] a fourth activation indication for instructing the terminal to deactivate at least one third function;

[0086] a first switching indication for instructing the terminal to switch to a second model;

[0087] a second switching indication for instructing the terminal to switch to a second function;

[0088] a condition for applying the second model;

[0089] a condition for applying the second function;

[0090] The first rollback indication information is used to instruct the terminal to rollback to non-artificial intelligence operation.

[0091] The second rollback indication information is used to instruct the terminal to rollback to a preset model.

[0092] The third rollback indication information is used to instruct the terminal to rollback to a preset function.

[0093] Optionally, the second information further comprises at least one of the following:

[0094] The performance index of the third model;

[0095] The performance index of the third function;

[0096] The list of available candidate models;

[0097] The list of available candidate functions;

[0098] The performance index of at least one candidate model;

[0099] The performance index of at least one candidate function;

[0100] The key information of at least one candidate model;

[0101] The key information of at least one candidate function;

[0102] The model rollback indication information;

[0103] The function rollback indication information;

[0104] The condition information of the terminal.

[0105] Optionally, the first information comprises at least one of the following:

[0106] The measurement configuration information;

[0107] The performance index needed to be monitored by the terminal;

[0108] The key performance indicator (KPI) needed to be monitored by the terminal;

[0109] The first indication information is used to instruct that the first information is used for model monitoring and / or function monitoring;

[0110] The second indication information is used to instruct the period information of the terminal reporting the second information;

[0111] The third indication information is used to instruct whether the terminal needs to report the performance index and / or the KPI;

[0112] The fourth indication information is used to instruct whether the terminal is allowed to report the management suggestion information;

[0113] a model supported by the network device and / or a function supported by the network device;

[0114] a second beam set corresponding to the model supported by the network device;

[0115] a second beam set corresponding to the function supported by the network device;

[0116] a configuration supported by the network device;

[0117] fifth indication information for indicating whether the terminal needs to report a management result;

[0118] an event triggering the terminal to perform model management and / or function management;

[0119] an event triggering the terminal to report the second information;

[0120] sixth indication information for indicating the terminal to report a management result.

[0121] To achieve the above object, an embodiment of the present disclosure provides a model monitoring management apparatus applied to a terminal, comprising:

[0122] a first receiving module configured to receive first information sent by a network device, wherein the first information is used to configure information related to monitoring of a model and / or a function;

[0123] a first sending module configured to send second information to the network device;

[0124] wherein the second information comprises at least one of the following:

[0125] a model identifier or index of at least one candidate model;

[0126] a function identifier or index of at least one candidate function;

[0127] a first beam set of the at least one candidate model;

[0128] a first beam set of the at least one candidate function;

[0129] first request information for requesting the network device to configure a first beam set of a first model;

[0130] second request information for requesting the network device to configure a first beam set of a first function.

[0131] Optionally, the apparatus further comprises:

[0132] a third receiving module configured to receive management decision information sent by the network device;

[0133] a fourth receiving module, configured to receive configuration information of the first beam set of the first model sent by the network device;

[0134] a fifth receiving module, configured to receive configuration information of the first beam set of the first function sent by the network device.

[0135] Optionally, the management decision information comprises at least one of the following:

[0136] a model identifier or index of at least one second model;

[0137] a function identifier or index of at least one second function;

[0138] a first activation indication for instructing the terminal to activate at least one second model;

[0139] a second activation indication for instructing the terminal to activate at least one second function;

[0140] a third activation indication for instructing the terminal to deactivate at least one third model;

[0141] a fourth activation indication for instructing the terminal to deactivate at least one third function;

[0142] a first switching indication for instructing the terminal to switch to a second model;

[0143] a second switching indication for instructing the terminal to switch to a second function;

[0144] a condition for applying the second model;

[0145] a condition for applying the second function;

[0146] first fallback indication information for instructing the terminal to fallback to a non-artificial intelligence operation;

[0147] second fallback indication information for instructing the terminal to fallback to a preset model;

[0148] third fallback indication information for instructing the terminal to fallback to a preset function.

[0149] Optionally, the second information further comprises at least one of the following:

[0150] a performance indicator of a third model;

[0151] a performance indicator of a third function;

[0152] a list of available candidate models;

[0153] a list of available candidate functions;

[0154] a performance indicator of at least one candidate model;

[0155] performance indicators of the at least one candidate function;

[0156] key information of the at least one candidate model;

[0157] key information of the at least one candidate function;

[0158] model fallback indication information;

[0159] function fallback indication information;

[0160] condition information of the terminal

[0161] Optionally, the first information comprises at least one of:

[0162] measurement configuration information;

[0163] performance indicators required to be monitored by the terminal;

[0164] key performance indicators (KPIs) required to be monitored by the terminal;

[0165] first indication information, used to indicate that the first information is used for model monitoring and / or function monitoring;

[0166] second indication information, used to indicate periodic information of reporting the second information by the terminal;

[0167] third indication information, used to indicate whether the terminal needs to report the performance indicators and / or the KPIs;

[0168] fourth indication information, used to indicate whether the terminal is allowed to report management suggestion information;

[0169] models and / or functions supported by the network device;

[0170] a second beam set corresponding to the models supported by the network device;

[0171] a second beam set corresponding to the functions supported by the network device;

[0172] configurations supported by the network device;

[0173] fifth indication information, used to indicate whether the terminal needs to report a management result;

[0174] an event triggering the terminal to perform model management and / or function management;

[0175] an event triggering the terminal to report the second information;

[0176] sixth indication information, used to indicate that the terminal reports a management result.

[0177] To achieve the above object, the embodiments of the present disclosure provide a model monitoring management device applied to a network device, comprising:

[0178] a second sending module configured to send first information to a terminal, wherein the first information is used to configure information related to monitoring of a model and / or a function;

[0179] a second receiving module configured to receive second information sent by the terminal;

[0180] wherein the second information comprises at least one of the following:

[0181] a model identifier or index of at least one candidate model;

[0182] a function identifier or index of at least one candidate function;

[0183] a first beam set of the at least one candidate model;

[0184] a first beam set of the at least one candidate function;

[0185] first request information used to request the network device to configure a first beam set of a first model;

[0186] second request information used to request the network device to configure a first beam set of a first function.

[0187] Optionally, the device further comprises:

[0188] a first processing module configured to determine at least one second model from the at least one candidate model and send management decision information to the terminal;

[0189] a second processing module configured to determine at least one second function from the at least one candidate function and send management decision information to the terminal;

[0190] a third sending module configured to send configuration information of the first beam set of the first model to the terminal;

[0191] a fourth sending module configured to send configuration information of the first beam set of the first function to the terminal.

[0192] Optionally, the management decision information comprises at least one of the following:

[0193] a model identifier or index of the at least one second model;

[0194] a function identifier or index of the at least one second function;

[0195] a first activation indication used to instruct the terminal to activate the at least one second model;

[0196] a second activation indication for instructing the terminal to activate at least one second function;

[0197] a third activation indication for instructing the terminal to deactivate at least one third model;

[0198] a fourth activation indication for instructing the terminal to deactivate at least one third function;

[0199] a first switching indication for instructing the terminal to switch to the second model;

[0200] a second switching indication for instructing the terminal to switch to the second function;

[0201] a condition for applying the second model;

[0202] a condition for applying the second function;

[0203] first fallback indication information for instructing the terminal to fallback to a non-artificial intelligence operation;

[0204] second fallback indication information for instructing the terminal to fallback to a preset model;

[0205] third fallback indication information for instructing the terminal to fallback to a preset function.

[0206] Optionally, the second information further comprises at least one of:

[0207] a performance index of the third model;

[0208] a performance index of the third function;

[0209] a list of available candidate models;

[0210] a list of available candidate functions;

[0211] a performance index of at least one candidate model;

[0212] a performance index of at least one candidate function;

[0213] key information of at least one candidate model;

[0214] key information of at least one candidate function;

[0215] model fallback indication information;

[0216] function fallback indication information;

[0217] condition information of the terminal.

[0218] Optionally, the first information comprises at least one of:

[0219] measurement configuration information;

[0220] a performance indicator that the terminal needs to monitor;

[0221] a key performance indicator KPI that the terminal needs to monitor;

[0222] first indication information, used to indicate that the first information is used for model monitoring and / or function monitoring;

[0223] second indication information, used to indicate periodic information of the terminal reporting the second information;

[0224] third indication information, used to indicate whether the terminal needs to report the performance indicator and / or the KPI;

[0225] fourth indication information, used to indicate whether the terminal is allowed to report management suggestion information;

[0226] a model and / or a function supported by the network device;

[0227] a second beam set corresponding to the model supported by the network device;

[0228] a second beam set corresponding to the function supported by the network device;

[0229] a configuration supported by the network device;

[0230] fifth indication information, used to indicate whether the terminal needs to report a management result;

[0231] an event triggering the terminal to perform model management and / or function management;

[0232] an event triggering the terminal to report the second information;

[0233] sixth indication information, used to indicate that the terminal reports the management result.

[0234] To achieve the above purpose, an embodiment of the present disclosure provides a terminal, comprising a processor and a transceiver, wherein the transceiver is configured to:

[0235] receive first information sent by a network device, the first information being used to configure information related to supervision of a model and / or a function;

[0236] send second information to the network device;

[0237] wherein the second information comprises at least one of the following:

[0238] a model identifier or index of at least one candidate model;

[0239] a function identifier or index of at least one candidate function;

[0240] a first beam set of the at least one candidate model;

[0241] a first beam set of the at least one candidate function;

[0242] first request information for requesting the network device to configure a first beam set of a first model;

[0243] second request information for requesting the network device to configure a first beam set of a first function.

[0244] Optionally, the transceiver is further configured to perform at least one of the following:

[0245] receive management decision information sent by the network device;

[0246] receive configuration information of the first beam set of the first model sent by the network device;

[0247] receive configuration information of the first beam set of the first function sent by the network device.

[0248] Optionally, the management decision information comprises at least one of the following:

[0249] model identification or index of at least one second model;

[0250] function identification or index of at least one second function;

[0251] a first activation indication for instructing the terminal to activate at least one second model;

[0252] a second activation indication for instructing the terminal to activate at least one second function;

[0253] a third activation indication for instructing the terminal to deactivate at least one third model;

[0254] a fourth activation indication for instructing the terminal to deactivate at least one third function;

[0255] a first switching indication for instructing the terminal to switch to a second model;

[0256] a second switching indication for instructing the terminal to switch to a second function;

[0257] a condition for applying the second model;

[0258] a condition for applying the second function;

[0259] first fallback indication information for instructing the terminal to fallback to a non-artificial intelligence operation;

[0260] second fallback indication information for instructing the terminal to fallback to a preset model;

[0261] a third fallback indication information, used for instructing the terminal to fallback to a preset function.

