Data collection method and apparatus, and device

Abstract

The present invention provides a data collection method and apparatus, and a device. The method is applied to a first device. The method comprises: acquiring measurement data related to artificial intelligence (AI) and / or machine learning (ML); and sending the measurement data to a second device. On the basis of the solution, the data can be acquired by means of the first device, and the second device receives, from the first device, the measurement data related to AI and / or ML.

Description

A data collection method, apparatus and equipment

[0001] This disclosure claims priority to Chinese Patent Application No. 202410976044.1, filed on July 19, 2024, entitled “A Data Collection Method, Apparatus and Device”, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This disclosure relates to the field of communication technology, and in particular to a data collection method, apparatus and device. Background Technology

[0003] Artificial intelligence (AI) and machine learning (ML) models require a large amount of training data during the training phase. This training data is used to teach the model features, adjust parameters, and build predictive models. After deployment, the model needs to perform actual inference or prediction tasks. During the inference or prediction phase, the model needs to process input data and generate corresponding outputs. The inference process requires a large amount of data to validate the model's accuracy, stability, and efficiency. Once deployed in real-world applications, the model needs to be monitored and evaluated to ensure its performance under different environments and data. This requires collecting large amounts of real-time data to monitor the model's performance and may necessitate adjustments and iterations.

[0004] Data collection plays a crucial role throughout the entire lifecycle of artificial intelligence and machine learning. However, due to the large data requirements of AI / ML models, it is often impossible to obtain sufficient data at a single stage to meet the usage needs of AI / ML models. Summary of the Invention

[0005] This disclosure provides a data collection method, apparatus, and device to address the problem that related technologies often cannot obtain sufficient measurement data to meet usage requirements at a single node.

[0006] In a first aspect, to address the aforementioned technical problems, embodiments of this disclosure provide a data collection method applied to a first device, comprising:

[0007] Acquire measurement data related to artificial intelligence (AI) and / or machine learning (ML);

[0008] The measurement data is sent to the second device.

[0009] In some embodiments, acquiring measurement data related to artificial intelligence (AI) and / or machine learning (ML) includes one of the following acquisition methods:

[0010] The measurement data are collected according to the first interval parameter;

[0011] The measurement data is collected when the first triggering condition is met;

[0012] When the first triggering condition is met, the measurement data is collected according to the first interval parameter.

[0013] In some embodiments, sending the measurement data to the second device includes at least one of the following methods:

[0014] The measurement data is sent according to the second interval parameter;

[0015] When the second triggering condition is met, the measurement data is sent;

[0016] The measurement data is sent according to the data acquisition request sent by the second device.

[0017] In some embodiments, the first interval parameter includes at least one of the following: a first time length, a first movement distance, and a first difference between two adjacent measurement results.

[0018] In some embodiments, the first triggering condition includes at least one of the following:

[0019] The first device measures and obtains the measurement data;

[0020] The first device triggers the reporting of Radio Resource Management (RRM) measurement events;

[0021] The first device experienced a radio link failure (RLF).

[0022] The first device experienced a handover failure (HOF).

[0023] The moving speed of the first device is greater than or equal to a preset speed threshold;

[0024] The first device is located in the first geographical region.

[0025] In some embodiments, the second interval parameter includes at least one of the following: a second time length, a second movement distance, and a second difference between two adjacent measurement results.

[0026] In some embodiments, where the transmission method includes transmitting the measurement data according to a data acquisition request sent by the second device, the method further includes one of the following before receiving the data acquisition request sent by the second device:

[0027] Based on the third interval parameter, send the first request message;

[0028] When the second triggering condition is met, the first request message is sent;

[0029] When the second triggering condition is met, the first request message is sent according to the third interval parameter.

[0030] In some embodiments, the second triggering condition includes at least one of the following:

[0031] The first device acquires the measurement data;

[0032] The measurement data reaches the storage space threshold;

[0033] The power level of the first device is less than or equal to a preset power threshold.

[0034] The first device is located in the second geographical region.

[0035] In some embodiments, the third interval parameter includes at least one of the following: a third time length, a third movement distance, and a third difference between two adjacent measurement results.

[0036] In some embodiments, collecting the measurement data according to a first interval parameter includes:

[0037] When the first device is located in the third geographic region, the measurement data is collected according to the first interval parameter; and / or,

[0038] While the first device is within a first time range, the measurement data is collected according to a first interval parameter.

[0039] In some embodiments, sending the measurement data according to the second interval parameter includes:

[0040] When the first device is located in the fourth geographic region, the measurement data is sent to the second device according to the second interval parameter; and / or,

[0041] When the second time range is in effect, the measurement data is sent to the second device according to the second interval parameter.

[0042] In some embodiments, sending the first request message according to the third interval parameter includes:

[0043] When the first device is in the fifth geographic region, the first request message is sent according to the third interval parameter; and / or,

[0044] When the first device is within the third time range, the first request message is sent according to the third interval parameter.

[0045] In some embodiments, the AI ​​and / or ML-related measurement data includes at least one of the following:

[0046] The time information of the measurement data is obtained by measurement;

[0047] Measurement results related to AI and / or ML;

[0048] Evaluation results related to AI and / or ML;

[0049] The measurement data corresponds to the relevant information about the cell;

[0050] Configuration information related to AI and / or ML.

[0051] In some embodiments, the above data collection method further includes:

[0052] Receive configuration information related to AI and / or ML sent by a third device;

[0053] The configuration information includes at least one of the following:

[0054] First configuration information related to the method of acquiring the measurement data;

[0055] Second configuration information related to the storage of the measurement data;

[0056] Third configuration information related to the method of transmitting the measurement data;

[0057] Fourth configuration information related to state transition processing;

[0058] The fifth configuration information related to community change processing.

[0059] In some embodiments, the fourth configuration information includes at least one of the following:

[0060] The first piece of information is used to indicate whether to stop collecting the measurement data in the event of a change in the Radio Resource Control (RRC) status;

[0061] The second piece of information is used to indicate whether to delete the configuration information related to AI and / or ML in the event of a change in RRC status;

[0062] The third piece of information is used to indicate whether the measurement data should be deleted if the RRC status changes.

[0063] The fourth piece of information indicates whether to resume collecting the measurement data in the event of a change in RRC status.

[0064] In some embodiments, the above data collection method further includes:

[0065] In the event of a change in RRC status, it is determined whether to execute the first target operation based on the fourth configuration information; wherein, each use case corresponds to one first target operation;

[0066] The first target operation includes at least one of the following:

[0067] Delete configuration information related to AI and / or ML;

[0068] Stop collecting the measurement data;

[0069] Delete the measurement data;

[0070] Resume collecting the measurement data;

[0071] Continue collecting the measurement data.

[0072] In some embodiments, the above data collection method further includes:

[0073] In the event of a change from RRC connected state to RRC disconnected state, determine whether to perform a second target operation for the target AI and / or ML use case;

[0074] The second target operation includes at least one of the following:

[0075] Stop collecting measurement data related to the target AI and / or ML use cases;

[0076] Delete the configuration information related to the target AI and / or ML use case;

[0077] Delete measurement data related to the target AI and / or ML use case;

[0078] Continue collecting measurement data related to the target AI and / or ML use case. In some embodiments, where the second target operation includes stopping the collection of the measurement data, the above data collection method further includes:

[0079] In the event of a change from an RRC disconnected state to an RRC connected state, the collection of measurement data related to the target AI and / or ML use case is resumed.

[0080] In some embodiments, the above data collection method further includes:

[0081] Upon entering the RRC idle or inactive state, determine whether to perform at least one of the following operations according to preset rules;

[0082] Stop collecting the measurement data;

[0083] Delete the configuration information related to the AI ​​and / or ML;

[0084] Delete the measurement data;

[0085] Continue collecting the measurement data.

[0086] In some embodiments, when it is determined, according to the preset rule, to stop collecting the measurement data, the method further includes:

[0087] When the RRC changes from an idle or inactive state to an RRC connected state, the collection of the measurement data resumes.

[0088] In some embodiments, when the first device is switched over from a first cell, reconnected, or reselected to a second cell, the method further includes:

[0089] If the acquisition methods for the first cell and the second cell are the same, continue collecting the measurement data; or,

[0090] If the acquisition methods corresponding to the first cell and the second cell are different, stop collecting the measurement data and do not delete the configuration information related to AI and / or ML, or stop collecting the measurement data and delete the configuration information related to AI and / or ML.

[0091] In some embodiments, when the first device is in RRC connected state and the first device is switched or reconnected to the second cell from the first cell, the method further includes:

[0092] If the transmission methods corresponding to the first cell and the second cell are the same, continue to send the measurement data to the second device; or,

[0093] If the transmission methods corresponding to the first cell and the second cell are different, stop sending the measurement data to the second device and do not delete the measurement data, or stop sending the measurement data to the second device and delete the measurement data.

[0094] Secondly, in order to solve the above-mentioned technical problems, embodiments of this disclosure provide a data collection method applied to a second device, comprising:

[0095] Receive measurement data related to AI and / or ML sent by the first device;

[0096] The measurement data includes at least one of the following:

[0097] The time information of the measurement data is obtained by measurement;

[0098] Measurement results related to AI and / or ML;

[0099] Evaluation results related to AI and / or ML;

[0100] The measurement data corresponds to the relevant information about the cell;

[0101] Configuration information related to AI and / or ML.

[0102] Thirdly, in order to solve the above-mentioned technical problems, embodiments of this disclosure provide a data collection method applied to a third device, comprising:

[0103] Send configuration information related to AI and / or ML to the first device;

[0104] The configuration information includes at least one of the following:

[0105] First configuration information related to the method of acquiring the measurement data of the AI ​​and / or ML;

[0106] Second configuration information related to the storage of the measurement data of the AI ​​and / or ML;

[0107] Third configuration information related to the method of transmitting the measurement data of the AI ​​and / or ML;

[0108] Fourth configuration information related to state transition processing;

[0109] The fifth configuration information related to community change processing.

[0110] In some embodiments, the fourth configuration information includes at least one of the following:

[0111] The first piece of information is used to indicate whether to stop collecting measurement data related to AI and / or ML in the event of a change in the Radio Resource Control (RRC) status;

[0112] The second piece of information is used to indicate whether the configuration information should be deleted if the RRC status changes.

[0113] The third piece of information is used to indicate whether to delete measurement data related to AI and / or ML in the event of a change in RRC status;

[0114] The fourth piece of information indicates whether to resume collecting the measurement data in the event of a change in RRC status.

[0115] Fourthly, in order to solve the above-mentioned technical problems, this disclosure provides a first device, including: a memory, a transceiver, and a processor;

[0116] A memory for storing computer programs; a transceiver for sending and receiving data under the control of the processor; and a processor for reading the computer programs from the memory and performing the following operations:

[0117] Acquire measurement data related to artificial intelligence (AI) and / or machine learning (ML);

[0118] The measurement data is sent to the second device.

[0119] In some embodiments, the processor is specifically configured to read a computer program from the memory and perform one of the following acquisition methods:

[0120] The measurement data are collected according to the first interval parameter;

[0121] The measurement data is collected when the first triggering condition is met;

[0122] When the first triggering condition is met, the measurement data is collected according to the first interval parameter.

[0123] In some embodiments, the processor is specifically configured to read a computer program from the memory and execute one of the following transmission methods:

[0124] The measurement data is sent according to the second interval parameter;

[0125] When the second triggering condition is met, the measurement data is sent;

[0126] The measurement data is sent according to the data acquisition request sent by the second device.

[0127] In some embodiments, the first interval parameter includes at least one of the following: a first time length, a first movement distance, and a first difference between two adjacent measurement results.

[0128] In some embodiments, the first triggering condition includes at least one of the following:

[0129] The first device measures and obtains the measurement data;

[0130] The first device triggers the reporting of a Radio Resource Management (RRM) measurement event;

[0131] The first device experienced a radio link failure (RLF).

[0132] The first device experienced a handover failure (HOF).

[0133] The moving speed of the first device is greater than or equal to a preset speed threshold;

[0134] The first device is located in the first geographical region.

[0135] In some embodiments, the second interval parameter includes at least one of the following: a second time length, a second movement distance, and a second difference between two adjacent measurement results.

[0136] In some embodiments, when the measurement data is sent in accordance with a data acquisition request sent by the second device, before receiving the data acquisition request sent by the second device, the processor is further configured to read a computer program in the memory and perform at least one of the following operations:

[0137] Based on the third interval parameter, a first request message is sent, which is used to request the measurement data to be sent to the second device;

[0138] When the second triggering condition is met, the first request message is sent;

[0139] When the second triggering condition is met, the first request message is sent according to the third interval parameter.

[0140] In some embodiments, the second triggering condition includes at least one of the following:

[0141] The first device acquires the measurement data;

[0142] The measurement data reaches the storage space threshold;

[0143] The power level of the first device is less than or equal to a preset power threshold.

[0144] The first device is located in the second geographical region.

[0145] In some embodiments, the third interval parameter includes at least one of the following: a third time length, a third movement distance, and a third difference between two adjacent measurement results.

[0146] In some embodiments, the processor is specifically configured to read a computer program from the memory and perform the following operations:

[0147] When the first device is located in the third geographic region, the measurement data is collected according to the first interval parameter; and / or,

[0148] While the first device is within a first time range, the measurement data is collected according to a first interval parameter.

[0149] In some embodiments, the processor is specifically configured to read a computer program from the memory and perform the following operations:

[0150] When the first device is located in the fourth geographic region, the measurement data is sent to the second device according to the second interval parameter; and / or,

[0151] When the second time range is in effect, the measurement data is sent to the second device according to the second interval parameter.

