Communication method and communication apparatus

Abstract

Provided in the present application are a communication method and a communication apparatus. The method comprises: receiving a first message, which is used for requesting to determine a user of a first type; and sending first information, which indicates a first terminal device, wherein a user type corresponding to the first terminal device is the first type, the first terminal device comprises at least one terminal device, the first terminal device is determined by performing prediction on the basis of a first model, the first model is constructed on the basis of multi-dimensional feature data of a second terminal device, and the second terminal device comprises a plurality of terminal devices, and also comprises the first terminal device. A terminal device of a certain user type is predicted on the basis of a first model, and a prediction result is returned to a requester, such that differentiated services can be provided for the terminal device of the user type, thereby improving the user experience.

Description

Communication methods and communication devices

[0001] This application claims priority to Chinese Patent Application No. 202411392036.9, filed with the China National Intellectual Property Administration on September 30, 2024, entitled "Communication Method and Communication Device", and to Chinese Patent Application No. 202511065298.9, filed with the China National Intellectual Property Administration on July 30, 2025, entitled "Communication Method and Communication Device", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communications, and more specifically, to a communication method and a communication device. Background Technology

[0003] Fifth generation (5) th In 5G communication systems, network data analytics function (NWDAF) network elements are introduced. These elements can receive subscription requests from consumer network elements, collect relevant data from network function (NF) network elements, process and analyze this data, and obtain statistical or predictive analysis results.

[0004] In existing solutions, NWDAF's ability to build data analysis by collecting user service access data and signaling data from NF through service-oriented or private interface extensions is relatively weak. For example, the dimensions of the data collected are relatively limited, which cannot effectively support operators in identifying different user types and providing differentiated services to different types of users, thus affecting user experience. Summary of the Invention

[0005] This application provides a communication method and a communication device that can predict the user type corresponding to a terminal device, thereby providing differentiated services for terminal devices with different user types and improving user experience.

[0006] Firstly, a communication method is provided that can be applied to a data analysis network element. Specifically, this method can be executed by the data analysis network element, or by a module (e.g., a chip or circuit) of the data analysis network element, or by a logical node, logical module, or software capable of implementing all or part of the data analysis functions of the network element; this application does not limit this.

[0007] The method comprises: receiving a first message, the first message being used for requesting to determine a user belonging to a first type; and sending first information, the first information indicating a first terminal device, a user type corresponding to the first terminal device being the first type, the first terminal device comprising at least one terminal device, the first terminal device being determined based on a first model, the first model being constructed based on multi-dimensional feature data of a second terminal device, the second terminal device comprising a plurality of terminal devices, and the second terminal device comprising the first terminal device.

[0008] Based on the above scheme, the data analysis network element can predict a terminal device belonging to a certain user type according to the first model, and return the prediction result to the requester, so as to enable to provide differentiated services for the terminal device of the user type and improve user experience, wherein the first model is constructed based on multi-dimensional feature data of a plurality of terminal devices.

[0009] In some implementations of the first aspect, the first model is a neural network model, and the multi-dimensional feature data of the second terminal device is used to pre-train the neural network model.

[0010] Based on the above scheme, the neural network model can be used to predict a terminal device belonging to the first type, and pre-training the neural network based on multi-dimensional feature data of a plurality of terminal devices can improve the performance and generalization ability of the neural network.

[0011] In some implementations of the first aspect, the first model is a knowledge graph, the multi-dimensional feature data of the second terminal device is used to train the knowledge graph, an entity object in the knowledge graph comprises the multi-dimensional feature data of the second terminal device, the knowledge graph is used to search data related to query feature data based on the query feature data, and the multi-dimensional feature data of the second terminal device comprises the data related to the query feature data.

[0012] Based on the above scheme, the knowledge graph can be trained based on multi-dimensional feature data of a plurality of terminal devices, a user portrait knowledge graph containing multi-dimensional feature data of a user can be generated, and the terminal device belonging to the first type can be queried through the knowledge graph.

[0013] In some implementations of the first aspect, the first model is a clustering algorithm, the clustering algorithm is used to evaluate data related to query feature data, and the multi-dimensional feature data of the second terminal device comprises the data related to the query feature data.

[0014] Based on the above scheme, the terminal device belonging to the first type can be queried through the clustering algorithm.

[0015] In some implementations of the first aspect, the multi-dimensional feature data of the third terminal device is obtained, the third terminal device including a plurality of terminal devices, the multi-dimensional feature data of each terminal device in the third terminal device corresponding to a user type corresponding to the each terminal device; and the second terminal device includes the third terminal device, and the user type corresponding to the third terminal device includes the first type.

[0016] Based on the above scheme, by obtaining the multi-dimensional feature data of the terminal device with the user type label, the first model for determining the user type can be constructed.

[0017] In some implementations of the first aspect, the first model is a neural network model, the neural network model is fine-tuned based on the multi-dimensional feature data of the third terminal device and the user type corresponding to the third terminal device, and the fine-tuned neural network model is used to predict the user type corresponding to the multi-dimensional feature data based on the multi-dimensional feature data.

[0018] Based on the above scheme, by fine-tuning the neural network model based on the multi-dimensional feature data of the terminal device with the user type label, the neural network model for determining a specific user type can be constructed, so that the terminal device belonging to the first type can be determined based on the neural network model.

[0019] In some implementations of the first aspect, the user type corresponding to the multi-dimensional feature data of the second terminal device is determined based on the fine-tuned neural network model, and the first terminal device is determined from the second terminal device according to the user type corresponding to the multi-dimensional feature data of the second terminal device.

[0020] Based on the above scheme, the data analysis network element can predict the user type corresponding to the multi-dimensional feature data of the second terminal device based on the fine-tuned neural network model, so that the terminal device of the first type can be selected from the user type corresponding to the multi-dimensional feature data of the second terminal device.

[0021] In some implementations of the first aspect, the first model is a knowledge graph, the feature data related to the query feature data is determined according to the query feature data and the knowledge graph, the query feature data being the multi-dimensional feature data of the third terminal device corresponding to the multi-dimensional feature data of the terminal device of the first type, and the first terminal device is determined according to the feature data related to the query feature data, the first terminal device being the terminal device corresponding to the feature data related to the query feature data in the second terminal device.

[0022] Based on the above scheme, the data analysis network element can predict the multi-dimensional feature data related to the multi-dimensional feature data of the terminal device of the first type based on the knowledge graph and the multi-dimensional feature data of the query, so as to select the terminal device of the first type from the second terminal device based on the related multi-dimensional feature data.

[0023] In some implementations of the first aspect, the first model is a clustering algorithm, and the multi-dimensional feature data of the second terminal device is clustered based on the clustering algorithm to obtain a clustering result, the clustering result including a user type corresponding to the multi-dimensional feature data of the second terminal device; and the first terminal device is determined based on the clustering result and the first type.

[0024] Based on the above scheme, the data analysis network element can cluster the multi-dimensional feature data of the second terminal device based on the clustering algorithm to obtain a user type corresponding to the multi-dimensional feature data of the second terminal device, so as to select the terminal device of the first type from the second terminal device.

[0025] In some implementations of the first aspect, the first model is a clustering algorithm, and the multi-dimensional feature data of the second terminal device is clustered based on the clustering algorithm to obtain a plurality of clusters; the feature data related to the feature data of the query is determined based on the feature data of the query and the plurality of clusters, the feature data of the query being the multi-dimensional feature data corresponding to the terminal device of the first type in the multi-dimensional feature data of the third terminal device; and the first terminal device is determined based on the feature data related to the feature data of the query.

[0026] Based on the above scheme, the data analysis network element can cluster the multi-dimensional feature data of the second terminal device based on the clustering algorithm to obtain a plurality of clusters, and determine the feature data related to the multi-dimensional feature data corresponding to the terminal device of the first type with a user label based on the plurality of clusters, so as to determine the first terminal device.

[0027] In some implementations of the first aspect, the multi-dimensional feature data of the second terminal device is obtained from a first network element, the first network element including at least one of an access and mobility management network element, a user plane function network element, a policy control function network element, or a first device, the first device being a device in an operator business operation and management system.

[0028] In some implementations of the first aspect, if the first network element includes the policy control function network element, the multi-dimensional feature data of the second terminal device includes at least one of subscription information of the second terminal device and rule information, the subscription information indicating information of a service to which the second terminal device subscribes, and the rule information being used for managing a service of the second terminal device.

[0029] In some implementations of the first aspect, if the first network element comprises the first device, the multi-dimensional feature data of the second terminal device comprises at least one of the following: personal attributes of the user, a package level, value-added service consumption data, and service experience data of the user.

[0030] In some implementations of the first aspect, if the first network element comprises the user plane function network element, the multi-dimensional feature data of the second terminal device comprises at least one of the following: a type of application accessed by the user, a start time and an end time of application access, traffic statistical information of application access, an access rate of application access, a key performance indicator of application access, a key quality indicator of application access, and a video quality experience score.

[0031] In some implementations of the first aspect, if the first network element comprises the access and mobility management network element, the multi-dimensional feature data of the second terminal device comprises at least one of the following: time information of the second terminal device accessing the access network device, location information of the second terminal device, and context information of the second terminal device; wherein the context information comprises at least one of the following: identification information of the second terminal device, an access point name of the second terminal device, and location information of the second terminal device.

[0032] Based on the above scheme, the data analysis network element can obtain multi-dimensional feature data of the second terminal device (i.e., multi-dimensional feature data of the second terminal device) from different network elements in the first network element, so as to construct the first model based on the multi-dimensional feature data of the second terminal device.

[0033] In a second aspect, a communication method is provided, which can be applied to a second network element. Specifically, the method can be executed by the second network element, or can also be executed by a module (such as a chip or a circuit) of the second network element, or can also be executed by a logic node, a logic module or software capable of realizing all or part of the functions of the second network element, and the present application does not make any limitation in this regard.

[0034] The method comprises: sending a first message, the first message being used to request to determine a user belonging to a first type; receiving first information, the first information indicating a first terminal device, a user type corresponding to the first terminal device being the first type, the first terminal device comprising at least one terminal device, the first terminal device being determined based on a first model, the first model being constructed based on multi-dimensional feature data of a second terminal device, the second terminal device comprising a plurality of terminal devices, the second terminal device comprising the first terminal device.

[0035] In some implementations of the second aspect, the first model is described with reference to the first aspect.

[0036] In some implementations of the second aspect, the first model is a neural network model, the neural network model is obtained by fine-tuning based on pairs of multi-dimensional feature data of the third terminal device, and the fine-tuned neural network model is used to predict a user type corresponding to the multi-dimensional feature data based on the multi-dimensional feature data; the third terminal device includes a plurality of terminal devices, the multi-dimensional feature data of each terminal device in the third terminal device corresponds to a user type corresponding to the each terminal device, the second terminal device includes the third terminal device, and the user types corresponding to the third terminal device include the first type.

[0037] In some implementations of the second aspect, the first model is a knowledge graph, the knowledge graph is used to determine feature data related to feature data of a query according to the feature data of the query, the feature data of the query is multi-dimensional feature data of the third terminal device, the multi-dimensional feature data of the first type of terminal device, and the first terminal device is a terminal device in the second terminal device corresponding to the feature data related to the feature data of the query; the third terminal device includes a plurality of terminal devices, the multi-dimensional feature data of each terminal device in the third terminal device corresponds to a user type corresponding to the each terminal device, the user types corresponding to the third terminal device include the first type, and the second terminal device includes the third terminal device.

[0038] In some implementations of the second aspect, the first model is a clustering algorithm, the clustering algorithm is used to cluster multi-dimensional feature data of the second terminal device with multi-dimensional feature data of the third terminal device as a clustering center to obtain a clustering result, the clustering result includes a user type corresponding to the multi-dimensional feature data of the second terminal device, and the first terminal device is a terminal device corresponding to the first type in the user type corresponding to the multi-dimensional feature data of the second terminal device; the third terminal device includes a plurality of terminal devices, the multi-dimensional feature data of each terminal device in the third terminal device corresponds to a user type corresponding to the each terminal device, the user types corresponding to the third terminal device include the first type, and the second terminal device includes the third terminal device.