[0262] Optionally, the second information further comprises at least one of:

[0263] a performance indicator of the third model;

[0264] a performance indicator of the third function;

[0265] a list of available candidate models;

[0266] a list of available candidate functions;

[0267] a performance indicator of at least one candidate model;

[0268] a performance indicator of at least one candidate function;

[0269] key information of at least one candidate model;

[0270] key information of at least one candidate function;

[0271] a model fallback indication information;

[0272] a function fallback indication information;

[0273] condition information of the terminal.

[0274] Optionally, the first information comprises at least one of:

[0275] measurement configuration information;

[0276] a performance indicator required to be monitored by the terminal;

[0277] a key performance indicator (KPI) required to be monitored by the terminal;

[0278] a first indication information, used for indicating that the first information is used for model monitoring and / or function monitoring;

[0279] a second indication information, used for indicating a periodicity information of reporting the second information by the terminal;

[0280] a third indication information, used for indicating whether the terminal needs to report the performance indicator and / or the KPI;

[0281] a fourth indication information, used for indicating whether the terminal is allowed to report management suggestion information;

[0282] a model and / or a function supported by the network device;

[0283] a second beam set corresponding to a model supported by the network device;

[0284] A second beam set corresponding to a function supported by the network device;

[0285] A configuration supported by the network device;

[0286] Fifth indication information for indicating whether the terminal needs to report a management result;

[0287] An event triggering the terminal to perform model management and / or function management;

[0288] An event triggering the terminal to report the second information;

[0289] Sixth indication information for indicating the terminal to report a management result.

[0290] To achieve the above-mentioned purposes, an embodiment of the present disclosure provides a network device comprising a processor and a transceiver, wherein the transceiver is configured to:

[0291] Send first information to a terminal, wherein the first information is used to configure information related to supervision of a model and / or a function;

[0292] Receive second information sent by the terminal;

[0293] The second information comprises at least one of the following:

[0294] A model identifier or index of at least one candidate model;

[0295] A function identifier or index of at least one candidate function;

[0296] A first beam set of the at least one candidate model;

[0297] A first beam set of the at least one candidate function;

[0298] First request information for requesting the network device to configure a first beam set of a first model;

[0299] Second request information for requesting the network device to configure a first beam set of a first function.

[0300] Optionally, the processor is configured to:

[0301] Determine at least one second model from the at least one candidate model, and send management decision information to the terminal;

[0302] Determine at least one second function from the at least one candidate function, and send management decision information to the terminal;

[0303] Send configuration information of the first beam set of the first model to the terminal;

[0304] transmit, to the terminal, configuration information of a first beam set of the first function.

[0305] Optionally, the management decision information comprises at least one of:

[0306] a model identifier or index of the at least one second model;

[0307] a function identifier or index of the at least one second function;

[0308] a first activation indication for instructing the terminal to activate the at least one second model;

[0309] a second activation indication for instructing the terminal to activate the at least one second function;

[0310] a third activation indication for instructing the terminal to deactivate the at least one third model;

[0311] a fourth activation indication for instructing the terminal to deactivate the at least one third function;

[0312] a first switching indication for instructing the terminal to switch to the second model;

[0313] a second switching indication for instructing the terminal to switch to the second function;

[0314] a condition for applying the second model;

[0315] a condition for applying the second function;

[0316] first fallback indication information for instructing the terminal to fallback to a non-artificial intelligence operation;

[0317] second fallback indication information for instructing the terminal to fallback to a preset model;

[0318] third fallback indication information for instructing the terminal to fallback to a preset function.

[0319] Optionally, the second information further comprises at least one of:

[0320] a performance indicator of the third model;

[0321] a performance indicator of the third function;

[0322] a list of available candidate models;

[0323] a list of available candidate functions;

[0324] a performance indicator of the at least one candidate model;

[0325] a performance indicator of the at least one candidate function;

[0326] key information of the at least one candidate model;

[0327] key information of at least one candidate function;

[0328] model fallback indication information;

[0329] function fallback indication information;

[0330] condition information of the terminal.

[0331] Optionally, the first information comprises at least one of:

[0332] measurement configuration information;

[0333] a performance indicator required to be monitored by the terminal;

[0334] a key performance indicator (KPI) required to be monitored by the terminal;

[0335] first indication information, used for indicating that the first information is used for model monitoring and / or function monitoring;

[0336] second indication information, used for indicating periodic information of the terminal reporting the second information;

[0337] third indication information, used for indicating whether the terminal needs to report the performance indicator and / or the KPI;

[0338] fourth indication information, used for indicating whether the terminal is allowed to report management suggestion information;

[0339] a model and / or a function supported by the network device;

[0340] a second beam set corresponding to the model supported by the network device;

[0341] a second beam set corresponding to the function supported by the network device;

[0342] a configuration supported by the network device;

[0343] fifth indication information, used for indicating whether the terminal needs to report a management result;

[0344] an event triggering the terminal to perform model management and / or function management;

[0345] an event triggering the terminal to report the second information;

[0346] sixth indication information, used for indicating that the terminal reports the management result.

[0347] To achieve the above object, the embodiment of the disclosure provides a terminal, comprising a transceiver, a processor, a memory and a program or instructions stored in the memory and executable on the processor; the processor implements the monitoring management method applied to the terminal as above when executing the program or instructions.

[0348] To achieve the above object, the embodiment of the disclosure provides a network device, comprising a transceiver, a processor, a memory and a program or instructions stored in the memory and executable on the processor; the processor implements the monitoring management method applied to the network device as above when executing the program or instructions.

[0349] To achieve the above object, a computer program product is provided, comprising computer instructions executable by a processor to implement the steps of the monitoring management method applied to the terminal as above, or to implement the steps of the monitoring management method applied to the network device as above.

[0350] To achieve the above object, the embodiment of the disclosure provides a readable storage medium, which stores a program or instructions, the program or instructions being executable by a processor to implement the steps of the monitoring management method applied to the terminal as above, or to implement the steps of the monitoring management method applied to the network device as above.

[0351] The beneficial effects of the above technical solutions of the disclosure are as follows:

[0352] The method of the embodiment of the disclosure defines the interaction content between the terminal and the network during model monitoring and model management, wherein the terminal sends second information to the network device, the second information can include a first beam set of at least one candidate model / candidate function, so that the network model can refer to the information to make management decisions, and the second information can also include first request information and / or second request information, so that in the scenario of management decisions made by the terminal, the network device can be requested to configure the first beam set for the first model and / or the first function. In this way, through the interaction between the network device and the terminal, the terminal can use better models for model inference and can avoid the case of introducing too much signaling interaction or other overhead to improve the prediction accuracy of the model. BRIEF DESCRIPTION OF DRAWINGS

[0353] FIG. 1 is a schematic diagram of model training in AI / ML according to an embodiment of the disclosure;

[0354] FIG. 2 is a schematic diagram of a channel state information (CSI) compression use case according to an embodiment of the disclosure;

[0355] FIG. 3a is a schematic diagram of a spatial beam prediction use case according to an embodiment of the disclosure;

[0356] FIG. 3b is a schematic diagram of a spatial beam prediction use case according to an embodiment of the present disclosure;

[0357] FIG. 4 is a schematic diagram of a time domain beam prediction use case according to an embodiment of the present disclosure;

[0358] FIG. 5 is a schematic diagram of a positioning accuracy enhancement use case according to an embodiment of the present disclosure;

[0359] FIG. 6 is a flowchart of a monitoring management method according to an embodiment of the present disclosure;

[0360] FIG. 7 is a schematic diagram of a monitoring management method in a scenario one according to an embodiment of the present disclosure;

[0361] FIG. 8 is a schematic diagram of a monitoring management method in a scenario two according to an embodiment of the present disclosure;

[0362] FIG. 9 is a schematic diagram of a monitoring management method in a scenario three according to an embodiment of the present disclosure;

[0363] FIG. 10 is a flowchart of a monitoring management method according to another embodiment of the present disclosure;

[0364] FIG. 11 is a structural diagram of a model monitoring management apparatus according to an embodiment of the present disclosure;

[0365] FIG. 12 is a structural diagram of a model monitoring management apparatus according to another embodiment of the present disclosure;

[0366] FIG. 13 is a structural diagram of a terminal according to an embodiment of the present disclosure;

[0367] FIG. 14 is a structural diagram of a network device according to an embodiment of the present disclosure;

[0368] FIG. 15 is a structural diagram of a terminal according to another embodiment of the present disclosure;

[0369] FIG. 16 is a structural diagram of a network device according to another embodiment of the present disclosure. DETAILED DESCRIPTION

[0370] To make the technical problems to be solved by the present disclosure, technical solutions and advantages clearer, specific embodiments will be described in detail below with reference to the accompanying drawings.

[0371] It should be understood that the "one embodiment" or "an embodiment" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present disclosure. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily mean the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner.

[0372] In various embodiments of the present disclosure, it should be understood that the size of the serial number of the following processes does not mean the order of execution, and the execution order of the processes should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present disclosure.

[0373] In addition, the terms "system" and "network" are often used interchangeably herein.

[0374] In the embodiments provided in the present disclosure, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that the determination of B according to A does not mean that B is determined only according to A, but B can also be determined according to A and / or other information.

[0375] Related content introduction:

[0376] The use cases discussed in the current air interface AI topic mainly include: CSI feedback enhancement, beam management and positioning accuracy enhancement, which are introduced as follows:

[0377] (1) AI-based CSI feedback enhancement includes the following two typical sub-use cases: CSI compression (double-sided model, deployed on the terminal side and the network side at the same time) and CSI prediction (terminal side model). As shown in FIG. 2, it is a schematic diagram of the CSI compression use case, in which the UE side compresses the CSI feedback, and the network side decompresses.

[0378] (2) AI-based beam management includes the following two typical sub-use cases: spatial beam prediction and time domain beam prediction, in which the AI model can be deployed on the terminal side or the base station side.

