A method and apparatus for data association of terminal devices
By obtaining the associated information and identifiers of terminal devices, the problem of data association on the RAN side is solved, enabling data analysis and privacy protection of terminal devices.
Patent Information
- Application Number
- CN202010732883.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-07-27
- Publication Date
- 2025-12-02
- Estimated Expiration
- 2040-07-27
AI Technical Summary
The RAN side cannot correlate data from individual terminal devices, making it impossible to perform data analysis on the terminal devices.
The first device acquires data from the terminal device on the second device, including first association information, determines the identifier of the terminal device, and sends the association information and identifier to the access network device to achieve data association and analysis.
It enables access network devices to correlate and analyze data from terminal devices, ensuring the accuracy of data analysis and privacy protection.
Smart Images

Figure CN113993121B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of communication technology, and in particular to a data association method and apparatus for a terminal device. Background Technology
[0002] Radio access networks (RANs) require data analysis for each terminal device. However, currently, the RAN cannot correlate data from individual terminal devices, thus preventing data analysis of terminal devices. Summary of the Invention
[0003] This application provides a data association method and apparatus for terminal devices, which enables the RAN side to associate data with a single terminal device, thereby enabling data analysis of the terminal device.
[0004] In a first aspect, this application provides a data association method for a terminal device, which may include: a first device acquiring first data of the terminal device on a second device; wherein the first data includes first association information, the first association information being used to associate the first data with second data of the terminal device on a first access network device, and the second data including the first association information; the first device determining a first identifier of the terminal device and sending the first association information and the first identifier of the terminal device to the second access network device; the terminal device may be one or more.
[0005] The above method can enable the access network device to associate data with the terminal device through the first device, thereby enabling the access network device to perform data analysis on the terminal device.
[0006] In one possible design, the first associated information may include one or more of the following: time information, an identifier assigned to the terminal device by the first access network device, an identifier assigned to the terminal by the second device, the identifier of the first access network device, and the identifier of the second device.
[0007] In one possible design, the first device may also receive a first request from the second access network device, the first request being used to request first association information and a first identifier of the terminal device.
[0008] In one possible design, the first request may include one or more of the following: a time window, a network region. This allows the terminal device to request the first associated information based on specific needs.
[0009] In one possible design, the first device can be a data analysis network element, and the second device can be an access and mobility management function network element.
[0010] In one possible design, the first device can be a data analysis network element, and the second device can be a user plane function network element.
[0011] In one possible design, both the first device and the second device can be terminal devices.
[0012] In one possible design, when the first device is a data analysis network element and the second device is an access and mobility management function network element or a user plane function network element, and the first data of the terminal device on the second device also includes the second identifier of the terminal device, the first device determines the first identifier of the terminal device. Specifically, the first device determines the first identifier of the terminal device based on the second identifier of the terminal device. In this way, the first device can generate a temporary identifier (i.e., the first identifier) for the terminal device to hide its actual identifier and prevent privacy leaks.
[0013] In one possible design, when both the first device and the second device are terminal devices, the first device determines a first identifier of the terminal device. Specifically, the first device sends a second request to the third device, requesting the first identifier of the terminal device, which includes the second identifier of the terminal device. The first device then receives the first identifier of the terminal device from the third device. In this way, the first device can accurately obtain the temporary identifier (i.e., the first identifier) of the terminal device from the third device, which can be used to hide the actual identifier of the terminal device and prevent privacy leaks.
[0014] In one possible design, when the first device is a data analysis network element and the second device is an access and mobility management function network element or a user plane function network element, the first device obtains the first data from the terminal device on the second device. Specifically, the first device sends a first message to the second device requesting the first data from the terminal device on the second device; the first device then receives the first data from the terminal device on the second device. In this way, the first device can accurately obtain the first data, and thus accurately obtain the first associated information.
[0015] In one possible design, the first device receives a third request from the third access network device. The third request is used to request a first identifier of the target terminal device. The third request includes second association information, which is used to associate third data of the target terminal device on the second device and fourth data of the target terminal device on the first access network device. The first device determines the first identifier of the target terminal device based on the second association information. The first device sends the first identifier of the target terminal device to the third access network device.