[0152] In some embodiments, the processor is specifically configured to read a computer program from the memory and perform the following operations:

[0153] When the first device is in the fifth geographic region, the first request message is sent according to the third interval parameter; and / or,

[0154] When the first device is within the third time range, the first request message is sent according to the third interval parameter.

[0155] In some embodiments, the AI ​​and / or ML-related measurement data includes at least one of the following:

[0156] The time information of the measurement data is obtained by measurement;

[0157] Measurement results related to AI and / or ML;

[0158] Evaluation results related to AI and / or ML;

[0159] The measurement data corresponds to the relevant information about the cell;

[0160] Configuration information related to AI and / or ML.

[0161] In some embodiments, the processor is further configured to read a computer program from the memory and perform the following operations:

[0162] Receive configuration information related to AI and / or ML sent by a third device;

[0163] The configuration information includes at least one of the following:

[0164] First configuration information related to the method of acquiring the measurement data;

[0165] Second configuration information related to the storage of the measurement data;

[0166] Third configuration information related to the method of transmitting the measurement data;

[0167] Fourth configuration information related to state transition processing;

[0168] The fifth configuration information related to community change processing.

[0169] In some embodiments, the fourth configuration information includes at least one of the following:

[0170] The first piece of information is used to indicate whether to stop collecting the measurement data in the event of a change in the Radio Resource Control (RRC) status;

[0171] The second piece of information is used to indicate whether to delete the configuration information related to AI and / or ML in the event of a change in RRC status;

[0172] The third piece of information is used to indicate whether the measurement data should be deleted if the RRC status changes.

[0173] The fourth piece of information indicates whether to resume collecting the measurement data in the event of a change in RRC status.

[0174] In some embodiments, the processor is further configured to read a computer program from the memory and perform the following operations:

[0175] In the event of a change in RRC status, it is determined whether to execute the first target operation based on the fourth configuration information; wherein, each use case corresponds to one first target operation;

[0176] The first target operation includes at least one of the following:

[0177] Delete configuration information related to AI and / or ML;

[0178] Stop collecting the measurement data;

[0179] Delete the measurement data;

[0180] Resume collecting the measurement data;

[0181] Continue collecting the measurement data.

[0182] In some embodiments, the processor is further configured to read a computer program from the memory and perform the following operations:

[0183] If the first device changes from an RRC connected state to an RRC disconnected state, determine whether to perform a second target operation for the target AI and / or ML use case;

[0184] The second target operation includes at least one of the following:

[0185] Stop collecting measurement data related to the target AI and / or ML use cases;

[0186] Delete the configuration information related to the target AI and / or ML use case;

[0187] Delete measurement data related to the target AI and / or ML use case;

[0188] Continue collecting measurement data related to the target AI and / or ML use case. In some embodiments, where the second target operation includes stopping the collection of the measurement data, the processor is further configured to read the computer program in the memory and perform the following operations:

[0189] In the event of a change from an RRC disconnected state to an RRC connected state, the collection of measurement data related to the target AI and / or ML use case is resumed.

[0190] In some embodiments, the processor is further configured to read a computer program from the memory and perform the following operations:

[0191] Upon entering the RRC idle or inactive state, determine whether to perform at least one of the following operations according to preset rules;

[0192] Stop collecting the measurement data;

[0193] Delete configuration information related to AI and / or ML;

[0194] Delete the measurement data;

[0195] Continue collecting the measurement data.

[0196] In some embodiments, if it is determined, according to the preset rule, to stop collecting the measurement data, the processor is further configured to read the computer program in the memory and perform the following operations:

[0197] When the RRC changes from an idle or inactive state to an RRC connected state, the collection of the measurement data resumes.

[0198] In some embodiments, when the first device is switched over from a first cell, reconnected, or reselected to a second cell, the processor is further configured to read the computer program in the memory and perform the following operations:

[0199] If the acquisition methods for the first cell and the second cell are the same, continue collecting the measurement data; or,

[0200] If the acquisition methods corresponding to the first cell and the second cell are different, stop collecting the measurement data and do not delete the configuration information related to AI and / or ML, or stop collecting the measurement data and delete the configuration information related to AI and / or ML.

[0201] In some embodiments, when the first device is in an RRC connected state and the first device is switched or reconnected to a second cell from a first cell, the processor is further configured to read the computer program in the memory and perform the following operations:

[0202] If the transmission methods corresponding to the first cell and the second cell are the same, continue to send the measurement data to the second device; or,

[0203] If the transmission methods corresponding to the first cell and the second cell are different, stop sending the measurement data to the second device and do not delete the measurement data, or stop sending the measurement data to the second device and delete the measurement data.

[0204] Fifthly, in order to solve the above-mentioned technical problems, embodiments of this disclosure provide a second device, including: a memory, a transceiver, and a processor;

[0205] A memory for storing computer programs; a transceiver for sending and receiving data under the control of the processor; and a processor for reading the computer programs from the memory and performing the following operations:

[0206] Receive measurement data related to AI and / or ML sent by the first device;

[0207] The measurement data includes at least one of the following:

[0208] The time information of the measurement data is obtained by measurement;

[0209] Measurement results related to AI and / or ML;

[0210] Evaluation results related to AI and / or ML;

[0211] The measurement data corresponds to the relevant information about the cell;

[0212] Configuration information related to AI and / or ML.

[0213] Sixthly, in order to solve the above-mentioned technical problems, embodiments of this disclosure provide a third device, including: a memory, a transceiver, and a processor;

[0214] A memory for storing computer programs; a transceiver for sending and receiving data under the control of the processor; and a processor for reading the computer programs from the memory and performing the following operations:

[0215] Send configuration information related to AI and / or ML to the first device;

[0216] The configuration information includes at least one of the following:

[0217] First configuration information related to the method of acquiring the measurement data of the AI ​​and / or ML;

[0218] Second configuration information related to the storage of the measurement data of the AI ​​and / or ML;

[0219] Third configuration information related to the method of transmitting the measurement data of the AI ​​and / or ML;

[0220] Fourth configuration information related to state transition processing;

[0221] The fifth configuration information related to community change processing.

[0222] In some embodiments, the fourth configuration information includes at least one of the following:

[0223] The first piece of information is used to indicate whether to stop collecting measurement data related to AI and / or ML in the event of a change in the Radio Resource Control (RRC) status;

[0224] The second piece of information is used to indicate whether the configuration information should be deleted if the RRC status changes.

[0225] The third piece of information is used to indicate whether to delete measurement data related to AI and / or ML in the event of a change in RRC status;

[0226] The fourth piece of information indicates whether to resume collecting the measurement data in the event of a change in RRC status.

[0227] Seventhly, in order to solve the above-mentioned technical problems, embodiments of this disclosure provide a data collection device, applied to a first device, comprising:

[0228] The first acquisition module is used to acquire measurement data related to artificial intelligence (AI) and / or machine learning (ML).

[0229] The first transmitting module is used to transmit the measurement data to the second device.

[0230] Eighthly, in order to solve the above-mentioned technical problems, embodiments of this disclosure provide a data collection device applied to a second device, comprising:

[0231] The second receiving module is used to receive measurement data related to AI and / or ML sent by the first device;

[0232] The measurement data includes at least one of the following:

[0233] The time information of the measurement data is obtained by measurement;

[0234] Measurement results related to AI and / or ML;

[0235] Evaluation results related to AI and / or ML;

[0236] The measurement data corresponds to the relevant information about the cell;

[0237] Configuration information related to AI and / or ML.

[0238] Ninthly, in order to solve the above-mentioned technical problems, embodiments of this disclosure provide a data collection apparatus applied to a third device, comprising:

[0239] The third sending module is used to send configuration information related to AI and / or ML to the first device;

[0240] The configuration information includes at least one of the following:

[0241] First configuration information related to the method of acquiring the measurement data of the AI ​​and / or ML;

[0242] Second configuration information related to the storage of the measurement data of the AI ​​and / or ML;

[0243] Third configuration information related to the method of transmitting the measurement data of the AI ​​and / or ML;

[0244] Fourth configuration information related to state transition processing;

[0245] The fifth configuration information related to community change processing.

[0246] In a tenth aspect, in order to solve the above-mentioned technical problems, embodiments of this disclosure provide a processor-readable storage medium storing a computer program for causing the processor to perform the methods described in the first, second, or third aspect.

[0247] Eleventhly, in order to solve the above-mentioned technical problems, this disclosure also provides a computer program product, including computer instructions, which, when executed by a processor, implement the method described in the first, second, or third aspect.

[0248] The beneficial effects of this disclosure are:

[0249] In the above scheme, the first device acquires measurement data related to artificial intelligence (AI) and / or machine learning (ML), and sends the measurement data to the second device. This enables data acquisition via the first device, and the second device to receive measurement data related to AI and / or machine learning (ML) from the first device, thus meeting the needs of model training, model inference, or model monitoring. Attached Figure Description

[0250] To more clearly illustrate the technical solutions in the embodiments or related technologies of this disclosure, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments recorded in this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0251] Figure 1 shows a schematic flowchart of one embodiment of the data collection method of this disclosure;

[0252] Figure 2 shows a second schematic flowchart of the data collection method according to an embodiment of the present disclosure;

[0253] Figure 3 illustrates a third flowchart of the data collection method according to an embodiment of this disclosure;

[0254] Figure 4 is a fourth schematic flowchart of the data collection method according to an embodiment of this disclosure;

[0255] Figure 5 is a fifth schematic flowchart of the data collection method according to an embodiment of the present disclosure;

[0256] Figure 6 shows a structural block diagram of one of the data collection devices according to an embodiment of the present disclosure;

[0257] Figure 7 shows a second structural block diagram of the data collection device according to an embodiment of the present disclosure;

[0258] Figure 8 shows a third structural block diagram of the data collection device according to an embodiment of the present disclosure;

[0259] Figure 9 shows a structural diagram of the first device according to an embodiment of the present disclosure.

[0260] Figure 10 shows a structural diagram of the second device according to an embodiment of the present disclosure;

[0261] Figure 11 shows a structural diagram of a third device according to an embodiment of this disclosure. Detailed Implementation

[0262] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this disclosure. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0263] The terms “first,” “second,” etc., used in this disclosure and in the claims are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this disclosure described herein may be implemented, for example, in sequences other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0264] In this disclosure, the term "and / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship. In this disclosure, the term "multiple" refers to two or more objects, and other quantifiers are similar.

[0265] In this disclosure, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" or "for example" in this disclosure should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0266] The technical solutions provided in this disclosure are applicable to a variety of systems, especially 5G systems. For example, applicable systems may include Global System for Mobile Communication (GSM), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA) General Packet Radio Service (GPRS), Long Term Evolution (LTE), LTE Frequency Division Duplex (FDD), LTE Time Division Duplex (TDD), Long Term Evolution Advanced (LTE-A), Universal Mobile Telecommunications System (UMTS), Worldwide Interoperability for Microwave Access (WiMAX), and 5G New Radio (NR). All of these systems include terminals (also referred to as terminal equipment) and network equipment. The system may also include a core network component, such as an evolved packet system (EPS) or a 5G system (5GS).

[0267] The terminal involved in the embodiments of this disclosure, also referred to as a terminal device, can be a device that provides voice and / or data connectivity to a user, a handheld device with wireless connectivity, or other processing devices connected to a wireless modem. The name of the terminal device may differ in different systems; for example, in a 5G system, the terminal device can be called User Equipment (UE). The wireless terminal device can communicate with one or more core networks (CNs) via a Radio Access Network (RAN). The wireless terminal device can be a mobile terminal device, such as a mobile phone (or "cellular" phone) and a computer with a mobile terminal device, for example, a portable, pocket-sized, handheld, computer-embedded, or vehicle-mounted mobile device, which exchanges voice and / or data with the RAN. Examples include Personal Communication Service (PCS) phones, cordless phones, Session Initiated Protocol (SIP) phones, Wireless Local Loop (WLL) stations, and Personal Digital Assistants (PDAs). Wireless terminal equipment can also be referred to as a system, subscriber unit, subscriber station, mobile station, mobile station, remote station, access point, remote terminal, access terminal, user terminal, user agent, or user device, but is not limited to these terms in the embodiments disclosed herein.

[0268] The network device disclosed in this embodiment may be a base station, which may include multiple cells providing services to terminals. Depending on the specific application, the base station may also be called an access point, or a device in the access network that communicates with the wireless terminal device through one or more sectors on the air interface, or other names. The network device may be used to exchange received air frames with Internet Protocol (IP) packets, acting as a router between the wireless terminal device and the rest of the access network, where the rest of the access network may include an Internet Protocol (IP) communication network. The network device may also coordinate the attribute management of the air interface. For example, the network equipment involved in this disclosure can be a base transceiver station (BTS) in a Global System for Mobile communications (GSM) or Code Division Multiple Access (CDMA) system, a NodeB in a wide-band Code Division Multiple Access (WCDMA) system, an evolved Node B (eNB or e-NodeB) in a long term evolution (LTE) system, a 5G base station (gNB) in a next generation system, a Home evolved Node B (HeNB), a relay node, a femto, a pico, etc., and is not limited in this disclosure. In some network structures, the network equipment may include centralized unit (CU) nodes and distributed unit (DU) nodes, and the centralized unit and distributed unit may be geographically separated.

[0269] Network devices and terminal devices can each use one or more antennas for Multiple Input Multiple Output (MIMO) transmission. MIMO transmission can be Single User MIMO (SU-MIMO) or Multiple User MIMO (MU-MIMO). Depending on the configuration and number of antenna combinations, MIMO transmission can be 2D MIMO, 3D MIMO, Full Dimension MIMO (FD-MIMO), or Massive MIMO, or it can be diversity transmission, pre-coded transmission, or beamforming transmission, etc.