[0379] As shown in FIGS. 3a-3b, spatial beam prediction is to measure fewer reference signals and predict the optimal beam in all beams through an AI model. Here, the set of beams that the terminal needs to measure is denoted as set B, and the total beam that needs to be predicted is denoted as set A. Among them, set B can be a subset of set A, or it can be the same as set A, or it can have no association with set A. As shown in FIG. 3a, the wide beam is used to predict the narrow beam, which is the case where set B is not a subset of set A; as shown in FIG. 3b, the narrow beam is used to predict the narrow beam, which is the case where set B is a subset of set A.

[0380] As shown in FIG. 4, the time-domain beam prediction is based on the reference signal measurement results at past time points, and the optimal beams at future time points are predicted by an AI model. For example, the measurement results at 5 time points within T1 (K=5 measurement instances within T1) are used to predict the optimal beams at 4 time points within T2 (F=4 prediction instances within T2). Wherein, the beam set at historical time points is denoted as set B, and the beam set at future time points to be predicted is denoted as set A.

[0381] (3) As shown in FIG. 5, the AI-based positioning accuracy enhancement includes the following two typical sub-use cases: direct positioning and assisted positioning, wherein the AI model can be deployed at the terminal side, the base station side or the location management function (LMF) side.

[0382] As shown in FIG. 6, a monitoring management method of an embodiment of the present disclosure is applied to a terminal, and includes:

[0383] Step 601, receiving first information sent by a network device, wherein the first information is used to configure information related to monitoring and / or management of a model and / or a function.

[0384] Here, the monitoring and / or management. The first information is used to configure information related to monitoring of a model, or is used to configure information related to monitoring of a function, or is used to configure information related to monitoring of a model and information related to monitoring of a function.

[0385] Step 602, sending second information to the network device;

[0386] Wherein, the second information includes at least one of the following:

[0387] (1) Model identifier or index of at least one candidate model. Here, the candidate model can be specifically a model that the terminal expects to switch to.

[0388] (2) Function identifier or index of at least one candidate function. Here, the candidate function can be specifically a function that the terminal expects to switch to.

[0389] (3) First beam set of at least one candidate model. Here, the first model can be specifically a model that the terminal decides to switch to.

[0390] (4) First beam set of at least one candidate function. Here, the first function can be specifically a function that the terminal decides to switch to.

[0391] (5) First request information, used to request the network device to configure the first beam set of the first model.

[0392] (6) second request information, used for requesting the network device to configure the first function with the first beam set.

[0393] The first beam set can be Set B and / or Set A, i.e., the beam set to be measured by the terminal and / or the beam set to be predicted by the terminal.

[0394] In this embodiment, the interaction between the terminal and the network during model monitoring and model management is defined, wherein the terminal sends second information to the network device, the second information can include the first beam set of at least one candidate model / candidate function, so that the network model can refer to the information to make management decisions, and the second information can also include first request information and / or second request information, so that in the scenario where the terminal makes management decisions, the network device can be requested to configure the first beam set for the first model and / or the first function. In this way, through the interaction between the network device and the terminal, the terminal can use a better model for model inference and can avoid introducing too much signaling interaction or other overhead to improve model prediction accuracy.

[0395] It should be noted that the monitoring and management of the terminal-side model / function mainly include the following scenarios: scenario one, the terminal monitors the AI model / function, and the network device makes decisions on the management / control of the model / function; scenario two, the terminal monitors the AI model / function and makes decisions on the management / control of the model / function; scenario three, the network device monitors the AI model / function and makes decisions on the management / control of the model / function.

[0396] It should be noted that the information exchanged between the terminal and the network device is different in different use cases, and the behaviors to be performed by the terminal and the network device are also different. In the following, for the above three scenarios, the model monitoring and management method provided by the embodiments of the present disclosure is introduced, and the specific content of the interaction between the terminal and the network device in different use cases is defined.

[0397] In some embodiments, the method further includes at least one of the following:

[0398] (1) receiving the management decision information sent by the network device.

[0399] For example, in the above scenario one, the network device makes decisions on the management (management and / or control) of the model / function, and then the network device (such as a base station) can send management decision information to the terminal to tell the terminal the decision of model management (such as switching or fallback), and then the terminal performs corresponding operations based on the indication of the network device, such as performing model switching (i.e., switching model / function) or fallback.

[0400] (ii) receiving configuration information of the first beam set of the first model sent by the network device.

[0401] Here, the first model can be a handover model decided by the network or the terminal.

[0402] For example, in the above scenario two, for the beam management use case, the first beam set corresponding to the model (e.g., the first model) of the handover is different from the first beam set of the current model (the third model), and the network device needs to configure the first beam set of the first model.

[0403] (iii) receiving configuration information of the first beam set of the first function sent by the network device.

[0404] Here, the first function can be a handover function decided by the network or the terminal.

[0405] In an optional embodiment, the management decision information can specifically include at least one of the following:

[0406] (1) model identifier or index of at least one second model, i.e., model ID or index of the handover decided by the network device.

[0407] Here, the second model can be a handover model decided by the network device.

[0408] It should be noted that if the model identifier (model ID) or index (index) of the second model is included in the management decision information, a list can be used, that is, the management decision information can include a list of model identifiers or a list of indexes of the handover or selection. For example, the terminal reports multiple model IDs to the network device, and the first beam set configurations corresponding to these model IDs are the same, and the KPIs are also similar, then the network device (e.g., a base station) can select multiple model IDs of the second model to send to the terminal, and the terminal uses which model has no effect on the base station configuration.

[0409] (2) function identifier or index of at least one second function.

[0410] Here, the second function can be a handover function decided by the network device.

[0411] (3) a first activation indication for instructing the terminal to activate at least one second model;

[0412] (4) a second activation indication for instructing the terminal to activate at least one second function;

[0413] (5) a third activation indication for instructing the terminal to deactivate at least one third model.

[0414] Here, the third model can be specifically a current model, that is, a currently used model.

[0415] (6) A fourth activation indication for instructing the terminal to deactivate at least one third function.

[0416] Here, the third model can be specifically a current function, that is, a currently used function.

[0417] (7) A first switching indication for instructing the terminal to switch to a second model;

[0418] (8) A second switching indication for instructing the terminal to switch to a second function;

[0419] (9) A condition for applying the second model, such as time, beam quality, scene, etc.

[0420] (10) A condition for applying the second function, such as time, beam quality, scene, etc.

[0421] (11) First fallback indication information for instructing the terminal to fallback to a non-artificial intelligence operation, that is, to fallback to a non-AI operation;

[0422] (12) Second fallback indication information for instructing the terminal to fallback to a preset model, that is, instructing the terminal to fallback to a default model;

[0423] (13) Third fallback indication information for instructing the terminal to fallback to a preset function.

[0424] In some preferable embodiments, the first information includes at least one of the following:

[0425] (1) Measurement configuration information;

[0426] (2) A performance indicator that needs to be monitored by the terminal;

[0427] (3) A key performance indicator KPI that needs to be monitored by the terminal;

[0428] (4) First indication information for indicating that the first information is used for model monitoring and / or function monitoring;

[0429] (5) Second indication information for indicating a period information of reporting the second information by the terminal;

[0430] (6) Third indication information for indicating whether the terminal needs to report the performance indicator and / or the KPI;

[0431] (7) Fourth indication information for indicating whether the terminal is allowed to report management suggestion information.

[0432] Here, the management suggestion information can be a suggestion for model management or a suggestion for function management. If the first indication information indicates that the terminal is allowed to report the management suggestion information, the first information can further carry at least one of the following: a model identifier (model ID) or an index of at least one candidate model, a function identifier or an index of at least one candidate function, key information (meta info) of at least one candidate model, key information of at least one candidate function, a performance indicator / KPI of at least one candidate model, a performance indicator / KPI of at least one candidate function, and the like.

[0433] (8) the model and / or function supported by the network device;

[0434] (9) the second beam set (Set B and / or Set A) corresponding to the model supported by the network device;

[0435] For example, the quality of 32 beams (Set A) can be predicted using the quality of the first 6 beams (Set B), or the quality of 32 beams (Set A) can be predicted using the quality of the first 8 beams (Set B).

[0436] (10) the second beam set corresponding to the function supported by the network device;

[0437] (11) the configuration supported by the network device;

[0438] (12) fifth indication information for indicating whether the terminal needs to report the management result;

[0439] (13) an event triggering the terminal to perform model management and / or function management;

[0440] (14) an event triggering the terminal to report the second information.

[0441] Specifically, it can be an event related to the monitored performance indicator / KPI. For example, a threshold of a certain performance indicator / KPI is set, and when the terminal monitors the performance indicator / KPI to meet the threshold condition, the reporting is triggered; for example, the beam prediction accuracy is 90%, and the beam prediction accuracy is lower than 90% to trigger the reporting.

[0442] It can also be an event related to the current channel quality, etc. For example, the channel quality is lower than a threshold to trigger the reporting.

[0442]

[0443] (15) sixth indication information for indicating that the terminal reports the management result.

[0444] In some preferred embodiments, the second information further includes at least one of the following:

[0445] (1) a performance indicator of the third model;

[0446] (2) performance indicator of the third function;

[0447] (3) list of available candidate models.

[0448] The list of candidate models can include information of one or more candidate models in model identification, index, performance indicator, key information, etc.

[0449] (4) list of available candidate functions.

[0450] The list of candidate functions can include information of one or more candidate functions in model identification, index, performance indicator, key information, etc.

[0451] (5) performance indicator of at least one candidate model;

[0452] (6) performance indicator of at least one candidate function;

[0453] (7) key information of at least one candidate model;

[0454] (8) key information of at least one candidate function;

[0455] (9) model fallback indication information;

[0456] (10) function fallback indication information;

[0457] (11) condition information of the terminal, such as speed, memory, computing power, etc. internal conditions of the terminal, and also the conditions of indoor or outdoor scenes, etc.

[0458] Here, the application of the embodiments of the present disclosure is explained in combination with specific scenarios:

[0459] Scenario one, the terminal performs AI model monitoring, and the network device makes decisions on model management / control:

[0460] Here, the network device can be a base station (the next Generation Node B, gNB), LMF, Operation Administration and Maintenance (OAM), etc. network entity, but is not limited thereto. Among them, LMF is a specific network entity in the positioning scenario, and gNB and OAM can be applied to all scenarios.