[0016] Using the above method, during the subsequent data analysis of the target terminal device by the third access network device, the third access network device can accurately obtain the first identifier of the target terminal device, and then determine the target model corresponding to the first identifier of the target terminal device, thereby realizing the data analysis of the target terminal device.
[0017] Secondly, this application provides a data association method for a terminal device. The method may include: a second access network device receiving first association information and a first identifier of the terminal device from a first device, and then determining a model of the terminal device based on the first association information; the second access network device sending the model of the terminal device and the first identifier of the terminal device to a third access network device, wherein the first identifier of the terminal device is used to identify the model of the terminal device; the first association information is used to associate first data of the terminal device on the second device with second data of the terminal device on the first access network device, the second data including the first association information, and the terminal device being one or more devices; the model of the terminal device is used to determine the data analysis results of the terminal device.
[0018] The above method can enable the access network device to associate data with the terminal device through the first device, thereby enabling the access network device to perform data analysis on the terminal device.
[0019] In one possible design, the first associated information includes one or more of the following: time information, an identifier assigned to the terminal device by the first access network device, an identifier assigned to the terminal by the second device, an identifier of the first access network device, and an identifier of the second device.
[0020] In one possible design, the second access network device determines the model corresponding to the terminal device based on the first association information. Specifically, the second access network device determines the training data corresponding to the terminal device based on the first association information and the second data of the terminal device on the first access network device, and then determines the model of the terminal device based on the training data. In this way, the second access network device can accurately complete the training of the terminal device's model, enabling the subsequent third access network device to perform data analysis on the terminal device based on the terminal device's model.
[0021] In one possible design, the training data includes sample data corresponding to at least one set of information, any set of information including one or more of the following: time information, the identifier assigned to the terminal device by the first access network device, and the identifier of the first access network device.
[0022] Thirdly, this application provides a data association method for terminal devices. This method may include: a third access network device receiving a model of at least one terminal device and a first identifier of at least one terminal device from a second access network device; the third access network device acquiring second association information; and the third access network device determining the data analysis result of a target terminal device based on the model of the at least one terminal device, the first identifier of the at least one terminal device, and the second association information. Specifically, the first identifier of each terminal device is used to identify the model of the corresponding terminal device, the model of each terminal device is used to determine the data analysis result of the corresponding terminal device, and the second association information is used to associate third data of the target terminal device on the second device and fourth data of the target terminal device on the first access network device; the target terminal device is one of at least one terminal device.
[0023] The above method can realize the data association between access network devices and terminal devices, thereby enabling access network devices to perform data analysis on terminal devices.
[0024] In one possible design, the third access network device determines the policy information of the target terminal device based on the data analysis results of the target terminal device; the third access network device then sends the policy information to the first access network device. In this way, the third access network device can accurately determine the policy information of the target terminal device and notify the first access network device to which the terminal device should connect.
[0025] In one possible design, the third access network device determines the data analysis result of the target terminal device based on the model of at least one terminal device, the first identifier of at least one terminal device, and the second association information. Specifically, the third access network device obtains the first identifier of the target terminal device; the third access network device determines the target model corresponding to the first identifier of the target terminal device based on the first identifier of the target terminal device, the model of at least one terminal device, and the first identifier of at least one terminal device; and the third access network device determines the data analysis result of the target terminal device based on the second association information and the target model.
[0026] Using the methods described above, the third access network device can accurately perform data analysis on the target terminal device.
[0027] In one possible design, the third access network device obtains the first identifier of the target terminal device. Specifically, the third access network device sends a third request to the first device, the third request requesting the first identifier of the target terminal device and including second association information; the third access network device then receives the first identifier of the target terminal device from the first device. In this way, the third access network device can accurately obtain the first identifier of the target terminal device, thereby accurately determining the target model of the target terminal device and enabling data analysis of the target terminal device.
