Data collection method and apparatus

Abstract

Embodiments of the present application provide a data collection method and apparatus. The method comprises: a first network device sends first configuration information to a terminal device, wherein the first configuration information is used for instructing the terminal device to collect artificial intelligence (AI)-related and / or machine learning (ML)-related data; and the first network device receives the AI-related and / or ML-related data sent by the terminal device. According to the embodiments of the present application, an access network device can obtain AI / ML-related air interface data on a terminal device side, thereby providing data support for model training and achieving a corresponding model training function.

Description

Data collection method and device Technical Field

[0001] The embodiments of the present application relate to the field of communication technologies. Background Art

[0002] The 3GPP R18 artificial intelligence / machine learning (AI / ML) project defines multiple scenarios or sub-scenario types, such as CSI enhancement (which may also include at least one sub-scenario of CSI compression and CSI predication), beam management, positioning, or other scenarios. The 3GPP R19 AI / ML-based mobility project considers new scenario types, such as normal handover, conditional handover, and layer 1 / L2 triggered mobility (LTM). Different scenarios or sub-scenarios can correspond to one or more features / feature groups. Applying AI / ML to the above feature / feature group is called an AI / ML-based / enabled feature / feature group. An AI / ML-based / enabled feature / feature group can correspond to one or more AI functions and / or one or more AI models. One AI function can correspond to one or more AI models.

[0003] It should be noted that the above introduction to the technical background is merely intended to provide a clear and complete description of the technical solutions of this application and facilitate understanding by those skilled in the art. Simply because these solutions are described in the background technology section of this application, it should not be assumed that the above technical solutions are well known to those skilled in the art.

[0004] Summary of the Invention

[0005] The inventors discovered that to obtain the corresponding AI model, model training based on data is required. Accordingly, the network elements performing model training need to obtain the corresponding data. However, existing mechanisms for collecting Layer 3 (L3) data do not support storage and reporting (logging), nor do they support the collection of Layer 1 (L1) data.

[0006] In response to at least one of the above problems or other similar problems, the embodiments of the present application provide a data collection method and device, so that access network equipment can obtain air interface data related to artificial intelligence (AI) / machine learning (ML) on the terminal device side, thereby providing data support for model training and realizing corresponding model training functions.

[0007] According to one aspect of an embodiment of the present application, a data collection device is provided, configured on a first network device, wherein the device includes:

[0008] a sending unit, configured to send first configuration information to a terminal device, where the first configuration information is used to instruct the terminal device to collect data related to artificial intelligence and / or machine learning;

[0009] A receiving unit, which receives the artificial intelligence-related and / or machine learning-related data sent by the terminal device.

[0010] According to another aspect of an embodiment of the present application, a data collection device is provided, configured in a terminal device, wherein the device includes:

[0011] a receiving unit, configured to receive first configuration information sent by a first network device, where the first configuration information is used to instruct the terminal device to collect artificial intelligence-related and / or machine learning-related data;

[0012] A sending unit, which sends the artificial intelligence-related and / or machine learning-related data to the first network device.

[0013] One of the beneficial effects of the embodiments of the present application is that: according to the embodiments of the present application, the access network device can obtain air interface data related to artificial intelligence (AI) / machine learning (ML) on the terminal device side, thereby providing data support for model training and realizing the corresponding model training function.

[0014] With reference to the following description and accompanying drawings, specific embodiments of the present application are disclosed in detail, indicating the manner in which the principles of the present application can be employed. It should be understood that the embodiments of the present application are not limited in scope. Within the spirit and scope of the appended claims, the embodiments of the present application include many variations, modifications and equivalents.

[0015] Features described and / or illustrated with respect to one embodiment may be used in the same or similar manner in one or more other embodiments, combined with features in other embodiments, or substituted for features in other embodiments.

[0016] It should be emphasized that the term "include / comprising" when used herein refers to the presence of features, integers, steps or components, but does not exclude the presence or addition of one or more other features, integers, steps or components. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The elements and features described in one figure or one embodiment of the present application can be combined with the elements and features shown in one or more other figures or embodiments. In addition, in the accompanying drawings, similar reference numerals represent corresponding parts in several figures and can be used to indicate corresponding parts used in more than one embodiment.

[0018] FIG1 is a schematic diagram of a data collection method according to an embodiment of the first aspect of the present application;

[0019] FIG2 is a schematic diagram of information interaction between a terminal device and a network device according to a data collection method according to an embodiment of the present application;

[0020] FIG3 is a schematic diagram of a data collection method according to an embodiment of the second aspect of the present application;

[0021] FIG4 is a schematic diagram of a data collection device according to an embodiment of the third aspect of the present application;

[0022] FIG5 is another schematic diagram of a data collection device according to an embodiment of the third aspect of the present application;

[0023] FIG6 is a schematic diagram of a communication system according to an embodiment of the present application;

[0024] FIG7 is a schematic diagram of a network device according to an embodiment of the present application;

[0025] FIG8 is a schematic diagram of a terminal device according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] The above and other features of the present application will become apparent through the following description with reference to the accompanying drawings. In the description and the accompanying drawings, specific embodiments of the present application are disclosed in detail, which illustrate some embodiments in which the principles of the present application can be adopted. It should be understood that the present application is not limited to the described embodiments. On the contrary, the present application includes all modifications, variations and equivalents that fall within the scope of the appended claims.

[0027] In the embodiments of the present application, the terms "first", "second", etc. are used to distinguish different elements from the name, but do not indicate the spatial arrangement or temporal order of these elements, and these elements should not be limited by these terms. The term "and / or" includes any one and all combinations of one or more of the associated listed terms. The terms "comprising", "including", "having", etc. refer to the presence of the stated features, elements, components or components, but do not exclude the presence or addition of one or more other features, elements, components or components.

[0028] In the embodiments of this application, the singular forms "a," "the," etc. include plural forms and should be broadly understood to mean "a" or "a type" rather than being limited to "one." Furthermore, the term "said" should be understood to include both singular and plural forms, unless the context clearly indicates otherwise. Furthermore, the term "according to" should be understood to mean "at least in part based on...", and the term "based on" should be understood to mean "at least in part based on...", unless the context clearly indicates otherwise.

[0029] In the embodiment of the present application, a scenario including a network device (also referred to as a network element) and / or a terminal device is taken as an example.

[0030] In the above scenario, the network device may include at least one of a core network device, a third-party application device, an operation administration and maintenance (OAM), and an access network device.

[0031] The core network device may refer to a device in the core network (CN) that provides service support for the terminal device. As some examples, the core network device may be at least one of the following: a mobility and management entity (MME), an access and mobility management function (AMF) entity, a session management function (SMF) entity, a user plane function (UPF) entity, a location management function (LMF) entity, and the like, which are not listed here one by one. Among them, the AMF entity may be responsible for the access management and mobility management of the terminal, the SMF entity may be responsible for session management, such as the establishment of a user session, and the UPF entity may be a functional entity of the user plane, mainly responsible for connecting to the external network. The LMF entity may manage the overall coordination and scheduling of resources required for the location of the terminal device registered with the core network device or accessing the core network device. It should be noted that in the embodiment of the present application, the entity may also be referred to as a network element or a functional entity, such as the AMF entity may also be referred to as an AMF network element or an AMF functional entity, and so on.