[0461] As shown in FIG. 7, the following details the content of the interaction between the terminal (UE) and the network (NW, i.e. network device) for each step in scenario one:

[0462] (1) The network device configures the terminal to perform monitoring and / or management of models / functions, specifically, the network device can send first information to the terminal for configuration, wherein the first information can include at least one of the following information:

[0463] 1. Measurement configuration information, for different use cases, the measurement configuration information is as follows:

[0464] (1) For beam management use cases: configure set A (i.e., all beams that the terminal needs to predict) or a subset of set A, the measurement configuration information can specifically include at least one of the following: reference signal (Reference Signal, RS) identity (Identity, ID), time domain and frequency domain resource configuration (such as period, occupied symbol, occupied resource block (Resource Block, RB)), etc.; the terminal compares the actual measurement results of set A or the subset of set A with the predicted results, and can calculate the monitored indicators or KPIs;

[0465] (2) For CSI compression use cases and CSI prediction use cases, the measurement configuration information can specifically include at least one of the following: target CSI, reconstructed CSI (CSI obtained after network decompression), etc.

[0466] (3) For positioning use cases, the measurement configuration information can specifically include positioning reference signals (Positioning Reference Signal, PRS), etc.

[0467] 2. Performance indicators and / or KPIs that the terminal needs to monitor:

[0468] (1) For beam management use cases, the performance indicators and / or KPIs that the terminal needs to monitor can specifically include at least one of the following: beam prediction accuracy, average L1-RSRP difference of the top-1 predicted beam (Average L1-RSRP difference of Top-1 predicted beam), cumulative distribution function (Cumulative Distribution Function, CDF) of the L1-RSRP difference for the top-1 predicted beam (CDF of L1-RSRP difference for Top-1 predicted beam), etc.

[0469] (2) For CSI compression and CSI prediction use cases, the performance indicators and / or KPIs that the terminal needs to monitor can specifically include at least one of the following: Squared Generalized Cosine Similarity (SGCS) (referring to the difference between predicted CSI and measured CSI), Normalized Mean Square Error (NMSE), etc.

[0470] (3) For positioning use cases, the performance indicators and / or KPIs that the terminal needs to monitor can specifically include positioning prediction accuracy, etc.

[0471] (4) System performance related indicators, such as: throughput, RS load reduction, etc.

[0472] (5) Data distribution information, which can specifically include the distribution of input data or the distribution of output data, such as input / output data drift, etc.

[0473] 3. First indication information, used to indicate that the first information is used for model monitoring and / or function monitoring.

[0474] That is, an indicator indicates that this configuration is used for model monitoring and / or function monitoring. It should be noted that if a new message is introduced for configuration, the first information can not include this indicator, or if the performance indicators and / or KPIs to be monitored are configured, it can be implicitly indicated that this configuration is used for model monitoring and / or function monitoring.

[0475] 4. Indicate the reporting mode of the terminal, such as periodic reporting, event triggering, or network aperiodic triggering, etc. Specifically, the first information can include at least one of the following:

[0476] (1) Second indication information, used to indicate the periodic information of the terminal reporting the second information.

[0477] Specifically, it can indicate the period of model monitoring, such as reporting once every 100ms.

[0478] (2) Triggered event: an event that triggers the terminal to perform model management and / or function management; and / or, an event that triggers the terminal to report the second information.

[0479] In addition, for the case of network aperiodic triggering, the terminal can report upon receiving network indication, or can report or stop through downlink control information (DCI), MAC layer control element (MAC CE), radio resource control (RRC) indication; for example, a new MAC CE is introduced for triggering and / or stopping of model monitoring.

[0480] 5. Third indication information, used to indicate whether the terminal needs to report the performance indicators and / or the KPIs.

[0481] 6. Fourth indication information, used to indicate whether the terminal is allowed to report management suggestion information (for example, model management suggestion and / or function management suggestion).

[0482] 7. Key information of at least one candidate model and / or key information of at least one candidate function.

[0483] It should be noted that the key information (meta info) can include at least one of the following: model input / output, function input / output, applicable scene / configuration, format, version, performance, set B / set A configuration or relationship (for the beam management use case), etc. Among them, the network device can instruct the terminal to report all meta info, or can instruct the terminal to report part of the meta info (i.e., report one or more information in the meta info).

[0484] 8. Model and / or function supported by the network device;

[0485] 9. Second beam set corresponding to the model supported by the network device;

[0486] 10. Second beam set corresponding to the function supported by the network device;

[0487] 11. Configuration information supported by the network device.

[0488] It should be noted that the configuration information can also be sent to the terminal (UE) through system information (System Information Block, SIB) or RRC message.

[0489] (II) The terminal performs model monitoring and reports based on network indication (periodic, event triggered, aperiodic triggered, etc.). The reported information includes one or more of the following, which can be reported based on the content of the network indication in the first step: Specifically, the terminal can send second information to the network device for configuration, wherein the second information can include at least one of the following information:

[0490] (1) Performance indicator / KPI of the current model (third model);

[0491] Here, the terminal can perform calculation based on the output of model inference, such as beam prediction accuracy, positioning prediction accuracy, etc.

[0492] (2) Identification (model ID) or index of the model or candidate model that the terminal wants to switch to, and / or identification or index of the function or candidate function that the terminal wants to switch to.

[0493] This model ID can be a global ID or a local ID.

[0494] (3) Meta info corresponding to the model ID and / or meta info corresponding to the function ID, which can be all meta info or part of the meta info (i.e., one or more information in the meta info). The key information (meta info) can include at least one of the following: model input / output, function input / output, applicable scenario / configuration, format, version, performance, set B / set A configuration or relationship, etc. For example, for the beam management use case, Set B is the key meta info, which must be reported by the terminal.

[0495] (4) Performance indicator / KPI of the model or candidate model that the terminal wants to switch to;

[0496] (5) Performance indicator / KPI of the function or candidate function that the terminal wants to switch to;

[0497] (6) Distribution of input data or distribution of output data of the model or candidate model that the terminal wants to switch to;

[0498] (7) Distribution of input data or distribution of output data of the function or candidate function that the terminal wants to switch to;

[0499] (8) The terminal wants to fallback to non-AI operation;

[0500] (9) The terminal wants to fallback to the default model / function, i.e., fallback to the preset model and / or fallback to the preset function;

[0501] (10) Current scenario, configuration, etc. information, or scenario, configuration, etc. information that the model / function the terminal expects to switch to can adapt to.

[0502] It should be noted that if only the model ID is reported, the network device (such as a base station) needs to know the meta info corresponding to the model ID in advance, and the meta info of the model ID needs to be interacted between the base station and the terminal online or offline.

[0503] For example, the reporting can take the following form:

[0504] {KPI of the current model;

[0505] candidate model model#1, meta info (optional), KPI (optional);

[0506] candidate model model#2, meta info (optional), KPI (optional);}

[0507] (Three) The network device (such as a base station) decides whether to switch the model / function, and to which model / function, or decides whether to fallback to non-AI operation or default model / function.

[0508] It should be noted that when making a decision, the network device (for example, a base station) will consider various factors, including model KPI, function KPI, system performance, base station overhead, measurement configuration, etc. The base station may select a model with better KPI and less impact on base station overhead, rather than selecting a model with the best KPI. The specific situation depends on the base station implementation. For example, model 1 has better KPI indicators, but model 1 has a greater impact on base station overhead. Model 2 has worse KPI indicators than model 1, but model 2 has no additional impact on base station overhead. In this case, the base station may select model 2 after considering various factors.

[0509] In addition, for the beam management use case, the base station needs to additionally consider whether the set B of the model / function is changed. If the set B of the model / function is changed, it will affect the configuration of the base station and introduce additional signaling overhead. For example, the current model#0 of the terminal corresponds to set B#1, the candidate model model#1 reported by the terminal corresponds to set B#1, the beam prediction accuracy is 95%, the candidate model model#2 corresponds to set B#2, and the beam prediction accuracy is 98%. In this case, considering that most terminals in the current cell use set B#1, if the base station sends set B#2, it will bring additional overhead. Therefore, even if the beam prediction accuracy of model#2 is higher than that of model#1, the base station may still switch the terminal to model#1.

[0510] (IV) The network device (e.g., base station) can send management decision information to the terminal to tell the terminal the decision of model management and / or function management, such as handover or fallback.

[0511] (V) The terminal performs corresponding operations based on the indication of the network device, such as performing handover of the model (i.e., switching the model / function) or fallback.

[0512] Scenario two, the terminal performs AI model monitoring and makes decisions for model management / control:

[0513] Here, the network device can be a base station, LMF, OAM, etc., but is not limited thereto.

[0514] As shown in FIG. 8, the following details the interaction between the terminal (UE) and the network (NW, i.e., network device) for scenario two:

[0515] (I) The terminal requests the network to issue measurement configuration for model monitoring and / or function monitoring.

[0516] 1. For different use cases, the measurement configuration information is as follows:

[0517] (1) For the beam management use case, the measurement configuration information includes at least one of the following: set B (i.e., the set of beams that the terminal needs to measure), set A (i.e., the set of all beams that the terminal needs to predict), or a subset of set A.

[0518] (2) For the CSI compression use case and the CSI prediction use case, the measurement configuration information can specifically include at least one of the following: target CSI, reconstructed CSI (CSI obtained after network decompression), etc.

[0519] 2. First indication information for indicating that the first information is used for model monitoring and / or function monitoring.

[0520] That is, an indicator indicates that this configuration is used for model monitoring and / or function monitoring. It should be noted that if a new message is introduced for configuration, the first information can not include this explicit indicator.

[0521] (II) In addition to issuing measurement configuration, the network device (e.g., base station) can also carry other information, for example:

[0522] (1) Fifth indication information for indicating whether the terminal needs to report management results.

[0523] (2) Events that trigger the terminal to perform model management and / or function management.

[0524] Specifically, it can be an event related to a performance indicator / KPI monitored. For example, a threshold of a certain performance indicator / KPI is set, and when the terminal monitors the performance indicator / KPI to meet the threshold condition, it triggers model management and / or function management. It should be noted that the thresholds of model switching and fallback can be different for the same event. For example, for beam prediction accuracy, the network device can configure the threshold triggering model switching to be 90%, and the threshold triggering fallback to be 70%, that is, the performance indicator / KPI is lower than 90% to perform model switching, and lower than 70% to perform fallback.

[0525] It can also be an event related to the current channel quality, etc. For example, when the channel quality is lower than a threshold, it triggers switching (model switching and / or function switching) or fallback. It should be noted that the thresholds of model switching and fallback can be set to different values for the same event.

[0526] (3) The model and / or function supported by the network device;

[0527] (4) The second beam set corresponding to the model supported by the network device;

[0528] (5) The second beam set corresponding to the function supported by the network device;

[0529] (6) The configuration information supported by the network device.