[0028] In one possible design, the third access network device determines the data analysis results of the target terminal device based on the second association information and the target model. Specifically, the third access network device determines the inference data of the target terminal device based on the second association information. The inference data includes the fourth data of the target terminal device on the first access network device. The third access network device determines the data analysis results of the target terminal device based on the inference data of the target terminal device and the target model.
[0029] In one possible design, the second associated information includes one or more of the following: time information, an identifier assigned to the terminal device by the first access network device, and an identifier of the first access network device.
[0030] Fourthly, this application also provides a communication device, which may be a first device having the functions of the first device in the first aspect or various possible design examples of the first aspect. The functions can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above-described functions.
[0031] In one possible design, the communication device may include a transceiver unit and a processing unit, which can perform the corresponding functions of the first device in the first aspect or various possible design examples of the first aspect, as detailed in the method examples, and will not be repeated here.
[0032] In one possible design, the communication device includes a transceiver and a processor, and optionally a memory. The transceiver is used for sending and receiving data, and for communicating and interacting with other devices in the communication system. The processor is configured to support the communication device in performing the corresponding functions of the first device described in the first aspect or in various possible design examples of the first aspect. The memory is coupled to the processor and stores the necessary program instructions and data for the communication device.
[0033] Fifthly, this application also provides a communication device, which can be a second access network device. This communication device has the functions of the second access network device described in the second aspect or various possible design examples of the second aspect. The functions can be implemented in hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above-described functions.
[0034] In one possible design, the communication device may include a transceiver unit and a processing unit. These units can perform the corresponding functions of the second access network device in the second aspect or various possible design examples of the second aspect, as detailed in the method examples, which will not be repeated here.
[0035] In one possible design, the communication device includes a transceiver and a processor, and optionally a memory. The transceiver is used for transmitting and receiving data, and for communicating and interacting with other devices in the communication system. The processor is configured to support the communication device in performing the corresponding functions of the second access network device described in the second aspect or in various possible design examples of the second aspect. The memory is coupled to the processor and stores the necessary program instructions and data for the communication device.
[0036] Sixthly, this application also provides a communication device, which can be a third access network device. This communication device has the functions of a third access network device as described in the third aspect or various possible design examples of the third aspect. The functions can be implemented in hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above-described functions.
[0037] In one possible design, the communication device may include a transceiver unit and a processing unit. These units can perform the corresponding functions of the third access network device in the above-described third aspect or various possible design examples of the third aspect, as detailed in the method examples, which will not be repeated here.
[0038] In one possible design, the communication device includes a transceiver and a processor, and optionally a memory. The transceiver is used for transmitting and receiving data, and for communicating and interacting with other devices in the communication system. The processor is configured to support the communication device in performing the corresponding functions of the third access network device described in the third aspect or various possible design examples of the third aspect. The memory is coupled to the processor and stores the necessary program instructions and data for the communication device.
[0039] In a seventh aspect, embodiments of this application provide a communication system that may include the first device, the first access network device, the second access network device, and the third access network device mentioned above.
[0040] Eighthly, embodiments of this application provide a computer-readable storage medium storing program instructions that, when executed on a computer, cause the computer to perform the first aspect and any possible design of the first aspect and any possible design of the second aspect and any possible design of the third aspect and any possible design of the embodiments of this application. Exemplarily, the computer-readable storage medium can be any available medium accessible to a computer. For example, but not limited to, the computer-readable medium can include non-transient computer-readable media, random-access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), CD-ROM or other optical disk storage, magnetic disk storage media, or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible to a computer.
[0041] Ninthly, embodiments of this application provide a computer program product including computer program code or instructions, which, when run on a computer, enables the computer to implement the first aspect and any possible design thereof, the second aspect and any possible design thereof, or the third aspect and any possible design thereof.
[0042] In a tenth aspect, this application also provides a chip coupled to a memory for reading and executing program instructions stored in the memory to implement the methods described in the first aspect and any possible design thereof, the second aspect and any possible design thereof, or the third aspect and any possible design thereof.