[0039] In some implementations of the second aspect, the first model is a clustering algorithm, and the clustering algorithm is configured to cluster the multi-dimensional feature data of the second terminal device to obtain a plurality of clusters; the plurality of clusters are configured to determine the feature data related to the queried feature data, the queried feature data being multi-dimensional feature data corresponding to the terminal device of the first type in the multi-dimensional feature data of the third terminal device, the terminal device of the first type being a terminal device corresponding to the feature data related to the queried feature data in the second terminal device; and the third terminal device includes a plurality of terminal devices, and the multi-dimensional feature data of each terminal device in the third terminal device corresponds to a user type corresponding to the each terminal device, and the user type corresponding to the third terminal device includes the first type, and the second terminal device includes the third terminal device.

[0040] In some implementations of the second aspect, the multi-dimensional feature data of the second terminal device is data obtained from a first network element, and the first network element includes at least one of an access and mobility management network element, a user plane function network element, a policy control function network element, or an operator business operation and management system.

[0041] In some implementations of the second aspect, the multi-dimensional feature data of the second terminal device is described with reference to the first aspect.

[0042] In a third aspect, a communication apparatus is provided, and the apparatus includes a transceiver configured to receive a first message, the first message being configured to request to determine a user belonging to a first type; and the transceiver is further configured to send first information, the first information being configured to indicate a first terminal device, the user type corresponding to the first terminal device being the first type, the first terminal device including at least one terminal device, and the first terminal device being determined based on a first model, the first model being constructed based on multi-dimensional feature data of a second terminal device, the second terminal device including a plurality of terminal devices, and the second terminal device including the first terminal device.

[0043] In some implementations of the third aspect, the first model is described with reference to the first aspect.

[0044] In some implementations of the third aspect, the transceiver is further configured to obtain multi-dimensional feature data of a third terminal device, the third terminal device including a plurality of terminal devices, and the multi-dimensional feature data of each terminal device in the third terminal device corresponding to a user type corresponding to the each terminal device; and the second terminal device includes the third terminal device, and the user type corresponding to the third terminal device includes the first type.

[0045] In some implementations of the third aspect, the apparatus further includes a processing unit, the first model being a neural network model, and the processing unit is configured to fine-tune the neural network model based on the multi-dimensional feature data of the third terminal device.

[0046] In some implementations of the third aspect, the processing unit is further configured to: determine a user type corresponding to the multi-dimensional feature data of the second terminal device based on the fine-tuned neural network model; and determine the first terminal device from the second terminal device according to the user type corresponding to the multi-dimensional feature data of the second terminal device.

[0047] In some implementations of the third aspect, the apparatus further comprises a processing unit, and the first model is a knowledge graph, and the processing unit is configured to: determine feature data related to the query feature data according to the query feature data and the knowledge graph, the query feature data being the multi-dimensional feature data of the third terminal device corresponding to the first type of terminal device; and determine the first terminal device according to the feature data related to the query feature data, the first terminal device being the terminal device corresponding to the feature data related to the query feature data in the second terminal device.

[0048] In some implementations of the third aspect, the apparatus further comprises a processing unit, and the first model is a clustering algorithm, and the processing unit is configured to: cluster the multi-dimensional feature data of the second terminal device to obtain a clustering result according to the clustering algorithm and taking the multi-dimensional feature data of the third terminal device as a clustering center, the clustering result including a user type corresponding to the multi-dimensional feature data of the second terminal device; and determine the first terminal device according to the clustering result and the first type.

[0049] In some implementations of the third aspect, the apparatus further comprises a processing unit, and the first model is a clustering algorithm, and the processing unit is configured to: cluster the multi-dimensional feature data of the second terminal device to obtain a plurality of clusters according to the clustering algorithm; determine feature data related to the query feature data according to the query feature data and the plurality of clusters, the query feature data being the multi-dimensional feature data of the third terminal device corresponding to the first type of terminal device; and determine the first terminal device according to the feature data related to the query feature data.

[0050] In some implementations of the third aspect, the transceiver is further configured to obtain the multi-dimensional feature data of the second terminal device from a first network element, and the first network element is described with reference to the first aspect.

[0051] In some implementations of the third aspect, when the first network element is the above network element, the multi-dimensional feature data of the second terminal device is described with reference to the first aspect.

[0052] In a fourth aspect, a communication apparatus is provided, which comprises a transceiver unit configured to: transmit a first message, the first message being used to request to determine a user belonging to a first type; and receive first information, the first information indicating a first terminal device, the first terminal device corresponding to the first type, the first terminal device comprising at least one terminal device, the first terminal device being determined based on a first model, the first model being constructed based on multi-dimensional feature data of a second terminal device, the second terminal device comprising a plurality of terminal devices, the second terminal device comprising the first terminal device.

[0053] In some implementations of the fourth aspect, the first model is described in the first aspect.

[0054] In some implementations of the fourth aspect, the first model is a neural network model, the neural network model being fine-tuned based on multi-dimensional feature data of a third terminal device, the third terminal device comprising a plurality of terminal devices, multi-dimensional feature data of each terminal device of the third terminal device corresponding to a user type corresponding to the each terminal device; wherein the second terminal device comprises the third terminal device, the user type corresponding to the third terminal device comprising the first type.

[0055] In some implementations of the fourth aspect, the first model is a knowledge graph, the knowledge graph being used to determine feature data related to query feature data according to the query feature data, the query feature data being multi-dimensional feature data of a terminal device of the first type, the terminal device being a terminal device of the second terminal device corresponding to the feature data related to the query feature data, the third terminal device comprising a plurality of terminal devices, multi-dimensional feature data of each terminal device of the third terminal device corresponding to a user type corresponding to the each terminal device; wherein the second terminal device comprises the third terminal device, the user type corresponding to the third terminal device comprising the first type.

[0056] In some implementations of the fourth aspect, the first model is a clustering algorithm, the clustering algorithm being used to cluster multi-dimensional feature data of the second terminal device with multi-dimensional feature data of the third terminal device as a clustering center to obtain a clustering result, the clustering result comprising a user type corresponding to the multi-dimensional feature data of the second terminal device, the first terminal device being a terminal device corresponding to the first type in the user type corresponding to the multi-dimensional feature data of the second terminal device; wherein the third terminal device comprises a plurality of terminal devices, multi-dimensional feature data of each terminal device of the third terminal device corresponding to a user type corresponding to the each terminal device, the user type corresponding to the third terminal device comprising the first type, the second terminal device comprising the third terminal device.

[0057] In some implementations of the fourth aspect, the first model is a clustering algorithm, and the clustering algorithm is configured to cluster the multi-dimensional feature data of the second terminal device to obtain a plurality of clusters; the plurality of clusters are configured to determine feature data related to the queried feature data, the queried feature data being multi-dimensional feature data corresponding to the first type of terminal device in multi-dimensional feature data of a third terminal device, the first terminal device being a terminal device in the second terminal device corresponding to the feature data related to the queried feature data; and the third terminal device includes a plurality of terminal devices, and the multi-dimensional feature data of each terminal device in the third terminal device corresponds to a user type corresponding to the each terminal device, and the user type corresponding to the third terminal device includes the first type, and the second terminal device includes the third terminal device.

[0058] In some implementations of the fourth aspect, the multi-dimensional feature data of the second terminal device is data obtained from a first network element, and the first network element includes at least one of an access and mobility management network element, a user plane function network element, a policy control function network element, or an operator business operation and management system.

[0059] In some implementations of the fourth aspect, the multi-dimensional feature data of the second terminal device is described in the first aspect.

[0060] In a fifth aspect, a communication apparatus is provided, and the apparatus includes a processor coupled to a memory, and the processor is configured to execute instructions in the memory to implement any of the first aspect and the second aspect, and the method in any possible implementation of the first aspect and the second aspect. Optionally, the apparatus further includes the memory, and the memory can be deployed separately from the processor or can be deployed centrally. Optionally, the apparatus further includes a communication interface, and the processor is coupled to the communication interface.

[0061] In one implementation, the communication interface can be a transceiver, or an input / output interface.

[0062] In another implementation, the apparatus is a data analysis network element or a second network element, or a chip deployed in the data analysis network element or the second network element, or a logic module or software capable of implementing all or part of the functions of the data analysis network element or the second network element. When the apparatus is a chip, the communication interface can be an input / output interface, an interface circuit, an output circuit, an input circuit, a pin, or related circuit on the chip or a chip system. The processor can also be embodied as a processing circuit or a logic circuit.

[0063] Optionally, the transceiver can be a transceiver circuit. Optionally, the input / output interface can be an input / output circuit.

[0064] In the implementation process, the processor can be one or more chips, the input circuit can be an input pin, the output circuit can be an output pin, and the processing circuit can be a transistor, a gate circuit, a flip-flop, various logic circuits, etc. The input signal received by the input circuit can be, but is not limited to, received and input by the receiver, the output signal output by the output circuit can be, but is not limited to, output to the transmitter and transmitted by the transmitter, and the input circuit and the output circuit can be the same circuit, which is used as the input circuit and the output circuit at different times. The embodiments of the present application do not limit the specific implementation of the processor and various circuits.

[0065] In a sixth aspect, the present application provides a chip system, comprising: a processor, the processor being configured to execute a computer program or instructions in the memory, so that the chip system implements the method in any one of the first aspect and the second aspect, and any possible implementation manner of the first aspect and the second aspect.

[0066] In a seventh aspect, the present application provides a communication system, comprising: at least one of a data analysis network element and a second network element, the data analysis function network element being configured to execute the method in the first aspect and any possible implementation manner of the first aspect; and the second network element being configured to execute the method in the second aspect and any possible implementation manner of the second aspect.

[0067] In an eighth aspect, a computer readable storage medium is provided, the computer readable storage medium storing a computer program (also referred to as code or instructions) which, when executed on a computer, causes the computer to execute the method in any one of the first aspect and the second aspect, and any possible implementation manner of the first aspect and the second aspect.

[0068] In a ninth aspect, a computer program product is provided, the computer program product comprising: a computer program (also referred to as code or instructions) which, when executed, causes a computer to execute the method in any one of the first aspect and the second aspect, and any possible implementation manner of the first aspect and the second aspect.

[0069] The beneficial effects brought by the above-mentioned second aspect to the ninth aspect can refer to the description of the beneficial effects in the first aspect, which will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0070] FIG. 1 is a schematic diagram of a network architecture suitable for embodiments of the present application.

[0071] FIG. 2 shows a basic flow of the NWDAF providing analysis results.

[0072] FIG. 3 is a schematic flowchart of a communication method 300 provided by the present application.

[0073] FIG. 4 is a schematic diagram of a knowledge graph provided by the present application.

[0074] FIG. 5 is a schematic flow chart of a communication method 500 provided by the present application.

[0075] FIG. 6 is a schematic block diagram of a communication apparatus 1000 provided by the present application.

[0076] FIG. 7 is a schematic block diagram of a communication apparatus 1100 provided by the present application.

[0077] FIG. 8 is a schematic block diagram of a chip system 1200 provided by the present application. DETAILED DESCRIPTION

[0078] The technical solutions in the present application will be described below in conjunction with the accompanying drawings.

[0079] The technical solutions of the embodiments of the present application can be applied to various communication systems, for example, long term evolution (LTE), 5th generation (5G), new radio (NR), internet of things (IoT), wireless-fidelity (Wi-Fi), 3rd generation partnership project (3GPP) related wireless communication, or future communication systems, etc., which are not limited by the present application.

[0080] The technical solutions provided by the present application can also be applied to machine type communication (MTC), device-to-device (D2D) network, machine to machine (M2M) network, internet of things (IoT) network or other networks. The IoT network may, for example, include a vehicle network. In the vehicle network, the communication mode is collectively referred to as vehicle to X (V2X, X can represent any thing), for example, the V2X can include vehicle to vehicle (V2V) communication, vehicle to infrastructure (V2I) communication, vehicle to pedestrian (V2P) communication or vehicle to network (V2N) communication, etc.

[0081] FIG. 1 is a schematic diagram of a network architecture applicable to embodiments of the present application. As shown in FIG. 1, the network architecture takes the 5G system (5GS) as an example.

[0082] The network architecture can be divided into an access network and a core network. The network architecture can include, but is not limited to: unified data management (UDM), network exposure function (NEF), network repository function (NRF), policy control function (PCF), application function (AF), access and mobility management function (AMF), session management function (SMF), user equipment (UE), wireless access network device, user plane function (UPF), data network (DN). Among them, the DN can be the Internet; the UDM, NEF, NRF, PCF, AF, AMF, SMF, UPF belong to the network element in the core network, since FIG. 1 takes the 5G system as an example, the core network can be referred to as the 5G core network (5GC or 5GCN).