[0032] The third-party application device can be an OTT service (over the top server) or other third-party device.

[0033] OAM is a network device that performs operations, management, and maintenance on the network according to the actual needs of the operator's network operations.

[0034] The access network device is an access device that the terminal device uses to access the communication system wirelessly. The access network device can be a base station (BS), an evolved NodeB (eNodeB), a transmission reception point (TRP), a base station (next generation NodeB, gNB) in the fifth generation (5G) mobile communication system, a base station in the sixth generation (6G) mobile communication system, a base station in a future mobile communication system, or an access node in a WiFi system. The access network device can also be a module or unit that completes part of the functions of the base station. For example, it can be at least one of the following modules or units: a centralized unit (CU), a distributed unit (DU), a centralized unit control plane (CU control plane, CU-CP), a centralized unit user plane (CU user plane, CU-CP), an integrated access backhaul (IAB) or other modules or units. The embodiments of the present application do not limit the specific technology and / or specific device form adopted by the access network device. The access network equipment can be deployed on land, including indoors / outdoors, and can be handheld or vehicle-mounted; it can also be deployed on the water, on an airplane, on a balloon or on a satellite; the access network equipment can be deployed in a fixed location or on a mobile carrier, and the embodiments of the present application do not limit this.

[0035] In the above scenarios, a terminal device can be a device with wireless transceiver capabilities that can send signals to and / or receive signals from an access network device. A terminal device can also be referred to as a terminal, mobile station, or mobile terminal. A terminal device can be a mobile phone, tablet, or other device with wireless intelligent transceiver capabilities. Terminal devices can be widely used in various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), the Internet of Things (IoT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, and various smart scenarios.

[0036] In the above scenarios, access network devices and terminal devices, and terminal devices and terminal devices can communicate via licensed spectrum, unlicensed spectrum, or both. The embodiments of this application do not limit the spectrum resources used for wireless communications.

[0037] In the embodiments of the present application, to obtain a corresponding model, model training is required based on data. Accordingly, the network element performing model training needs to obtain the corresponding data. For the above scenario, the network element performing model training needs to collect corresponding L1 and / or L3 data. The L1 and / or L3 data can be at least one of L1 and / or L3 measurement result information and ground truth. The measurement result information includes at least one of the following information: reference signal receiving power (RSRP), reference signal receiving quality (RSRQ), reference signal strength indicator (RSSI), signal to interference plus noise ratio (SINR), channel quality indicator (CQI), precoding matrix indicator (PMI), CSI-RS resource indicator (CSI Reference Signal Resource Indicator, CRI, CSI reference information resource indicator), SS / PBCH block resource indicator (SSBRI), layer indicator (LI), rank indicator (RI), precoding matrix (Precoding matrix), raw channel matrix, right singular vectors of the channel matrix, scalar quantization information (Scalar quantization information), quantization), codebook-based quantization, or other signal quality information. A true value refers to a measured value that can serve as a benchmark. Generally speaking, a true value is a relative concept, meaning it is a value obtained using a relatively reliable measurement method.

[0038] Taking the CSI enhancement scenario as an example, the network element performing model training needs to collect at least one of the following data: channel quality indicator (CQI), precoding matrix indicator (PMI), CSI-RS resource indicator (CSI Reference Signal Resource Indicator, CRI, CSI reference information number resource indicator), SS / PBCH block resource indicator (SS / PBCH Block Resource Indicator, SSBRI), layer indicator (LI), channel matrix (channel matrix), right singular vectors of the channel matrix (right singular vectors of the channel matrix), rank indicator (RI), L1-RSRP, true value, L1-SINR or other L1 measurement result information.

[0039] Taking beam management as an example, the network element performing model training needs to collect at least one of the following data: precoding matrix, original channel matrix, scalar quantization information, codebook-based quantization information, true value, beam measurement result information, or other measurement result information.

[0040] Currently, the RAN2#123bis Release 18 3GPP RAN1 AI project has agreed on a data collection mechanism for base stations performing AI model training, known as gNB-centric data collection. Specifically, the standard adopts a logging reporting mechanism, meaning that upon collecting data, the UE can wait until multiple pieces of data have been collected before reporting to the base station. The standard also allows for the collection of AI model training data via Layer 3 signaling, such as RRC (Radio Resource Control) signaling.

[0041] In the current layer 3 measurement mechanism, the base station sends measurement configuration information to the connected UE. The measurement configuration information includes measurement object configuration information and reporting configuration information.

[0042] The above-mentioned measurement object configuration information may include at least one of the following information: measurement object information, beam type information, and configuration information for determining cell quality. The measurement object information is used to indicate the same-frequency information, different-frequency information, or different-system information that needs to be measured; further, the measurement object information can also be used to indicate the cell information to be measured. The beam type information can be at least one of a channel state information reference signal (CSI-RS), a synchronization signal block (SSB), or other physical signals. The configuration information for determining cell quality may include at least one of beam quality threshold information and maximum number of beams information; the beam quality threshold information is used to indicate that when the beam quality is greater than or equal to the threshold, the beam quality can be used to determine the cell quality.

[0043] The above-mentioned reporting configuration information may include at least one of the following: periodic reporting configuration information, event-triggered reporting configuration information or other reporting configuration information.

[0044] The following describes embodiments of the present application with reference to the accompanying drawings and detailed descriptions. For ease of description, the following description uses a base station as an example of an access network device. In the following description, "if," "under the circumstances," and "when" can be used interchangeably to avoid confusion.

[0045] Embodiments of the first aspect

[0046] The embodiment of the present application provides a data collection method, which is described from the perspective of a first network device. The first network device may be an access network device.

[0047] FIG1 is a schematic diagram of a data collection method according to an embodiment of the present application. As shown in FIG1 , the method includes:

[0048] 110: The first network device sends first configuration information to the terminal device, where the first configuration information is used to instruct the terminal device to collect artificial intelligence-related and / or machine learning-related data;

[0049] 120: The first network device receives artificial intelligence-related and / or machine learning-related data sent by the terminal device.

[0050] It is worth noting that FIG1 above only schematically illustrates an embodiment of the present application, and the present application is not limited thereto. For example, other operations may be added or some operations may be reduced. Those skilled in the art may make appropriate modifications based on the above content, and are not limited to the description of FIG1 above.

[0051] According to the above embodiment, as an access network device, the first network device instructs the terminal device to collect AI / ML-related data through the first configuration information. Thus, the access network device can obtain AI / ML-related air interface data on the terminal device side, thereby providing data support for model training and realizing the corresponding model training function.

[0052] In some embodiments, in operation 110, the first configuration information includes at least one of the following: data collection object information; data collection information; data reporting configuration information; and data processing information.

[0053] In the above embodiment, the data collection object information is used to indicate the objects for which the terminal device needs to perform data collection. The data collection objects include, for example, at least one of the following: beam information, cell information, intra-frequency information, inter-frequency information, inter-system information, scenario type information, sub-scenario type information, feature information, feature group information, function information, and model information. Thus, the terminal device can obtain the corresponding data by measuring the above data collection objects.