[0270] The embodiments of this disclosure are described below with reference to the accompanying drawings. The data collection methods, apparatus, and devices provided in the embodiments of this disclosure can be applied to wireless communication systems. This wireless communication system can be a system employing fifth-generation (5G) mobile communication technology (hereinafter referred to as a 5G system). Those skilled in the art will understand that the 5G NR system is merely an example and not a limitation.

[0271] As shown in Figure 1, this embodiment of the present disclosure provides a data collection method applied to a first device, including:

[0272] Step 101: Obtain measurement data related to artificial intelligence (AI) and / or machine learning (ML).

[0273] It should be noted that the first device acquires measurement data related to AI and / or ML in the following ways: receiving measurement data related to AI and / or ML sent by other devices; or collecting measurement data related to AI and / or ML from the measurement data already measured inside the first device. That is, it can be understood as filtering / summarizing measurement data related to AI and / or ML from its own existing measurement data in a certain way.

[0274] Step 102: Send the measurement data to the second device.

[0275] In some embodiments, the first device is a terminal node and the second device is a network node; wherein, the network node includes, but is not limited to, an access network node, a core network node, an operator's data collection node, or an OTT server.

[0276] In some embodiments, the first device is a first network node, and the second device is a second network node or a model training node. The first and second network nodes include, but are not limited to, access network nodes, core network nodes, operator data collection nodes, or OTT servers.

[0277] It should be noted that after receiving the measurement data related to AI and / or ML sent by the first device, the second device can perform model training or model inference on the second device side, or it can send it to other network nodes (such as training nodes for AI / ML models) for model training or model inference.

[0278] The training nodes for AI / ML models can include, but are not limited to: nodes within the 3GPP system (such as base stations or core network nodes); or nodes of the operator outside the 3GPP system or OTT servers, etc. OTT stands for "Over-the-Top" service, which in the communications industry refers to Internet companies bypassing operators to develop various video and data service businesses based on the open Internet.

[0279] In the above embodiments, data can be acquired through the first device, and the second device can receive measurement data related to artificial intelligence (AI) and / or machine learning (ML) from the first device to meet the needs of model training, model inference, or model monitoring.

[0280] In some alternative embodiments, the AI ​​and / or ML-related measurement data includes at least one of the following:

[0281] The time information of the measurement data is obtained by measurement;

[0282] Measurement results related to AI and / or ML;

[0283] Evaluation results related to AI and / or ML;

[0284] The measurement data corresponds to the relevant information about the cell;

[0285] Configuration information related to AI and / or ML.

[0286] The time information may include at least one of the following: absolute time, timestamp of measurement configuration issuance, timestamp of measurement data transmission, and relative timestamp. The relative timestamp can be the time interval between the measurement data collection time and the measurement configuration issuance time, or the time interval between the measurement data transmission time, or the time interval between the previous measurement data collection time.

[0287] In practice, for beam management (BM) use cases, the time interval between entries (each measurement data) may be at the time slot / subframe level; for positioning accuracy enhancements (PoS) or mobility enhancements (mob) use cases, the time interval between entries may be at the millisecond / second / minute level.

[0288] For example, for BM, the measurement results related to Layer 1 / Layer 3 measurements may include at least one of the following: Reference Signal Received Power (RSRP) measurement, Reference Signal Received Quality (RSRQ) measurement, Signal to Interference plus Noise Ratio (SINR) measurement, cell and beam identifier information, etc.; for example, for PoS, the measurement results for UE may include at least one of the following: geographic location coordinates, Downlink Reference Signal Time Difference (DL RSTD), UE receive-transmit time difference (Rx-Tx time difference), Power Delay Profile (PDP) / Delay Profile (DP) / Channel Impulse Response (CIR), Line of Sight (LOS) / Non-Line of Sight (LOS). Sight (NLOS), etc.; for example, for mob, the layer 1 / layer 3 measurement results of UE include at least one of the following: RSRP measurement value, RSRQ measurement value, SINR measurement value, cell, beam identifier, triggered measurement event identifier, relevant records of link failures such as RLF / HOF, etc.

[0289] It should be noted that measurement data related to AI and / or ML includes measurement results and / or evaluation results. Evaluation results related to AI and / or ML can be obtained by filtering from measurement results, such as the top K measurement results; for example, DL RSTD can be obtained from CIR evaluation.

[0290] The cell-related information corresponding to the measurement data may include at least one of the following: cell identifier, tracking area (TA) identifier, radio access network-based notification area (RNA) identifier, and public land mobile network (PLMN) identifier.

[0291] Among them, the condition configuration information related to AI and / or ML may include: condition information related to AI models or functions, condition information related to ML models or functions, such as the conditions corresponding to the model training stage and / or the conditions corresponding to the model inference stage. The condition configuration information may include, but is not limited to: the configuration of moving speed, antenna selection, beam pattern, frequency of use, timing offset, etc.

[0292] The following section introduces how to acquire measurement data related to artificial intelligence (AI) and / or machine learning (ML).

[0293] First, it should be pointed out that in the data collection methods of related technologies, measurement data over a period of time is usually collected for model training. This method can lead to similar measurement data, resulting in redundancy and missing sample types in the training samples, which affects the accuracy of model training. Redundant samples also cause unnecessary signaling overhead.

[0294] To address the aforementioned issues, this disclosure provides the following embodiments to illustrate the acquisition of measurement data related to artificial intelligence (AI) and / or machine learning (ML).

[0295] In some optional embodiments, step 101 above, acquiring measurement data related to artificial intelligence (AI) and / or machine learning (ML), includes one of the following acquisition methods:

[0296] The measurement data are collected according to the first interval parameter;

[0297] The measurement data is collected when the first triggering condition is met;

[0298] When the first triggering condition is met, the measurement data is collected according to the first interval parameter.

[0299] It should be noted that the first device can use different acquisition methods to collect measurement data each time. For example, the measurement data can be collected according to the first interval parameter when the measurement data is sent for the i-th time; the measurement data can be collected when the i+1-th trigger condition is met, where i is a positive integer.

[0300] It should be noted that the first device can always use the same transmission method when collecting measurement data, such as always collecting measurement data according to the first interval parameter.

[0301] In some embodiments, the first interval parameter includes at least one of the following: a first time length, a first movement distance, and a first difference between two adjacent measurement results.

[0302] In specific implementation, when the first interval parameter includes a first time length, data is collected once every first time length; when the first time interval includes a first moving distance, data is collected once every first moving distance the first device moves; when the first interval parameter includes a first difference, data is collected once if the difference between the current measurement result and the previous measurement result is greater than the first difference.

[0303] In specific implementation, when the first interval parameter includes two or three of the following: first time length, first travel distance, and first difference, collecting measurement data based on the first interval parameter may include:

[0304] Method 1: Perform a data collection when any one of the parameters in the first interval is satisfied; or,

[0305] Method 2: When multiple interval parameters in the first interval parameter are satisfied simultaneously, perform one data collection.

[0306] In some embodiments, the first triggering condition includes at least one of the following:

[0307] The first device measures and obtains the measurement data;

[0308] The first device triggers the reporting of a Radio Resource Management (RRM) measurement event;

[0309] The first device experienced a radio link failure (RLF).

[0310] The first device experienced a handover failure (HOF).

[0311] The moving speed of the first device is greater than or equal to a preset speed threshold;

[0312] The first device is located in the first geographical region.

[0313] In some embodiments, the first geographic region refers to a geographic region range that is explicitly configured by the network, implicitly configured by the network, or defaulted by the system, including but not limited to: geographic region ranges corresponding to cells, gNBs, TAs, RNAs, or PLMNs. In the above embodiments, the scheme for collecting the measurement data according to the first interval parameter can achieve measurement data collection according to at least one of a first time length, a first movement distance, and a first difference, which can avoid the collected measurement data being too similar, making the measurement data more balanced and avoiding the loss of training samples. When the first trigger condition is met, the scheme for collecting measurement data, since the first trigger condition involves multiple factors such as Radio Resource Control (RRC) measurement, RLF, HOF, movement speed, and geographic region, can make the collected measurement data diverse, meeting the different types of measurement data collection purposes for AI / ML models applied to various uses / functions; when the first trigger condition is met, the scheme for collecting the measurement data according to the first interval parameter can take into account the advantages of both schemes, improving the quantity and quality of collected training samples.

[0314] In some alternative embodiments, collecting the measurement data according to the first interval parameter includes:

[0315] When the first device is located in the third geographic region, the measurement data is collected according to the first interval parameter; and / or,

[0316] While the first device is within a first time range, the measurement data is collected according to a first interval parameter.

[0317] In some embodiments, the first time range and the third geographic region refer to the network's explicit configuration, implicit configuration, or system default setting. The third geographic region includes, but is not limited to, the geographic area range corresponding to a cell, gNB, TA, RNA, or PLMN.

[0318] In the above embodiments, the measurement data is only allowed to be collected according to the first interval parameter when the first device moves to the third geographical area or is within the first time range. In this way, it can be ensured that the measurement data within the required geographical range or the required time range is collected in a targeted manner to meet the needs of model training, model inference or model monitoring.

[0319] The following describes how the measurement data is sent to the second device.

[0320] First, it should be noted that the data transmission methods in related technologies mainly include two mechanisms: Immediate MDT and Logged MDT. MDT can be understood as Measurement Data Transmission. The Immediate MDT mechanism performs MDT measurements and reporting in connected state, using a method where the UE collects the data and reports it immediately. Logged MDT performs MDT measurements in idle / inactive state, using a method where the UE stores the data first and then reports it. It receives the configuration in connected state, performs measurement collection after leaving connected state, and reports it upon re-entering connected state.

[0321] However, due to the large data requirements of AI / ML models, the immediate MDT mechanism in related technologies easily generates a large amount of reporting signaling; while the logged MDT mechanism can only be applied in the disconnected state. When the UE is in the connected state, data collection cannot be performed, and when the UE does not receive signaling such as cell handover / reconstruction / connection establishment / connection restoration / reconfiguration, it cannot notify the network that the UE has saved the collected data. Therefore, neither of the current MDT data collection mechanisms can meet the data collection requirements of AI / ML models.

[0322] To address the aforementioned issues, this disclosure provides the following embodiments to illustrate how a first device sends measurement data to a second device.

[0323] In some alternative embodiments, step 102 above, sending the measurement data to the second device, includes at least one of the following sending methods:

[0324] The measurement data is sent according to the second interval parameter;

[0325] When the second triggering condition is met, the measurement data is sent;

[0326] The measurement data is sent according to the data acquisition request sent by the second device.

[0327] It is understandable that, depending on the combination method, the sending method may include one of the following:

[0328] The measurement data is sent according to the second interval parameter;

[0329] When the second triggering condition is met, the measurement data is sent;

[0330] When the second triggering condition is met, the measurement data is sent according to the second interval parameter;

[0331] The measurement data is sent according to the data acquisition request sent by the second device;

[0332] The measurement data is sent according to the data acquisition request and the second interval parameter sent by the second device;

[0333] Based on the data acquisition request sent by the second device, the measurement data is sent when the second triggering condition is met;

[0334] Based on the data acquisition request and the second interval parameter sent by the second device, the measurement data is sent when the second trigger condition is met.

[0335] It should be noted that the first device can use different transmission methods each time it sends measurement data. For example, the i-th transmission of measurement data can be based on the second interval parameter; the (i+1)-th transmission of measurement data can be based on the second triggering condition, where i is a positive integer.

[0336] It should be noted that the first device may always use the same transmission method each time it transmits measurement data, for example, always transmit the measurement data according to the second interval parameter.

[0337] In some embodiments, the second interval parameter includes at least one of the following: a second time length, a second movement distance, and a second difference between two adjacent measurement results.

[0338] In specific implementation, when the second interval parameter includes the second time length, the first device sends the measurement data collected by the first device to the second device every second time length; when the second time interval includes the second moving distance, the first device sends the measurement data collected by the first device to the second device every second moving distance; when the second interval parameter includes the first difference, if the difference between the current measurement result and the previous measurement result is greater than the second difference, then the first device sends the measurement data collected by the first device to the second device.

[0339] In specific implementation, when the second interval parameter includes two or three of the following: second time length, second travel distance, and second difference, sending measurement data to the second device according to the second interval parameter may include:

[0340] Method 1: When any one of the parameters in the second interval parameters is satisfied, the first device sends the measurement data collected by the first device to the second device; or,

[0341] Method 2: When multiple interval parameters in the second interval parameters are satisfied simultaneously, the first device sends the measurement data collected by the first device to the second device.

[0342] In some embodiments, the second triggering condition includes at least one of the following:

[0343] The first device acquires the measurement data;

[0344] The measurement data reaches the storage space threshold;

[0345] The power level of the first device is less than or equal to a preset power threshold.

[0346] The first device is located in the second geographical region.

[0347] In some embodiments, the second geographic region refers to the geographic region range that is explicitly configured by the network, implicitly configured by the network, or defaulted by the system, including but not limited to the geographic region range corresponding to cells, gNBs, TAs, RNAs, or PLMNs.

[0348] In the above embodiments, the first device can avoid frequently sending the collected measurement data to the second device, reducing signaling overhead. Moreover, in the scenario where the second device is a network node and the first device is a terminal node, even if the terminal node does not receive any handover / reconstruction / establishment / reconnection / reconfiguration signaling, the network node can still know from the terminal node that it has collected measurement data and further acquire measurement data. This avoids the problem that the network node cannot collect data when the terminal node does not receive cell handover / reconstruction / establishment / reconnection / reconfiguration signaling.

[0349] In some alternative embodiments, sending the measurement data according to the second interval parameter includes:

[0350] When the first device is located in the fourth geographic region, the measurement data is sent to the second device according to the second interval parameter; and / or,

[0351] When the second time range is in effect, the measurement data is sent to the second device according to the second interval parameter.