[0083] The network elements shown in FIG. 1 are briefly introduced as follows.

[0084] 1. User equipment (UE): can be referred to as terminal device, access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user equipment.

[0085] The terminal device can be a device providing voice / data to a user, for example, a handheld device with wireless connection function, a vehicle-mounted device, etc. Currently, some examples of the terminal are: a mobile phone, a tablet computer, a notebook computer, a palm computer, a mobile internet device (MID), a virtual reality (VR) device, an augmented reality (AR) device, a wireless terminal in industrial control, a wireless terminal in self driving, a wireless terminal in remote medical surgery, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a terminal device in a 5G network, or a terminal device in a future evolved public land mobile network (PLMN), etc. The embodiments of the present application are not limited thereto.

[0086] By way of example and not limitation, in the embodiments of the present application, the terminal device can also be a wearable device. The wearable device can also be referred to as a wearable smart device, which is a general term for devices that are designed and developed by applying wearable technology to daily wear, such as glasses, gloves, watches, clothing, and shoes. The wearable device is a portable device that is directly worn on the body or integrated into the clothes or accessories of the user. The wearable device is not only a hardware device, but also has strong functions through software support and data interaction and cloud interaction. The general wearable smart device includes a device with full functions and large size, which can realize complete or partial functions without relying on a smart phone, such as a smart watch or smart glasses, and a device that focuses on a certain application function and needs to cooperate with other devices such as a smart phone, such as various smart wristbands and smart jewelry for monitoring vital signs.

[0087] In addition, in the embodiments of the present application, the terminal device can also be a terminal device in an IoT system. IoT is an important part of future information technology development, and its main technical feature is to connect objects to the network through communication technology, thereby realizing an intelligent network of human-machine interconnection and object interconnection.

[0088] It should be noted that the terminal device and the access network device can communicate with each other using a certain air interface technology (such as new radio (NR) or LTE technology, etc.). The terminal device and the terminal device can also communicate with each other using a certain air interface technology (such as NR or LTE technology, etc.).

[0089] In the embodiments of the present application, the device for implementing the function of the terminal device can be a terminal device, or a device capable of supporting the terminal device to implement the function, such as a chip system or a chip, which can be installed in the terminal device. In the embodiments of the present application, the chip system can be composed of a chip, or can include a chip and other discrete devices.

[0090] 2, (radio) access network ((R)AN): can provide access to a communication network for authorized users in a specific area, and can specifically include a wireless network device in a 3rd generation partnership project (3GPP) network, and can also include an access point in a non-3GPP (non-3GPP) network.

[0091] The RAN can manage radio resources and provide access services for user equipment, and then complete the forwarding of control signals and user equipment data between user equipment and a core network. The RAN can also be understood as a base station in a traditional network.

[0092] Exemplarily, the access network device in the embodiments of the present application can be any kind of communication device with wireless transceiving function for communicating with user equipment. The access network device includes but is not limited to evolved Node B (eNB), baseband unit (BBU), access point (AP) in a wireless fidelity (WIFI) system, wireless relay node, wireless backhaul node, transmission point (TP) or transmission and reception point (TRP), etc., and can also be gNB or TP in a 5G, such as a NR, system, one or a group of (including multiple antenna panels) antenna panels of a base station in a 5G system, or a network node constituting a gNB or a transmission point, such as a baseband unit (BBU) or a distributed unit (DU), etc.

[0093] In some deployments, a gNB can include a centralized unit (CU) and a DU. The gNB can also include an active antenna unit (AAU). The CU implements part of the functions of the gNB, and the DU implements part of the functions of the gNB. For example, the CU is responsible for processing non-real-time protocols and services, implementing radio resource control (RRC), and the functions of the packet data convergence protocol (PDCP) layer. The DU is responsible for processing the physical layer protocol and real-time services, implementing the functions of the radio link control (RLC) layer, the media / medium access control (MAC) layer, and the physical (PHY) layer. The AAU implements part of the physical layer processing functions, radio frequency processing, and related functions of the active antenna. Since the information of the RRC layer eventually becomes the information of the PHY layer, or is converted from the information of the PHY layer, under this architecture, high-layer signaling, such as RRC layer signaling, can also be considered as being sent by the DU, or by the DU+AAU. It can be understood that the access network device can be a device including one or more of the CU node, the DU node, and the AAU node. In addition, the CU can be divided into an access network device in a radio access network (RAN), or can be divided into an access network device in a core network (CN), which is not limited in the present application.

[0094] In different systems, the CU (or CU-CP and CU-UP), DU or RU can also have different names, but those skilled in the art can understand their meanings. For example, in an open-radio access network (O-RAN) system, the CU can also be referred to as an open-central unit (O-CU) (open CU); the DU can also be referred to as an open-distributed unit (O-DU) (open DU); the CU-CP can also be referred to as an O-CU-CP, the CU-UP can also be referred to as an O-CU-UP, and the RU can also be referred to as an O-RU. For the convenience of description, the CU, CU-CP, CU-UP, DU and RU are taken as examples for description in this application. Any one of the CU (or CU-CP, CU-UP), DU and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0095] 3. A user plane function (UPF) network element: used for packet routing and forwarding, quality of service (QoS) processing of user plane data, etc. User data can access a data network (DN) through the network element. In the embodiments of this application, the function of the user plane network element can be implemented.

[0096] 4. A data network (DN): a network used to provide data transmission. For example, a network of operator services, the Internet, a third-party service network, etc.

[0097] 5. An operations, administration and management (OAM) network element: mainly used for analysis, prediction, planning and configuration of network and services, and testing and fault management of network and services, etc.

[0098] 6. An access and mobility management function (AMF) network element: mainly used for mobility management and access management, etc., and can be used to implement other functions in the mobility management entity (MME) function except session management, such as access authorization / authentication functions, etc.

[0099] 7. Session management function (SMF) network element: mainly used for session management, terminal device internet protocol (IP) address allocation and management, selection and management of user plane function, terminal point of policy control and charging function interface and downlink data notification, etc.

[0100] 8. Policy control function (PCF) network element: a unified policy framework for guiding network behavior, providing policy rule information for network elements (such as AMF, SMF network elements, etc.) or terminal devices, etc.

[0101] 9. Network repository function (NRF) network element: used to save the description information of network function entities and the services provided thereby, and support service discovery, network element entity discovery, etc.

[0102] 10. Network exposure function (NEF) network element: used to safely open the services and capabilities provided by the third generation partnership project (3GPP) network function to the outside, etc.

[0103] 11. Unified data management (UDM) network element: used for unified data management, 5G user data management, processing user identification, access authentication, registration, or mobility management, etc.

[0104] 12. Application function (AF) network element: used for data routing for application influence, accessing the network exposure function network element, interacting with the policy framework for policy control, etc.

[0105] 13. Network data analytics function (NWDAF) network element: the NWDAF is provided with data collection, training, analysis, and inference functions. For example, the NWDAF collects relevant data from network elements (for example, AMF, SMF, UPF, UDM, AF (directly or through NEF)), third-party service servers, terminal devices, or network management systems; for another example, the NWDAF collects location information from a location-based service (LCS) system and collects data from a message framework adapter function (MFAF); for another example, the NWDAF performs analysis and training based on the relevant data and provides data analysis results to network elements, third-party service servers, terminal devices, or network management systems, which can assist the network in selecting service quality parameters for services, or assist the network in performing traffic routing, or assist the network in selecting background data transmission strategies, and the like.

[0106] In embodiments of the present application, the NWDAF can be a separate network element or can be combined with other network elements, for example, the NWDAF network element can be combined with the AMF or combined with the SMF.

[0107] It should be understood that the network elements included in the communication system listed above are only exemplary and the present application is not limited thereto.

[0108] In the above network architecture, the N2 interface is the interface between the RAN and the AMF network element, used for sending wireless parameters, non-access stratum (NAS) signaling, and the like; the N3 interface is the interface between the RAN and the UPF network element, used for transmitting user plane data and the like; the N4 interface is the interface between the SMF network element and the UPF network element, used for transmitting information such as service policies, N3 connection tunnel identification information, data caching indication information, and downlink data notification messages. The N6 interface is the interface between the DN network element and the UPF network element, used for transmitting user plane data and the like.

[0109] It should be understood that in the above network architecture, the network elements can exchange information through service interfaces. For example, the NWDAF network element can collect data generated by terminals on the network elements through service interfaces (such as Namf, Nsmf, etc.) provided by other network elements (such as AMF, SMF, etc.) from these network elements, and provide analysis results (Analytics), models, also known as machine learning models, data, etc. through the Nnwdaf interface to other network elements (such as AMF, PCF, etc.).

[0110] It should be understood that the network architecture applied to the embodiments of the present application is only a network architecture described from the perspective of the traditional point-to-point architecture and the service-oriented architecture, and the network architecture applicable to the embodiments of the present application is not limited thereto, and any network architecture capable of realizing the functions of the above-mentioned network elements is applicable to the embodiments of the present application.

[0111] It should be noted that the names of the various network elements and interfaces in the present application are only examples, and the present application does not exclude the case where the various network elements are named otherwise and the functions of the various network elements are merged. With the evolution of technology, any device or network element capable of realizing the functions of the above-mentioned network elements is within the protection scope of the present application.

[0112] The above-mentioned network elements can also be referred to as entities, devices, apparatuses or modules, etc., which are not particularly limited in the present application. In the present application, in order to facilitate understanding and description, the description of "network element" is omitted in part of the description, for example, the NWDAF network element is simply referred to as NWDAF, in this case, the "NWDAF" should be understood as the NWDAF network element, and hereinafter, the description of the same or similar cases is omitted.

[0113] In addition, the network architecture described above can also include a business operation support system (BOSS) system or a business analytics system.

[0114] The BOSS system is the core business support system of a telecommunications operator, mainly used to provide user data management, business processing, billing and settlement functions, including user profile maintenance, user authentication, business opening, change, termination, etc., and generate bills according to user usage, complete settlement with partners, etc. The business analytics system can be simply referred to as a business system, which is an important tool for enterprise management, mainly used to collect, organize, analyze and report enterprise business activity data based on data analysis technology, to help enterprise management make decisions and plans. The business system can provide comprehensive data analysis for enterprises, support in-depth analysis of multiple dimensions such as finance, sales, procurement and inventory, and generate various forms of reports and visual charts to intuitively display the results and trends of data analysis.

[0115] The network architecture described above can also include operations, administration and management (OAM), simply referred to as network management, mainly used to complete daily network and business analysis, prediction, planning and configuration, as well as testing and fault management of the network and its business. OAM can interact with RAN to obtain information such as wireless channel conditions and wireless resource utilization on the RAN side.

[0116] The network architecture can further include a packet flow description function (PFDF). The PFDF can be deployed in the NEF, which can be a functional element. The PFDF can receive and manage packet flow description (PFD) information associated with application identities from a service capability exposure function (SCEF) through a Nu reference point, and the NWDAF can obtain the PFD information through the NEF (PFDF).

[0117] The network architecture can further include a data collection coordination function (DCCF) network element and an analytics data repository function (ADRF) network element.

[0118] The DCCF can be used in cooperation with the NWDAF to implement a data collection coordination function, reduce repeated data collection, and implement data formatting processing. Specifically, the NWDAF can request the DCCF to collect data of certain network elements through an Ndccf interface, for example, the DCCF can learn the specific network elements serving the UE through service interfaces provided by the NRF, UDM, binding support function (BSF), etc., and then initiate a data collection request to these network elements. The DCCF can feed back data to the NWDAF after the collection is completed.

[0119] The ADRF can be used to store data collected by the network (e.g., the NWDAF or the DCCF) and models and analysis results obtained by the NWDAF training, and to provide services for retrieving historical data (from network elements) and analysis results (from the NWDAF). The network elements can store and retrieve historical data (analysis results) through an Nadrf interface of the ADRF. In addition, the ADRF can subscribe to a data notification service from the DCCF, so that the DCCF will feed back to the ADRF when receiving data that meets the conditions.