[0054] In the above embodiment, the data collection information is used to instruct the terminal device to perform data collection according to the first configuration information. For example, the data collection information may include at least one of the following: data collection mode, data collection time information, and data collection trigger information.

[0055] The data collection method may include, for example, storage reporting (logging) and / or cache reporting (logged); wherein, logging means that when the terminal device is in a connected state, it can collect at least one piece of data and cache reporting mechanism; logged means that when the terminal device is in a non-connected state, it can collect at least one piece of data and cache reporting mechanism.

[0056] Data collection time information indicates the maximum duration of data collection by the terminal device. This information may include a start time and duration, or a start time and end time. This information may be absolute time or system frame number (SFN).

[0057] The data collection trigger information may include, for example, data collection trigger type information and / or data collection trigger configuration information. The data collection trigger type may be periodic collection and / or event-triggered collection; and the data collection trigger configuration information may include at least one of data collection period information, data collection event type information, data collection threshold information, and data collection interval information.

[0058] In the above embodiment, the data reporting configuration information is used to indicate the reporting configuration of the above data of the terminal device. For example, the data reporting configuration information may include active reporting configuration information and / or request-based reporting configuration information. The active reporting configuration information may, for example, include at least one of the following: maximum entry information of data, memory threshold information, data collection threshold information, terminal device status tendency change indication information, abnormal situation confirmation information, and collection time information. The data reporting configuration information is used by the terminal device to determine the reporting timing of the collected data. For example, when the conditions corresponding to the above active reporting configuration information are met, the terminal device actively sends a data storage indication message to the network device or sends the above data.

[0059] In the above embodiment, the data processing information is used to indicate the processing mechanism used by the terminal device to process the collected data. For example, the data processing information may include complete data processing information or incomplete data processing information, wherein complete data processing information is used to indicate that the data is original data, and incomplete data processing information is used to indicate that the data has been compressed and / or biased. For example, based on the data processing information, the terminal device may use the first data as a baseline and perform bias processing on the collected data other than the first data.

[0060] In an embodiment of the present application, after receiving the first configuration information, the terminal device may perform corresponding data collection according to the first configuration information. In operation 120, the AI / ML-related data sent by the terminal device is the data collected by the terminal device according to the first configuration information. The AI / ML-related data may be at least one of L1 and / or L3 measurement result information and ground truth. The specific description is described above and is not repeated here.

[0061] In some embodiments, if the above-mentioned data reporting configuration information includes active reporting configuration information, if at least one condition corresponding to the active reporting configuration information is met, the terminal device can determine to send data storage indication information or send the above-mentioned data to the first network device.

[0062] For example, if the actively reported configuration information includes maximum data entry information, when the data entries collected by the terminal device are greater than or equal to the maximum entry information, the terminal device determines to send data storage indication information or the above data to the network device.

[0063] For another example, if the actively reported configuration information includes memory threshold information, when the remaining memory information of the terminal device is less than or equal to the threshold information, the terminal device determines to send data storage indication information or the above data to the network device.

[0064] For another example, if the actively reported configuration information includes data collection threshold information, when the amount of data collected by the terminal device is greater than or equal to the data collection threshold information, the terminal device determines to send data storage indication information or the above data to the network device.

[0065] For another example, if the actively reported configuration information includes the terminal device's status tendency change indication information, when the terminal device sends the network device a status tendency of non-connected state, the terminal device can also determine to send data storage indication information or send the above data to the network device.

[0066] For another example, if the actively reported configuration information includes abnormal situation confirmation information, when the terminal device is unable to collect data that meets the data collection trigger information for a period of time (abnormal time information) or for multiple consecutive times (abnormal number information), or the terminal device is unable to collect the data required by the network device, the terminal device determines to send data storage indication information to the network device or send the above data. It can be understood that the abnormal situation confirmation information may include the above-mentioned abnormal time information, and / or, abnormal number information. The present application is not limited to this, and the above-mentioned abnormal time information / abnormal number information may also be predefined by the protocol.

[0067] For another example, if the actively reported configuration information includes collection time information, when the collection time expires, the terminal device determines to send data storage indication information or the above data to the network device.

[0068] In one possible example, if at least one condition corresponding to the active reporting of configuration information is met, the terminal device directly sends the collected data related to the AI / ML of the terminal device to the first network device.

[0069] In another possible example, if at least one condition corresponding to the active reporting of configuration information is met, the terminal device first sends the above-mentioned data storage indication information to the first network device, receives the data reporting indication information sent by the first network device, and then sends the collected AI / ML-related data of the above-mentioned terminal device to the first network device.

[0070] In the above example, the data storage indication information is used to indicate that the terminal device stores data related to artificial intelligence and / or machine learning. As a possible implementation, the data storage indication information may include at least one of the following: data storage indication information related to artificial intelligence and / or machine learning, data storage indication information corresponding to scenario type information, data storage indication information corresponding to sub-scenario type information, data storage indication information corresponding to feature information, data storage indication information corresponding to feature group information, data storage indication information corresponding to function information, or data storage indication information corresponding to model information.

[0071] In the above example, the data reporting indication information is used to indicate the artificial intelligence-related and / or machine learning-related data to be reported by the terminal device. As a possible implementation, the data reporting indication information may include at least one of the following: artificial intelligence-related and / or machine learning-related data reporting indication information, data reporting indication information corresponding to scenario type information, data reporting indication information corresponding to sub-scenario type information, data reporting indication information corresponding to feature information, data reporting indication information corresponding to feature group information, data reporting indication information corresponding to function information, or data reporting indication information corresponding to model information.

[0072] In the above example, the relevant contents of scene type information, sub-scene type information, feature information, feature group information, function information and model information have been explained in the previous description and will not be repeated here.

[0073] In other embodiments, if the above-mentioned data reporting configuration information includes request-based reporting configuration information, the terminal device first receives the data reporting indication information sent by the first network device, and then sends the collected AI / ML-related data of the above-mentioned terminal device to the first network device.

[0074] The relevant contents of the data reporting indication information have been explained in the previous description and will not be repeated here.

[0075] In some embodiments, as shown in FIG1 , the method may further include:

[0076] 100: The first network device obtains artificial intelligence-related and / or machine learning-related data collection capability information of the terminal device.

[0077] For example, the first network device receives artificial intelligence-related and / or machine learning-related data collection capability information of the terminal device sent by at least one of the core network device, the second network device, the operation and maintenance management (OAM) entity, and the above-mentioned terminal device.

[0078] In the above embodiment, the second network device may be an access network device other than the above first network device, or may be other network devices instead of an access network device, and this application does not impose any restrictions on this.

[0079] In the above embodiments, the AI / ML-related data may be at least one of L1 and / or L3 measurement information, ground truth, or other data required by the network device for model training, and this application is not limited thereto. The description of L1 / L3 measurement information and ground truth can be found above and will not be repeated here.

[0080] In the above embodiment, the data collection capability information is used to indicate the AI / ML-related data collection capabilities supported by the terminal device. As a possible implementation method, the data collection capability information may include at least one of the following: data collection support information corresponding to the scenario type information, data collection support information corresponding to the sub-scenario type information, data collection support information corresponding to the feature information, data collection support information corresponding to the feature group information, data collection support information corresponding to the function information, data collection support information corresponding to the model information, data collection support information corresponding to the model type, support information for the data collection method, support information for the data collection reporting method, memory support information related to data collection of the terminal device, or support information for other capabilities. By obtaining the above-mentioned data collection capability information of the terminal device, the first network device can determine whether to configure the terminal device to perform corresponding data collection based on the data collection capability information.