[0043] For the various aspects from the fourth to the tenth aspects mentioned above, and the technical effects that each aspect may achieve, please refer to the description of the technical effects that can be achieved by the various possible solutions for the first, second, or third aspects mentioned above. They will not be repeated here. Attached Figure Description
[0044] Figure 1 A schematic diagram of the architecture of a communication system provided in this application;
[0045] Figure 2 A flowchart of a data association method for a terminal device provided in this application;
[0046] Figure 3 A flowchart illustrating an example of a data association method for a terminal device provided in this application;
[0047] Figure 4 A flowchart illustrating an example of another data association method for a terminal device provided in this application;
[0048] Figure 5 A flowchart illustrating an example of another data association method for a terminal device provided in this application;
[0049] Figure 6 A flowchart illustrating an example of another data association method for a terminal device provided in this application;
[0050] Figure 7 A schematic diagram of the structure of a communication device provided in this application;
[0051] Figure 8 A structural diagram of a communication device provided in this application;
[0052] Figure 9 This is a schematic diagram of the structure of an access network device provided in this application. Detailed Implementation
[0053] The present application will now be described in further detail with reference to the accompanying drawings.
[0054] This application provides a data association method and apparatus for terminal devices, which enables data association of a single terminal device on the RAN side, thereby achieving data analysis of the terminal device. The method and apparatus of this application are based on the same technical concept. Since the principles by which the method and apparatus solve the problem are similar, the implementation of the apparatus and method can be referred to each other, and repeated details will not be elaborated further.
[0055] The data association method for terminal devices provided in this application embodiment is applicable to a possible communication system architecture, which may include: a wireless access network, a terminal device, and a core network. For example, Figure 1 This illustrates a possible example of a communication system architecture. In this architecture, the radio access network may include access network equipment, RAN-side inference functions, RAN-side training functions, and operation, administration, and maintenance (OAM) network elements. The core network may include: network exposure function (NEF) network elements, policy control function (PCF) network elements, unified data repository (UDR) network elements, and application function (AF) network elements (including third-party application function network elements (3)). rdThe network elements include: AF (Access Detection and Authentication), operator AF (Operator AF), authentication server function (AUSF), access and mobility management function (AMF), session management function (SMF), network data analytics function (NWDAF), and user plane function (UPF). Specifically, AMF network elements can be connected to access network equipment via the N2 interface, access network equipment to UPF via the N3 interface, SMF and UPF via the N4 interface, RAN-side inference equipment to RAN-side training equipment via the X1 interface, RAN-side inference equipment to access network equipment via the X2 interface, and RAN-side training equipment to access network equipment via the X3 interface. The interface names are merely illustrative and are not specifically limited in this application. It should be understood that this application is not limited to... Figure 1 The communication system shown Figure 1 The names of the network elements shown here are merely illustrative and are not intended to limit the network elements included in the communication system architecture to which the method of this application applies. The functions of each network element or device in the communication system are described in detail below:
[0056] Terminal equipment, also known as user equipment (UE), mobile station (MS), mobile terminal (MT), etc., is a device that provides voice and / or data connectivity to users. For example, terminal equipment can include handheld devices with wireless connectivity, in-vehicle devices, etc. Currently, terminal equipment can include: mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, or wireless terminals in smart homes, etc. Figure 1 The terminal device shown is a UE, which is only an example and does not limit the terminal device.
[0057] Access network equipment is the equipment in a communication system that connects terminal devices to a wireless network. Access network equipment is a node in the radio access network, also known as a base station or a radio access network (RAN) node (or device). Examples of access network equipment include: gNB, transmission reception point (TRP), evolved Node B (eNB), radio network controller (RNC), Node B (NB), base station controller (BSC), base transceiver station (BTS), home base station (e.g., home evolved Node B, or home Node B, HNB), base band unit (BBU), or wireless fidelity (Wi-Fi) access point (AP), etc.