[0352] In some embodiments, the second time range and the fourth geographic region refer to those explicitly configured by the network, implicitly configured by the network, or set by the system default. The fourth geographic region includes, but is not limited to, the geographic area range corresponding to a cell, gNB, TA, RNA, or PLMN.

[0353] In the above embodiments, the collected measurement data is only allowed to be sent to the second device according to the second interval parameter when the first device moves to the fourth geographical area or is within the second time range. In this way, the problem of frequent sending of measurement data to the second device, which leads to large signaling overhead, can be avoided. Moreover, in the scenario where the second device is a network node and the first device is a terminal node, even if the terminal node does not receive any handover / rebuild / establish connection / restore connection / reconfiguration signaling, the terminal node can still send measurement data to the network node through the method provided in this embodiment.

[0354] In some alternative embodiments, when the transmission method includes transmitting the measurement data according to a data acquisition request sent by the second device, the method further includes one of the following before receiving the data acquisition request sent by the second device:

[0355] Based on the third interval parameter, send the first request message;

[0356] When the second triggering condition is met, the first request message is sent;

[0357] When the second triggering condition is met, the first request message is sent according to the third interval parameter.

[0358] It should be noted that the first device can use different sending methods each time it sends the first request message. For example, the first request message can be sent according to the third interval parameter for the i-th time; the first request message can be sent when the i+1-th trigger condition is met, where i is a positive integer.

[0359] It should be noted that the first device may always use the same sending method when sending the first request message, such as always sending the first request message according to the first interval parameter.

[0360] In a specific implementation, the first request message is used to indicate to the second device that measurement data related to AI and / or ML is available or to request the sending of measurement data related to AI and / or ML; accordingly, after receiving the first request message, the second device sends a data acquisition request to the first device; the first device sends the measurement data related to AI and / or ML to the second device according to the data acquisition request.

[0361] In some embodiments, the third interval parameter includes at least one of the following: a third time length, a third movement distance, and a third difference between two adjacent measurement results.

[0362] In specific implementation, when the third interval parameter includes the third time length, a first request message is sent to the second device every third time length; when the third time interval includes the third movement distance, the first device sends a first request message to the second device every third movement distance; when the third interval parameter includes the third difference, if the difference between the current measurement result and the previous measurement result is greater than the third difference, a first request message is sent to the second device.

[0363] In specific implementation, when the third interval parameter includes two or three of the following: third time length, third travel distance, and third difference, sending the first request message according to the third interval parameter may include:

[0364] Method 1: Send the first request message when any one of the multiple parameters in the first interval parameter is satisfied; or,

[0365] Method 2: When multiple interval parameters in the first interval parameter are satisfied simultaneously, send the first request message.

[0366] In some embodiments, the second triggering condition includes at least one of the following:

[0367] The first device acquires the measurement data;

[0368] The measurement data reaches the storage space threshold;

[0369] The power level of the first device is less than or equal to a preset power threshold.

[0370] The first device is located in the second geographical region.

[0371] It should be noted that the storage space threshold can be a limitation on the amount of data. For example, a certain number of bytes / megabyte in cache, or a certain number of measurement results; the preset power threshold can be a percentage of the total power consumption or the actual power consumption value.

[0372] In some embodiments, if the first device requests the second device to send measurement data related to AI / ML, but the second device does not instruct the acquisition of measurement data, the first device continues to collect and record measurement data related to AI / ML. If the measurement data reaches the storage space limit, the first device deletes the oldest measurement result and records the latest one, or stops collecting measurement data.

[0373] In some embodiments, the second geographic region refers to the geographic region range that is explicitly configured by the network, implicitly configured by the network, or defaulted by the system, including but not limited to the geographic region range corresponding to cells, gNBs, TAs, RNAs, or PLMNs.

[0374] In the above embodiments, the frequent sending of first request messages from the first device to the second device can be avoided, reducing signaling overhead. Moreover, in scenarios where the second device is a network node and the first device is a terminal node, even if the terminal node does not receive any handover / rebuild / establish connection / restore connection / reconfiguration signaling, the terminal node can still notify / instruct the network node that it has collected measurement data through the method provided in this embodiment.

[0375] In some alternative embodiments, sending the first request message according to a third interval parameter includes:

[0376] When the first device is in the fifth geographic region, the first request message is sent according to the third interval parameter; and / or,

[0377] When the first device is within the third time range, the first request message is sent according to the third interval parameter.

[0378] In some embodiments, the third time range and the fifth geographic region refer to those explicitly configured by the network, implicitly configured by the network, or set by the system default. The sixth geographic region includes, but is not limited to, the geographic region range corresponding to a cell, gNB, TA, RNA, or PLMN.

[0379] In the above embodiments, the first request message is only allowed to be sent to the second device according to the third interval parameter when the first device moves to the fifth geographical area or is within the third time range. In this way, the problem of frequent sending of the first request message to the second device, which leads to large signaling overhead, can be avoided.

[0380] It should be noted that, depending on the specific implementation, the first, second, third, fourth, and fifth geographical regions mentioned above may be the same or different.

[0381] The following section introduces the data collection methods for application scenarios involving changes in RRC status and cell changes.

[0382] In some optional embodiments, the above data collection method further includes:

[0383] Receive configuration information related to AI and / or ML sent by a third device;

[0384] The configuration information includes at least one of the following:

[0385] First configuration information related to the method of acquiring the measurement data;

[0386] Second configuration information related to the storage of the measurement data;

[0387] Third configuration information related to the method of transmitting the measurement data;

[0388] Fourth configuration information related to state transition processing;

[0389] The fifth configuration information related to community change processing.

[0390] It should be noted that the third device may be the same as or different from the second device. For example, if the first device is a terminal and the second device is a base station, then the second and third devices are the same if the terminal does not undergo cell handover; however, if the terminal undergoes cell handover, then the second and third devices are different.

[0391] In specific implementation, before collecting measurement data related to AI and / or ML, configuration information related to AI and / or ML sent by a third device is received; or, before sending measurement data related to AI and / or ML to a second device, configuration information related to AI and / or ML sent by a third device is received.

[0392] In some embodiments, the first configuration information is used to configure the acquisition method of measurement data related to AI and / or ML, such as including: a first interval parameter and / or a first trigger condition, etc.

[0393] In some embodiments, the second configuration information is used to configure at least one of the following: whether to store measurement data related to AI and / or ML, the storage location corresponding to the measurement data related to AI and / or ML, the storage capacity limit corresponding to the measurement data related to AI and / or ML, and the processing method after the measurement data related to AI and / or ML reaches the storage space limit (such as deleting old data or stopping data collection).

[0394] In some embodiments, the third configuration information is used to configure the transmission method of measurement data related to AI and / or ML, such as including a second interval parameter, a third interval parameter, and / or a second trigger condition.

[0395] In some embodiments, the fourth configuration information includes at least one of the following:

[0396] The first piece of information is used to indicate whether to stop collecting the measurement data in the event of a change in the Radio Resource Control (RRC) status;

[0397] The second piece of information is used to indicate whether to delete the configuration information related to AI and / or ML in the event of a change in RRC status;

[0398] The third piece of information is used to indicate whether the measurement data should be deleted if the RRC status changes.

[0399] The fourth piece of information indicates whether to resume collecting the measurement data in the event of a change in RRC status.

[0400] For example, the first information is used to instruct that when the RRC connected state changes to the disconnected state, the collection of AI and / or ML related measurement data should be stopped; the second information is used to instruct that when the RRC connected state changes to the disconnected state, the configuration information related to AI and / or ML should be deleted; the third information is used to instruct that when the RRC connected state changes to the disconnected state, the measurement data related to AI and / or ML should be deleted; and the fourth information is used to instruct that when the RRC state changes from the disconnected state to the connected state, the collection of AI and / or ML related measurement data should be resumed.

[0401] In some embodiments, the fifth configuration information includes at least one of the following:

[0402] The fifth piece of information is used to indicate whether to stop collecting the measurement data in the event of a change in the community.

[0403] The sixth piece of information is used to indicate whether to delete the configuration information related to AI and / or ML in the event of a change in the cell.

[0404] The seventh piece of information is used to indicate whether the measurement data should be deleted in the event of a change in the community.

[0405] The eighth piece of information indicates whether to resume collecting the measurement data in the event of a change in the cell.

[0406] In some optional embodiments, the above data collection method further includes:

[0407] In the event of a change in RRC status, it is determined whether to execute the first target operation based on the fourth configuration information; wherein, each use case corresponds to one first target operation;

[0408] The first target operation includes at least one of the following:

[0409] Delete configuration information related to AI and / or ML;

[0410] Stop collecting the measurement data;

[0411] Delete the measurement data;

[0412] Resume collecting the measurement data;

[0413] Continue collecting the measurement data.

[0414] In some embodiments, the type of use case is related to the function or purpose of the AI / ML model. For example, it may include: beam management (BM) use case, positioning accuracy enhancements (PoS) use case, mobility enhancement (mob) use case, etc.

[0415] In the above embodiments, the network node can explicitly indicate the first target operation corresponding to each use case when the RRC state changes through the fourth configuration information. In this way, different data collection and processing methods can be implemented for different use cases when the RRC state changes.

[0416] In some optional embodiments, the above data collection method further includes:

[0417] In the event of a change from RRC connected state to RRC disconnected state, determine whether to perform a second target operation for the target AI and / or ML use case;

[0418] The second target operation includes at least one of the following:

[0419] Stop collecting measurement data related to the target AI and / or ML use cases;

[0420] Delete the configuration information related to the target AI and / or ML use case;

[0421] Delete measurement data related to the target AI and / or ML use case;

[0422] Continue collecting measurement data related to the target AI and / or ML use case. For example, for the BM or mob use case, when the first device leaves the connected state, the collection of measurement data stops, and the first device may delete or not delete the configuration information related to the AI ​​and / or ML use case corresponding to BM or mob; if the configuration information is not deleted, the collection of measurement data related to the target AI and / or ML use case can continue after the connected state is restored.

[0423] For example, for the PoS use case, the same operation can be performed as the BM use case mentioned above, or the UE can leave the connected state and continue to collect measurement data without being affected by the state transition, and the configuration information can be deleted.

[0424] In the above embodiments, the target AI and / or ML use case can be understood as a specified use case or a specific use case, that is, when the first device changes from RRC connected state to RRC disconnected state, the second target operation is only performed on the specific use case.

[0425] In some alternative embodiments, when the second target operation includes stopping the collection of the measurement data, the above data collection method further includes:

[0426] When the RRC is changed from a non-connected state to a connected state, the collection of the measurement data is resumed.

[0427] In this embodiment, when the RRC disconnected state changes to the RRC connected state, the collection of the measurement data is resumed, which enables the continued collection of measurement data related to the target AI and / or ML use cases without the need for other signaling interactions, thus reducing signaling overhead.

[0428] In some optional embodiments, the above data collection method further includes:

[0429] Upon entering the RRC idle or inactive state, determine whether to perform at least one of the following operations according to preset rules;

[0430] Stop collecting the measurement data;

[0431] Delete configuration information related to AI and / or ML;

[0432] Delete the measurement data;

[0433] Continue collecting the measurement data.

[0434] For example, in an application scenario where the first device is a UE and the second device is a network node, after the UE enters the idle state, it can determine whether to delete / retain configuration information related to AI and / or ML based on default preset rules; it can also determine whether to delete / retain recorded measurement data based on default preset rules; and it can also determine whether to stop collecting configuration information related to AI and / or ML based on default preset rules.

[0435] For example, in an application scenario where the first device is a UE and the second device is a network node, after the UE enters the inactive state, it can determine whether to delete / retain configuration information related to AI and / or ML based on default preset rules; it can also determine whether to delete / retain recorded measurement data based on default preset rules; and it can also determine whether to stop collecting configuration information related to AI and / or ML based on default preset rules.

[0436] In some optional embodiments, when it is determined, according to the preset rule, to stop collecting the measurement data, the above data collection method further includes:

[0437] Upon transition from an RRC idle or inactive state to an RRC connected state, the collection of measurement data related to the target AI and / or ML use case is resumed.

[0438] In this embodiment, when the RRC disconnected state changes to the RRC connected state, the collection of the measurement data is resumed, which enables the continued collection of measurement data related to AI and / or ML without the need for other signaling interactions, thus reducing signaling overhead.

[0439] In some optional embodiments, when the first device is switched over from a first cell, reconnected, or reselected to a second cell, the above data collection method further includes:

[0440] If the acquisition methods for the first cell and the second cell are the same, continue collecting the measurement data; or,

[0441] If the transmission methods corresponding to the first cell and the second cell are different, stop collecting the measurement data and do not delete the configuration information related to AI and / or ML, or stop collecting the measurement data and delete the configuration information related to AI and / or ML.

[0442] It should be noted that "same acquisition method" means that the execution conditions and execution parameters of the acquisition method are the same.

[0443] For example, if the first device uses the same acquisition method—collecting measurement data based on the first interval parameter—in both application scenarios where it is covered by the first cell and the second cell, then the acquisition methods for the first cell and the second cell are the same only if the type and specific value of the first interval parameter are the same; if either the type or the specific value of the first interval parameter is different, then the acquisition methods for the first cell and the second cell are different.

[0444] For example, if the first device collects measurement data when the first trigger condition is met, whether it is under the coverage of the first cell or the second cell, then the first trigger condition for both the first cell and the second cell is the same and the execution parameters involved (such as the preset speed threshold and the first geographical area) are the same. Only after the first device switches from the first cell to the second cell, rebuilds the connection, or is reselected, will it continue to collect measurement data.

[0445] In the above embodiments, in the scenario where the first device undergoes cell handover, if the acquisition methods before and after the handover are the same, the first device continues to collect measurement data; if the acquisition methods are different, the first device stops collecting measurement data. In this way, the first device and the second device do not need to perform other signaling interactions, thus reducing signaling overhead.