[0120] After the introduction of the NWDAF network element, the NWDAF can receive a subscription request of a consumer network element (such as a network function (NF), operations, administration and management (OAM)), collect corresponding data from the network, and process and analyze the data to obtain statistical or predicted analysis results. The NWDAF network element feeds back the analysis results to the consumer network element or to the network element specified by the consumer network element (such as an NF or an OAM). In the current 5G network architecture, the consumer network element herein can refer to a consumer of the NWDAF service, such as a 5GC NF (such as a PCF, an NSSF, an AMF, an SMF, an NEF, an AF, an NWDAF, a DCCF) or an OAM.

[0121] It should be understood that in this application, the analysis result can also be referred to as a data analysis result, which is generated by the NWDAF and can include one or more parameters statistically or predicted by the NWDAF. The NWDAF supports providing different types of analysis results, which can be distinguished by an analysis identifier (Analytics ID).

[0122] The current 3GPP standard defines the capability of the NWDAF to expose related data analysis to the AF through the NEF. The analysis result exposed by the NWDAF to the AF can be performed by the NEF using an analysis request to the NWDAF.

[0123] FIG. 2 shows a method 200 for an AF to obtain analysis information from a NWDAF through an NEF. The method can include the following steps.

[0124] S210, the NEF controls the analysis exposure mapping.

[0125] Exemplarily, the NEF controls the analysis exposure mapping between an AF identifier and allowed Analytics IDs. The identifier has allowed related inbound restrictions (i.e., Analytics IDs applied to AF requests) and / or outbound restrictions (i.e., responses to Analytics IDs to AF).

[0126] In this version, the AF is configured (for example, by static OAM configuration) to use the appropriate NEF for subscribing to analysis information, allowed Analytics IDs, and allowed inbound restrictions (i.e., parameters and / or parameter values) for requesting each Analytics ID.

[0127] S220, the AF requests analysis information from the NEF.

[0128] Exemplarily, the AF can request analytics information from the NEF via the Nnef_AnalyticsExplosure_Fetch service operation. If the request is authorized by the NEF, the NEF proceeds with the following steps.

[0129] S230, the NEF requests analytics information from the NWDAF according to the request of the AF.

[0130] Exemplarily, the NEF requests and obtains analytics information from the NWDAF by invoking the Nnwdaf_AnalyticsInfo_Request service operation.

[0131] If the parameters and / or parameter values requested by the AF comply with the restrictions in the analytics exposure map, the NEF forwards the Analytics ID, parameters and / or parameter values of the AF in the request to the NWDAF in the subscription of the NWDAF service.

[0132] For example, the input of the Nnwdaf_AnalyticsInfo_Request service operation can include the following parameters:

[0133] 1) a list of analytics ID(s): including one or more analytics IDs, each analytics ID is used to identify the type of requested analytics result. The analytics ID can also be referred to as an event ID.

[0134] 2) analytics filter information: such as area of interest (AOI), single network slice selection assistance information (S-NSSAI), etc., indicating the applicable conditions of the analytics result.

[0135] 3) target of analytics reporting: indicating the target to which the analytics request applies, which can be a specific UE, a group of UEs, or any UE.

[0136] 4) analytics target period: indicating the time period to which the analytics result applies, i.e., indicating which time analytics result the AF wants to obtain.

[0137] If the received request from the AF does not comply with the restrictions in the analytics exposure map, the NEF can apply restrictions (e.g. restrictions on parameters or parameter values of the Nnwdaf_AnalyticsInfo_Request service operation) to the request to the NWDAF based on the configuration and / or can apply parameter mapping (e.g. mapping of geographical coordinates to TA(s), Cell-id(s)).

[0138] Optionally, the NEF records the association between the analytics request from the AF and the analytics request sent to the NWDAF.

[0139] Alternatively, the NEF selects a NWDAF that supports the analytics information requested by the AF according to the NWDAF discovery procedure defined in TS 23.501.

[0140] S240, the NWDAF responds to the NEF with the analytics information.

[0141] That is, in response to the request of the NEF, the NWDAF sends the analytics information to the NEF.

[0142] S250, the NEF responds to the AF with the analytics information.

[0143] That is, in response to the request of the AF, the NEF sends the analytics information to the AF. Exemplarily, the NEF can apply restrictions (e.g. restrictions on parameters or parameter values of the Nnef_AnalyticsExposure_Fetch response service operation) to the response to the AF according to operator configuration.

[0144] In the 5G communication system, any 5GC NF is allowed to request analytics information from a NWDAF containing an analytics logical function (AnLF). Optionally, the NWDAF belongs to the same PLMN as the 5GC NF using the analytics information. For example, a 5GC NF can request analytics information from a NWDAF through the service-based interface Nnwdaf. The Nnwdaf interface is defined for 5GC NFs to request subscription to network analytics delivery for a specific context, to unsubscribe from network analytics delivery, and to request specific reports of network analytics for a specific context.

[0145] Exemplarily, the information of the consuming network elements of the NWDAF and the service operation requesting the analytics information is shown in Table 1.

[0146] Table 1

[0147] In addition, the analysis type information supported by the NWDAF is defined in 3GPP Rel-17 23.288, which can be identified by an Analytics ID. Table 2 shows an example of the relevant content of the Analytics ID:

[0148] Table 2

[0149] For example, Analytics ID = "Service Experience" represents the analysis result of service experience; Analytics ID = "Network Performance" represents the analysis result of network performance; and Analytics ID = "UE Mobility" represents the analysis result of UE mobility. When a consumer network element subscribes to the analysis result from the NWDAF, it can carry one or more Analytics IDs to identify the type of analysis result that it wants to obtain from the NWDAF; the NWDAF then collects the corresponding data from the network according to the Analytics ID and feeds back the derived corresponding analysis result to the consumer network element.

[0150] One application scenario of the NWDAF is customization or optimization of terminal parameters. That is, the NWDAF can collect information such as connection management, mobility management, session management, and service access of users, use reliable analysis and prediction models to evaluate and analyze different types of users, build user portraits, determine user mobility trajectories and service usage habits, and optimize mobility management parameters and radio resource management parameters of users.

[0151] In the existing scheme, the analysis of terminal users and the self-defined report scenario of the NWDAF are both based on specified conditions and rules to analyze and aggregate calculate multi-dimensional user data. This scheme needs to specify relevant behavior characteristics to implement construction of user portraits and behavior analysis, so as to realize classification of types of users. In this scheme, the NWDAF expands through a service or private interface to collect service access data and signaling data of users from NFs to build the ability of data analysis, which is relatively weak, and cannot well support operators to determine different types of users and provide differentiated services for different types of users, affecting user experience.

[0152] In view of this, the present application provides a communication method and a communication device, which can determine one or more users belonging to a certain type based on multi-dimensional feature data of users, so as to provide differentiated services for users of the type and improve user experience.

[0153] The method provided by the embodiments of the present application will be described in detail below with reference to the drawings. The embodiments provided by the present application can be applied to the network architecture shown in FIG. 1, without limitation.

[0154] FIG. 3 is a schematic diagram of a communication method 300 provided by an embodiment of the present application. The method 300 can include the following steps.

[0155] S310, the second network element sends a first message to the data analysis network element. Accordingly, the data analysis network element receives the first message.

[0156] The first message can be used to request to determine a user belonging to a first type; or in other words, the first message is used to request the data network element to generate analysis information, and the analysis information corresponds to an analysis identifier for determining a user belonging to a first type.

[0157] Wherein, the user and the terminal device or the identifier of the terminal device (user identity) have a corresponding relationship, and hereinafter, “user” and “terminal device” can be replaced sometimes, without limitation.

[0158] In addition, in the communication network, each user can be assigned multiple types of user identity, which is used to uniquely identify the user, that is, the information corresponding to “user” or “terminal device” hereinafter can also be understood as the information corresponding to the user identity.

[0159] Exemplarily, the user identity includes at least one of the following:

[0160] Mobile Subscriber ISDN Number (MSISDN), i.e., the Integrated Services Digital Network (ISDN) number of a mobile user; International Mobile Subscription Identity (IMSI), stored in a SIM (Subscriber Identity Modules) card of a mobile phone, which can be simply understood as the ID of the SIM card, and the association between IMSI and MSISDN can be stored in user subscription data; Generic Public Subscription Identifier (GPSI); Subscription Permanent Identifier (SUPI), and the association between GPSI and SUPI can be stored in 5G user subscription data; IP Multimedia Public Identity (IMPU); IP Multimedia Private Identity (IMPI), and the like.

[0161] As an example, the data analytics network element can refer to a network data analytics function (NWDAF) network element, and the data analytics network element can also be other network elements with a data analytics function, and no limitation is made thereto.

[0162] The second network element can be a consumer NF network element of the data analytics network element, i.e., other functional network elements in the network that request to obtain the analysis information generated by the NWDAF. For example, the second network element can be an operator business operation and management system, such as a business operation support system (BOSS) or a business analytics system, or an AF, and no limitation is made thereto.

[0163] For example, in the case where the second network element is a BOSS / business analytics system, the first message can be an analysis subscription request (Nnwdaf_AnalyticsSubscription_Subscribe Request) message.

[0164] For another example, in the case that the second network element is an AF, the AF can send the first message through the NEF, for example, the AF requests analytics information from the NEF through the Nnef_AnalyticsExplosure_Fetch service operation. Details can be referred to the description in S220.

[0165] The first message can carry a list of analytics ID(s). The list of analytics ID(s) includes one or more analytics ID(s), each analytics ID is used to identify the type of requested analytics information. The analytics ID can also be referred to as an event ID. The one or more analytics ID(s) includes a first analytics ID, which is an analytics ID of determining a user belonging to a first type; the first message can also carry an identifier of the first type.

[0166] Exemplarily, the first type can be one of a plurality of user types. Each user type in the plurality of user types can correspond to at least one user, and the user portrait corresponding to each user type has the same or similar characteristics, or in other words, the users belonging to the same user type can have the same or similar user portrait characteristics. The application does not limit the dimension of dividing the user types, for example, different users can be corresponded to different user types based on at least one attribute such as age, gender, occupation (such as a driver of a car-hailing platform, a business elite), hobby (such as games, movies), behavior (such as subway commuting to work), consumption ability, lifestyle, etc., that is, users with different ages, genders, occupations, hobbies, behaviors, consumption abilities, lifestyles, etc. can be corresponded to different user portraits. The identifier corresponding to the user type can be agreed by the protocol, which is not limited.

[0167] The first message further carries at least one of the following information:

[0168] 1) Target of analytics reporting: indicates the target to which the analytics request applies, which can be a specific UE, a group of UEs, or any UE.

[0169] 2) Notification target address (+ notification correlation ID), which allows associating the notification received from the data analytics network element with this subscription.

[0170] 3) Analytics reporting parameters (including analytics target period, etc.). The analytics reporting target can be provided according to a single analytics ID.

[0171] Optionally, the first message further carries at least one of the following information:

[0172] 1) Analytics filter information: such as area of interest (AOI), single network slice selection assistance information (S-NSSAI), etc., indicating the applicable condition of analytics information;

[0173] 2) Time window of historical analytics: can refer to how long the data is based on for user profiling analysis, such as the last half year, one year, or an absolute time period from January to June.

[0174] 3) Reporting threshold, which can be used to indicate the condition of each requested analytics level, when the condition is reached, the data analytics network element should be notified.

[0175] 4) Maximum number of objects requested (max);

[0176] 5) Preferred order of results, maximum number of SUPIs requested (SUPI max);

[0177] 6) Time when analytics information is needed, if the time is reached, the consumer no longer needs to wait for analytics information, but the data analytics network element can send an error response to the consumer;

[0178] 7) Output policy: indicates relevant factors for determining when to report analytics, that is, defines what time allows reporting.

[0179] 8) Data time window: if this field is carried, only events created within the specified time interval are considered for analytics generation.

[0180] 9) Service area or NF ID of the consumer NF;

[0181] 10) Information of previous analytics subscription, that is, NWDAF identifier (that is, instance ID or set ID), analytics ID (including SUPI and UE-related analytics filter information), and subscription association ID;

[0182] 11) Use case context: indicates the context of using analytics to select the most relevant model.

[0183] 12) Analytics accuracy request information, used to request the accuracy of analytics information;

[0184] 13) Analytics feedback information: can refer to the content of the consumer NF after receiving the notification information, executing the policy and feeding back to the data analytics network element.

[0185] S320, the data analytics network element sends the first information to the second network element. Correspondingly, the second network element receives the first information.