[0058] Access and mobility management (AM) network elements are used to manage the access control and mobility of terminal devices. In practical applications, they include the mobility management functions of the Mobility Management Entity (MME) in the Long Term Evolution (LTE) network framework, and also incorporate access management functions. Specifically, they can be responsible for terminal device registration, mobility management, tracking area update procedures, reachability detection, selection of session management network elements, and mobility state transition management. For example, in 5G, the AMMF network element can be an AMF network element, such as... Figure 1 As shown; in future communications, such as 6G, the access and mobility management function network element can still be an AMF network element, or have other names, which is not limited in this application. When the access and mobility management function network element is an AMF network element, the AMF can provide Namf services.
[0059] Session management function network elements are responsible for session management of terminal devices (including session establishment, modification, and release), selection and reselection of user plane function network elements, allocation of Internet Protocol (IP) addresses for terminal devices, and quality of service (QoS) control. For example, in 5G, the session management function network element can be an SMF network element, such as... Figure 1 As shown; in future communications, such as 6G, the session management function network element can still be an SMF network element, or have other names, which is not limited in this application. When the session management function network element is an SMF network element, the SMF can provide Nsmf services.
[0060] Network data analysis network elements can be used for big data analysis (e.g., in the embodiments of this application, they can analyze the background traffic transmission data analysis results of terminal devices). For example, in 5G, the network data analysis network element can be an NWDAF network element, such as... Figure 1 As shown; in future communications, such as 6G, the data analysis network element may still be an NWDAF network element, or may have other names, which are not limited in this application. When the network data analysis network element is an NWDAF network element, the NWDAF network element can provide Nnwdaf services.
[0061] Policy control function network elements can be used to handle policy control decisions (e.g., in this embodiment, they can handle background traffic transmission policy decisions), provide functions such as service data flow and application detection, gating, QoS, and flow-based charging control. For example, in 5G, the policy control function network element can be a PCF network element, such as... Figure 1As shown; in future communications, such as 6G, the policy control function network element can still be a PCF network element, or have other names, which is not limited in this application. When the policy control function network element is a PCF network element, the PCF network element can provide NPCF services.
[0062] Application network elements primarily function to interact with the 3rd Generation Partnership Project (3GPP) core network to provide services, influencing service flow routing, access network capability openness, and policy control. For example, in 5G, application network elements can be AF (Active Front-End) network elements or third-party AF (Active Front-End) elements. rd AF network elements and operator AF network elements, where AF network elements can directly interact with operator network elements (e.g., AMF network elements, SMF network elements, PCF network elements, etc.). rd AF network elements need to interact with operator network elements through network open function network elements (such as NEF network elements). For example Figure 1 As shown; in future communications, such as 6G, the application network element can still be an AF network element, 3G network element, etc. rd The term "AF network element" may have other names, which are not limited in this application. When the applied network element is an AF network element, the AF network element can provide NAF services.
[0063] A unified database network element can be used for storing data, etc. For example, in 5G, a unified database network element can be a UDR network element, such as... Figure 1 As shown; in future communications, such as 6G, the database network element may still be a UDR network element, or may have other names, which is not limited in this application. When the unified database network element is a UDR network element, the UDR network element can provide NuDR services.
[0064] Network Open Functions (NEF) elements enable 3GPP to securely provide network service capabilities to third-party AFs (e.g., Services Capability Servers (SCS), Application Servers (AS)). For example, in 5G, a NEF element can be a network open function element, such as... Figure 1 As shown; in future communications, such as 6G, the Network Open Functions (NEF) element may still be a NEF element, or may have other names, which are not limited in this application. When the Network Open Functions (NEF) element is a NEF, the NEF can provide Nnef services to other Network Functions (NNF) elements.
[0065] User plane function network elements (UPFs) are used to forward user plane data from terminal devices. Their main functions include packet routing and forwarding, mobility anchoring, uplink classifiers to support routing traffic to the data network, and branching points to support multi-homed packet data unit (PDU) sessions. For example, in 5G, a UPF can be a UPF network element, such as... Figure 1 As shown; in future communications, such as 6G, user plane function network elements may still be UPF network elements, or may have other names, which are not limited in this application.