[0446] In some optional embodiments, when the first device is in RRC connected state and the first device is switched or reconnected to the second cell from the first cell, the above data collection method further includes:

[0447] If the transmission methods corresponding to the first cell and the second cell are the same, continue to send the measurement data to the second device;

[0448] If the transmission methods corresponding to the first cell and the second cell are different, stop sending the measurement data to the second device and do not delete the measurement data, or stop sending the measurement data to the second device and delete the measurement data.

[0449] It should be noted that "same transmission method" means that the execution conditions and parameters of the transmission method are the same. For example, if the first device uses the same transmission method in both the first and second cells to send measurement data to the second device based on the second interval parameter, then the transmission methods corresponding to the first and second cells are the same only if the type and specific value of the second interval parameter are the same; if either the type or the specific value of the second interval parameter is different, then the transmission methods corresponding to the first and second cells are different.

[0450] For example, if the first device sends measurement data to the second device when the second trigger condition is met in both the first and second cells, then the measurement data will only be sent to the second device when the second trigger conditions for the first and second cells are the same and the execution parameters involved (such as the preset speed threshold and the second geographical area) are the same.

[0451] In the above embodiments, in the scenario where the first device undergoes cell handover, if the corresponding transmission methods before and after the handover are the same, the first device continues to send measurement data to the second device; if the transmission methods are different, the first device stops sending measurement data to the second device. In this way, the first device and the second device do not need to perform other signaling interactions, thus reducing signaling overhead.

[0452] The data collection methods provided in this disclosure will be illustrated below with specific application scenarios.

[0453] Example 1: The first device is the UE, and the second device is the network node.

[0454] In some embodiments, network nodes include, but are not limited to: access network nodes, core network nodes, operator data collection nodes, or OTT servers.

[0455] As shown in Figure 2, the data collection method provided in this disclosure includes the following steps:

[0456] Step 201: The UE receives configuration information related to AI and / or ML sent by the network node; wherein the configuration information includes at least one of the following:

[0457] First configuration information related to the method of acquiring the measurement data;

[0458] Second configuration information related to the storage of the measurement data;

[0459] Third configuration information related to the method of transmitting the measurement data;

[0460] Fourth configuration information related to state transition processing;

[0461] The fifth configuration information related to community change processing.

[0462] Step 202: The UE determines the method for acquiring measurement data based on the configuration information;

[0463] The acquisition method includes one of the following:

[0464] The measurement data are collected according to the first interval parameter;

[0465] The measurement data is collected when the first triggering condition is met;

[0466] When the first triggering condition is met, the measurement data is collected according to the first interval parameter.

[0467] The first triggering condition includes at least one of the following:

[0468] The UE measures and obtains the measurement data;

[0469] The UE triggers the reporting of Radio Resource Management (RRM) measurement events;

[0470] The UE experiences a radio link failure (RLF).

[0471] UE handover failure (HOF) occurred;

[0472] The UE's moving speed is greater than or equal to a preset speed threshold;

[0473] The UE is located in the first geographic region.

[0474] The first interval parameter includes at least one of the following: a first time length, a first movement distance, and a first difference between two adjacent measurement results.

[0475] It should be noted that steps 201 to 202 above are optional, meaning that the UE can also determine the acquisition method based on preset configuration or implicit configuration.

[0476] Step 203: The UE uses a defined acquisition method to collect measurement data related to AI and / or ML;

[0477] Step 204: The UE stores measurement data related to AI and / or ML.

[0478] Step 204 is optional.

[0479] It should be noted that the UE can perform measurement data storage related to AI / ML in the default manner or in the network configuration in step 201 above.

[0480] In practice, when the AI / ML-related measurement data stored by the UE does not exceed the storage space size of the UE's default or network configuration, the storage of subsequent measurement data is executed; when the AI / ML-related measurement data stored by the UE reaches the storage space size of the UE's default or network configuration, the storage of AI / ML-related measurement data can be stopped, or the earliest AI / ML-related measurement data with the earliest time information can be deleted, and the storage of subsequent AI / ML-related measurement data can continue.

[0481] Step 205: The UE uses a defined transmission method to send measurement data related to AI and / or ML to the network node;

[0482] The sending method includes at least one of the following:

[0483] The measurement data is sent according to the second interval parameter;

[0484] When the second triggering condition is met, the measurement data is sent;

[0485] The measurement data is sent according to the data acquisition request sent by the second device.

[0486] The second triggering condition includes at least one of the following:

[0487] The UE acquires the measurement data;

[0488] The measurement data reaches the storage space threshold;

[0489] The UE's battery level is less than or equal to a preset battery threshold.

[0490] The UE is located in the second geographical region.

[0491] The second interval parameter includes at least one of the following: second time length, second movement distance, and second difference between two adjacent measurement results.

[0492] Step 206: Network nodes store measurement data related to AI and / or ML.

[0493] Step 206 is optional.

[0494] It should be noted that when a network node receives AI / ML-related measurement data (including measurement results and / or evaluation results) sent by a UE, or when a network node records / collects AI / ML-related measurement data (including measurement results and / or evaluation results) on its own, it can store the AI / ML-related measurement results or directly send the AI / ML-related measurement data to other network-side nodes or AI / ML model training nodes.

[0495] Step 207: The network node sends measurement data related to AI and / or ML to the model training node.

[0496] Step 207 is optional because network nodes can also perform AI / ML model training without sending data to the model training node. The network node performs model training based on the measurement data sent by the UE.

[0497] It should be noted that if the network side stores measurement data related to AI / ML, at least one of the following can be performed:

[0498] The measurement data is sent according to the fourth interval parameter;

[0499] When the third triggering condition is met, the measurement data is sent;

[0500] The measurement data is sent according to the data acquisition request sent by the model training node.

[0501] The third triggering condition includes at least one of the following:

[0502] The network node acquires the measurement data;

[0503] The measurement data has reached the storage space threshold.

[0504] The network node's battery level is less than or equal to a preset battery threshold.

[0505] In some embodiments, the method by which the network node sends measurement data to the model training node, as well as the corresponding execution conditions and parameters, are consistent with the method by which the UE reports measurement data to the network node and the corresponding execution conditions and parameters.

[0506] It should be noted that in the data collection process from the UE to the network-side node, and from the network-side node to other network-side nodes (including AI / ML model training nodes), the transmission methods from the UE to the network-side node and from the network-side node to other network-side nodes can be different. That is, at least one of the transmission methods, execution conditions, and parameters corresponding to the two processes must be different. For example, although both processes use a second interval parameter to send measurement data, the specific type or value of the second interval parameter can be different.

[0507] It should be noted that a data collection process may only support data collection processes from the UE to the network-side node, or from the network-side node to other network-side nodes (including AI / ML model training nodes).

[0508] Example 2: The first device is a first network node, and the second device is a model training node. In some embodiments, the model training node may be a second network node. The first and second network nodes may include, but are not limited to: access network nodes, core network nodes, operator data collection nodes, or OTT servers.

[0509] As shown in Figure 3, the data collection method provided in this disclosure includes the following steps:

[0510] Step 301: The network node receives configuration information related to AI and / or ML sent by the model training node; wherein the configuration information includes at least one of the following:

[0511] First configuration information related to the method of acquiring the measurement data;

[0512] Second configuration information related to the storage of the measurement data;

[0513] Third configuration information related to the method of transmitting the measurement data;

[0514] Fourth configuration information related to state transition processing;

[0515] The fifth configuration information related to community change processing.

[0516] Step 302: The network node determines the acquisition method based on the configuration information;

[0517] The acquisition method includes one of the following:

[0518] The measurement data are collected according to the first interval parameter;

[0519] The measurement data is collected when the first triggering condition is met;

[0520] When the first triggering condition is met, the measurement data is collected according to the first interval parameter.

[0521] The first triggering condition includes at least one of the following:

[0522] The measurement data is obtained by measuring the network nodes;

[0523] The network node triggered the reporting of a Radio Resource Management (RRM) measurement event.

[0524] The first interval parameter includes at least one of the following: a first time length, a first movement distance, and a first difference between two adjacent measurement results.

[0525] It should be noted that steps 301 to 302 above are optional, meaning that network nodes can also determine the acquisition method according to preset configuration or implicit configuration, and collect measurement data related to AI and / or ML according to the acquisition method.

[0526] Step 303: Network nodes collect measurement data related to AI and / or ML using a defined acquisition method;

[0527] Step 304: Network nodes store measurement data related to AI and / or ML.

[0528] Step 304 is optional.

[0529] It should be noted that network nodes can perform AI / ML-related measurement data storage in the default manner, or network nodes can determine whether to store AI / ML-related measurement data based on the configuration information sent by the model training nodes.

[0530] In practice, when the AI / ML-related measurement data stored by the network node does not exceed the default or network-configured storage space size of the network node, the storage of subsequent measurement data is executed; when the AI / ML-related measurement data stored by the network node reaches the default or network-configured storage space size of the UE, the storage of AI / ML-related measurement data can be stopped, or the earliest AI / ML-related measurement data with time information can be deleted, and the storage of subsequent AI / ML-related measurement data can continue.

[0531] Step 305: The network node sends measurement data related to AI and / or ML to the model training node using a defined sending method;

[0532] The sending method includes at least one of the following:

[0533] The measurement data is sent according to the second interval parameter;

[0534] When the second triggering condition is met, the measurement data is sent;

[0535] The measurement data is sent according to the data acquisition request sent by the second device.

[0536] The second triggering condition includes at least one of the following:

[0537] The network node acquires the measurement data;

[0538] The measurement data reaches the storage space threshold;

[0539] The network node's battery level is less than or equal to a preset battery threshold.

[0540] The second interval parameter includes at least one of the following: second time length, second movement distance, and second difference between two adjacent measurement results.

[0541] As shown in Figure 4, this embodiment of the present disclosure provides a data collection method applied to a second device, including:

[0542] Step 401: Receive measurement data related to AI and / or ML sent by the first device;

[0543] The measurement data includes at least one of the following:

[0544] The time information of the measurement data is obtained by measurement;

[0545] Measurement results related to AI and / or ML;

[0546] Evaluation results related to AI and / or ML;

[0547] The measurement data corresponds to the relevant information about the cell;

[0548] Configuration information related to AI and / or ML.

[0549] In some embodiments, the first device is a terminal node and the second device is a network node.

[0550] In some embodiments, the first device is a first network node, and the second device is a second network side node or a model training phase node.

[0551] It should be noted that the interpretation of the measurement data can be found in the description of the first device-side embodiment, and will not be repeated here to avoid repetition.

[0552] It should be noted that after receiving the measurement data related to AI and / or ML sent by the first device, the second device can perform model training or model inference on the second device side, or it can send it to other network nodes (such as training nodes for AI / ML models) for model training or model inference.

[0553] In the above embodiments, data can be acquired through the first device, and the second device can receive measurement data related to artificial intelligence (AI) and / or machine learning (ML) from the first device to meet the needs of model training, model inference, or model monitoring.

[0554] As shown in Figure 5, this disclosure provides a data collection method applied to a third device, including:

[0555] Step 501: Send configuration information related to AI and / or ML to the first device;

[0556] The configuration information includes at least one of the following:

[0557] First configuration information related to the method of acquiring the measurement data of the AI ​​and / or ML;

[0558] Second configuration information related to the storage of the measurement data of the AI ​​and / or ML;

[0559] Third configuration information related to the method of transmitting the measurement data of the AI ​​and / or ML;

[0560] Fourth configuration information related to state transition processing;

[0561] The fifth configuration information related to community change processing.

[0562] In some embodiments, the fourth configuration information includes at least one of the following:

[0563] The first piece of information is used to indicate whether to stop collecting measurement data related to AI and / or ML in the event of a change in the Radio Resource Control (RRC) status;

[0564] The second piece of information is used to indicate whether the configuration information should be deleted if the RRC status changes.

[0565] The third piece of information is used to indicate whether to delete measurement data related to AI and / or ML in the event of a change in RRC status;

[0566] The fourth piece of information indicates whether to resume collecting the measurement data in the event of a change in RRC status.

[0567] Accordingly, the first device determines, based on configuration information related to AI and / or ML, how to perform measurement data collection, how to transmit measurement data, and how to handle situations involving RRC state transitions or cell changes.

[0568] As shown in Figure 6, this embodiment of the present disclosure provides a data collection device 700, applied to a first device, comprising:

[0569] The first acquisition module 601 is used to acquire measurement data related to artificial intelligence (AI) and / or machine learning (ML).

[0570] The first transmitting module 602 is used to transmit the measurement data to the second device.

[0571] In some embodiments, the first acquisition module 601 is specifically used for one of the following acquisition methods:

[0572] The measurement data are collected according to the first interval parameter;

[0573] The measurement data is collected when the first triggering condition is met;

[0574] When the first triggering condition is met, the measurement data is collected according to the first interval parameter.

[0575] In some embodiments, the first transmitting module 602 is specifically used for at least one of the following transmitting methods:

[0576] The measurement data is sent according to the second interval parameter;

[0577] When the second triggering condition is met, the measurement data is sent;

[0578] The measurement data is sent according to the data acquisition request sent by the second device.

[0579] In some embodiments, the first interval parameter includes at least one of the following: a first time length, a first movement distance, and a first difference between two adjacent measurement results.

[0580] In some embodiments, the first triggering condition includes at least one of the following:

[0581] The first device measures and obtains the measurement data;

[0582] The first device triggers the reporting of a Radio Resource Management (RRM) measurement event;

[0583] The first device experienced a radio link failure (RLF).

[0584] The first device experienced a handover failure (HOF).