[0186] The first information indicates at least one terminal device (denoted as a first terminal device), and a user corresponding to the first terminal device is a user of the first type. For example, the first information can include at least one user identity (an identifier of a terminal device).

[0187] For example, the first terminal device is determined by the data analytics network element based on a first model. The first model is constructed based on multi-dimensional feature data of a plurality of terminal devices (denoted as second terminal devices). The multi-dimensional feature data of the plurality of terminal devices can be understood as: multi-dimensional feature data corresponding to each terminal device in the plurality of terminal devices. The second terminal devices include the first terminal device.

[0188] Optionally, before constructing the first model, the method further includes: obtaining, by the data analytics network element, the multi-dimensional feature data of the second terminal devices from a first network element.

[0189] The first network element can include at least one of the following network elements: an access and mobility management network element, a policy control function network element, a user plane function network element, or an operator business operation and management system.

[0190] For example, in a 5G communication system, the access and mobility management network element is an AMF network element or a functional module in the AMF network element; the policy control function network element is a PCF network element or a functional module in the PCF network element; the user plane network element is a UPF network element or a functional module in the UPF network element; and the operator business operation and management system can be a BOSS / operation and maintenance system. The above network elements can refer to the related description in FIG. 1.

[0191] It should be understood that the name of the network element is not limited in the present application. For example, in a future communication system, the access and mobility management network element can also be a network element with another name. For ease of description, the following describes the network elements as network elements in a 5G communication system.

[0192] It can be understood that for a terminal device, the feature data of one dimension of the terminal device can correspond to one network element in the above-mentioned second network element, or in other words, the feature data of a certain dimension of the terminal device can be obtained from one network element in the above-mentioned second network element. The multi-dimensional feature data of the terminal device is obtained from the above-mentioned plurality of network elements.

[0193] It should be understood that the above correspondence between the dimensions of the feature data of the terminal device and the network elements is only an example, and the terminal device can also have multiple dimensions of data obtained from the above-mentioned network elements, which is not limited.

[0194] In an example, the feature data of the terminal device (denoted as data #1) obtained by the data analytics network element from the AMF can include mobility information of the terminal device, registration information of the terminal device, session information of the terminal device, and context information of the terminal device, and the like.

[0195] The mobility information of the terminal device can include, for example, (current) location information of the terminal device, time information of accessing the access network device (for example, including a time point or a time period of the terminal device accessing the access network device), a moving track, a moving speed, a moving direction, and the like; the registration information of the terminal device can include, for example, a radio access technology (RAT) corresponding to the terminal device, a signal transmission mode (for example, including frequency division duplexing (FDD) and time division duplexing (TDD)), a network access state, a registration area, a subscribed service, and the like; and the context information of the terminal device can include, for example, at least one of a user identity corresponding to the terminal device (which can refer to the description above), an access point name (APN), and location information.

[0196] As an example, the location information of the terminal device can be associated with the access network device accessed by the terminal device, for example, the location information is a cell identifier, or the location information is an identifier of an area covered by the access network device. For example, the area covered by the access network device can be divided in a granularity of a tracking area (TA), and the location information of the terminal device can be a tracking area identifier (TAI) corresponding to a TA to which the terminal device belongs, or the area covered by the access network device is an area divided in other granularity, for example, a cell identifier (cell ID), a geographical area identifier, a network code (NC), a country code (CC), a city code, a county code, and the like, which are not limited. The location information of the terminal device can also be geodetic location information, which can be used to confirm the location information of the user accessing the cell and the access network device.

[0197] For example, the data analytics network element can obtain data #1 from the AMF via message #1. This message #1 can be a Location Event Subscription Request (Namf_Location_EventNotify Subscribe Request) message; optionally, in response to the Location Event Subscription Request message, the AMF sends a Location Event Subscription Response (Namf_Location_EventNotify Subscribe Response) message to the data analytics network element, and optionally, the AMF returns the data #1 to the NWDAF via a Location Event Notification (Namf_Location_EventNotify) message. That is, the AMF pushes real-time information of the access network devices of users who meet the subscription conditions to the NWDAF for user profile feature modeling.

[0198] In another example, the characteristic data of the terminal device obtained by the data analysis network element from the PCF (denoted as data #2) may include: the terminal device's subscription information and rule information, etc.

[0199] The terminal device's subscription information may include details of the user's subscribed service package, such as the package name or identifier (e.g., "Home Broadband Package," "5G Data Package"), package contents (e.g., voice call duration, SMS messages, data traffic, broadband speed), package fees (e.g., monthly fees, one-time fees, and fees during promotional periods), activation and expiration dates (recording the package's activation and expiration dates, and whether automatic renewal is supported), and additional services (e.g., international roaming, value-added services, etc., which the user may subscribe to separately).

[0200] The rule information for terminal devices can be the rule information used by PCF to manage the services subscribed to by the terminal devices. For example, it specifically includes the following rule information: traffic management rules: such as traffic capping, traffic rate limiting, traffic priority, etc., which can be used to control users' data usage under different conditions; billing rules: including various billing methods such as pay-as-you-go billing, time-based billing, tiered billing, etc., as well as related preferential and discount policies; service change rules: the rules and procedures that users need to follow when they need to change their plan, upgrade their service, or cancel their service.

[0201] For example, a data analytics network element can obtain data #2 from the PCF via message #2. This message #2 can be a PCF event exposure subscription request (Npcf_EventExposure_Subscribe) message. This message carries at least one of the following information:

[0202] 1) NF ID, the identifier for the subscribed network element;

[0203] 2) target of analytics reporting, indicating the target to which the analytics request is applied, which can be a specific UE, a group of UEs, or any UE.

[0204] 3) a list of analytics ID(s). The list of analytics ID(s) includes one or more analytics ID(s), each of which is used to identify the type of requested analytics information. The analytics ID can also be referred to as an event ID. The one or more analytics IDs include a second analytics ID and a third analytics ID, wherein the second analytics ID can be an analytics ID corresponding to the subscription information; and the third analytics ID can be an analytics ID corresponding to the rule information.

[0205] 4) notification target address (+ notification associated ID): a target address to which an event notification message is sent;

[0206] 5) event reporting information: other key information of event reporting, for example, adding some filtering conditions to report only the information of a package whose subscription duration exceeds a certain time period, or the information of a specified value-added service package.

[0207] Optionally, the message carries the following information:

[0208] 1) analytics filter information, which can be specifically referred to the description in the foregoing.

[0209] 2) timeout time: used to specify the timeout time of the subscription message, for example, the subscription is valid until next Friday 12:00.

[0210] Further, in response to the PCF event exposure subscription request message, the PCF sends a PCF event exposure subscription response (Npcf_EventExposure_Subscribe Response) message to the data analysis network element, and optionally, the PCF returns the data #2 to the NWDAF through a PCF event exposure notification (Npcf_EventExposure_Notify) message. That is, the PCF returns the user subscription information and the rule information that meet the subscription conditions to the NWDAF for user portrait feature modeling.

[0211] In another example, the feature data of the terminal device acquired by the data analytics network element from the UPF (denoted as data #3) can include: information of the application accessed by the user, for example, type of the application accessed by the user, start and end time of accessing the application, traffic statistical information of accessing the application, access rate of accessing the application, key performance indicator (KPI), key quality indicator (KQI), and Video Mean Opinion Score (vMOS) of the video quality experience, and the like.

[0212] For example, the KPI mainly focuses on quantitative indicators of network conditions and capabilities, including traffic conditions, propagation conditions, resource conditions, credibility performance, and billing performance, and the like; the KQI focuses on evaluating the quality of video services from the perspective of the user. It can be divided according to the business life cycle, and statistics are made on aspects such as business support performance, business operability performance, business performance, and security performance. In video quality evaluation, the KQI can include indicators such as video clarity, smoothness, and loading speed that directly affect the user experience; the vMOS can be used to evaluate the video quality, operation experience, and playback experience of the video service, and the like. For example, the video quality can be reflected by parameters such as resolution, frame rate, code rate, and encoding level of the video; the operation experience can be reflected by indicators such as initial loading time and first screen second opening time; and the playback experience can be reflected by indicators such as smoothness, including frequency and duration of phenomena such as freezing and screen tearing.

[0213] Exemplarily, the data analytics network element can acquire the data #3 from the UPF through a message #3. The message #3 can be a UPF event exposure subscription request (Nupf_EventExposure_Subscribe Request) message; optionally, in response to the UPF event exposure subscription request message, the UPF sends a UPF event exposure subscription (Nupf_EventExposure_Subscribe Response) message to the data analytics network element, and optionally, the UPF returns the data #3 to the NWDAF through an event exposure notification (Nupf_EventExposure_Notify) message.

[0214] In another example, the feature data of the terminal device acquired by the data analytics network element from the BOSS / through system (an example of an operator business operation and management system) (denoted as data #4) can include: personal attributes of the user, package level, value-added service consumption data, and service experience data (such as satisfaction / complaint and related data) of the user, and the like.

[0215] The personal attributes of the user can include inherent attributes and dynamically changing attributes of the user, for example, the inherent attributes of the user include gender, age, etc., and the dynamically changing attributes of the user include a package subscribed by the user, etc.

[0216] Exemplarily, the data analysis network element can obtain data #4 from the BOSS / mediation system through message #4. The message #4 can be a message type defined by the data analysis network element and the operator, for example, the message #4 is a User_info_Subscribe Request message. Optionally, in response to the User_info_Subscribe Request message, the BOSS / mediation system sends a User_info_Subscribe Response message to the data analysis network element, and optionally, the BOSS / mediation system returns the data #4 to the NWDAF through a User_info_Notify message.

[0217] That is, through the above example, the data analysis network element can obtain multi-dimensional feature data of a plurality of terminal devices from the first network element. The multi-dimensional feature data of each terminal device corresponds to an identifier corresponding to the terminal device (such as an identifier of the terminal device and / or a user identity identifier). That is, the data analysis network element maintains a data set including multi-dimensional feature data corresponding to each of a plurality of terminal devices, and the data set is used to construct a first model.

[0218] Optionally, the data analysis network element can also perform data processing on the data set. Data cleaning processing can include removing duplicate records, processing missing values, anomaly value detection and correction, etc.

[0219] The first model and a specific manner of determining the first terminal device based on the first model are described in detail below.

[0220] In one example, the first model is a neural network model. The neural network model can be pre-trained based on the multi-dimensional feature data of the second terminal device.

[0221] Optionally, before pre-training the neural network model, tokenization processing, data normalization, token vectorization processing, etc. can also be performed on the pre-training data set.

[0222] Among them, the tokenization processing is a process of converting text or category data into a format that the model can understand. For non-text data (such as age, gender, etc.), it can be directly encoded into numerical tokens; for text data (such as user comments, descriptions, etc.), it needs to be split into word or subword units (tokens). For example, for numerical data, it can be directly used or transformed through appropriate mapping (such as one-hot encoding, label encoding) to token; for text data, it can be tokenized by word segmentation (such as space segmentation, regular expression segmentation) or natural language processing (NLP) library to convert text into token sequence.

[0223] Data normalization is to make all features on the same scale so that the model can learn more effectively. For example, for numerical features, common normalization methods include standardization (Z-score normalization) and normalization (Min-Max normalization). For tokenized text data, data normalization can include steps such as removing stop words, stemming, and lemmatization.

[0224] Token vectorization processing can convert tokens into fixed-length vectors for model processing.

[0225] It should be understood that the present application does not limit the specific structure of the neural network model, as long as the neural network model can encode the input text and extract its feature and semantic information. For example, the neural network model can be a large model based on the above feature data after tokenization / vectorization processing, which is an encoder-only (Encoder-only) Transformer structure.

[0226] It should also be understood that in the present application, the neural network model can also be referred to as a machine learning model, or an artificial intelligence (AI) model or other names, which are not limited.

[0227] In another example, the first model is a knowledge graph. The knowledge graph is obtained by training based on the multi-dimensional feature data of the second terminal device. The entity objects in the knowledge graph include the multi-dimensional feature data of the second terminal device, that is, the data analysis network element constructs a knowledge graph based on the multi-dimensional feature data of multiple terminal devices, and the knowledge graph can be used for searching data related to the query feature data based on the query feature data. The query feature data can refer to the description below; the data related to the query feature data includes the multi-dimensional feature data of the second terminal device.