[0081] The data collection support information corresponding to the scenario type information indicates the data collection scenarios supported by the terminal device; the data collection support information corresponding to the sub-scenario type information indicates the data collection sub-scenario supported by the terminal device; the data collection support information corresponding to the feature information indicates the data collection features supported by the terminal device; the data collection support information corresponding to the feature group information indicates the data collection feature groups supported by the terminal device; the data collection support information corresponding to the function information indicates the data collection functions supported by the terminal device; and the data collection support information corresponding to the model information indicates the data collection models supported by the terminal device. The scenario / sub-scenario type can be CSI enhancement or CSI compression, CSI prediction, beam management, positioning, normal handover, conditional handover, bottom-layer triggered mobility, or other scenarios / sub-scenarios. For details about the scenario type information, sub-scenario type information, feature information, feature group information, function information, and model information, please refer to the relevant art and are not described here. The terminal device can report the data collection support information (i.e., data collection capability information) corresponding to a supported scenario / sub-scenario / feature / feature group / function / model, so that the network device can determine whether to configure the terminal device to perform the corresponding data collection based on the data to be collected.

[0082] The data collection support information corresponding to the model type is used to indicate the model type of data collection supported by the terminal device. Model types may include, for example, single-sided models and multi-sided models. A single-sided model refers to a model deployed on a single device, which can be called a one-sided model. Depending on the deployed device, it can be divided into a model on the terminal device side (UE-sided model) and a model on the network device side (NW-sided model). It can be understood that, depending on the deployed network device, the NW-sided model can be further divided into a gNB-sided model, an LMF-sided model or a model on the side of other network devices. A multi-sided model refers to a model deployed on at least two devices. For example, in the CSI compression scenario, the model can be deployed on the terminal device and the network device respectively, and the model can be called a two-sided model.

[0083] The data collection method support information is used to indicate the data collection methods supported by the terminal device. Data collection methods may include, for example, storage reporting (logging) and cache reporting (logged). Storage reporting is a mechanism whereby a terminal device in a connected state collects at least one piece of data and caches it for reporting; cache reporting is a mechanism whereby a terminal device in a disconnected state collects at least one piece of data and caches it for reporting.

[0084] The data collection and reporting method support information indicates the data collection and reporting methods supported by the terminal device. Data collection and reporting methods may include, for example, proactive reporting and request-based reporting. Proactive reporting refers to the terminal device proactively sending data storage instructions or the aforementioned data to the network device; request-based reporting refers to the terminal device sending the aforementioned data based on data reporting instructions sent by the network device.

[0085] The terminal device's memory support information related to data collection is used to indicate the terminal device's memory size, memory level, and / or maximum number of data items supported, or other information indicating the terminal device's memory capabilities. The memory support information may include, for example, at least one of the following: memory size, memory level, and maximum number of data items supported.

[0086] The data collection method of the embodiment of the present application is described below through a specific example.

[0087] FIG2 is a schematic diagram of information interaction between a terminal device and a network device according to a data collection method according to an embodiment of the present application. As shown in FIG2 , the information interaction process includes:

[0088] 210: The access network device obtains AI / ML-related data collection capability information of the terminal device;

[0089] 220: The access network device sends first configuration information to the terminal device, where the first configuration information is used to instruct the terminal device to perform the above data collection;

[0090] 230: The terminal device performs corresponding data collection according to the first configuration information;

[0091] 240: If the condition corresponding to at least one of the actively reported configuration information is met, the terminal device determines to send data storage indication information or the above data to the access network device;

[0092] 250: The terminal device sends data storage indication information to the access network device;

[0093] 260: The terminal device receives the receipt reporting instruction information sent by the access network device;

[0094] 270: The terminal device sends the above data to the access network device.

[0095] It is worth noting that FIG2 above only schematically illustrates an embodiment of the present application, and the present application is not limited thereto. For example, other operations may be added or some operations may be reduced. Those skilled in the art may make appropriate modifications based on the above content, and are not limited to the description of FIG2 above.

[0096] In operation 210, the access network device (i.e., the aforementioned first network device) can obtain the above-mentioned data collection capability information from at least one of the core network device, other access network devices, OAM, terminal devices or other network devices. For example, the access network device receives the data collection capability information sent by at least one of the core network device, other access network devices, OAM, terminal devices or other network devices.

[0097] In the above example, for the description of the AI / ML-related data collection capability information of the terminal device, please refer to the description of operation 100 and will not be repeated here.

[0098] In operation 220, the first configuration information may include at least one of the following information: data collection object information, data collection information, data reporting configuration information, and data processing information. For details about the first configuration information, please refer to the description in operation 110 and will not be repeated here.

[0099] In operation 230 , the terminal device may perform corresponding data collection according to the first configuration information.

[0100] In the above example, if the data reporting configuration information includes active reporting configuration information, in one possible example, operations 240 and 270 are performed; in another possible example, operations 240 to 270 are performed; if the data reporting configuration information includes request-based reporting configuration information, operations 260 and 270 are performed.

[0101] In operation 240, if at least one condition corresponding to the active reporting configuration information is met, the terminal device determines to send data storage indication information or the above-mentioned data to the access network device.

[0102] For example, the terminal device directly executes operation 270 to send the above data to the access network device.

[0103] For another example, the terminal device executes operation 250 to send data storage indication information to the access network device, and executes operation 260 to receive data reporting indication information sent by the access network device, and then executes operation 270 to send the above data to the access network device.

[0104] In operation 250, the data storage indication information may be data storage indication information corresponding to the scene type information, data storage indication information corresponding to the sub-scene type information, data storage indication information corresponding to the feature information, data storage indication information corresponding to the feature group information, data storage indication information corresponding to the function information, or data storage indication information corresponding to the model information. For a specific description, please refer to the description in operation 120 and will not be repeated here.

[0105] In operation 260, the data reporting indication information may be data reporting indication information corresponding to the scene type information, data reporting indication information corresponding to the sub-scene type information, data reporting indication information corresponding to the characteristic information, data reporting indication information corresponding to the characteristic group information, data reporting indication information corresponding to the function information, or data reporting indication information corresponding to the model information. For a specific description, please refer to the description in operation 120 and will not be repeated here.

[0106] In operation 270, the terminal device may send the collected data to the access network device. The data here may be AI / ML-related data or other data required by the network device (e.g., access network device) for model training, but the present application is not limited thereto. The description of AI / ML-related data can refer to the description in operation 120 and will not be repeated here.

[0107] The above embodiments are merely exemplary descriptions of the methods of the present application, but the present application is not limited thereto, and appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used individually, or one or more of the above embodiments may be combined.

[0108] According to the method of the embodiment of the present application, the access network device can obtain AI / ML-related air interface data on the terminal device side, thereby providing data support for model training and realizing the corresponding model training function.