[0585] The moving speed of the first device is greater than or equal to a preset speed threshold;

[0586] The first device is located in the first geographical region.

[0587] In some embodiments, the second interval parameter includes at least one of the following: a second time length, a second movement distance, and a second difference between two adjacent measurement results.

[0588] In some embodiments, when the measurement data is sent in accordance with a data acquisition request sent by the second device, the apparatus further includes:

[0589] The second sending module is configured to perform one of the following before receiving the data acquisition request sent by the second device:

[0590] Based on the third interval parameter, send the first request message;

[0591] When the second triggering condition is met, the first request message is sent;

[0592] When the second triggering condition is met, the first request message is sent according to the third interval parameter.

[0593] In some embodiments, the second triggering condition includes at least one of the following:

[0594] The first device acquires the measurement data;

[0595] The measurement data reaches the storage space threshold;

[0596] The power level of the first device is less than or equal to a preset power threshold.

[0597] The first device is located in the second geographical region.

[0598] In some embodiments, the third interval parameter includes at least one of the following: a third time length, a third movement distance, and a third difference between two adjacent measurement results.

[0599] In some embodiments, when collecting the measurement data according to a first interval parameter, the first acquisition module 601 is specifically used for:

[0600] When the first device is located in the third geographic region, the measurement data is collected according to the first interval parameter; and / or,

[0601] While the first device is within a first time range, the measurement data is collected according to a first interval parameter.

[0602] In some embodiments, when the measurement data is transmitted according to a second interval parameter, the first transmitting module 602 is specifically configured to:

[0603] When the first device is located in the fourth geographic region, the measurement data is sent to the second device according to the second interval parameter; and / or,

[0604] When the second time range is in effect, the measurement data is sent to the second device according to the second interval parameter.

[0605] In some embodiments, the second sending module is specifically used for:

[0606] When the first device is in the fifth geographic region, the first request message is sent according to the third interval parameter; and / or,

[0607] When the first device is within the third time range, the first request message is sent according to the third interval parameter.

[0608] In some embodiments, the AI ​​and / or ML-related measurement data includes at least one of the following:

[0609] The time information of the measurement data is obtained by measurement;

[0610] Measurement results related to AI and / or ML;

[0611] Evaluation results related to AI and / or ML;

[0612] The measurement data corresponds to the relevant information about the cell;

[0613] Configuration information related to AI and / or ML.

[0614] In some embodiments, the device 600 further includes:

[0615] The first receiving module is used to receive configuration information related to AI and / or ML sent by the third device;

[0616] The configuration information includes at least one of the following:

[0617] First configuration information related to the method of acquiring the measurement data;

[0618] Second configuration information related to the storage of the measurement data;

[0619] Third configuration information related to the method of transmitting the measurement data;

[0620] Fourth configuration information related to state transition processing;

[0621] The fifth configuration information related to community change processing.

[0622] In some embodiments, the fourth configuration information includes at least one of the following:

[0623] The first piece of information is used to indicate whether to stop collecting the measurement data in the event of a change in the Radio Resource Control (RRC) status;

[0624] The second piece of information is used to indicate whether to delete the configuration information related to AI and / or ML in the event of a change in RRC status;

[0625] The third piece of information is used to indicate whether the measurement data should be deleted if the RRC status changes.

[0626] The fourth piece of information indicates whether to resume collecting the measurement data in the event of a change in RRC status.

[0627] In some embodiments, the device 600 further includes:

[0628] The first processing module is used to determine whether to execute the first target operation based on the fourth configuration information when the RRC status changes; wherein, each use case corresponds to one first target operation;

[0629] The first target operation includes at least one of the following:

[0630] Delete configuration information related to AI and / or ML;

[0631] Stop collecting the measurement data;

[0632] Delete the measurement data;

[0633] Resume collecting the measurement data;

[0634] Continue collecting the measurement data.

[0635] In some embodiments, the device 600 further includes:

[0636] The second processing module is used to determine whether to perform a second target operation for the target AI and / or ML use case when the RRC connected state changes to the RRC disconnected state.

[0637] The second target operation includes at least one of the following:

[0638] Stop collecting measurement data related to the target AI and / or ML use cases;

[0639] Delete the configuration information related to the target AI and / or ML use case;

[0640] Delete measurement data related to the target AI and / or ML use case;

[0641] Continue collecting measurement data related to the target AI and / or ML use case. In some embodiments, where the second target operation includes stopping the collection of the measurement data, the second processing module is further configured to resume collecting measurement data related to the target AI and / or ML use case upon changing from an RRC disconnected state to an RRC connected state.

[0642] In some embodiments, the device 600 further includes:

[0643] The third processing module is used to determine, according to preset rules, whether to perform at least one of the following operations when entering the RRC idle state or inactive state;

[0644] Stop collecting the measurement data;

[0645] Delete configuration information related to AI and / or ML;

[0646] Delete the measurement data;

[0647] Continue collecting the measurement data.

[0648] In some embodiments, if it is determined, according to the preset rule, to stop collecting the measurement data, the third processing module is further configured to:

[0649] When the RRC changes from an idle or inactive state to an RRC connected state, the collection of the measurement data resumes.

[0650] In some embodiments, when the first device is switched over from a first cell, reconnected, or reselected to a second cell, the apparatus 600 further includes:

[0651] The fourth processing module is configured to continue collecting the measurement data when the acquisition methods for the first cell and the second cell are the same; or,

[0652] The fifth processing module is configured to, when the acquisition methods corresponding to the first cell and the second cell are different, either stop collecting the measurement data and not delete the configuration information related to AI and / or ML, or stop collecting the measurement data and delete the configuration information related to AI and / or ML.

[0653] In some embodiments, when the first device is in RRC connected state and the first device is switched or reconnected to the second cell from the first cell, the apparatus 600 further includes:

[0654] The sixth processing module is configured to continue sending the measurement data to the second device when the transmission methods corresponding to the first cell and the second cell are the same; or,

[0655] The seventh processing module is configured to, when the transmission methods corresponding to the first cell and the second cell are different, either stop sending the measurement data to the second device without deleting the measurement data, or stop sending the measurement data to the second device and delete the measurement data.

[0656] It should be noted that this device embodiment corresponds one-to-one with the above method embodiments. All implementation methods in the above method embodiments are applicable to this device embodiment and can achieve the same technical effect.

[0657] As shown in Figure 7, this embodiment of the present disclosure provides a data collection device 700, applied to a second device, comprising:

[0658] The second receiving module 701 is used to receive measurement data related to AI and / or ML sent by the first device;

[0659] The measurement data includes at least one of the following:

[0660] The time information of the measurement data is obtained by measurement;

[0661] Measurement results related to AI and / or ML;

[0662] Evaluation results related to AI and / or ML;

[0663] The measurement data corresponds to the relevant information about the cell;

[0664] Configuration information related to AI and / or ML.

[0665] It should be noted that this device embodiment corresponds one-to-one with the above method embodiments. All implementation methods in the above method embodiments are applicable to this device embodiment and can achieve the same technical effect.

[0666] As shown in Figure 8, this embodiment of the present disclosure provides a data collection device 800, applied to a third device, comprising:

[0667] The third sending module 801 is used to send configuration information related to AI and / or ML to the first device;

[0668] The configuration information includes at least one of the following:

[0669] First configuration information related to the method of acquiring the measurement data of the AI ​​and / or ML;

[0670] Second configuration information related to the storage of the measurement data of the AI ​​and / or ML;

[0671] Third configuration information related to the method of transmitting the measurement data of the AI ​​and / or ML;

[0672] Fourth configuration information related to state transition processing;

[0673] The fifth configuration information related to community change processing.

[0674] In some embodiments, the fourth configuration information includes at least one of the following:

[0675] The first piece of information is used to indicate whether to stop collecting measurement data related to AI and / or ML in the event of a change in the Radio Resource Control (RRC) status;

[0676] The second piece of information is used to indicate whether the configuration information should be deleted if the RRC status changes.

[0677] The third piece of information is used to indicate whether to delete measurement data related to AI and / or ML in the event of a change in RRC status;

[0678] The fourth piece of information indicates whether to resume collecting the measurement data in the event of a change in RRC status.

[0679] It should be noted that this device embodiment corresponds one-to-one with the above method embodiments. All implementation methods in the above method embodiments are applicable to this device embodiment and can achieve the same technical effect.

[0680] As shown in Figure 9, this embodiment of the present disclosure also provides a first device, including a processor 900, a transceiver 910, a memory 920, and a program stored in the memory 920 and executable on the processor 900; wherein the transceiver 910 is connected to the processor 900 and the memory 920 via a bus interface, and the processor 900 is used to read the program in the memory and execute the following processes:

[0681] Acquire measurement data related to artificial intelligence (AI) and / or machine learning (ML);

[0682] The measurement data is sent to the second device.

[0683] Transceiver 910 is used to receive and send data under the control of processor 900.

[0684] In Figure 9, the bus architecture can include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors represented by processor 900 and memory represented by memory 920. The bus architecture can also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. The transceiver 910 can be multiple elements, including a transmitter and a receiver, providing a unit for communicating with various other devices over a transmission medium, including wireless channels, wired channels, optical fibers, and other transmission media.

[0685] The processor 900 is responsible for managing the bus architecture and general processing, while the memory 920 can store the data used by the processor 900 during operation.

[0686] In some embodiments, the processor 900 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a complex programmable logic device (CPLD), and the processor may also adopt a multi-core architecture.

[0687] The processor executes any of the methods described in the embodiments of this disclosure by invoking a computer program stored in memory, according to the obtained executable instructions. The processor and memory may also be physically separated.

[0688] In some embodiments, the processor 900 is specifically configured to read a program from memory and execute one of the following acquisition methods:

[0689] The measurement data are collected according to the first interval parameter;

[0690] The measurement data is collected when the first triggering condition is met;

[0691] When the first triggering condition is met, the measurement data is collected according to the first interval parameter.

[0692] In some embodiments, the processor 900 is specifically configured to read a program from memory and execute one of the following transmission methods:

[0693] The measurement data is sent according to the second interval parameter;

[0694] When the second triggering condition is met, the measurement data is sent;

[0695] The measurement data is sent according to the data acquisition request sent by the second device.

[0696] In some embodiments, the first interval parameter includes at least one of the following: a first time length, a first movement distance, and a first difference between two adjacent measurement results.

[0697] In some embodiments, the first triggering condition includes at least one of the following:

[0698] The first device measures and obtains the measurement data;

[0699] The first device triggers the reporting of a Radio Resource Management (RRM) measurement event;

[0700] The first device experienced a radio link failure (RLF).

[0701] The first device experienced a handover failure (HOF).

[0702] The moving speed of the first device is greater than or equal to a preset speed threshold;

[0703] The first device is located in the first geographical region.

[0704] In some embodiments, the second interval parameter includes at least one of the following: a second time length, a second movement distance, and a second difference between two adjacent measurement results.

[0705] In some embodiments, when the measurement data is sent according to a data acquisition request sent by the second device, before receiving the data acquisition request sent by the second device, the processor 900 is further configured to read a program in memory and execute one of the following processes:

[0706] Based on the third interval parameter, a first request message is sent, which is used to request the measurement data to be sent to the second device;

[0707] When the second triggering condition is met, the first request message is sent;

[0708] When the second triggering condition is met, the first request message is sent according to the third interval parameter.

[0709] In some embodiments, the second triggering condition includes at least one of the following:

[0710] The first device acquires the measurement data;

[0711] The measurement data reaches the storage space threshold;

[0712] The power level of the first device is less than or equal to a preset power threshold.

[0713] The first device is located in the second geographical region.

[0714] In some embodiments, the third interval parameter includes at least one of the following: a third time length, a third movement distance, and a third difference between two adjacent measurement results.

[0715] In some embodiments, when the measurement data is collected according to a first interval parameter, the processor 900 is specifically configured to read a program from memory and execute the following processes:

[0716] When the first device is located in the third geographic region, the measurement data is collected according to the first interval parameter; and / or,

[0717] While the first device is within a first time range, the measurement data is collected according to a first interval parameter.

[0718] In some embodiments, the processor 900 is specifically configured to read a program from memory and execute the following processes:

[0719] When the first device is located in the fourth geographic region, the measurement data is sent to the second device according to the second interval parameter; and / or,

[0720] When the second time range is in effect, the measurement data is sent to the second device according to the second interval parameter.

[0721] In some embodiments, the processor 900 is specifically configured to read a program from memory and execute the following processes:

[0722] When the first device is in the fifth geographic region, the first request message is sent according to the third interval parameter; and / or

[0723] When the first device is within the third time range, the first request message is sent according to the third interval parameter.

[0724] In some embodiments, the AI ​​and / or ML-related measurement data includes at least one of the following:

[0725] The time information of the measurement data is obtained by measurement;

[0726] Measurement results related to AI and / or ML;

[0727] Evaluation results related to AI and / or ML;

[0728] The measurement data corresponds to the relevant information about the cell;

[0729] Configuration information related to AI and / or ML.

[0730] In some embodiments, the processor 900 is specifically configured to read a program from memory and execute the following processes:

[0731] Receive configuration information related to AI and / or ML sent by a third device;

[0732] The configuration information includes at least one of the following:

[0733] First configuration information related to the method of acquiring the measurement data;

[0734] Second configuration information related to the storage of the measurement data;

[0735] Third configuration information related to the method of transmitting the measurement data;

[0736] Fourth configuration information related to state transition processing;

[0737] The fifth configuration information related to community change processing.

[0738] In some embodiments, the fourth configuration information includes at least one of the following:

[0739] The first piece of information is used to indicate whether to stop collecting the measurement data in the event of a change in the Radio Resource Control (RRC) status;

[0740] The second piece of information is used to indicate whether to delete the configuration information related to AI and / or ML in the event of a change in RRC status;

[0741] The third piece of information is used to indicate whether the measurement data should be deleted if the RRC status changes.