[0228] For example, the relationships and attributes among multiple entities in the knowledge graph are shown in FIG. 4. The knowledge graph includes entity objects (such as user information, package usage data, application (APP) access data, website access data, Internet protocol (IP) access data, environmental data, and the like) and relationships among all the entity objects (for example, purchase, access website, access APP, access IP, and the like).

[0229] In yet another example, the first model is an unsupervised machine learning algorithm, for example, a clustering algorithm (such as a K-Means algorithm, a hierarchical clustering algorithm, and the like). The unsupervised machine learning algorithm is used to evaluate data related to the feature data of the query. The feature data of the query can be referred to the description below; the data related to the feature data of the query includes the multi-dimensional feature data of the second terminal device.

[0230] It should be understood that, because the feature data of different user types is different, for example, the data packet size of the browsing type feature data is small, and the number of data packets sent per unit time is small; the data packet size of the video type feature data is large, and it is relatively continuous, and the idle time is small, therefore, the data analysis network element can perform clustering on the multi-dimensional feature data of multiple terminal devices based on the unsupervised machine learning algorithm, so that each multi-dimensional feature data of each terminal device corresponds to a user type, for example, the user belonging to type #1 corresponds to the video type feature data, and the user belonging to type #2 corresponds to the browsing type feature data.

[0231] Optionally, before the data analysis network element determines the user belonging to the first type, the method further includes: the data analysis network element obtaining the multi-dimensional feature data corresponding to the third terminal device. The third terminal device includes multiple terminal devices, and the multi-dimensional feature data of each terminal device in the third terminal device corresponds to the user type corresponding to each terminal device. The second terminal device includes the third terminal device.

[0232] In one example, the data analysis network element obtains information #1, which can include the user type corresponding to each terminal device in the third terminal device, or in other words, the information #1 includes the identifier of each terminal device in the third terminal device and the corresponding relationship between the identifier of each terminal device and the user type. The data analysis network element obtains the multi-dimensional feature data of the third terminal device from the collected data (for example, the multi-dimensional feature data of the second terminal device), and labels this data, that is, adds a user type label to the corresponding multi-dimensional feature data, or in other words, so that the multi-dimensional feature data of each terminal device in the third terminal device corresponds to the user type.

[0233] The multi-dimensional feature data of the third terminal device can be understood as a labeled data set, or a labeled sample (set), labeled sample data, and the name is not limited, that is, the multi-dimensional feature data of each terminal device in the third terminal device corresponds to a label of a user type.

[0234] It should be understood that there is a corresponding relationship between the terminal device, the multi-dimensional feature data of the terminal device, and the user type of the terminal device, so in the present application, the "user type corresponding to the terminal device" can also be understood as "the user type corresponding to the multi-dimensional feature data of the terminal device", and the two can be replaced by each other.

[0235] It should also be understood that each terminal device in the third terminal device can correspond to a user type, and the user type corresponding to each terminal device can be the same or different, or in other words, in the present application, the terminal devices belonging to the same user type can be one or more (such as a terminal device list), and this is not limited.

[0236] The data analysis network element can obtain information 1 from the BOSS / mediation system or the AF. Or in other words, the BOSS / mediation system or the AF can inject the labeled data set into the data analysis network element.

[0237] Exemplarily, the service operation of the BOSS / mediation system or the AF injecting the labeled data set into the data analysis network element can be a newly defined service operation, for example, a label data transfer (Nnwdaf_LabelData_Transfer) service operation. The input of the service operation can include a user type label, and a user list conforming to the user type label. Optionally, the input of the service operation further includes: a partial feature list related to the user type, such as location information, user application access information and experience information, subscription package, etc.

[0238] Exemplarily, the BOSS / mediation system can carry a user list information of a group of user type labels (such as online users and offline users) through an extended NWDAF label data transfer request (Nnwdaf_LabelData_Transfer Request) message to inject the labeled sample data into the NWDAF.

[0239] Exemplarily, the AF can carry a user list information of a set of users with user type labels (such as game players, VR pioneers) through an NEF label data transfer request (Nnef_LabelData_Transfer Request) to inject the labeled sample data into the NWDAF via the NEF. In this case, when the NEF sends the user list information to the data analysis network element, the NEF can convert the Nnef_LabelData_Transfer Request into a NWDAF label data transfer request (Nnwdaf_LabelData_Transfer Request) message to inject the labeled sample data into the data analysis network element.

[0240] In another example, the data analysis network element directly obtains the multi-dimensional feature data corresponding to each terminal device in the third terminal device. For example, the data analysis network element obtains the multi-dimensional feature data corresponding to each terminal device in the third terminal device from the second network element, and the specific obtaining manner can refer to the description in the foregoing.

[0241] That is, the multi-dimensional feature data of the third terminal device is labeled data, and the label is the user type corresponding to each terminal device. That is, the multi-dimensional feature data of each terminal device in the third terminal device corresponds to the user type corresponding to the terminal device. The user type corresponding to the multi-dimensional feature data of the third terminal device includes the first type.

[0242] Optionally, the method further includes: the data analysis network element constructs the first model based on the multi-dimensional feature data of the third terminal device.

[0243] Exemplarily, in the case where the first model is a neural network, the data analysis network element can fine-tune the neural network model based on the multi-dimensional feature data of the third terminal device.

[0244] Wherein, fine-tuning can refer to retraining a pre-trained model with smaller task-related data for a specific task, adjusting its model parameters to adapt to the new task. That is, the data analysis network element can use the data set composed of the multi-dimensional feature data of the third terminal device with user type labels to further train (i.e., fine-tune) the pre-trained neural network model based on the pre-trained neural network model based on the unlabeled data set (the multi-dimensional feature data of the second terminal device), so that the neural network model after fine-tuning can adapt to the user type classification task.

[0245] For example, after obtaining the multi-dimensional feature data of the terminal device corresponding to the user type label of game heavy users (an example of the multi-dimensional feature data of the third terminal device), the data analysis network element can perform feature engineering processing based on the multi-dimensional feature data and the user label of game heavy users to generate a training set with the user label of game heavy users. The data analysis network element can fine-tune the neural network model based on the training set. The fine-tuned neural network model can have the ability to classify game terminal users based on the multi-dimensional feature data of the terminal device.

[0246] That is, the data analysis network element first pre-trains the neural network based on a large amount of unlabeled data set (multi-dimensional feature data of the second terminal device), and then can obtain a small amount of labeled data set (multi-dimensional feature data of the third terminal device) to fine-tune the neural network, thereby realizing downstream task model training for different tasks, for example, training a downstream task to identify players of a certain game based on a sample set with the game label.

[0247] For example, the data analysis network element determines the first terminal device based on the fine-tuned neural network model.

[0248] In one possible implementation, the data analysis network element determines the user type corresponding to the multi-dimensional feature data of the second terminal device (also referred to as the user type corresponding to the second terminal device) based on the fine-tuned neural network model, and determines the first terminal device from the second terminal device according to the user type corresponding to the second terminal device.

[0249] As described above, the fine-tuned neural network model has the ability to classify terminal devices based on the multi-dimensional feature data of the terminal devices (i.e., determine the user type corresponding to the terminal device), so the data analysis network element can determine the user type of the second terminal device based on the fine-tuned neural network model, and thus can determine the terminal device belonging to the first type from the second terminal device.

[0250] It should be understood that the second terminal device for determining the user type corresponding to the multi-dimensional feature data based on the fine-tuned neural network model can include the terminal device for pre-training, and optionally, the second terminal device further includes a newly added terminal device, i.e., after the data analysis network element obtains the multi-dimensional feature data of the second terminal device for pre-training, the data analysis network element can continue to obtain the multi-dimensional feature data of the terminal device, or in other words, the multi-dimensional feature data of the terminal device on the data analysis network element side can be continuously updated, i.e., in addition to the multi-dimensional feature data of the second terminal device that has been obtained for pre-training of the neural network model, the data analysis network element can continue to obtain the multi-dimensional feature data of other second terminal devices (e.g., terminal devices obtained after pre-training) for predicting the corresponding user type based on the fine-tuned neural network model, so that the first type of terminal device can be determined from the pre-trained second terminal device and / or the updated second terminal device. Alternatively, the second terminal device can further include a terminal device for pre-training in which the multi-dimensional feature data changes, i.e., the multi-dimensional feature data of the terminal device that has been obtained by the data analysis network element can also change.

[0251] In the case where the first model is a knowledge graph, the data analysis network element can determine the multi-dimensional feature data corresponding to the first type (denoted as the query feature data) based on the labeled data set (e.g., the multi-dimensional feature data of the third terminal device and the corresponding user type), and perform an association query on the query feature data in the knowledge graph to determine the related feature data of the query feature data, and then find other related user lists (i.e., users belonging to the first type) based on the related feature data, or in other words, the users belonging to the first type include the terminal devices corresponding to the feature data related to the multi-dimensional feature data corresponding to the first type.

[0252] Among them, the query feature can be the multi-dimensional feature data corresponding to the terminal device of the first type in the multi-dimensional feature data of the third terminal device. That is, the data analysis network element can query the feature data related to the multi-dimensional feature data corresponding to the first type from the knowledge graph with the multi-dimensional feature data corresponding to the terminal device of the first type in the third terminal device as the query feature data.

[0253] In the case where the first model is a clustering algorithm, in one possible implementation, the data analysis network element can perform clustering on the multi-dimensional feature data of a plurality of terminal devices based on the labeled data set (i.e., perform feature mapping and clustering centered on the feature data of the labeled user), and obtain the user type corresponding to the multi-dimensional feature data of each terminal device; the data analysis network element can determine the user with the same or similar features as the query feature data based on the clustering result, thereby determining the user belonging to the first type.

[0254] Specifically, the data analysis network element can cluster the multi-dimensional feature data of the second terminal device based on the multi-dimensional feature data of the third terminal device and the corresponding user type as a clustering center to obtain the user type corresponding to the second terminal device (denoted as a clustering result); and the data analysis network element can determine the first terminal device based on the clustering result. The first terminal device can include terminal devices of the second terminal device whose corresponding user type is the first type.

[0255] In another possible implementation, the data analysis network element clusters the multi-dimensional feature data of the second terminal device according to the clustering algorithm to obtain a plurality of clusters; and the data analysis network element determines feature data related to the query feature data according to the query feature data and the plurality of clusters, and determines the first terminal device according to the feature data related to the query feature data. The query feature data is the multi-dimensional feature data corresponding to the terminal device of the first type in the multi-dimensional feature data of the third terminal device, and the query feature data can refer to the description in the foregoing.

[0256] Subsequently, the BOSS / mediation system and the AF mediation system can provide differentiated services for users in the form of group sending of short messages, redirection of pages, pushing of advertisements, and the like based on the user types corresponding to the user list, thereby improving user experience.

[0257] Based on the communication method provided in the present application, the data analysis network element can respectively collect relevant user data for constructing a user portrait from different NFs, construct a full-amount user feature network through unsupervised learning of multi-dimensional features or by using knowledge graph technology, and then realize precise user portrait capability based on a small amount of labeled user data, so as to meet the classification of people groups by operators, realize precise services, and improve user experience.

[0258] The communication method provided in the present application will be described in detail below in combination with specific network elements.

[0259] FIG. 5 is a schematic flowchart of a communication method 500 provided in the present application, which can include the following steps.

[0260] Step one: the NWDAF (an example of a data analysis network element) collects user data. Step one can specifically include S501 to S512.

[0261] S501, the NWDAF sends a message #1 to the AMF. Correspondingly, the AMF receives the message #1.

[0262] The message #1 is used to request user data in the AMF, and the specific information carried by the message #1 can refer to the description in S320.

[0263] For example, the message #1 is a Namf_Location_EventNotify Subscribe Request message.

[0264] S502, the AMF sends a response message #1 to the NWDAF.

[0265] For example, the response message #1 is a Namf_Location_EventNotify Subscribe Response message.

[0266] S503, the AMF returns the data #1 to the NWDAF.

[0267] The AMF returns the data #1 to the NWDAF through a Namf_Location_EventNotify message. That is, the AMF pushes the real-time information of the access network device accessed by the user meeting the subscription condition to the NWDAF for user portrait feature modeling.

[0268] The data #1 can include mobility information of the terminal device, registration information of the terminal device, session information of the terminal device, and context information of the terminal device, etc.

[0269] S504, the NWDAF sends a message #2 to the PCF. Correspondingly, the PCF receives the message #2.