[0109] Embodiments of the second aspect

[0110] The embodiment of the present application provides a data collection method, which is described from the side of the terminal device. The principle of solving the problem by this method is the same as that of the embodiment of the first aspect, and the same contents will not be repeated.

[0111] FIG3 is a schematic diagram of a data collection method according to an embodiment of the present application. As shown in FIG3 , the method includes:

[0112] 310: The terminal device receives first configuration information sent by the first network device, where the first configuration information is used to instruct the terminal device to collect artificial intelligence-related and / or machine learning-related data.

[0113] 320: The terminal device sends artificial intelligence-related and / or machine learning-related data to the first network device.

[0114] In the above embodiment, the relevant content of the first configuration information can refer to the description of operation 110 and operation 220 in the embodiment of the first aspect, and the description is omitted here.

[0115] For example, the first configuration information includes at least one of the following:

[0116] Data collection object information, used to indicate the object for which the terminal device needs to perform data collection;

[0117] Data collection information, used to instruct the terminal device to perform data collection according to the first configuration information;

[0118] Data reporting configuration information, used to indicate the reporting configuration of the data of the terminal device;

[0119] Data processing information is used to indicate the processing mechanism of the terminal device to process the collected data.

[0120] As a possible example, the data collection object may include at least one of the following: beam information, cell information, same-frequency information, different-frequency information, different-system information, scene type information, sub-scene type information, feature information, feature group information, function information, and model information.

[0121] As a possible example, the data collection information may include at least one of the following: a data collection method, data collection time information, and data collection trigger information. The data collection method may include, for example, storage reporting and / or cache reporting; the data collection time information is used to indicate the maximum duration range for data collection by the terminal device, and may include, for example, start time information and duration information, or start time information and end time information, where the time information is absolute time information or system frame number information; the data collection trigger information may include, for example, data collection trigger type information and / or data collection trigger configuration information.

[0122] Among them, the data collection trigger type may include, for example, periodic collection and / or event-triggered collection; the data collection trigger configuration information may include, for example, at least one of the following: periodic information of data collection, event type information of data collection, threshold information of data collection, and interval information of data collection.

[0123] As a possible example, data reporting configuration information may include active reporting configuration information and / or request-based reporting configuration information; active reporting configuration information may, for example, include at least one of the following: maximum data entry information, memory threshold information, data collection threshold information, terminal device status tendency change indication information, abnormal situation confirmation information, and collection time information.

[0124] As a possible example, the data processing information may include complete data processing information or incomplete data processing information, wherein the complete data processing information is used to indicate that the data is original data, and the incomplete data processing information is used to indicate that the data has been compressed and / or biased.

[0125] In some embodiments, the terminal device may also send artificial intelligence-related and / or machine learning-related data collection capability information of the terminal device to the first network device. For relevant content of the data collection capability information, reference may be made to the description of operations 100 and 210 in the embodiment of the first aspect, and description thereof is omitted here.

[0126] For example, the data collection capability information may include at least one of the following:

[0127] Data collection support information corresponding to the scenario type information, used to indicate the scenarios supported by the terminal device;

[0128] Data collection support information corresponding to the sub-scenario type information, used to indicate the sub-scenario supported by the terminal device;

[0129] Data collection support information corresponding to the characteristic information, used to indicate the characteristics of data collection supported by the terminal device;

[0130] The data collection support information corresponding to the feature group information is used to indicate the feature group of data collection supported by the terminal device;

[0131] The data collection support information corresponding to the function information is used to indicate the data collection functions supported by the terminal device;

[0132] Data collection support information corresponding to the model information, used to indicate the data collection model supported by the terminal device;

[0133] Data collection support information corresponding to the model type, used to indicate the data collection model type supported by the terminal device;

[0134] Support information of data collection methods, used to indicate the data collection methods supported by the terminal device;

[0135] Support information for data collection and reporting methods, used to indicate the data collection and reporting methods supported by the terminal device;

[0136] The memory support information related to data collection of the terminal device is used to indicate the memory size, memory level, and / or the maximum number of data items supported by the terminal device.

[0137] As a possible example, the model type may include a single-sided model and / or a multi-sided model; a single-sided model refers to a model deployed on a single device; a multi-sided model refers to a model deployed on at least two devices; the devices here may include terminal devices and / or network devices.

[0138] As a possible example, the data collection method may include storage reporting and / or cache reporting; storage reporting is that a terminal device in a connected state collects at least one piece of data and caches the reporting; cache reporting is that a terminal device in a non-connected state collects at least one piece of data and caches the reporting.

[0139] As a possible example, the data collection and reporting method may include active reporting and / or request-based reporting; active reporting means that the terminal device actively sends data storage indication information or sends the above data to the network device; request-based reporting means that the terminal device sends the above data based on the data reporting indication information sent by the network device.

[0140] As a possible example, the memory support information includes at least one of the following: memory size, memory level, and maximum number of data items supported.

[0141] In some embodiments, as shown in FIG3 , the method further includes:

[0142] 315: The terminal device collects the above data according to the first configuration information.

[0143] For relevant contents of operation 315 , reference may be made to the description of operation 230 in the embodiment of the first aspect, and will not be repeated here.

[0144] In some embodiments, if the data reporting configuration information includes active reporting configuration information, and if a condition corresponding to at least one of the active reporting configuration information is met, the terminal device may further determine to send data storage indication information and / or the above-mentioned data to the first network device. For specific operations, reference may be made to the description of operation 240 in the embodiment of the first aspect, and will not be repeated here.

[0145] As a possible example, the terminal device sends data storage indication information to the first network device; receives data reporting indication information sent by the first network device; and then sends the above data to the first network device. For specific operations, please refer to the description of operations 250 to 270 in the embodiment of the first aspect, and will not be repeated here.

[0146] As another possible example, the terminal device directly sends the data to the first network device. For specific operations, reference may be made to the description of operation 270 in the embodiment of the first aspect, which will not be repeated here.

[0147] In some embodiments, if the data reporting configuration information includes request-based reporting configuration information, the terminal device may further receive data reporting indication information sent by the first network device, and then send the data to the first network device. For specific operations, reference may be made to the description of operations 260 to 270 in the embodiment of the first aspect, and will not be repeated here.

[0148] In the above embodiments, the data storage indication information may include at least one of the following: data storage indication information related to artificial intelligence and / or machine learning, data storage indication information corresponding to scene type information, data storage indication information corresponding to sub-scene type information, data storage indication information corresponding to feature information, data storage indication information corresponding to feature group information, data storage indication information corresponding to function information, or data storage indication information corresponding to model information.

[0149] In the above embodiment, the data reporting indication information may include at least one of the following: data reporting indication information related to artificial intelligence and / or machine learning, data reporting indication information corresponding to scene type information, data reporting indication information corresponding to sub-scene type information, data reporting indication information corresponding to feature information, data reporting indication information corresponding to feature group information, data reporting indication information corresponding to function information, or data reporting indication information corresponding to model information.

[0150] The above embodiments are merely exemplary of the methods of the present application, but the present application is not limited thereto. Appropriate modifications may be made based on the above embodiments. For example, the above embodiments may be used individually, or one or more of the above embodiments may be combined.