[0530] It should be noted that the configuration information can also be sent to the terminal (UE) through system information (System Information Block, SIB) or RRC message.

[0531] (Three) The terminal monitors the model, and performs model management (switching or fallback) based on the monitoring result.

[0532] It depends on the terminal implementation, for example, the model can be selected based on the calculated KPI, the threshold configured by the network, the terminal internal information (such as UE power consumption, memory, etc.), etc. Finally, a model with better KPI and less consumption of terminal power consumption or memory, etc. may be selected. For example, assume that the prediction accuracy of model 1 is 98%, and the prediction accuracy of model 2 is 95%, but the power consumption of the terminal running model 1 is greater than that of running model 2. If the terminal pays more attention to power consumption at this time, model 2 is selected as the first model (that is, the model decided by the terminal to switch), and if the terminal pays more attention to prediction accuracy, model 1 is selected as the first model.

[0533] (iv) The terminal reports the management result (the result of model management and / or the result of function management) to the network device. Specifically, the terminal can report the management result by sending second information to the network device.

[0534] 1. Whether the terminal reports to the network device can be determined according to network indication, or terminal implementation, or protocol specification, or influence on the network device. For example:

[0535] (1) The network device indicates that the terminal needs to report, and then the terminal needs to report.

[0536] (2) For the beam management use case, the set B of the model switched by the terminal is different from the set B of the original model, and the network device needs to reconfigure the set B in the future. In this scenario, the terminal needs to report. If the set B of the model switched by the terminal is the same as the set B of the original model, the network device has no influence, and in this scenario, the terminal can not report.

[0537] (3) The terminal decides whether to report by itself.

[0538] (4) Fallback to non-AI needs to be reported.

[0539] (5) Fallback to the default model needs to be reported.

[0540] 2. The management result reported by the terminal can include at least one of the following:

[0541] (1) Model identifier or index of the first model, i.e., model ID or index decided by the terminal to switch.

[0542] Here, the first model can be a switching model decided by the terminal.

[0543] (2) Function identifier or index of the first function, i.e., function ID or index decided by the terminal to switch.

[0544] Here, the first function can be a switching function decided by the terminal.

[0545] (3) Fallback to non-AI.

[0546] (4) Model fallback indication information, used to indicate that the terminal Fallbacks to the default model.

[0547] (5) Function fallback indication information, used to indicate that the terminal Fallbacks to the default function.

[0548] (6) The switched model / function (i.e., the first model and / or the first function) needs configuration of the network device.

[0549] 3. Request the network device to issue a new configuration.

[0550] For example, for the beam management use case, the model / function of switching corresponds to different set B, and the network device needs to configure the set B corresponding to the model / function of switching. In this case, the terminal may need to request the network device to issue a new configuration. Specifically, this can be implemented by the terminal sending first request information and / or second request information to the network device. The first request information is used to request the network device to configure a first beam set of a first model, and the second request information is used to request the network device to configure a first beam set of a first function.

[0551] (Five) If the network device needs to issue a new configuration, after receiving the first request information / second request information, the network device issues a new configuration, such as a new first beam set (i.e., a first beam set of a first model and / or a first beam set of a first function), to the terminal.

[0552] Scenario three, the network device performs AI model monitoring and makes decisions on model management / control:

[0553] Here, the network device can be a base station, LMF, OAM, etc., but is not limited thereto.

[0554] As shown in FIG. 9, the following details the interaction between the terminal (UE) and the network (NW, i.e., network device) for scenario three:

[0555] (One) The network device issues a measurement configuration to the terminal for configuring the terminal to perform model / function monitoring and / or management. Specifically, the network device can configure the terminal by sending first information to the terminal, wherein the first information can include at least one of the following information:

[0556] 1. Measurement configuration information, which is as follows for different use cases:

[0557] (1) For the beam management use case: the measurement configuration information includes at least one of the following: set B (i.e., a beam set that the terminal needs to measure), set A (i.e., all beams that the terminal needs to predict) or a subset of set A;

[0558] (2) For the CSI compression use case and the CSI prediction use case: the measurement configuration information includes target CSI, etc.

[0559] (3) For the positioning use case: the measurement configuration information includes PRS, etc.

[0560] 2. First indication information, used to indicate that the first information is used for model monitoring and / or function monitoring;

[0561] That is, an indicator indicates that the configuration is for model monitoring and / or function monitoring. It should be noted that if a new message is introduced for configuration, the explicit indicator can not be included in the first information.

[0562] (ii) The terminal reports the measurement results of Set A; the terminal can include the Set A measurement results in one reporting message (such as L1 signaling) or multiple reporting messages.

[0563] (iii) The network device performs model monitoring and / or function monitoring, calculates performance indicators / KPIs, and makes decisions on model management and / or function management.

[0564] (iv) The network device can send management decision information to the terminal to notify the terminal of the decision on model management and / or function management. For example:

[0565] (1) Model identifier or index of at least one second model, i.e., model ID or index of the network device decision switching.

[0566] Here, the second model can be a switching model decided by the network device.

[0567] (2) First fallback indication information, used to instruct the terminal to fallback to non-artificial intelligence operation, i.e., Fallback to non-AI.

[0568] (3) Second fallback indication information, used to instruct the terminal to fallback to a preset model, i.e., instruct the terminal to Fallback to a default model.

[0569] (4) Third fallback indication information, used to instruct the terminal to fallback to a preset function, i.e., instruct the terminal to Fallback to a default function.

[0570] The terminal performs corresponding operations based on the indication of the network device (such as a base station), such as performing model switching or fallback.

[0571] In the above embodiments, the monitoring and management process of the AI model / function is given, the specific content of the interaction between the network device and the terminal in the process is defined, and different information is defined for different use cases, thereby providing a specific monitoring and management method for the application of the AI model / function in the air interface. In this way, through the monitoring and management of the model / function, the terminal can use a better model for model inference, which will be a globally optimal model rather than a locally optimal model, and can improve the model prediction accuracy and / or system performance.

[0572] The monitoring management method of the embodiment can enable the terminal to use a better model for model inference through interaction between the network device and the terminal, and can consider both the improvement of model prediction accuracy and the influence of the overall system performance and / or overhead during model management, thereby avoiding the introduction of excessive signaling interaction or other overhead for improving model prediction accuracy.

[0573] As shown in FIG. 10, the monitoring management method of an embodiment of the present disclosure, applied to a network device, includes the following steps:

[0574] In step 1001, first information is sent to a terminal, and the first information is used to configure information related to the supervision of a model and / or a function.

[0575] In step 1002, second information sent by the terminal is received.

[0576] The second information includes at least one of the following:

[0577] The model identifier or index of the at least one candidate model;

[0578] The function identifier or index of the at least one candidate function;

[0579] The first beam set of the at least one candidate model;

[0580] The first beam set of the at least one candidate function;

[0581] The first request information is used to request the network device to configure the first beam set of the first model.

[0582] The second request information is used to request the network device to configure the first beam set of the first function.

[0583] It should be noted that the network device-side model monitoring management method provided by the embodiment of the present disclosure is similar to the method implemented by the above-mentioned monitoring management method embodiment applied to the terminal, and can achieve the same technical effects. Therefore, the same parts and beneficial effects of the method embodiment in this embodiment will not be described in detail.

[0584] In this embodiment, the interaction content between the terminal and the network during model monitoring and model management is defined, wherein the network device receives the second information sent by the terminal, the second information can include the first beam set of at least one candidate model / candidate function, so that the network model can refer to the information to make management decisions, and the second information can also include the first request information and / or the second request information, so that in the scenario where the terminal makes management decisions, the network device can be requested to configure the first beam set for the first model and / or the first function. In this way, through the interaction between the network device and the terminal, the terminal can use a better model for model inference, and can avoid the case of introducing too much signaling interaction or other overhead to improve the prediction accuracy of the model.

[0585] Optionally, the method further comprises at least one of the following:

[0586] (1) determining at least one second model from the at least one candidate model, and sending management decision information to the terminal.

[0587] Here, at least one second model can be determined according to the first beam set of the at least one candidate model.

[0588] (2) determining at least one second function from the at least one candidate function, and sending management decision information to the terminal.

[0589] Here, at least one second function can be determined according to the first beam set of the at least one candidate function.

[0590] (3) sending configuration information of the first beam set of the first model to the terminal.

[0591] Here, the configuration information of the first beam set of the first model can be sent to the terminal according to the first request information.

[0592] (4) sending configuration information of the first beam set of the first function to the terminal.

[0593] Here, the configuration information of the first beam set of the first function can be sent to the terminal according to the second request information.

[0594] Optionally, the management decision information comprises at least one of the following:

[0595] a model identifier or index of at least one second model;

[0596] a function identifier or index of at least one second function;

[0597] a first activation indication for instructing the terminal to activate at least one second model;

[0598] a second activation indication for instructing the terminal to activate at least one second function;

[0599] a third activation indication, used to instruct the terminal to deactivate at least one third model;

[0600] a fourth activation indication, used to instruct the terminal to deactivate at least one third function;

[0601] a first switching indication, used to instruct the terminal to switch to a second model;

[0602] a second switching indication, used to instruct the terminal to switch to a second function;

[0603] a condition for applying the second model;

[0604] a condition for applying the second function;

[0605] first fallback indication information, used to instruct the terminal to fallback to a non-artificial intelligence operation;

[0606] second fallback indication information, used to instruct the terminal to fallback to a preset model;

[0607] third fallback indication information, used to instruct the terminal to fallback to a preset function.

[0608] Optionally, the second information further comprises at least one of the following:

[0609] a performance index of the third model;

[0610] a performance index of the third function;

[0611] a list of available candidate models;

[0612] a list of available candidate functions;

[0613] a performance index of at least one candidate model;

[0614] a performance index of at least one candidate function;

[0615] key information of at least one candidate model;

[0616] key information of at least one candidate function;

[0617] model fallback indication information;

[0618] function fallback indication information;

[0619] condition information of the terminal.