[0270] The message #2 is used to request user data in the PCF, and specific information carried by the message #2 can refer to the description in S320.

[0271] For example, the message #2 is a Npcf_EventExposure_Subscribe message.

[0272] S505, the PCF sends a response message #2 to the NWDAF.

[0273] For example, the response message #2 is a Npcf_EventExposure_Subscribe Response message.

[0274] S506, the PCF returns the data #2 to the NWDAF.

[0275] For example, the PCF returns the data #2 to the NWDAF through a Npcf_EventExposure_Notify message.

[0276] The data #2 can include subscription information of the terminal device and rule information, etc.

[0277] S507, the NWDAF sends a message #3 to the UPF. Correspondingly, the UPF receives the message #3.

[0278] The message #3 is used for requesting user data in the UPF, and specific information carried in the message #3 can refer to the description in S320.

[0279] For example, the message #3 is a Nupf_EventExposure_Subscribe Request message.

[0280] S508, the UPF sends a response message #3 to the NWDAF.

[0281] For example, the response message #3 is a Nupf_EventExposure_Subscribe Response message.

[0282] S509, the UPF returns the data #3 to the NWDAF.

[0283] For example, the UPF returns the data #3 to the NWDAF through a Nupf_EventExposure_Notify message.

[0284] The data #3 can refer to the description in S320.

[0285] S510, the NWDAF sends a message #4 to the BOSS / mediation system. Correspondingly, the BOSS / mediation system receives the message #4.

[0286] The message #4 is used for requesting user data in the BOSS / mediation system, and specific information carried in the message #4 can refer to the description in S320.

[0287] For example, the message #4 is a User_info_Subscribe Request message.

[0288] S511, the BOSS / mediation system sends a response message #4 to the NWDAF.

[0289] For example, the response message #4 is a User_info_Subscribe Response message.

[0290] S512, the BOSS / mediation system returns the data #4 to the NWDAF.

[0291] For example, the BOSS / mediation system returns the data #4 to the NWDAF through a User_info_Notify message.

[0292] The data #4 can refer to the description in S320.

[0293] Step two: the NWDAF constructs a first model. Step two can specifically include S513.

[0294] S513, the NWDAF builds a model (an example of the first model) for determining the user type based on the user data collected in the above steps.

[0295] This step can be specifically referred to the description in S320.

[0296] Step three: inject the labeled data set, which can be specifically referred to S514 to S516.

[0297] S514, the BOSS / Call Center sends a request message #1 to the NWDAF.

[0298] The request message #1 can be used to request to inject the data set carrying the label of the user type. For example, the request message #1 is Nnwdaf_LabelData_Transfer Request.

[0299] S515, the AF sends a request message #2 to the NWDAF through the NEF.

[0300] The request message #2 can be used to request to inject the data set carrying the label of the user type. For example, the request message #2 sent by the AF to the NEF is Nnef_LabelData_Transfer Request, and the request message #2 sent by the NEF to the NWDAF is Nnwdaf_LabelData_Transfer Request.

[0301] S516, the NWDAF sends a response message #3 to the BOSS / Call Center or the AF device through the NEF.

[0302] For example, the response message #3 can be Nnwdaf_LabelData_Transfer Response message.

[0303] The NWDAF obtains the original multi-dimensional feature data of the corresponding user from the collected data in the received labeled user list, labels the data, maintains the labeled data set of different user labels, and replies the response message #3 to the BOSS / Call Center or the AF.

[0304] Step four, subscribe to the users belonging to the user type #1 (an example of the first type) to realize the accurate user portrait. This step can include S517 to S519.

[0305] S517, the BOSS / Call Center subscribes to the users belonging to the user type #1 (an example of the first type) to the NWDAF.

[0306] For example, the BOSS / mediation system initiates an analytics subscription request for a precise user portrait to the NWDAF by carrying a specified user type (user type #1) in the Nnwdaf_AnalyticsSubscription_Subscribe Request (an example of the first message).

[0307] The information carried in the Nnwdaf_AnalyticsSubscription_Subscribe Request can refer to the information carried in the first message.

[0308] Optionally, the NWDAF sends a subscription response message to the BOSS / mediation system at S518.

[0309] For example, the subscription response message can be a Nnwdaf_AnalyticsSubscription_Subscribe Response message.

[0310] The NWDAF sends a list of users belonging to the user type #1 to the BOSS / mediation system at S519.

[0311] The list of users belonging to the user type #1 is determined based on the first model, and the details can refer to the description in S320.

[0312] Optionally, other NFs in the network subscribe to users belonging to a certain user type from the NWDAF. Details are not described herein.

[0313] The above describes the communication method provided by the embodiments of the present application in detail in combination with FIGS. 1-5. It should be understood that the sequence of the above processes does not mean the execution sequence, and the execution sequence of the processes should be determined according to the functions and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0314] It should also be understood that in various embodiments of the present application, the terms and / or descriptions of different embodiments are consistent and can be mutually referred to if there is no special description and no logical conflict, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0315] It can be understood that the methods and operations implemented by the devices (such as the data analysis network element and the BOSS / mediation system, AF, etc. described above) in each of the above method embodiments can also be implemented by components (such as chips or circuits) of the devices.

[0316] The above communication method is mainly introduced from the perspective of the interaction between various network elements. It can be understood that each network element contains a hardware structure and / or software module corresponding to each function in order to implement the above functions.

[0317] The following describes the communication apparatus provided by the embodiments of the present application in detail in combination with FIG. 6 to FIG. 8. It should be understood that the description of the apparatus embodiments corresponds to the description of the method embodiments, and thus, the content not described in detail can be referred to the method embodiments described above, which will not be described here for brevity.

[0318] FIG. 6 shows a schematic diagram of a communication apparatus 1000 provided by an embodiment of the present application.

[0319] The apparatus 1000 includes an interface unit 1010, which can be configured to implement corresponding communication functions. The interface unit 1010 can also be referred to as a communication interface, a communication unit, or a transceiver unit.

[0320] Optionally, the apparatus 1000 can further include a processing unit 1020, which can be configured to perform data processing.

[0321] Optionally, the apparatus 1000 further includes a storage unit, which can be configured to store instructions and / or data. The processing unit 1020 can read the instructions and / or data in the storage unit, so that the apparatus implements the actions of different devices in the foregoing various method embodiments.

[0322] In a possible design, the apparatus 1000 can be a data analytics network element (for example, the NWDAF) in the foregoing embodiments, or can be a component (for example, a chip) of the data analytics network element. The apparatus 1000 can implement the steps or processes corresponding to the steps performed by the data analytics network element in the foregoing method embodiments. Specifically, the interface unit 1010 can be configured to perform the operations related to receiving and transmitting of the data analytics network element in the foregoing method embodiments; and the processing unit 1020 can be configured to perform the operations related to processing of the data analytics network element in the foregoing method embodiments.

[0323] In another possible design, the apparatus 1000 can be a second network element (for example, the BOSS / branched system, the AF) in the foregoing embodiments, or can be a component (for example, a chip) of the second network element. The apparatus 1000 can implement the steps or processes corresponding to the steps performed by the second network element in the foregoing method embodiments. Specifically, the interface unit 1010 can be configured to perform the operations related to receiving and transmitting of the second network element in the foregoing method embodiments; and the processing unit 1020 can be configured to perform the operations related to processing of the second network element in the foregoing method embodiments.

[0324] FIG. 7 is a schematic block diagram of a communication apparatus 1100 provided by an embodiment of the present application.

[0325] The apparatus 1100 includes a processor 1110 coupled to a memory 1120. Optionally, the apparatus 1100 further includes the memory 1120. The memory 1120 is configured to store computer programs or instructions and / or data. The processor 1110 is configured to execute the computer programs or instructions stored in the memory 1120, or read the data stored in the memory 1120, to perform the methods in the above method embodiments.

[0326] Optionally, the processor 1110 is one or more.

[0327] Optionally, the memory 1120 is one or more.

[0328] Optionally, the memory 1120 is integrated with the processor 1110, or is separately arranged.

[0329] Optionally, as shown in FIG. 7, the apparatus 1100 further includes a communication interface 1130 configured to receive and / or send signals. For example, the processor 1110 is configured to control the communication interface 1130 to receive and / or send signals.

[0330] Illustratively, the communication interface 1130 can be a transceiver, a circuit, a bus, a module, or other types of communication interfaces. The communication interface 1130 can also be referred to as an interface.

[0331] As one solution, the apparatus 1100 is configured to implement operations performed by the data analysis network element in the above method embodiments.

[0332] For example, the processor 1110 is configured to execute the computer programs or instructions stored in the memory 1120 to implement the related operations of the second network element in the above method embodiments.

[0333] As another solution, the apparatus 1100 is configured to implement operations performed by the second network element in the above method embodiments.

[0334] For example, the processor 1110 is configured to execute the computer programs or instructions stored in the memory 1120 to implement the related operations of the second network element in the above method embodiments.

[0335] In the implementation process, each step of the above method can be completed by integrated logic circuit of hardware in the processor 1110 or instruction in the form of software. The method disclosed in combination with the embodiments of the present application can be directly embodied as hardware processor execution completion, or combined with hardware and software modules in the processor for execution completion. The software module can be located in the mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, register, etc. The storage medium is located in the memory 1120, and the processor 1110 reads the information in the memory 1120, and combines the hardware to complete the steps of the above method. To avoid repetition, it will not be described in detail here.

[0336] It should be understood that in the embodiments of the present application, the processor can be one or more integrated circuits for executing related programs to execute the method embodiments of the present application.

[0337] The processor (for example, the processor 1110) can include one or more processors and be implemented as a combination of computing devices. The processor can respectively include one or more of the following: a microprocessor, a microcontroller, a digital signal processor (digital signal processor, DSP), a digital signal processing device (digital signal processing device, DSPD), an application specific integrated circuit (application specific integrated circuit, ASIC), a field programmable gate array (field programmable gate array, FPGA), a programmable logic device (programmable logic device, PLD), a gating logic, a transistor logic, a discrete hardware circuit, a processing circuit or other suitable hardware, firmware and / or combination of hardware and software for executing various functions described in the present disclosure. The processor can be a general purpose processor or a special purpose processor. For example, the processor 1110 can be a baseband processor or a central processor. The baseband processor can be used to process communication protocols and communication data. The central processor can be used to make the device execute software programs and process data in the software programs. In addition, a part of the processor can also include a non-volatile random access memory. For example, the processor can also store device type information.

[0338] The program in the present application is used to represent software in a broad sense. Non-limiting examples of software include: program code, program, subprogram, instruction, instruction set, code, code segment, software module, application program, or software application, etc. The program can run in the processor and / or computer. So that the device executes various functions and / or processes described in the present application.

[0339] The memory (e.g., the memory 1120) can store data required by the processor (e.g., the processor 1110) when executing software. The memory can be implemented using any suitable storage technology. For example, the memory can be any available storage media that can be accessed by the processor and / or computer. Non-limiting examples of storage media include random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), Compact Disc Read-Only Memory (CD-ROM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM), flash memory, registers, state machines, remotely mounted memory, locally mounted memory, or any other storage medium that can be used to carry or store software, data, or information in the memory that is accessible to the processor / computer. It is understood that the memory described herein is intended to include, without being limited to, these and any other suitable types of memory.

[0340] The memory (e.g., the memory 1120) and the processor (e.g., the processor 1110) can be disposed separately or integrated together. The memory can be used to connect with the processor, so that the processor can read information from the memory, store and / or write information in the memory. The memory can be integrated in the processor. The memory and the processor can be disposed in an integrated circuit (for example, the integrated circuit can be disposed in the UE or other network node).

[0341] FIG. 8 is a schematic block diagram of a chip system 1200 according to an embodiment of the present application. The chip system 1200 (or also referred to as a processing system) includes a logic circuit 1210 and an input / output interface 1220.

[0342] The logic circuit 1210 can be a processing circuit in the chip system 1200. The logic circuit 1210 can be coupled to a storage unit, and invoke instructions in the storage unit, so that the chip system 1200 can implement the methods and functions of the embodiments of the present application. The input / output interface 1220 can be an input / output circuit in the chip system 1200, and output information processed by the chip system 1200, or input data or signaling information to be processed by the chip system 1200.

[0343] As an option, the chip system 1200 is configured to implement operations performed by the data analysis network element in the above method embodiments.