[0151] According to the method of the embodiment of the present application, the access network device can obtain AI / ML-related air interface data on the terminal device side, thereby providing data support for model training and realizing the corresponding model training function.

[0152] Embodiments of the third aspect

[0153] An embodiment of the present application provides a data collection device.

[0154] FIG4 is a schematic diagram of a data collection device according to an embodiment of the present application. The device may be, for example, a network device, or one or more components or assemblies configured on the network device. Since the principle of solving the problem of the device is the same as the method of the embodiment of the first aspect, its specific implementation can refer to the implementation of the method of the embodiment of the first aspect, and the same content will not be repeated here. As shown in FIG4, the device 400 includes:

[0155] A sending unit 410 is configured to send first configuration information to a terminal device, where the first configuration information is used to instruct the terminal device to collect data related to artificial intelligence and / or machine learning;

[0156] A receiving unit 420 receives the artificial intelligence-related and / or machine learning-related data sent by a terminal device.

[0157] In some embodiments, the first configuration information includes at least one of the following:

[0158] Data collection object information, used to indicate the object for which the terminal device needs to perform data collection;

[0159] Data collection information, used to instruct the terminal device to perform data collection according to the first configuration information;

[0160] Data reporting configuration information, used to indicate the reporting configuration of the data of the terminal device;

[0161] Data processing information is used to indicate the processing mechanism of the terminal device to process the collected data.

[0162] In the above embodiment, the data collection object may include at least one of the following: beam information, cell information, same-frequency information, different-frequency information, different-system information, scene type information, sub-scene type information, feature information, feature group information, function information, and model information.

[0163] In the above embodiment, the data collection information may include at least one of the following: data collection method, data collection time information, and data collection trigger information.

[0164] Among them, the data collection method may include, for example, storage reporting and / or cache reporting; the data collection time information is used to indicate the maximum duration range for the terminal device to perform data collection, for example, it may include start time information and duration length information, or include start time information and end time information, and the above time information is absolute time information or system frame number information; the data collection trigger information may include, for example, data collection trigger type information and / or data collection trigger configuration information.

[0165] Among them, the data collection trigger type may include, for example, periodic collection and / or event-triggered collection; the data collection trigger configuration information may include, for example, at least one of the following: periodic information of data collection, event type information of data collection, threshold information of data collection, and interval information of data collection.

[0166] In the above embodiment, the data reporting configuration information may include active reporting configuration information and / or request-based reporting configuration information; the active reporting configuration information may include at least one of the following: maximum data entry information, memory threshold information, data collection threshold information, terminal device status tendency change indication information, abnormal situation confirmation information, and collection time information.

[0167] In the above embodiment, the data processing information may include complete data processing information or incomplete data processing information, wherein the complete data processing information is used to indicate that the above data is original data, and the incomplete data processing information is used to indicate that the above data has been compressed and / or biased.

[0168] In some embodiments, the receiving unit 420 also receives artificial intelligence-related and / or machine learning-related data collection capability information sent by at least one of the core network device, the second network device, the operation and maintenance management (OAM) entity, and the above-mentioned terminal device.

[0169] In the above embodiment, the data collection capability information may include at least one of the following:

[0170] Data collection support information corresponding to the scenario type information, used to indicate the data collection scenarios supported by the terminal device;

[0171] The data collection support information corresponding to the sub-scenario type information is used to indicate the data collection sub-scenario supported by the terminal device;

[0172] Data collection support information corresponding to the characteristic information, used to indicate the characteristics of data collection supported by the terminal device;

[0173] The data collection support information corresponding to the feature group information is used to indicate the feature group of data collection supported by the terminal device;

[0174] The data collection support information corresponding to the function information is used to indicate the data collection functions supported by the terminal device;

[0175] Data collection support information corresponding to the model information, used to indicate the data collection model supported by the terminal device;

[0176] Data collection support information corresponding to the model type, used to indicate the data collection model type supported by the terminal device;

[0177] Support information of data collection methods, used to indicate the data collection methods supported by the terminal device;

[0178] Support information for data collection and reporting methods, used to indicate the data collection and reporting methods supported by the terminal device;

[0179] The memory support information related to data collection of the terminal device is used to indicate the memory size, memory level, and / or the maximum number of data items supported by the terminal device.

[0180] Among them, the model type may include a single-sided model and / or a multi-sided model; a single-sided model refers to a model deployed on a single device; a multi-sided model refers to a model deployed on at least two devices; the devices include terminal devices and / or network devices.

[0181] Among them, the data collection method may include storage reporting and / or cache reporting; storage reporting is that the terminal device in a connected state collects at least one piece of data and caches the reporting; cache reporting is that the terminal device in a non-connected state collects at least one piece of data and caches the reporting.

[0182] Among them, the data collection and reporting method can include active reporting and / or request-based reporting; active reporting means that the terminal device actively sends data storage indication information or sends the data to the network device; request-based reporting means that the terminal device sends the data based on the data reporting indication information sent by the network device.

[0183] The memory support information may include at least one of the following: memory size, memory level, and maximum number of data items supported.

[0184] In some embodiments, the sending unit 410 may also send data reporting indication information to the terminal device.

[0185] In some embodiments, the receiving unit 420 may also receive data storage indication information sent by the terminal device.

[0186] In the above embodiments, the data storage indication information may include at least one of the following: data storage indication information related to artificial intelligence and / or machine learning, data storage indication information corresponding to scene type information, data storage indication information corresponding to sub-scene type information, data storage indication information corresponding to feature information, data storage indication information corresponding to feature group information, data storage indication information corresponding to function information, or data storage indication information corresponding to model information.

[0187] In the above embodiment, the data reporting indication information may include at least one of the following: data reporting indication information related to artificial intelligence and / or machine learning, data reporting indication information corresponding to scene type information, data reporting indication information corresponding to sub-scene type information, data reporting indication information corresponding to feature information, data reporting indication information corresponding to feature group information, data reporting indication information corresponding to function information, or data reporting indication information corresponding to model information.

[0188] FIG5 is another schematic diagram of a data collection device according to an embodiment of the present application. The device may be, for example, a terminal device, or one or more components or assemblies configured on the terminal device. Since the principle of solving the problem of the device is the same as that of the embodiment of the second aspect, its specific implementation can refer to the implementation of the method of the embodiment of the second aspect, and the same content will not be repeated here. As shown in FIG5, the device 500 includes:

[0189] A receiving unit 510 receives first configuration information sent by a first network device, where the first configuration information is used to instruct the terminal device to collect artificial intelligence-related and / or machine learning-related data;

[0190] A sending unit 520 sends artificial intelligence-related and / or machine learning-related data to the first network device.

[0191] In the above embodiment, for the relevant content of the first configuration information, reference may be made to the description of operation 110 in the embodiment of the first aspect, which will not be repeated here.

[0192] In some embodiments, the sending unit 520 may also send artificial intelligence-related and / or machine learning-related data collection capability information to the first network device.

[0193] In the above embodiment, for the relevant content of the data collection capability information, reference may be made to the description of operation 100 in the embodiment of the first aspect, which will not be repeated here.

[0194] In some embodiments, as shown in FIG5 , the apparatus 500 further includes:

[0195] The processing unit 530 collects the above data according to the first configuration information.