[0066] OAM network elements can be used for network management, including network resource allocation and management, network performance monitoring, network fault detection, diagnosis and recovery, etc.
[0067] RAN-side training equipment is used for model training in wireless access networks.
[0068] RAN-side inference devices are devices in wireless access networks that perform inference based on models trained by RAN-side training devices and inference data.
[0069] Among them, the RAN-side inference equipment and the RAN-side training equipment can also be regarded as access network equipment.
[0070] In the core network, each network element can also be called a functional entity or device. It can be a network element implemented on dedicated hardware, a software instance running on dedicated hardware, or an instance of virtualized function on an appropriate platform. For example, the virtualization platform mentioned above can be a cloud platform.
[0071] It should be noted that, Figure 1 The architecture of the communication system shown is not limited to the network elements shown in the figure, but may also include other devices not shown in the figure. These will not be listed here.
[0072] It should be noted that the embodiments of this application do not limit the distribution form of each network element. Figure 1 The distribution shown is merely exemplary and is not intended to limit the scope of this application.
[0073] For ease of explanation, all subsequent references to this application will be made to it. Figure 1 The network element shown is used as an example for illustration, and network element XX will be directly referred to as XX. It should be understood that the names of all network elements in this application are merely examples and may be referred to by other names in future communications, or the network element involved in this application may be replaced by other entities or devices with the same function in future communications. This application does not limit these possibilities. This is a unified explanation here and will not be repeated hereafter.
[0074] It should be noted that, Figure 1The communication system shown does not constitute a limitation on the communication systems applicable to the embodiments of this application. Figure 1 The communication system architecture shown is a 5G system architecture. Optionally, the method of this application embodiment is also applicable to various future communication systems, such as 6G or other communication networks.
[0075] In this application embodiment, the main focus is on scenarios where the RAN side performs data analysis for each terminal device (per UE), for example:
[0076] Scenario 1: Access network devices can perform per-UE traffic steering or mobility management, meaning each UE has a separate machine learning model.
[0077] Scenario 2: The access network equipment side performs service management operation system (MOS) model training. For example, the training data includes 10 million samples, while only 100,000 UEs provide training data. Through data association, the data of a single UE can be extracted to achieve deduplication or data dimensionality reduction.
[0078] Scenario 3: During the inference phase, the access network device can predict the UE's future behavior data based on the UE's historical data, assisting the access network device in making decisions such as handover and radio resource control (RRC) reconstruction.
[0079] Currently, data analysis for each terminal device on the RAN side requires the RAN side to be aware of the data of individual terminal devices. However, due to the privacy data of terminal devices, the RAN side cannot perceive the terminal device's identity (ID) (e.g., Subscription Permanent Identifier (SUPI) or International Mobile Equipment Identity (IMEI)). Because terminal devices undergo registration and deregistration processes, and RRC activation and deactivation processes, the access network equipment connected to the terminal device changes during these processes. However, the RAN side cannot perceive that this change applies to the same terminal device. Therefore, the RAN side cannot perform data association for each terminal device, resulting in the inability to perform data analysis on the terminal devices. Based on this, this application provides a data association method for terminal devices to achieve data association of individual terminal devices on the RAM side, thereby enabling data analysis of the terminal devices.
[0080] It should be noted that in the description of this application, terms such as "first" and "second" are used only for the purpose of distinguishing descriptions and should not be construed as indicating or implying relative importance or order. In the description of this application, "at least one" means one or more, and "more" means two or more.
[0081] To more clearly describe the technical solutions of the embodiments of this application, the data association method and apparatus for terminal devices provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings.
[0082] The data association method for terminal devices provided in this application embodiment can be applied to... Figure 1 The communication system shown is described in the reference document. Figure 2 As shown, the specific process of this method may include:
[0083] Step 201: The first device acquires the first data of the terminal device on the second device; wherein, the first data includes first association information, the first association information is used to associate the first data with the second data of the terminal device on the first access network device, the second data includes the first association information, and the terminal device is one or more.