[0742] The fourth piece of information indicates whether to resume collecting the measurement data in the event of a change in RRC status.

[0743] In some embodiments, the processor 900 is further configured to read a program from memory and execute the following processes:

[0744] In the event of a change in RRC status, it is determined whether to execute the first target operation based on the fourth configuration information; wherein, each use case corresponds to one first target operation;

[0745] The first target operation includes at least one of the following:

[0746] Delete configuration information related to AI and / or ML;

[0747] Stop collecting the measurement data;

[0748] Delete the measurement data;

[0749] Resume collecting the measurement data;

[0750] Continue collecting the measurement data.

[0751] In some embodiments, the processor 900 is further configured to read a program from memory and execute the following processes:

[0752] In the event of a change from RRC connected state to RRC disconnected state, determine whether to perform a second target operation for the target AI and / or ML use case;

[0753] The second target operation includes at least one of the following:

[0754] Stop collecting measurement data related to the target AI and / or ML use cases;

[0755] Delete the configuration information related to the target AI and / or ML use case;

[0756] Delete measurement data related to the target AI and / or ML use case;

[0757] Continue collecting measurement data related to the target AI and / or ML use case. In some embodiments, where the second target operation includes stopping the collection of the measurement data, the processor 900 is further configured to read a program from memory and execute the following process:

[0758] In the event of a change from an RRC disconnected state to an RRC connected state, the collection of measurement data related to the target AI and / or ML use case is resumed.

[0759] In some embodiments, the processor 900 is further configured to read a program from memory and execute the following processes:

[0760] Upon entering the RRC idle or inactive state, determine whether to perform at least one of the following operations according to preset rules;

[0761] Stop collecting the measurement data;

[0762] Delete configuration information related to AI and / or ML;

[0763] Delete the measurement data;

[0764] Continue collecting the measurement data.

[0765] In some embodiments, if it is determined, according to the preset rule, to stop collecting the measurement data, the processor 900 is further configured to read the program in the memory and execute the following process:

[0766] When the RRC changes from an idle or inactive state to an RRC connected state, the collection of the measurement data resumes.

[0767] In some embodiments, when the first device is switched over from a first cell, reconnected, or reselected to a second cell, the processor 900 is further configured to read a program from the memory and execute the following processes:

[0768] If the acquisition methods for the first cell and the second cell are the same, continue collecting the measurement data; or,

[0769] If the acquisition methods corresponding to the first cell and the second cell are different, stop collecting the measurement data and do not delete the configuration information related to AI and / or ML, or stop collecting the measurement data and delete the configuration information related to AI and / or ML.

[0770] In some embodiments, when the first device is in an RRC connected state and the first device is switched or reconnected to a second cell from a first cell, the processor 900 is further configured to read a program from the memory and execute the following process:

[0771] If the transmission methods corresponding to the first cell and the second cell are the same, continue to send the measurement data to the second device;

[0772] If the transmission methods corresponding to the first cell and the second cell are different, stop sending the measurement data to the second device and do not delete the measurement data, or stop sending the measurement data to the second device and delete the measurement data.

[0773] It should be noted that the first device provided in this embodiment can implement all the method steps implemented in the method embodiment applied to the first device side and can achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.

[0774] As shown in Figure 10, this embodiment of the present disclosure also provides a second device, including a processor 1000, a transceiver 1010, a memory 1020, and a program stored in the memory 1020 and executable on the processor 1000; wherein the transceiver 1010 is connected to the processor 1000 and the memory 1020 via a bus interface, and the processor 1000 is used to read the program in the memory and execute the following processes:

[0775] Receive measurement data related to AI and / or ML sent by the first device;

[0776] The measurement data includes at least one of the following:

[0777] The time information of the measurement data is obtained by measurement;

[0778] Measurement results related to AI and / or ML;

[0779] Evaluation results related to AI and / or ML;

[0780] The measurement data corresponds to the relevant information about the cell;

[0781] Configuration information related to AI and / or ML.

[0782] Transceiver 1010 is used to receive and send data under the control of processor 1000.

[0783] In Figure 10, the bus architecture may include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors represented by processor 1000 and memory represented by memory 1020 together. The bus architecture may also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. The transceiver 1010 may be multiple elements, including a transmitter and a receiver, providing a unit for communicating with various other devices over a transmission medium, including wireless channels, wired channels, optical fibers, and other transmission media.

[0784] The processor 1000 is responsible for managing the bus architecture and general processing, while the memory 1020 can store the data used by the processor 1000 when performing operations.

[0785] In some embodiments, the processor 1000 may be a CPU, ASIC, FPGA or CPLD, and the processor may also adopt a multi-core architecture.

[0786] The processor executes any of the methods described in the embodiments of this disclosure by invoking a computer program stored in memory, according to the obtained executable instructions. The processor and memory may also be physically separated.

[0787] It should be noted that the second device provided in this embodiment can implement all the method steps implemented in the method embodiment applied to the second device side and can achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.

[0788] As shown in Figure 11, this embodiment of the present disclosure also provides a third device, including a processor 1100, a transceiver 1110, a memory 1120, and a program stored in the memory 1120 and executable on the processor 1100; wherein the transceiver 1110 is connected to the processor 1100 and the memory 1120 via a bus interface, and the processor 1100 is used to read the program in the memory and execute the following processes:

[0789] Send configuration information related to AI and / or ML to the first device;

[0790] The configuration information includes at least one of the following:

[0791] First configuration information related to the method of acquiring the measurement data of the AI ​​and / or ML;

[0792] Second configuration information related to the storage of the measurement data of the AI ​​and / or ML;

[0793] Third configuration information related to the method of transmitting the measurement data of the AI ​​and / or ML;

[0794] Fourth configuration information related to state transition processing;

[0795] The fifth configuration information related to community change processing.

[0796] Transceiver 1110 is used to receive and send data under the control of processor 1100.

[0797] In Figure 11, the bus architecture may include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors represented by processor 1100 and memory represented by memory 1120. The bus architecture may also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. Transceiver 1110 may be multiple elements, including transmitters and receivers, providing units for communicating with various other devices over transmission media, including wireless channels, wired channels, optical fibers, etc. Processor 1100 is responsible for managing the bus architecture and general processing, and memory 1120 may store data used by processor 1100 during operation.

[0798] In some embodiments, the processor 1100 may be a CPU, ASIC, FPGA or CPLD, and the processor may also adopt a multi-core architecture.

[0799] The processor executes any of the methods described in the embodiments of this disclosure by invoking a computer program stored in memory, according to the obtained executable instructions. The processor and memory may also be physically separated.

[0800] In some embodiments, the fourth configuration information includes at least one of the following:

[0801] The first piece of information is used to indicate whether to stop collecting measurement data related to AI and / or ML in the event of a change in the Radio Resource Control (RRC) status;

[0802] The second piece of information is used to indicate whether the configuration information should be deleted if the RRC status changes.

[0803] The third piece of information is used to indicate whether to delete measurement data related to AI and / or ML in the event of a change in RRC status;

[0804] The fourth piece of information indicates whether to resume collecting the measurement data in the event of a change in RRC status.

[0805] It should be noted that the third device provided in this embodiment can implement all the method steps implemented in the method embodiment applied to the first device side and can achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.

[0806] This disclosure also provides a computer-readable storage medium storing a computer program thereon, wherein the computer program, when executed by a processor, implements the steps of a signal measurement method applied to a first device. The processor-readable storage medium can be any available medium or data storage device accessible to the processor, including but not limited to magnetic storage (e.g., floppy disk, hard disk, magnetic tape, magneto-optical disk (MO), etc.), optical storage (e.g., compact disc (CD), digital video disc (DVD), Blu-ray disc (BD), high-definition versatile disc (HVD), etc.), and semiconductor storage (e.g., ROM, erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), non-volatile memory (NAND (Non-volatile Memory Device) FLASH), solid-state drives (SSDs), etc.).

[0807] This disclosure also provides a computer program product, including computer instructions. When executed by a processor, these computer instructions implement the various processes in the above method embodiments and achieve the same technical effects. To avoid repetition, further details are omitted here.

[0808] Those skilled in the art will understand that embodiments of this disclosure can be provided as methods, systems, or computer program products. Therefore, this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this disclosure can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0809] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-executable instructions. These computer-executable instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more flowchart illustrations and / or one or more block diagrams.

[0810] These processor-executable instructions may also be stored in a processor-readable memory that can instruct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the processor-readable memory produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0811] These processor-executable instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

[0812] Furthermore, it should be noted that in the apparatus and method of this disclosure, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent solutions of this disclosure. Moreover, the steps performing the above series of processes can naturally be executed in the order described, but are not necessarily required to be executed in chronological order; some steps can be executed in parallel or independently of each other. Those skilled in the art will understand that all or any step or component of the method and apparatus of this disclosure can be implemented in any computing device (including processors, storage media, etc.) or network of computing devices, in hardware, firmware, software, or a combination thereof, which can be achieved by those skilled in the art using their basic programming skills after reading the description of this disclosure.

[0813] It should be noted that the above division of modules is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, these modules can be implemented entirely in software via processing element calls; they can be fully implemented in hardware; or some modules can be implemented by processing element calls to software, while others are implemented in hardware. For example, a module can be a separate processing element, or it can be integrated into a chip in the aforementioned device. Alternatively, it can be stored as program code in the memory of the aforementioned device, and its function can be called and executed by a processing element of the device. The implementation of other modules is similar. Moreover, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element mentioned here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed through integrated logic circuits in the hardware of the processor element or through software instructions.

[0814] For example, each module, unit, subunit, or submodule can be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs). As another example, when a module is implemented using processing element scheduler code, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor capable of calling program code. Furthermore, these modules can be integrated together to implement a system-on-a-chip (SOC).

[0815] The terms “first,” “second,” etc., used in this disclosure and in the claims are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of this disclosure described herein may be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus. Additionally, the use of “and / or” in the specification and claims indicates at least one of the connected objects, such as A and / or B and / or C, indicating seven possibilities: A alone, B alone, C alone, and both A and B, both B and C, both A and C, and A, B, and C. Similarly, the use of “at least one of A and B” in this specification and claims should be understood as “A alone, B alone, or both A and B.”

[0816] Obviously, those skilled in the art can make various modifications and variations to this disclosure without departing from its spirit and scope. Therefore, if such modifications and variations fall within the scope of the claims of this disclosure and their equivalents, this disclosure is also intended to include such modifications and variations.