[0196] In some embodiments, as shown in FIG5 , the apparatus 500 further includes:

[0197] The determination unit 540 determines to send data storage indication information and / or the above-mentioned data to the first network device when the first configuration information includes data reporting configuration information and the data reporting configuration information includes active reporting configuration information if at least one condition corresponding to the active reporting configuration information is met.

[0198] In some embodiments, the sending unit 520 sends data storage indication information to the first network device; and the receiving unit 510 receives the data reporting indication information sent by the first network device.

[0199] In some embodiments, when the first configuration information includes data reporting configuration information, and the data reporting configuration information includes request-based reporting configuration information, the receiving unit 510 receives data reporting indication information sent by the first network device.

[0200] In the above embodiment, for the relevant content of the data storage indication information and the relevant content of the data reporting indication information, reference may be made to the description of operation 110 in the embodiment of the first aspect, which will not be repeated here.

[0201] The above embodiments of the present application are illustrative, but the present application is not limited thereto, and appropriate modifications can be made based on the above embodiments. For example, the above embodiments can be used alone, or one or more of the above embodiments can be combined.

[0202] It is worth noting that the above description only describes the components or modules related to this application, but this application is not limited thereto. The above-mentioned device may also include other components or modules. For the specific content of these components or modules, please refer to the relevant art. In addition, the above-mentioned components or modules can be implemented by hardware facilities such as processors, memories, transmitters, and receivers; the implementation of this application is not limited to this.

[0203] According to the apparatus of the embodiment of the present application, the access network device can obtain the air interface data related to AI / ML on the terminal device side, thereby providing data support for model training and realizing the corresponding model training function.

[0204] Embodiments of the fourth aspect

[0205] An embodiment of the present application also provides a communication system, including a network device and a terminal device.

[0206] FIG6 is a schematic diagram of a communication system according to an embodiment of the present application, schematically illustrating a situation using a terminal device and a network device as an example. As shown in FIG6 , a communication system 600 may include a network device 601 and terminal devices 602 and 603. For simplicity, FIG6 illustrates only two terminal devices and one network device as an example, but the embodiments of the present application are not limited thereto.

[0207] In the embodiment of the present application, existing services or future services can be transmitted between the network device 601 and the terminal devices 602 and 603. For example, these services may include but are not limited to: enhanced mobile broadband (eMBB), massive machine type communication (mMTC), and ultra-reliable and low-latency communication (URLLC), etc.

[0208] It is worth noting that FIG6 shows that both terminal devices 602 and 603 are within the coverage of network device 601, but the present application is not limited thereto. Both terminal devices 602 and 603 may not be within the coverage of network device 601, or one terminal device 602 may be within the coverage of network device 601 while the other terminal device 603 is outside the coverage of network device 601.

[0209] In some embodiments, the network device includes the apparatus 400 described in the embodiment of the third aspect, configured to execute the method described in the embodiment of the first aspect. Since the method has been described in detail in the embodiment of the first aspect, its content is incorporated herein and will not be repeated.

[0210] In some embodiments, the terminal device includes the apparatus 500 described in the embodiment of the third aspect, and is configured to perform the method described in the embodiment of the second aspect. Since the method has been described in detail in the embodiment of the second aspect, its content is incorporated herein and will not be repeated.

[0211] An embodiment of the present application further provides a network device, which may be, for example, a base station, but the present application is not limited thereto and may also be other network devices.

[0212] Figure 7 is a schematic diagram of a network device according to an embodiment of the present application. As shown in Figure 7 , network device 700 may include a processor 701 and a memory 702 ; the memory 702 is coupled to the processor 701 . The memory 702 may store various data and information processing programs, which are executed under the control of the processor 701 .

[0213] In some embodiments, the functions of the device 400 of the embodiment of the third aspect can be integrated into the processor 701, wherein the processor 701 can be configured to execute a program to implement the method of the embodiment of the first aspect, the content of which is incorporated herein and will not be repeated here.

[0214] In other embodiments, the apparatus 400 of the embodiment of the third aspect may be configured separately from the processor 701. For example, the apparatus 400 of the embodiment of the third aspect may be configured as a chip connected to the processor 701, and the functions of the apparatus 400 of the embodiment of the third aspect may be implemented through the control of the processor 701.

[0215] Furthermore, as shown in FIG7 , network device 700 may further include transceivers 703 and 704. The functions of these components are similar to those in the prior art and are not further described here. It is worth noting that network device 700 does not necessarily include all of the components shown in FIG7 ; furthermore, network device 700 may also include components not shown in FIG7 , for which reference may be made to the prior art.

[0216] An embodiment of the present application further provides a terminal device, which may be, for example, a UE, but the present application is not limited thereto and may also be other terminal devices.

[0217] Figure 8 is a schematic diagram of a terminal device according to an embodiment of the present application. As shown in Figure 8 , terminal device 800 may include a processor 801 and a memory 802. Memory 802 stores data and programs and is coupled to processor 801. It should be noted that this diagram is exemplary; other types of structures may be used to supplement or replace this structure to implement telecommunication or other functions.

[0218] In some embodiments, the functions of the device 500 of the embodiment of the third aspect can be integrated into the processor 801, wherein the processor 801 can be configured to execute a program to implement the method described in the embodiment of the second aspect, the content of which is incorporated herein and will not be repeated here.

[0219] In other embodiments, the apparatus 500 of the embodiment of the third aspect may be configured separately from the processor 801. For example, the apparatus 500 of the embodiment of the third aspect may be configured as a chip connected to the processor 801, and the functions of the apparatus 500 of the embodiment of the third aspect may be implemented through the control of the processor 801.

[0220] As shown in Figure 8 , the terminal device 800 may further include: a communication module 803, an input unit 804, a display 805, and a power supply 806. The functions of these components are similar to those in the prior art and are not described in detail here. It is worth noting that the terminal device 800 does not necessarily include all of the components shown in Figure 8 , and the above components are not essential. Furthermore, the terminal device 800 may also include components not shown in Figure 8 , for which reference may be made to related art.

[0221] An embodiment of the present application further provides a computer program, wherein when the program is executed in a network device, the program causes the network device to execute the method described in the embodiment of the first aspect.

[0222] An embodiment of the present application further provides a storage medium storing a computer program, wherein the computer program enables a network device to execute the method described in the embodiment of the first aspect.

[0223] An embodiment of the present application further provides a computer program, wherein when the program is executed in a terminal device, the program causes the terminal device to execute the method described in the embodiment of the second aspect.

[0224] An embodiment of the present application further provides a storage medium storing a computer program, wherein the computer program enables a terminal device to execute the method described in the embodiment of the second aspect.

[0225] The above devices and methods of the present application can be implemented by hardware or by a combination of hardware and software. The present application relates to such a computer-readable program that, when executed by a logic component, enables the logic component to implement the devices or components described above, or enables the logic component to implement the various methods or steps described above. The present application also relates to a storage medium for storing the above program, such as a hard disk, a magnetic disk, an optical disk, a DVD, a flash memory, etc.