[0620] Optionally, the first information comprises at least one of the following:

[0621] measurement configuration information;

[0622] a performance index required to be monitored by the terminal;

[0623] a key performance indicator (KPI) that the terminal needs to monitor;

[0624] first indication information, used to indicate that the first information is used for model monitoring and / or function monitoring;

[0625] second indication information, used to indicate periodic information of the terminal reporting the second information;

[0626] third indication information, used to indicate whether the terminal needs to report the performance indicator and / or the KPI;

[0627] fourth indication information, used to indicate whether the terminal is allowed to report management suggestion information;

[0628] a model and / or a function supported by the network device;

[0629] a second beam set corresponding to the model supported by the network device;

[0630] a second beam set corresponding to the function supported by the network device;

[0631] a configuration supported by the network device;

[0632] fifth indication information, used to indicate whether the terminal needs to report a management result;

[0633] an event triggering the terminal to perform model management and / or function management;

[0634] an event triggering the terminal to report the second information;

[0635] sixth indication information, used to indicate that the terminal reports a management result.

[0636] The model monitoring and management method of this embodiment, through the interaction between the network device and the terminal, the terminal can use a better model for model inference, and in the process of model management, both the improvement of model prediction accuracy and the influence of the overall system performance and / or overhead are considered, and the case that too much signaling interaction or other overhead is introduced to improve the model prediction accuracy can be avoided.

[0637] As shown in FIG. 11, a model monitoring and management apparatus of an embodiment of the present disclosure is applied to a terminal and includes:

[0638] a first receiving module 1110, configured to receive first information sent by a network device, the first information being used to configure information related to the supervision of a model and / or a function;

[0639] a first sending module 1120, configured to send second information to the network device;

[0640] The second information includes at least one of the following:

[0641] A model identifier or index of the at least one candidate model;

[0642] A function identifier or index of the at least one candidate function;

[0643] A first beam set of the at least one candidate model;

[0644] A first beam set of the at least one candidate function;

[0645] First request information for requesting the network device to configure a first beam set of the first model;

[0646] Second request information for requesting the network device to configure a first beam set of the first function.

[0647] In this embodiment, the interaction content between the terminal and the network during model monitoring and model management is defined. The terminal sends second information to the network device, which can include a first beam set of at least one candidate model / candidate function, so that the network model can refer to the information to make a management decision. The second information can also include first request information and / or second request information, so that in the scenario where the terminal makes a management decision, the network device can be requested to configure a first beam set for the first model and / or the first function. In this way, through the interaction between the network device and the terminal, the terminal can use a better model for model inference and can avoid introducing too much signaling interaction or other overhead to improve model prediction accuracy.

[0648] Optionally, the apparatus further includes:

[0649] A third receiving module configured to receive management decision information sent by the network device;

[0650] A fourth receiving module configured to receive configuration information of a first beam set of the first model sent by the network device;

[0651] A fifth receiving module configured to receive configuration information of a first beam set of the first function sent by the network device.

[0652] Optionally, the management decision information includes at least one of the following:

[0653] A model identifier or index of at least one second model;

[0654] A function identifier or index of at least one second function;

[0655] A first activation indication for instructing the terminal to activate at least one second model;

[0656] a second activation indication for instructing the terminal to activate at least one second function;

[0657] a third activation indication for instructing the terminal to deactivate at least one third model;

[0658] a fourth activation indication for instructing the terminal to deactivate at least one third function;

[0659] a first switching indication for instructing the terminal to switch to the second model;

[0660] a second switching indication for instructing the terminal to switch to the second function;

[0661] a condition for applying the second model;

[0662] a condition for applying the second function;

[0663] first fallback indication information for instructing the terminal to fallback to a non-artificial intelligence operation;

[0664] second fallback indication information for instructing the terminal to fallback to a preset model;

[0665] third fallback indication information for instructing the terminal to fallback to a preset function.

[0666] Optionally, the second information further comprises at least one of:

[0667] a performance index of the third model;

[0668] a performance index of the third function;

[0669] a list of available candidate models;

[0670] a list of available candidate functions;

[0671] a performance index of at least one candidate model;

[0672] a performance index of at least one candidate function;

[0673] key information of at least one candidate model;

[0674] key information of at least one candidate function;

[0675] model fallback indication information;

[0676] function fallback indication information;

[0677] condition information of the terminal

[0678] Optionally, the first information comprises at least one of:

[0679] measurement configuration information;

[0680] a performance indicator that the terminal needs to monitor;

[0681] a key performance indicator KPI that the terminal needs to monitor;

[0682] first indication information, used to indicate that the first information is used for model monitoring and / or function monitoring;

[0683] second indication information, used to indicate periodic information of the terminal reporting the second information;

[0684] third indication information, used to indicate whether the terminal needs to report the performance indicator and / or the KPI;

[0685] fourth indication information, used to indicate whether the terminal is allowed to report management suggestion information;

[0686] a model and / or a function supported by the network device;

[0687] a second beam set corresponding to the model supported by the network device;

[0688] a second beam set corresponding to the function supported by the network device;

[0689] a configuration supported by the network device;

[0690] fifth indication information, used to indicate whether the terminal needs to report a management result;

[0691] an event triggering the terminal to perform model management and / or function management;

[0692] an event triggering the terminal to report the second information;

[0693] sixth indication information, used to indicate that the terminal reports a management result.

[0694] It should be noted that the model monitoring management apparatus provided by the embodiments of the present disclosure can realize all the method steps realized by the monitoring management method applied to the terminal, and achieve the same technical effects. Therefore, the same parts and beneficial effects of the method embodiments will not be described in detail.

[0695] As shown in FIG. 12, a model monitoring management apparatus of an embodiment of the present disclosure, applied to a network device, comprises:

[0696] a second sending module 1210, configured to send first information to a terminal, wherein the first information is used to configure information related to supervision of a model and / or a function;

[0697] a second receiving module 1220, configured to receive second information sent by the terminal;

[0698] The second information includes at least one of the following:

[0699] a model identifier or index of the at least one candidate model;

[0700] a function identifier or index of the at least one candidate function;

[0701] a first beam set of the at least one candidate model;

[0702] a first beam set of the at least one candidate function;

[0703] first request information for requesting the network device to configure a first beam set for the first model;

[0704] second request information for requesting the network device to configure a first beam set for the first function.

[0705] In this embodiment, the interaction content between the terminal and the network during model monitoring and model management is defined, wherein the network device receives the second information sent by the terminal, the second information can include a first beam set of at least one candidate model / candidate function, so that the network model can refer to the information to make a management decision, and the second information can also include first request information and / or second request information, so that in the scenario where the terminal makes a management decision, the network device can be requested to configure a first beam set for the first model and / or the first function. In this way, through the interaction between the network device and the terminal, the terminal can use a better model for model inference and can avoid introducing too much signaling interaction or other overhead to improve model prediction accuracy.

[0706] Optionally, the apparatus further includes:

[0707] a first processing module configured to determine at least one second model from the at least one candidate model and send management decision information to the terminal;

[0708] a second processing module configured to determine at least one second function from the at least one candidate function and send management decision information to the terminal;

[0709] a third sending module configured to send configuration information of a first beam set of the first model to the terminal;

[0710] a fourth sending module configured to send configuration information of a first beam set of the first function to the terminal.

[0711] Optionally, the management decision information includes at least one of the following:

[0712] a model identifier or index of the at least one second model;

[0713] a function identifier or index of the at least one second function;

[0714] a first activation indication for instructing the terminal to activate the at least one second model;

[0715] a second activation indication for instructing the terminal to activate the at least one second function;

[0716] a third activation indication for instructing the terminal to deactivate the at least one third model;

[0717] a fourth activation indication for instructing the terminal to deactivate the at least one third function;

[0718] a first switching indication for instructing the terminal to switch to the second model;

[0719] a second switching indication for instructing the terminal to switch to the second function;

[0720] a condition for applying the second model;

[0721] a condition for applying the second function;

[0722] first fallback indication information for instructing the terminal to fallback to a non-artificial intelligence operation;

[0723] second fallback indication information for instructing the terminal to fallback to a preset model;

[0724] third fallback indication information for instructing the terminal to fallback to a preset function.

[0725] Optionally, the second information further comprises at least one of the following:

[0726] a performance index of the third model;

[0727] a performance index of the third function;

[0728] a list of available candidate models;

[0729] a list of available candidate functions;

[0730] a performance index of the at least one candidate model;

[0731] a performance index of the at least one candidate function;

[0732] key information of the at least one candidate model;

[0733] key information of the at least one candidate function;

[0734] model fallback indication information;

[0735] function fallback indication information;

[0736] condition information of the terminal.

[0737] Optionally, the first information comprises at least one of:

[0738] measurement configuration information;

[0739] a performance indicator required to be monitored by the terminal;

[0740] a key performance indicator (KPI) required to be monitored by the terminal;

[0741] first indication information, used for indicating that the first information is used for model monitoring and / or function monitoring;

[0742] second indication information, used for indicating periodic information of the terminal reporting the second information;

[0743] third indication information, used for indicating whether the terminal needs to report the performance indicator and / or the KPI;

[0744] fourth indication information, used for indicating whether the terminal is allowed to report management suggestion information;

[0745] a model and / or a function supported by the network device;

[0746] a second beam set corresponding to the model supported by the network device;

[0747] a second beam set corresponding to the function supported by the network device;

[0748] a configuration supported by the network device;

[0749] fifth indication information, used for indicating whether the terminal needs to report a management result;

[0750] an event triggering the terminal to perform model management and / or function management;

[0751] an event triggering the terminal to report the second information;

[0752] sixth indication information, used for indicating that the terminal reports the management result.

[0753] It should be noted that the model monitoring and management apparatus provided by the embodiments of the present disclosure can realize all the method steps achieved by the monitoring and management method applied to the network device, and achieve the same technical effects. Therefore, the same parts and beneficial effects of the method embodiments will not be described in detail.

[0754] As shown in FIG. 13, a terminal 1300 of an embodiment of the present disclosure includes a processor 1310 and a transceiver 1320, wherein the transceiver 1320 is configured to:

[0755] receive first information sent by a network device, the first information being used for configuring information related to model and / or function supervision;

[0756] send second information to the network device;

[0757] wherein the second information comprises at least one of:

[0758] model identification or index of at least one candidate model;

[0759] function identification or index of at least one candidate function;

[0760] first beam set of at least one candidate model;

[0761] first beam set of at least one candidate function;

[0762] first request information for requesting the network device to configure the first beam set of the first model;

[0763] second request information for requesting the network device to configure the first beam set of the first function.

[0764] In this embodiment, the interaction content between the terminal and the network during model monitoring and model management is defined, wherein the terminal sends second information to the network device, the second information can include the first beam set of at least one candidate model / candidate function, so that the network model can refer to the information to make management decisions, and the second information can also include first request information and / or second request information, so that in the scenario of terminal management decision, the network device can be requested to configure the first beam set for the first model and / or the first function. In this way, through the interaction between the network device and the terminal, the terminal can use a better model for model inference, and can avoid the case of introducing too much signaling interaction or other overhead to improve the prediction accuracy of the model.