Claims

A data collection method applied to a first device, the method comprising: obtaining measurement data related to artificial intelligence (AI) and / or machine learning (ML); sending the measurement data to a second device. The method of claim 1, wherein, The obtaining of the measurement data related to AI and / or ML comprises one of the following obtaining manners: collecting the measurement data according to a first interval parameter; collecting the measurement data in a case where a first trigger condition is met; and / or collecting the measurement data according to the first interval parameter in a case where the first trigger condition is met. The method of claim 1, wherein, The sending of the measurement data to the second device comprises at least one of the following sending manners: sending the measurement data according to a second interval parameter; sending the measurement data in a case where a second trigger condition is met; and / or sending the measurement data according to a data acquisition request sent by the second device. The method of claim 2, wherein, The first interval parameter comprises at least one of the following: a first time length, a first moving distance, and a first difference between adjacent measurement results. The method of claim 2, wherein, The first trigger condition comprises at least one of the following: the first device measures the measurement data; the first device triggers reporting of a radio resource management (RRM) measurement event; the first device experiences a radio link failure (RLF); the first device experiences a handover failure (HOF); a moving speed of the first device is greater than or equal to a preset speed threshold; and / or the first device is in a first geographic area. The method of claim 3, wherein, The second interval parameter comprises at least one of the following: a second time length, a second moving distance, and a second difference between adjacent measurement results. The method of claim 3, wherein, In a case where the sending manner comprises sending the measurement data according to the data acquisition request sent by the second device, before receiving the data acquisition request sent by the second device, the method further comprises one of the following: sending a first request message according to a third interval parameter, the first request message being used to request sending of the measurement data to the second device; sending the first request message in a case where a second trigger condition is met; and / or sending the first request message according to the third interval parameter in a case where the second trigger condition is met. The method according to claim 3 or 7, wherein The second trigger condition comprises at least one of the following: the first device obtains the measurement data; the measurement data reaches a storage space threshold value; a power of the first device is less than or equal to a preset power threshold value; and / or the first device is in a second geographic area. The method of claim 7, wherein, The third interval parameter comprises at least one of the following: a third time length, a third moving distance, and a third difference between adjacent measurement results. The method of claim 2, wherein, The collecting of the measurement data according to the first interval parameter comprises: collecting the measurement data according to the first interval parameter in a case where the first device is in a third geographic area; and / or collecting the measurement data according to the first interval parameter in a case where the first device is in a first time range. The method of claim 3, wherein, The sending of the measurement data according to the second interval parameter comprises: In a case that the first device is in a fourth geographical area, the measurement data is transmitted to the second device according to a second interval parameter; and / or, In a case that a second time range is reached, the measurement data is transmitted to the second device according to a second interval parameter. The method of claim 7, wherein, The transmitting the first request message according to the third interval parameter comprises: In a case that the first device is in a fifth geographical area, the first request message is transmitted according to a third interval parameter; and / or In a case that a third time range is reached, the first request message is transmitted according to a third interval parameter. The method of claim 1, wherein, The AI and / or ML related measurement data comprises at least one of: Time information of obtaining the measurement data; AI and / or ML related measurement result; AI and / or ML related evaluation result; Cell related information corresponding to the measurement data; AI and / or ML related condition configuration information. The method according to claim 1, further comprising: receiving AI and / or ML related configuration information transmitted by a third device; wherein the configuration information comprises at least one of: first configuration information related to a manner of obtaining the measurement data; second configuration information related to storage of the measurement data; third configuration information related to a manner of transmitting the measurement data; fourth configuration information related to state transition processing; fifth configuration information related to cell change processing. The method of claim 14, wherein, The fourth configuration information comprises at least one of: first information indicating whether to stop collecting the measurement data in a case that a radio resource control (RRC) state is changed; second information indicating whether to delete the AI and / or ML related configuration information in a case that the RRC state is changed; third information indicating whether to delete the measurement data in a case that the RRC state is changed; fourth information indicating whether to resume collecting the measurement data in a case that the RRC state is changed. The method according to claim 14, further comprising: in a case that the RRC state is changed, determining whether to perform a first target operation according to the fourth configuration information; wherein each use case corresponds to one of the first target operations; the first target operation comprises at least one of: deleting AI and / or ML related configuration information; stopping collecting the measurement data; deleting the measurement data; resuming collecting the measurement data; continuing collecting the measurement data. The method according to claim 1, further comprising: in a case that an RRC connected state is changed to an RRC non-connected state, determining whether to perform a second target operation for a target AI and / or ML use case; wherein the second target operation comprises at least one of: stopping collecting measurement data related to the target AI and / or ML use case; deleting configuration information related to the target AI and / or ML use case; deleting measurement data related to the target AI and / or ML use case; continuing collecting measurement data related to the target AI and / or ML use case. The method of claim 17, wherein, In a case where the second target operation comprises stopping collection of the measurement data, the method further comprises: In a case of changing from an RRC idle state or an RRC inactive state to an RRC connected state, resuming collection of the measurement data related to the target AI and / or ML use case. The method of claim 1, further comprising: In a case of entering an RRC idle state or an RRC inactive state, determining whether to perform at least one of the following operations according to a preset rule; stopping collection of the measurement data; deleting configuration information related to the AI and / or ML; deleting the measurement data; continuing collection of the measurement data. The method of claim 19, wherein, In a case where it is determined to perform stopping collection of the measurement data according to the preset rule, the method further comprises: In a case of changing from an RRC idle state or an RRC inactive state to an RRC connected state, resuming collection of the measurement data. The method of claim 2, wherein, In a case where the first device is handed over from a first cell or reestablishes connection or reselects to a second cell, the method further comprises: In a case where the acquisition manners corresponding to the first cell and the second cell are the same, continuing collection of the measurement data; or, In a case where the acquisition manners corresponding to the first cell and the second cell are different, stopping collection of the measurement data and not deleting configuration information related to AI and / or ML, or stopping collection of the measurement data and deleting configuration information related to AI and / or ML. The method of claim 3, wherein, In a case where the first device is in an RRC connected state and the first device is handed over from a first cell or reestablishes connection to a second cell, the method further comprises: In a case where the transmission manners corresponding to the first cell and the second cell are the same, continuing transmission of the measurement data to the second device; In a case where the transmission manners corresponding to the first cell and the second cell are different, stopping transmission of the measurement data to the second device and not deleting the measurement data, or stopping transmission of the measurement data to the second device and deleting the measurement data. A data collection method applied to a second device, the method comprising: receiving measurement data related to AI and / or ML transmitted by a first device; wherein the measurement data comprises at least one of the following: time information of measuring the measurement data; a measurement result related to AI and / or ML; an evaluation result related to AI and / or ML; cell-related information corresponding to the measurement data; condition configuration information related to AI and / or ML. A data collection method applied to a third device, the method comprising: transmitting configuration information related to AI and / or ML to a first device; wherein the configuration information comprises at least one of the following: first configuration information related to an acquisition manner of measurement data of the AI and / or ML; second configuration information related to storage of measurement data of the AI and / or ML; third configuration information related to a transmission manner of measurement data of the AI and / or ML; fourth configuration information related to state transition processing; fifth configuration information related to cell change processing. The method of claim 24, wherein, The fourth configuration information comprises at least one of the following: The first information is used to indicate whether to stop collecting the measurement data related to AI and / or ML in the case that the RRC state changes; The second information is used to indicate whether to delete the configuration information in the case that the RRC state changes; The third information is used to indicate whether to delete the measurement data related to AI and / or ML in the case that the RRC state changes; The fourth information is used to indicate whether to resume collecting the measurement data in the case that the RRC state changes. A first device comprising: The memory, the transceiver, and the processor; The memory is used to store the computer program; The transceiver is used to transceive data under the control of the processor; The processor is used to read the computer program in the memory and perform the following operations: Obtain measurement data related to artificial intelligence (AI) and / or machine learning (ML); Send the measurement data to a second device. The first device of claim 26, wherein The processor is specifically configured to read the computer program in the memory and perform one of the following obtaining manners: Collect the measurement data according to a first interval parameter; Collect the measurement data in the case that a first trigger condition is met; Collect the measurement data according to the first interval parameter in the case that the first trigger condition is met. The first device of claim 26, wherein The processor is specifically configured to read the computer program in the memory and perform one of the following sending manners: Send the measurement data according to a second interval parameter; Send the measurement data in the case that a second trigger condition is met; Send the measurement data according to a data acquisition request sent by the second device. The first device of claim 27, wherein The first interval parameter includes at least one of the following: a first time length, a first moving distance, and a first difference value between adjacent measurement results. The first device of claim 27, wherein The first trigger condition includes at least one of the following: The first device measures the measurement data; The first device triggers reporting of a radio resource management (RRM) measurement event; The first device experiences a radio link failure (RLF); The first device experiences a handover failure (HOF); The moving speed of the first device is greater than or equal to a preset speed threshold; The first device is in a first geographic area. The first device of claim 28, wherein The second interval parameter includes at least one of the following: a second time length, a second moving distance, and a second difference value between adjacent measurement results. The first device of claim 28, wherein Before receiving the data acquisition request sent by the second device, the processor is further configured to read the computer program in the memory and perform one of the following operations: Send a first request message according to a third interval parameter, the first request message being used to request sending the measurement data to the second device; Send the first request message in the case that a second trigger condition is met; Send the first request message according to the third interval parameter in the case that the second trigger condition is met. The first device according to claim 28 or 32, wherein The second trigger condition includes at least one of the following: The first device obtains the measurement data; The measurement data reaches a storage space threshold value; The power of the first device is less than or equal to a preset power threshold value; The first device is in a second geographic area. The first device of claim 32, wherein The third interval parameter comprises at least one of the following: a third time length, a third moving distance, and a third difference value between adjacent measurement results. The first device of claim 27, wherein The processor is specifically configured to read a computer program in the memory and perform the following operations: In a case where the first device is in a third geographic area, the measurement data is collected according to a first interval parameter; and / or, In a case where the first device is in a first time range, the measurement data is collected according to a first interval parameter. The first device of claim 28, wherein The processor is specifically configured to read a computer program in the memory and perform the following operations: In a case where the first device is in a fourth geographic area, the measurement data is sent to the second device according to a second interval parameter; and / or, In a case where the first device is in a second time range, the measurement data is sent to the second device according to a second interval parameter. The first device of claim 32, wherein The processor is specifically configured to read a computer program in the memory and perform the following operations: In a case where the first device is in a fifth geographic area, the first request message is sent according to a third interval parameter; and / or, In a case where the first device is in a third time range, the first request message is sent according to a third interval parameter. The first device of claim 26, wherein The measurement data related to AI and / or ML comprises at least one of the following: Time information of measuring the measurement data; AI and / or ML related measurement results; AI and / or ML related evaluation results; Cell related information corresponding to the measurement data; AI and / or ML related condition configuration information. The first device of claim 26, wherein The processor is further configured to read a computer program in the memory and perform the following operations: Receiving AI and / or ML related configuration information sent by a third device; The configuration information comprises at least one of the following: First configuration information related to a measurement data acquisition method; Second configuration information related to measurement data storage; Third configuration information related to a measurement data sending method; Fourth configuration information related to state conversion processing; Fifth configuration information related to cell change processing. The first device of claim 39, wherein The fourth configuration information comprises at least one of the following: First information for indicating whether to stop collecting the measurement data in a case where a radio resource control (RRC) state changes; Second information for indicating whether to delete the AI and / or ML related configuration information in a case where the RRC state changes; Third information for indicating whether to delete the measurement data in a case where the RRC state changes; Fourth information for indicating whether to resume collecting the measurement data in a case where the RRC state changes. The first device of claim 39, wherein The processor is further configured to read a computer program in the memory and perform the following operations: In a case where the RRC state changes, determining whether to perform a first target operation according to the fourth configuration information; wherein each use case corresponds to a first target operation; The first target operation comprises at least one of the following: Deleting AI and / or ML related configuration information; Stopping collecting the measurement data; Deleting the measurement data; resume collecting the measurement data; continue collecting the measurement data. The first device of claim 26, wherein The processor is further configured to read the computer program in the memory and perform the following operations: In a case of changing from an RRC connected state to an RRC non-connected state, determining whether to perform a second target operation for a target AI and / or ML use case; The second target operation includes at least one of: stopping collecting measurement data related to the target AI and / or ML use case; deleting configuration information related to the target AI and / or ML use case; deleting measurement data related to the target AI and / or ML use case; continuing collecting measurement data related to the target AI and / or ML use case. The first device of claim 42, wherein In a case where the second target operation includes stopping collecting the measurement data, the processor is further configured to read the computer program in the memory and perform the following operation: In a case of changing from an RRC non-connected state to an RRC connected state, resuming collecting measurement data related to the target AI and / or ML use case. The first device of claim 26, wherein The processor is further configured to read the computer program in the memory and perform the following operation: In a case of entering an RRC idle state or an RRC inactive state, determining whether to perform at least one of the following operations according to a preset rule; stopping collecting the measurement data; deleting configuration information related to the AI and / or ML; deleting the measurement data; continuing collecting the measurement data. The first device of claim 44, wherein In a case where it is determined to perform stopping collecting the measurement data according to the preset rule, the processor is further configured to read the computer program in the memory and perform the following operation: In a case of changing from an RRC idle state or an RRC inactive state to an RRC connected state, resuming collecting the measurement data. The first device of claim 27, wherein In a case where the first device is switched by a first cell or reconnected or reselected to a second cell, the processor is further configured to read the computer program in the memory and perform the following operation: In a case where the acquisition manners corresponding to the first cell and the second cell are the same, continuing collecting the measurement data; or In a case where the acquisition manners corresponding to the first cell and the second cell are different, stopping collecting the measurement data and not deleting configuration information related to AI and / or ML, or stopping collecting the measurement data and deleting configuration information related to AI and / or ML. The first device of claim 28, wherein In a case where the first device is in an RRC connected state and the first device is switched by a first cell or reconnected to a second cell, the processor is further configured to read the computer program in the memory and perform the following operation: In a case where the transmission manners corresponding to the first cell and the second cell are the same, continuing transmitting the measurement data to the second device; or In a case where the transmission manners corresponding to the first cell and the second cell are different, stopping transmitting the measurement data to the second device and not deleting the measurement data, or stopping transmitting the measurement data to the second device and deleting the measurement data. A second device comprising: a memory, a transceiver, and a processor; a memory, configured to store a computer program; a transceiver configured to transceive data under control of the processor; a processor configured to read a computer program in the memory and perform the following operations: receiving, from a first device, measurement data related to AI and / or ML; wherein the measurement data comprises at least one of: time information of obtaining the measurement data; a measurement result related to AI and / or ML; an evaluation result related to AI and / or ML; cell-related information corresponding to the measurement data; condition configuration information related to AI and / or ML. A third device comprising: a memory, a transceiver, and a processor; a memory configured to store a computer program; a transceiver configured to transceive data under control of the processor; a processor configured to read a computer program in the memory and perform the following operations: sending, to a first device, configuration information related to AI and / or ML; wherein the configuration information comprises at least one of: first configuration information related to a manner of obtaining measurement data of the AI and / or ML; second configuration information related to storage of the measurement data of the AI and / or ML; third configuration information related to a manner of sending the measurement data of the AI and / or ML; fourth configuration information related to a state transition process; fifth configuration information related to a cell change process. The third device of claim 49, wherein The fourth configuration information comprises at least one of: first information indicating whether to stop collecting measurement data related to AI and / or ML in a case where a radio resource control (RRC) state is changed; second information indicating whether to delete the configuration information in the case where the RRC state is changed; third information indicating whether to delete measurement data related to AI and / or ML in the case where the RRC state is changed; fourth information indicating whether to resume collecting the measurement data in the case where the RRC state is changed. A data collection apparatus applied to a first device, the apparatus comprising: a first obtaining module configured to obtain measurement data related to artificial intelligence (AI) and / or machine learning (ML); a first sending module configured to send, to a second device, the measurement data. A data collection apparatus applied to a second device, the apparatus comprising: a second receiving module configured to receive, from a first device, measurement data related to AI and / or ML; wherein the measurement data comprises at least one of: time information of obtaining the measurement data; a measurement result related to AI and / or ML; an evaluation result related to AI and / or ML; cell-related information corresponding to the measurement data; condition configuration information related to AI and / or ML. A data collection apparatus applied to a third device, the apparatus comprising: a third sending module configured to send, to a first device, configuration information related to AI and / or ML; wherein the configuration information comprises at least one of: first configuration information related to a manner of obtaining measurement data of the AI and / or ML; second configuration information related to storage of the measurement data of the AI and / or ML; third configuration information related to a manner of sending the measurement data of the AI and / or ML; Fourth configuration information related to the state transition processing; Fifth configuration information related to the cell change processing. A processor-readable storage medium storing a computer program for causing a processor to perform the method of any one of claims 1 to 22, or the method of claim 23, or the method of claims 24 to 25.

Images