[0226] The method / device described in conjunction with the embodiments of the present application can be directly embodied as hardware, a software module executed by a processor, or a combination of the two. For example, one or more of the functional block diagrams shown in the figure and / or one or more combinations of functional block diagrams can correspond to various software modules of the computer program flow or to various hardware modules. These software modules can respectively correspond to the various steps shown in the figure. These hardware modules can be implemented by solidifying these software modules, for example, using a field programmable gate array (FPGA).

[0227] The software module may be located in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. A storage medium may be coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium; or the storage medium may be an integral part of the processor. The processor and the storage medium may be located in an ASIC. The software module may be stored in the memory of the mobile terminal or in a memory card that can be inserted into the mobile terminal. For example, if the device (such as a mobile terminal) uses a large-capacity MEGA-SIM card or a large-capacity flash memory device, the software module may be stored in the MEGA-SIM card or the large-capacity flash memory device.

[0228] One or more of the functional blocks and / or one or more combinations of functional blocks described in the accompanying drawings may be implemented as a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, or any appropriate combination thereof for performing the functions described in this application. One or more of the functional blocks and / or one or more combinations of functional blocks described in the accompanying drawings may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in communication with a DSP, or any other such configuration.

[0229] The present application has been described above in conjunction with specific embodiments. However, those skilled in the art should understand that these descriptions are merely illustrative and are not intended to limit the scope of protection of the present application. Those skilled in the art may make various modifications and variations to the present application based on the spirit and principles of the present application, and such modifications and variations are also within the scope of the present application.

[0230] Regarding the above implementation methods disclosed in this embodiment, the following additional notes are also disclosed:

[0231] 1. A network device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the following method:

[0232] The first network device sends first configuration information to the terminal device, where the first configuration information is used to instruct the terminal device to collect artificial intelligence-related and / or machine learning-related data;

[0233] The first network device receives the artificial intelligence-related and / or machine learning-related data sent by the terminal device.

[0234] 2. A terminal device comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the following method:

[0235] The terminal device receives first configuration information sent by the first network device, where the first configuration information is used to instruct the terminal device to collect data related to artificial intelligence and / or machine learning;

[0236] The terminal device sends the artificial intelligence-related and / or machine learning-related data to the first network device.

[0237] 3. A communication system comprising the terminal device described in Note 2 and / or the network device described in Note 1.

Claims

1. A data collection device, configured in a first network device, wherein, The device includes: a sending unit, which sends first configuration information to a terminal device, and the first configuration information is used to instruct the terminal device to collect data related to artificial intelligence and / or machine learning; a receiving unit, which receives the data related to artificial intelligence and / or machine learning sent by the terminal device.

2. The device according to claim 1, wherein the first configuration information includes at least one of the following: data collection object information, which is used to indicate the object for which the terminal device needs to perform data collection; data collection information, which is used to instruct the terminal device to perform data collection according to the first configuration information; data reporting configuration information, which is used to instruct the terminal device about the reporting configuration of the data; data processing information, which is used to instruct the terminal device about the processing mechanism for processing the collected data.

3. The device according to claim 2, wherein the data collection object includes at least one of the following: beam information, cell information, same-frequency information, different-frequency information, different-system information, scenario type information, sub-scenario type information, characteristic information, characteristic group information, function information, model information.

4. The device according to claim 2, wherein the data collection information includes at least one of the following: data collection method, data collection time information, data collection trigger information.

5. The device according to claim 4, wherein the data collection method includes storage reporting and / or cache reporting; and / or the data collection time information is used to indicate the maximum duration range for the terminal device to perform data collection; and / or the data collection trigger information includes data collection trigger type information and / or data collection trigger configuration information.

6. The device according to claim 5, wherein the data collection time information includes start time information and duration length information, or includes start time information and end time information; the time information is absolute time information or system frame number information.

7. The device according to claim 5, wherein the data collection trigger type includes periodic collection and / or event-triggered collection; and / or the data collection trigger configuration information includes at least one of the following: data collection period information, data collection event type information, data collection threshold information, data collection interval information.

8. The device according to claim 2, wherein the data reporting configuration information includes active reporting configuration information and / or request-based reporting configuration information; the active reporting configuration information includes at least one of the following: maximum entry information of data, memory threshold information, data collection threshold information, terminal device status tendency change indication information, abnormal situation confirmation information, collection time information.

9. The device according to claim 2, wherein the data processing information includes complete data processing information or incomplete data processing information, wherein the complete data processing information is used to indicate that the data is raw data, and the incomplete data processing information is used to indicate that the data has been subjected to compression processing and / or the data has been subjected to offset processing.

10. The device according to claim 1, wherein the receiving unit further receives artificial intelligence-related and / or machine learning-related data collection capability information sent by at least one of a core network device, a second network device, an operation and maintenance management entity, and the terminal device.

11. A data collection device is configured in a terminal device, wherein, The device comprises: a receiving unit, which receives first configuration information sent by a first network device, the first configuration information being used to instruct the terminal device to collect artificial intelligence-related and / or machine learning-related data; a sending unit, which sends the artificial intelligence-related and / or machine learning-related data to the first network device.

12. The device according to claim 11, wherein the first configuration information includes at least one of the following: data collection object information, which is used to indicate an object for which the terminal device needs to perform data collection; data collection information, which is used to instruct the terminal device to perform data collection according to the first configuration information; data reporting configuration information, which is used to instruct the terminal device about the reporting configuration of the data; data processing information, which is used to instruct the terminal device about a processing mechanism for processing the collected data.

13. The device according to claim 12, wherein the data collection object includes at least one of the following: beam information, cell information, same-frequency information, different-frequency information, different-system information, scenario type information, sub-scenario type information, characteristic information, characteristic group information, function information, model information.

14. The device according to claim 12, wherein the data collection information includes at least one of the following: data collection method, data collection time information, data co lection trigger information.

15. The device according to claim 14, wherein the data collection method includes storage reporting and / or cache reporting; and / or, the data collection time information is used to indicate a maximum duration range for the terminal device to perform data collection; and / or, the data collection trigger information includes data collection trigger type information and / or data collection trigger configuration information.

16. The device according to claim 15, wherein the data collection time information includes start time information and duration length information, or includes start time information and end time information; the time information is absolute time information or system frame number information.

17. The device according to claim 15, wherein the data collection trigger type includes periodic collection and / or event-triggered collection; and / or, the data collection trigger configuration information includes at least one of the following: data collection period information, data collection event type information, data collection threshold information, data collection interval information.

18. The device according to claim 12, wherein the data reporting configuration information includes active reporting configuration information and / or request-based reporting configuration information; the active reporting configuration information includes at least one of the following: maximum entry information of data, memory threshold information, data collection threshold information, terminal device status tendency change indication information, abnormal situation confirmation information, collection time information.

19. The device according to claim 12, wherein The data processing information includes complete data processing information or incomplete data processing information, wherein the complete data processing information is used to indicate that the data is original data, and the incomplete data processing information is used to indicate that the data has been subjected to compression processing, and / or the data has been subjected to offset processing.

20. The apparatus according to claim 11, wherein The first configuration information includes data reporting configuration information, and the data reporting configuration information includes active reporting configuration information. The device further includes: a determination unit, if the conditions corresponding to at least one of the active reporting configuration information are satisfied, the determination unit determines to send data storage indication information and / or the data to the first network device.

Images