[0765] Optionally, the transceiver 1320 is further configured to perform at least one of:

[0766] receive management decision information sent by the network device;

[0767] receive configuration information of the first beam set of the first model sent by the network device;

[0768] receive configuration information of the first beam set of the first function sent by the network device.

[0769] Optionally, the management decision information comprises at least one of:

[0770] model identification or index of at least one second model;

[0771] a function identifier or index of the at least one second function;

[0772] a first activation indication for instructing the terminal to activate the at least one second model;

[0773] a second activation indication for instructing the terminal to activate the at least one second function;

[0774] a third activation indication for instructing the terminal to deactivate the at least one third model;

[0775] a fourth activation indication for instructing the terminal to deactivate the at least one third function;

[0776] a first switching indication for instructing the terminal to switch to the second model;

[0777] a second switching indication for instructing the terminal to switch to the second function;

[0778] a condition for applying the second model;

[0779] a condition for applying the second function;

[0780] first fallback indication information for instructing the terminal to fallback to a non-artificial intelligence operation;

[0781] second fallback indication information for instructing the terminal to fallback to a preset model;

[0782] third fallback indication information for instructing the terminal to fallback to a preset function.

[0783] Optionally, the second information further comprises at least one of the following:

[0784] a performance index of the third model;

[0785] a performance index of the third function;

[0786] a list of available candidate models;

[0787] a list of available candidate functions;

[0788] a performance index of the at least one candidate model;

[0789] a performance index of the at least one candidate function;

[0790] key information of the at least one candidate model;

[0791] key information of the at least one candidate function;

[0792] model fallback indication information;

[0793] function fallback indication information;

[0794] condition information of the terminal.

[0795] Optionally, the first information comprises at least one of:

[0796] measurement configuration information;

[0797] a performance indicator required to be monitored by the terminal;

[0798] a key performance indicator (KPI) required to be monitored by the terminal;

[0799] first indication information, used for indicating that the first information is used for model monitoring and / or function monitoring;

[0800] second indication information, used for indicating periodic information of the terminal reporting the second information;

[0801] third indication information, used for indicating whether the terminal needs to report the performance indicator and / or the KPI;

[0802] fourth indication information, used for indicating whether the terminal is allowed to report management suggestion information;

[0803] a model and / or a function supported by the network device;

[0804] a second beam set corresponding to the model supported by the network device;

[0805] a second beam set corresponding to the function supported by the network device;

[0806] a configuration supported by the network device;

[0807] fifth indication information, used for indicating whether the terminal needs to report a management result;

[0808] an event triggering the terminal to perform model management and / or function management;

[0809] an event triggering the terminal to report the second information;

[0810] sixth indication information, used for indicating that the terminal reports the management result.

[0811] It should be noted that the terminal provided in the embodiment of the present disclosure can implement all the method steps achieved by the monitoring management method applied to the terminal, and achieve the same technical effects. Therefore, the same parts and beneficial effects of the method embodiment will not be described in detail.

[0812] As shown in FIG. 14, a network device 1400 in an embodiment of the present disclosure includes a processor 1410 and a transceiver 1420, wherein the transceiver 1420 is configured to:

[0813] send first information to the terminal, the first information being used for configuring information related to supervision of the model and / or the function;

[0814] receive second information sent by the terminal;

[0815] The second information includes at least one of the following:

[0816] a model identifier or index of the at least one candidate model;

[0817] a function identifier or index of the at least one candidate function;

[0818] a first beam set of the at least one candidate model;

[0819] a first beam set of the at least one candidate function;

[0820] first request information for requesting the network device to configure the first beam set of the first model;

[0821] second request information for requesting the network device to configure the first beam set of the first function.

[0822] In this embodiment, the interaction content between the terminal and the network during model monitoring and model management is defined, wherein the network device receives the second information sent by the terminal, the second information can include the first beam set of the at least one candidate model / candidate function, so that the network model can refer to the information to make management decisions. The second information can also include first request information and / or second request information, so that in the scenario where the terminal makes management decisions, the network device can be requested to configure the first beam set for the first model and / or the first function. In this way, through the interaction between the network device and the terminal, the terminal can use a better model for model inference and can avoid the case of introducing too much signaling interaction or other overhead to improve the prediction accuracy of the model.

[0823] Optionally, the processor 1410 is configured to:

[0824] determine at least one second model from the at least one candidate model, and send management decision information to the terminal;

[0825] determine at least one second function from the at least one candidate function, and send management decision information to the terminal;

[0826] send configuration information of the first beam set of the first model to the terminal;

[0827] send configuration information of the first beam set of the first function to the terminal.

[0828] Optionally, the management decision information includes at least one of the following:

[0829] a model identifier or index of the at least one second model;

[0830] a function identifier or index of the at least one second function;

[0831] a first activation instruction for instructing the terminal to activate the at least one second model;

[0832] a second activation instruction for instructing the terminal to activate the at least one second function;

[0833] a third activation instruction for instructing the terminal to deactivate the at least one third model;

[0834] a fourth activation instruction for instructing the terminal to deactivate the at least one third function;

[0835] a first switching instruction for instructing the terminal to switch to the second model;

[0836] a second switching instruction for instructing the terminal to switch to the second function;

[0837] a condition for applying the second model;

[0838] a condition for applying the second function;

[0839] first fallback instruction information for instructing the terminal to fallback to a non-artificial intelligence operation;

[0840] second fallback instruction information for instructing the terminal to fallback to a preset model;

[0841] third fallback instruction information for instructing the terminal to fallback to a preset function.

[0842] Optionally, the second information further comprises at least one of the following:

[0843] a performance indicator of the third model;

[0844] a performance indicator of the third function;

[0845] a list of available candidate models;

[0846] a list of available candidate functions;

[0847] a performance indicator of the at least one candidate model;

[0848] a performance indicator of the at least one candidate function;

[0849] key information of the at least one candidate model;

[0850] key information of the at least one candidate function;

[0851] model fallback instruction information;

[0852] function fallback indication information;

[0853] condition information of the terminal.

[0854] Optionally, the first information comprises at least one of:

[0855] measurement configuration information;

[0856] performance indicators that the terminal needs to monitor;

[0857] key performance indicators (KPIs) that the terminal needs to monitor;

[0858] first indication information, used to indicate that the first information is used for model monitoring and / or function monitoring;

[0859] second indication information, used to indicate periodic information of the terminal reporting the second information;

[0860] third indication information, used to indicate whether the terminal needs to report the performance indicators and / or the KPIs;

[0861] fourth indication information, used to indicate whether the terminal is allowed to report management suggestion information;

[0862] models and / or functions supported by the network device;

[0863] a second beam set corresponding to the models supported by the network device;

[0864] a second beam set corresponding to the functions supported by the network device;

[0865] configuration supported by the network device;

[0866] fifth indication information, used to indicate whether the terminal needs to report management results;

[0867] an event triggering the terminal to perform model management and / or function management;

[0868] an event triggering the terminal to report the second information;

[0869] sixth indication information, used to indicate that the terminal reports management results.

[0870] It should be noted that the above network device provided by the embodiments of the present disclosure can implement all the method steps achieved by the above monitoring management method applied to the network device, and achieve the same technical effects. Therefore, the same parts and beneficial effects of the method embodiments in the embodiments will not be described in detail.

[0871] Another embodiment of the present disclosure is a terminal, as shown in Figure 15, comprising a transceiver 1510, a processor 1500, a memory 1520, and a program or instruction stored in the memory 1520 and executable on the processor 1500; the processor 1500 implements the above-mentioned monitoring management method applied to the terminal when executing the program or instruction.

[0872] The transceiver 1510 is configured to receive and send data under the control of the processor 1500.

[0873] In Figure 15, the bus architecture can include any number of interconnected buses and bridges, which link various circuits together, including the processor 1500 and the memory 1520 represented by one or more processors and memories. The bus architecture can also link various other circuits such as peripheral devices, voltage stabilizers, and power management circuits, which are well known in the art, and therefore, will not be further described herein. The bus interface provides an interface. The transceiver 1510 can be a plurality of elements, i.e., including a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium. The user interface 1530 can also be an interface that can be externally connected to the required device, including but not limited to a keypad, a display, a speaker, a microphone, a joystick, etc.

[0874] The processor 1500 is responsible for managing the bus architecture and general processing, and the memory 1520 can store data used by the processor 1500 in performing operations.

[0875] Another embodiment of the present disclosure is a network device, as shown in Figure 16, comprising a transceiver 1610, a processor 1600, a memory 1620, and a program or instruction stored in the memory 1620 and executable on the processor 1600; the processor 1600 implements the above-mentioned monitoring management method applied to the network device when executing the program or instruction.

[0876] The transceiver 1610 is configured to receive and send data under the control of the processor 1600.

[0877] In Figure 16, the bus architecture can include any number of interconnected buses and bridges, specifically, various circuit links between one or more processors, represented by the processor 1600, and memory, represented by the memory 1620. The bus architecture can also link various other circuitry, such as peripheral devices, voltage stabilizers, and power management circuitry, which are well known in the art, and therefore, will not be further described herein. The bus interface provides an interface. The transceiver 1610 can be a plurality of elements, i.e., including a transmitter and a receiver, which provide a unit for communicating with various other devices on a transmission medium. The processor 1600 is responsible for managing the bus architecture and general processing, and the memory 1620 can store data used by the processor 1600 in performing operations.

[0878] The embodiment of the present disclosure further provides a computer program product, comprising computer instructions, which, when executed by a processor, implement each process of the method embodiments shown in Figure 6 or Figure 10, and can achieve the same technical effects. To avoid repetition, details are not described herein.

[0879] The embodiment of the present disclosure provides a readable storage medium, which stores a program or instructions, and when the program or instructions are executed by a processor, the steps of the monitoring management method described above are implemented, and the same technical effects can be achieved. To avoid repetition, details are not described herein. The computer readable storage medium, such as a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0880] It is further noted that the terminal described in the specification includes but is not limited to a smart phone, a tablet computer, etc., and many functional components described are referred to as modules, in order to more particularly emphasize the independence of their implementation.