[0084] Specifically, the first associated information corresponding to the same terminal device can be one or more.
[0085] In one alternative implementation, the first device and the second device can have the following three configurations in different scenarios:
[0086] Case a1: The first device is a data analysis network element, such as NWDAF, and the second device is an access and mobility management function network element, such as AMF.
[0087] Case a2: The first device is a data analysis network element, and the second device is a user plane function network element, such as a UPF.
[0088] Case a3: The first and second devices are terminal devices, such as UE.
[0089] In one optional implementation, the first associated information may include one or more of the following: time information, an identifier assigned to the terminal device by the first access network device, an identifier assigned to the terminal by the second device, an identifier of the first access network device, and an identifier of the second device. The time information refers to the time when the first data was generated; it may also be called a timestamp (Timestamp x) or a time period (Time Window x, Time Interval x).
[0090] Specifically, in scenario a1 above, the identifier assigned by the first access network device to the terminal device can be an identifier assigned by the first access network device to the terminal device on the NG interface, such as the RAN UE Next Generation Application Protocol (NGAP) ID, like RAN UE NGAP ID x; the identifier assigned by the second device to the terminal device can be the AMF UE NGAP ID, like AMF UE NGAP ID x; the identifier of the first access network device can be a globally unique RAN Node ID, like Global RAN Node ID x; the identifier assigned by the second device to the terminal device can also be a globally unique AMF ID (GUAMI).
[0091] In scenario a2 above, the identifier assigned by the first access network device to the terminal device can be the tunnel information (AN tunnel Info) assigned by the first access network device to the terminal device's session on the N3 interface, such as AN tunnel Info x. The identifier assigned by the second device to the terminal device can be the tunnel information (CN tunnel Info) assigned by the second device to the terminal device's session on the N3 interface, such as CN tunnel Info x.
[0092] In scenario a3 above, the identifier assigned by the first access device to the terminal device can be a cell radio network temporary identifier (C-RNTI); the identifier of the first access network device can be a Global RAN Node ID, such as Global RAN Node ID x.
[0093] For example, the first access network device may be, but is not limited to, a base station (gNB, RAN-CU, RAN-DU), etc.
[0094] In one optional implementation, before the first device acquires the first data from the terminal device on the second device, the first device receives a first request from the second access network device. The first request requests first association information and a first identifier of the terminal device. The first request includes one or more of the following information: a time window and a network area. The time window can be a preset time period, and the network area can include cells or a cell list, a tracking area (TA) or a TA list, or a physical area (such as a Global Positioning System (GPS) list).
[0095] For example, the identifier of the terminal device in the embodiments of this application can be one or more of the following: Internet Protocol address (IP), subscription permanent identifier (SUPI), permanent equipment identifier (PEI), generic public subscription identifier (GPSI), international mobile subscriber identifier (IMSI), international mobile equipment identity (IMEI), IP address, and mobile station international integrated service digital network number (MSISDN). The identifiers of the terminal devices involved in the following embodiments can all be referred to in the description herein, and will not be repeated hereafter.
[0096] For example, in the embodiments of this application, the regional information of the terminal device can be one or more of the following information about the region where the terminal device is located: tracking area identifier (TAI), list of tracking area identifiers (TAI(s)), routing area identifier (RAI), list of routing area identifiers (RAI(s)), cell identifier (Cell ID), list of cell identifiers (Cell ID(s)), geographical area identifier (Geographical area identifier), network code (NC), country code (CC), city code, and county code. The regional information of the terminal involved in the following embodiments can be referred to in the description herein, and will not be repeated hereafter.
[0097] For example, the second access network device can be a RAN-side training device.
[0098] In an alternative implementation, in cases a1 and a2 above, the first request can be an analytics subscription message (Nnwdaf_AnalyticsSubscription_Subscribe); in case a3 above, the first request can be a correlation information request.