[0344] For example, the logic circuit 1210 is configured to implement processing-related operations performed by the data analysis network element in the above method embodiments; and the input / output interface 1220 is configured to implement sending and / or receiving-related operations performed by the data analysis network element in the above method embodiments.

[0345] The embodiments of the present application also provide a computer readable storage medium, which stores computer instructions for implementing the method performed by the communication device (such as the data analysis network element or the second network element) in the above method embodiments.

[0346] The embodiments of the present application also provide a computer program product, which contains instructions executed by a computer to implement the method performed by the communication device (such as the data analysis network element or the second network element) in the above method embodiments.

[0347] The embodiments of the present application also provide a communication system, which includes at least one of the data analysis network element and the second network element in the above embodiments.

[0348] The explanations and advantages of the related contents in any of the above devices can refer to the corresponding method embodiments provided above, and will not be repeated here.

[0349] In the above embodiments, the terms and / or descriptions of different embodiments are consistent and can be mutually referred to if there is no special description and no logical conflict. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0350] In the embodiments of the present application, the words "exemplary", "for example", and the like are used to mean serving as an example, instance, or illustration. Any embodiment or design presented as "exemplary" in the present application should not be interpreted as being more preferred or advantageous than other embodiments or design solutions. Rather, the word "exemplary" is used to present concepts in a concrete manner.

[0351] It should be understood that the term "embodiment" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, the various embodiments throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner.

[0352] It should be understood that the size of the sequence number of each process described above in various embodiments of the present application does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The names of all nodes and messages in the present application are only the names set by the present application for convenience of description, and the names in the actual network can be different, and the present application should not be understood as limiting the names of various nodes and messages. On the contrary, any name with the same or similar function as the node or message used in the present application is regarded as the method or equivalent replacement of the present application, and is within the protection scope of the present application.

[0353] It should also be understood that in the present application, "when", "if" and "if" all refer to the corresponding processing of the network element under certain objective circumstances, not the time limit, and it is not required that the network element implementation must have a judgment action, nor does it mean that there are other limitations.

[0354] It should be noted that in the embodiments of the present application, "pre-setting", "pre-configuration" and the like can be realized by pre-saving corresponding codes, tables or other means for indicating related information in the device (for example, terminal device), and the specific implementation manner is not limited in the present application, for example, the rules and preset constants in the embodiments of the present application.

[0355] In addition, the terms "system" and "network" are often used interchangeably in this document.

[0356] The term "at least one of" or "at least one of" in this document means all or any combination of the listed items, for example, "at least one of A, B and C" can mean: A exists alone, B exists alone, C exists alone, A and B exist together, B and C exist together, A, B and C exist together. Six cases. "At least one" in this document means one or more. "Multiple" means two or more.

[0357] It should be understood that in various embodiments of the present application, "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean that B is determined only according to A, but B can also be determined according to A and / or other information.

[0358] In addition, "of", "corresponding", "corresponding" and "associate" can be mixed sometimes, it should be pointed out that the meaning expressed is consistent when the distinction is not emphasized. The terms "include", "contain", "have" and their variants mean "include but not limited to", unless otherwise specifically emphasized otherwise.

[0359] Those skilled in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0360] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0361] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be realized by other ways. For example, the above-described device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0362] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0363] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit.

[0364] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes various media that can store program codes, such as a U disk, a mobile hard disk, a ROM, a RAM, a magnetic disk or an optical disk, etc.

[0365] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A communication method characterized by comprising: Comprise: receiving a first message, the first message is used for requesting to determine the user belonging to the first type; sending first information, the first information indicates the first terminal device, the user type corresponding to the first terminal device is the first type, the first terminal device includes at least one terminal device, the first terminal device is determined based on the first model, the first model is constructed based on the multidimensional feature data of the second terminal device, and the second terminal device includes a plurality of terminal devices, and the second terminal device includes the first terminal device.

2. The method of claim 1, wherein, The first model is a neural network model, and the multidimensional feature data of the second terminal device is used to pretrain the neural network model.

3. The method of claim 1, wherein, The first model is a knowledge graph, the multidimensional feature data of the second terminal device is used to train the knowledge graph, the entity object in the knowledge graph includes the multidimensional feature data of the second terminal device, and the knowledge graph is used to search data related to the query feature data based on the query feature data, Wherein, the multidimensional feature data of the second terminal device includes the data related to the query feature data.

4. The method of claim 1, wherein, The first model is a clustering algorithm, and the clustering algorithm is used to evaluate data related to query feature data; Wherein, the multidimensional feature data of the second terminal device includes the data related to the query feature data.

5. The method according to any one of claims 2 to 4, characterized in that, The method further comprises: obtaining the multidimensional feature data of the third terminal device, the third terminal device includes a plurality of terminal devices, and the multidimensional feature data of each terminal device in the third terminal device corresponds to the user type corresponding to the each terminal device; Wherein, the second terminal device includes the third terminal device, and the user type corresponding to the third terminal device includes the first type.

6. The method of claim 5, wherein, The first model is a neural network model, and the method further comprises: Fine-tuning the neural network model based on the multidimensional feature data of the third terminal device and the user type corresponding to the third terminal device, and the fine-tuned neural network model is used to predict the user type corresponding to the multidimensional feature data based on the multidimensional feature data.

7. The method of claim 6, wherein, The method further comprises: determining the user type corresponding to the multidimensional feature data of the second terminal device based on the fine-tuned neural network model; Determining the first terminal device from the second terminal device according to the user type corresponding to the multidimensional feature data of the second terminal device.

8. The method of claim 5, wherein, The first model is a knowledge graph, and the method further comprises: determining the feature data related to the query feature data according to the query feature data and the knowledge graph, the query feature data is the multidimensional feature data corresponding to the terminal device of the first type in the multidimensional feature data of the third terminal device; determining the first terminal device according to the feature data related to the query feature data, and the first terminal device is the terminal device corresponding to the feature data related to the query feature data in the second terminal device.

9. The method of claim 5, wherein, The first model is a clustering algorithm, and the method further comprises: According to the clustering algorithm, the multi-dimensional feature data of the third terminal device is taken as a clustering center, and the multi-dimensional feature data of the second terminal device is clustered to obtain a clustering result, the clustering result including a user type corresponding to the multi-dimensional feature data of the second terminal device; According to the clustering result and the first type, the first terminal device is determined.

10. The method of claim 5, wherein, The first model is a clustering algorithm, and the method further includes: According to the clustering algorithm, the multi-dimensional feature data of the second terminal device is clustered to obtain a plurality of clusters; According to the query feature data and the plurality of clusters, feature data related to the query feature data is determined, the query feature data being multi-dimensional feature data corresponding to the first type of terminal device in the multi-dimensional feature data of the third terminal device; According to the feature data related to the query feature data, the first terminal device is determined, the first terminal device being a terminal device corresponding to the feature data related to the query feature data in the second terminal device.

11. The method according to any one of claims 1 to 10, characterized in that, The method further includes: Obtaining the multi-dimensional feature data of the second terminal device from a first network element, the first network element including at least one of: an access and mobility management network element, a user plane function network element, a policy control function network element, or an operator business operation and management system.

12. The method of claim 11, wherein, If the first network element includes the policy control function network element, the multi-dimensional feature data of the second terminal device includes at least one of subscription information and rule information of the second terminal device; The subscription information indicates information of services to which the second terminal device subscribes, and the rule information is used to manage services of the second terminal device.

13. The method of claim 11, wherein, If the first network element includes the operator business operation and management system, the multi-dimensional feature data of the second terminal device includes at least one of the following data: personal attributes of a user, a package level, value-added service consumption data, and service experience data of the user.

14. The method of claim 11, wherein, If the first network element includes the user plane function network element, the multi-dimensional feature data of the second terminal device includes at least one of: an application type accessed by a user, start and end time of application access, traffic statistical information of application access, access rate of application access, key performance indicators of application access, key quality indicators of application access, and video quality experience score.

15. The method of claim 11, wherein, If the first network element includes the access and mobility management network element, the multi-dimensional feature data of the second terminal device includes at least one of the following information: time information of the second terminal device accessing an access network device, location information of the second terminal device, and context information of the second terminal device; The context information includes at least one of identification information of the second terminal device, an access point name of the second terminal device, and location information of the second terminal device.

16. A method of communication, comprising: The method further includes: sending a first message, the first message being used to request to determine a user belonging to a first type; receive first information, the first information indicating a first terminal device, a user type corresponding to the first terminal device being the first type, the first terminal device including at least one terminal device, the first terminal device being determined based on a first model, the first model being constructed based on multi-dimensional feature data of a second terminal device, the second terminal device including a plurality of terminal devices, the second terminal device including the first terminal device.

17. The method of claim 16, wherein, The first model is a neural network model, and the multi-dimensional feature data of the second terminal device is used to pre-train the neural network model.

18. The method of claim 16, wherein, The first model is a knowledge graph, the multi-dimensional feature data of the second terminal device is used to train the knowledge graph, an entity object in the knowledge graph includes the multi-dimensional feature data of the second terminal device, and the knowledge graph is used to search data related to query feature data based on the query feature data, wherein the multi-dimensional feature data of the second terminal device includes the data related to the query feature data.

19. The method of claim 16, wherein, The first model is a clustering algorithm, and the clustering algorithm is used to evaluate data related to query feature data. wherein the multi-dimensional feature data of the second terminal device includes the data related to the query feature data.

20. The method of any one of claims 17-19, wherein, The first model is a neural network model, and the neural network model is fine-tuned based on multi-dimensional feature data of a third terminal device and a user type corresponding to the third terminal device, and the fine-tuned neural network model is used to predict a user type corresponding to multi-dimensional feature data based on the multi-dimensional feature data. wherein the third terminal device includes a plurality of terminal devices, multi-dimensional feature data of each terminal device in the third terminal device corresponds to a user type corresponding to the each terminal device, the second terminal device includes the third terminal device, and the user type corresponding to the third terminal device includes the first type.

21. The method of any one of claims 17-19, wherein, The first model is a knowledge graph, the knowledge graph is used to determine feature data related to query feature data according to the query feature data, the query feature data is multi-dimensional feature data of a terminal device of the first type in multi-dimensional feature data of a third terminal device, and the first terminal device is a terminal device in the second terminal device corresponding to the feature data related to the query feature data; wherein the third terminal device includes a plurality of terminal devices, multi-dimensional feature data of each terminal device in the third terminal device corresponds to a user type corresponding to the each terminal device, the user type corresponding to the third terminal device includes the first type, and the second terminal device includes the third terminal device.

22. The method of any one of claims 17-19, wherein, The first model is a clustering algorithm, and the clustering algorithm is used to cluster the multi-dimensional feature data of the second terminal device with the multi-dimensional feature data of the third terminal device as a clustering center to obtain a clustering result, the clustering result including a user type corresponding to the multi-dimensional feature data of the second terminal device, and the first terminal device being a terminal device corresponding to a first type in the user type corresponding to the multi-dimensional feature data of the second terminal device. The third terminal device includes a plurality of terminal devices, and the multi-dimensional feature data of each terminal device in the third terminal device corresponds to a user type corresponding to the each terminal device, and the user type corresponding to the third terminal device includes the first type, and the second terminal device includes the third terminal device.

23. The method of any one of claims 17-19, wherein, The first model is a clustering algorithm, and the clustering algorithm is used to cluster the multi-dimensional feature data of the second terminal device to obtain a plurality of clusters, and the plurality of clusters are used to determine feature data related to queried feature data, the queried feature data being multi-dimensional feature data corresponding to a terminal device of the first type in the multi-dimensional feature data of the third terminal device, and the first terminal device being a terminal device corresponding to the feature data related to the queried feature data in the second terminal device. The third terminal device includes a plurality of terminal devices, and the multi-dimensional feature data of each terminal device in the third terminal device corresponds to a user type corresponding to the each terminal device, and the user type corresponding to the third terminal device includes the first type, and the second terminal device includes the third terminal device.

24. A communications device, characterized by Comprising: A processor coupled with a memory, the memory storing instructions that, when executed by the processor, cause the apparatus to perform the method of any one of claims 1-23.

25. A computer readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program, when the computer program is run on a computer, so that the computer executes the method of any one of claims 1-23.

26. A computer program product, characterised in that, The computer program product includes a computer program or instructions for executing the method of any one of claims 1-23.

Images