[0881] In the embodiment of the present disclosure, the module can be implemented by software, so as to be executed by various types of processors. For example, an identified executable code module can include one or more physical or logical blocks of computer instructions, which can be constructed as objects, processes or functions, for example. However, the executable code of the identified module does not need to be physically located together, but can include different instructions stored in different bits, which, when logically combined together, constitute the module and achieve the specified purpose of the module.

[0882] In practice, an executable code module can be a single instruction or many instructions, and can even be distributed across multiple different code segments, different programs, and across multiple memory devices. Similarly, operational data can be identified within the module and can be implemented in any suitable form and organized within any suitable type of data structure. This operational data can be collected as a single dataset or distributed across different locations (including different storage devices), and can exist, at least in part, solely as electronic signals within the system or network.

[0883] When a module can be implemented using software, considering the current level of hardware technology, modules that can be implemented in software can be implemented using hardware circuits by those skilled in the art to achieve the corresponding functions, without considering cost. These hardware circuits include conventional Very Large Scale Integration (VLSI) circuits or gate arrays, as well as existing semiconductors such as logic chips and transistors, or other discrete components. Modules can also be implemented using programmable hardware devices, such as field-programmable gate arrays, programmable array logic, and programmable logic devices.

[0884] The exemplary embodiments described above are with reference to the accompanying drawings. Many different forms and embodiments are feasible without departing from the spirit and teaching of this disclosure. Therefore, this disclosure should not be construed as limiting the exemplary embodiments set forth herein. Rather, these exemplary embodiments are provided to make this disclosure complete and convey the scope of this disclosure to those skilled in the art. In these drawings, component dimensions and relative dimensions may be exaggerated for clarity. The terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. As used herein, unless clearly indicated otherwise, the singular forms “a,” “an,” and “the” are intended to include all such forms. It will be further understood that the terms “comprising” and / or “including”, when used in this specification, indicate the presence of the stated features, integers, steps, operations, components, and / or elements, but do not exclude the presence or addition of one or more other features, integers, steps, operations, components, and / or groups thereof. Unless otherwise indicated, when stated, a range of values ​​includes the upper and lower limits of the range and any subranges in between.

[0885] The above description represents the preferred embodiments of this disclosure. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles described herein, and these improvements and modifications should also be considered within the scope of protection of this disclosure.

Claims

1. A monitoring management method applied to a terminal, the method comprising: receiving first information sent by a network device, the first information being used for configuring information related to model and / or function supervision; and sending second information to the network device; wherein the second information comprises at least one of the following: model identification or index of at least one candidate model; function identification or index of at least one candidate function; first beam set of the at least one candidate model; first beam set of the at least one candidate function; first request information used for requesting the network device to configure the first beam set of the first model; and second request information used for requesting the network device to configure the first beam set of the first function.

2. The method of claim 1, further comprising at least one of the following: receiving management decision information sent by the network device; receiving configuration information of the first beam set of the first model sent by the network device; and receiving configuration information of the first beam set of the first function sent by the network device; wherein the management decision information comprises at least one of the following: model identification or index of at least one second model; function identification or index of at least one second function; first activation indication used for instructing the terminal to activate the at least one second model; second activation indication used for instructing the terminal to activate the at least one second function; third activation indication used for instructing the terminal to deactivate at least one third model; fourth activation indication used for instructing the terminal to deactivate at least one third function; first switching indication used for instructing the terminal to switch to the second model; second switching indication used for instructing the terminal to switch to the second function; condition for applying the second model; condition for applying the second function; first fallback indication information used for instructing the terminal to fallback to non-artificial intelligence operation; second fallback indication information used for instructing the terminal to fallback to a preset model; and third fallback indication information used for instructing the terminal to fallback to a preset function; wherein the second information further comprises at least one of the following: performance indicator of a third model; performance indicator of a third function; list of available candidate models; list of available candidate functions; performance indicator of at least one candidate model; performance indicator of at least one candidate function; key information of at least one candidate model; key information of at least one candidate function; model fallback indication information; function fallback indication information; and condition information of the terminal; wherein the first information comprises at least one of the following: measurement configuration information; performance indicator to be monitored by the terminal; key performance indicator (KPI) to be monitored by the terminal; first indication information used for indicating that the first information is used for model monitoring and / or function monitoring; second indication information used for indicating periodicity information of the terminal reporting the second information; third indication information used for indicating whether the terminal needs to report the performance indicator and / or the KPI; fourth indication information used for indicating whether the terminal is allowed to report management suggestion information; model and / or function supported by the network device; second beam set corresponding to the model supported by the network device; and second beam set corresponding to the function supported by the network device. ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ 3. The method of claim 2, wherein, ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ 4. The method of claim 1, wherein, ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ 5. The method of claim 1, wherein, ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ The configuration supported by the network device; Fifth indication information, used for indicating whether the terminal needs to report a management result; An event triggering the terminal to perform model management and / or function management; An event triggering the terminal to report the second information; Sixth indication information, used for indicating the terminal to report a management result.

6. A monitoring management method, applied to a network device, the method comprising: sending first information to a terminal, the first information being used for configuring information related to monitoring of a model and / or a function; receiving second information sent by the terminal; The second information includes at least one of the following: Model identifier or index of at least one candidate model; Function identifier or index of at least one candidate function; First beam set of at least one candidate model; First beam set of at least one candidate function; First request information, used for requesting the network device to configure a first beam set of a first model; Second request information, used for requesting the network device to configure a first beam set of a first function.

7. The method of claim 6, further comprising at least one of the following: determining at least one second model from the at least one candidate model, and sending management decision information to the terminal; determining at least one second function from the at least one candidate function, and sending management decision information to the terminal; sending configuration information of the first beam set of the first model to the terminal; sending configuration information of the first beam set of the first function to the terminal.

8. The method of claim 7, wherein, The management decision information includes at least one of the following: Model identifier or index of at least one second model; Function identifier or index of at least one second function; First activation indication, used for instructing the terminal to activate at least one second model; Second activation indication, used for instructing the terminal to activate at least one second function; Third activation indication, used for instructing the terminal to deactivate at least one third model; Fourth activation indication, used for instructing the terminal to deactivate at least one third function; First switching indication, used for instructing the terminal to switch to a second model; Second switching indication, used for instructing the terminal to switch to a second function; Condition for applying the second model; Condition for applying the second function; First fallback indication information, used for instructing the terminal to fallback to a non-artificial intelligence operation; Second fallback indication information, used for instructing the terminal to fallback to a preset model; Third fallback indication information, used for instructing the terminal to fallback to a preset function.

9. The method of claim 6, wherein, The second information further includes at least one of the following: Performance indicator of a third model; Performance indicator of a third function; List of available candidate models; List of available candidate functions; Performance indicator of at least one candidate model; Performance indicator of at least one candidate function; Key information of at least one candidate model; Key information of at least one candidate function; Model fallback indication information; Function fallback indication information; Condition information of the terminal.

10. The method of claim 6, wherein, The first information includes at least one of the following: Measurement configuration information; Performance indicator to be monitored by the terminal; Key performance indicator (KPI) to be monitored by the terminal; First indication information, used for indicating that the first information is used for model monitoring and / or function monitoring; Second indication information, used for indicating periodicity information of the terminal reporting the second information; Third indication information, used for indicating whether the terminal needs to report the performance index and / or the KPI; Fourth indication information, used for indicating whether the terminal is allowed to report management suggestion information; A model and / or a function supported by the network device; A second beam set corresponding to the model supported by the network device; A second beam set corresponding to the function supported by the network device; Configuration supported by the network device; Fifth indication information, used for indicating whether the terminal needs to report a management result; An event triggering the terminal to perform model management and / or function management; An event triggering the terminal to report the second information; Sixth indication information, used for indicating the terminal to report a management result.

11. A model monitoring management apparatus, applied to a terminal, the apparatus comprising: A first receiving module, configured to receive first information sent by a network device, the first information being used for configuring information related to supervision of a model and / or a function; A first sending module, configured to send second information to the network device; The second information comprises at least one of the following: Model identification or index of at least one candidate model; Function identification or index of at least one candidate function; First beam set of the at least one candidate model; First beam set of the at least one candidate function; First request information, used for requesting the network device to configure the first beam set of the first model; Second request information, used for requesting the network device to configure the first beam set of the first function.

12. A model monitoring management apparatus, applied to a network device, the apparatus comprising: A second sending module, configured to send first information to a terminal, the first information being used for configuring information related to supervision of a model and / or a function; A second receiving module, configured to receive second information sent by the terminal; The second information comprises at least one of the following: Model identification or index of at least one candidate model; Function identification or index of at least one candidate function; First beam set of the at least one candidate model; First beam set of the at least one candidate function; First request information, used for requesting the network device to configure the first beam set of the first model; Second request information, used for requesting the network device to configure the first beam set of the first function.

13. A terminal comprising: A transceiver and a processor; the transceiver is configured to: Receive first information sent by a network device, the first information being used for configuring information related to supervision of a model and / or a function; Send second information to the network device; The second information comprises at least one of the following: Model identification or index of at least one candidate model; Function identification or index of at least one candidate function; First beam set of the at least one candidate model; First beam set of the at least one candidate function; First request information, used for requesting the network device to configure the first beam set of the first model; Second request information, used for requesting the network device to configure the first beam set of the first function.

14. A network device comprising: A transceiver and a processor; the transceiver is configured to: Send first information to a terminal, the first information being used for configuring information related to supervision of a model and / or a function; receive second information sent by the terminal; wherein the second information comprises at least one of: a model identifier or index of the at least one candidate model; a function identifier or index of the at least one candidate function; a first beam set of the at least one candidate model; a first beam set of the at least one candidate function; first request information for requesting the network device to configure the first beam set of the first model; second request information for requesting the network device to configure the first beam set of the first function.

15. A terminal comprising: a transceiver, a processor, a memory, and a program or instructions stored in the memory and executable in the processor; the processor executes the program or instructions to implement the monitoring management method according to any one of claims 1-5.

16. A network device comprising: a transceiver, a processor, a memory, and a program or instructions stored in the memory and executable in the processor; the processor executes the program or instructions to implement the monitoring management method according to any one of claims 6-10.

17. A computer program product comprising computer instructions, which, when executed by a processor, implement the steps of the monitoring management method according to any one of claims 1-5, or implement the steps of the monitoring management method according to any one of claims 6-10.

18. A readable storage medium having stored thereon a program or instructions, which, when executed by a processor, implement the steps of the monitoring management method according to any one of claims 1-5, or implement the steps of the monitoring management method according to any one of claims 6-10.

Images