[0099] In one specific implementation, in cases a1 and a2 above, the first device acquiring the first data from the terminal device on the second device can specifically involve: the first device sending a first message to the second device, the first message requesting the first data from the terminal device on the second device; and the first device receiving the first data from the terminal device on the second device. Specifically, in case a1, the first message can be an AMF event open subscription message (Namf_EventExposure_Subscribe), and the first device receives the first data from the second device via an AMF event open notification message (Namf_EventExposure_Notify). In case a2, the first message can be a UPF event open subscription message (Nupf_EventExposure_Subscribe), and the first device receives the first data from the second device via a UPF event open notification message (Nupf_EventExposure_Subscribe).
[0100] In an optional implementation, in case a2 above, the first device may further send a second message to the SMF. The second message requests data from the terminal device on the SMF, including association information. This association information is used to associate the first data from the terminal device on the second device with the data from the terminal device on the SMF. The first device receives the data from the terminal device on the SMF from the SMF. The second message may be an SMF event open subscription message (Nsmf_EventExposure_Subscribe); the first device may receive the data from the terminal device on the SMF from the SMF via an SMF event open notification message (Nsmf_EventExposure_notify).
[0101] It should be noted that in scenario a1 above, if the network area includes multiple AMFs, the NWDAF needs to obtain the first data from each of the multiple AMFs, that is, perform the above-described process of obtaining the first data multiple times. In this case, the NWDAF can request the addresses of multiple AMFs in the network area from the NRF, or the NWDAF can obtain the addresses of pre-configured AMFs.
[0102] In an optional implementation, in case a3 above, when the first device obtains the first data of the terminal device on the second device, the specific method may be: the first device obtains the first data stored locally.
[0103] Step 202: The first device determines the first identifier of the terminal device.
[0104] Specifically, the first identifier of the terminal device is the Temporary UE ID.
[0105] In an optional implementation, in case a1 or a2 above, the first device determines the first identifier of the terminal device. Specifically, the method may involve: the first data of the terminal device on the second device further including the second identifier of the terminal device; the first device generating or assigning the first identifier of the terminal device based on the second identifier of the terminal device. The second identifier of the terminal device may be one or more of SUPI, IMSI, PEI, IMEI, GPSI, and IP address.
[0106] In another optional implementation, in case a3 above, the first device determines the first identifier of the terminal device. Specifically, the method may be as follows: the terminal device sends a second request to the third device, the second request requesting the third device to generate or allocate the first identifier of the terminal device, the second request including the second identifier of the terminal device; the first device receives the first identifier of the terminal device from the third device. The third device may be an application network element, such as an AF.
[0107] Step 203: The first device sends the first association information and the first identifier of the terminal device to the second access network device.
[0108] In one alternative implementation, the first association information of the terminal device can be one or more.
[0109] Specifically, in scenario a1 above, when the first device sends the first association information and the first identifier of the terminal device in step 203, it can send them in the following form: Temporary UE ID X, List of<Timestamp,RAN UENGAP ID,Global RAN Node ID> X, X = 1, 2, 3…N; In case a2 above, the first device can send in the following form: (Temporary UE ID X, List of<Timestamp,AN Tunnel Info> X, X = 1, 2, 3…N); In case a3 above, the first device can send the Temporary UE ID X and the corresponding associated information (Timestamp x1, C-RNTI x1 and Global RAN Node ID x1) list.
[0110] It should be noted that, since the first identifier of the terminal device is a temporary terminal device identifier, the second access network device, after obtaining the first identifier, cannot perceive which specific terminal device the first association information refers to. This is because the temporary terminal device identifier is not equivalent to unique identifiers of terminal devices such as SUPI or IMEI; rather, it is temporarily assigned by the first device or with the help of a third device, and cannot be used to uniquely identify the terminal device.
[0111] Step 204: The second access network device determines the model of the terminal device based on the first association information.
[0112] The terminal device model is used for data analysis of the terminal device; that is, the terminal device model is used to determine the data analysis results of the terminal device. Specifically, the terminal device's data model can perform data analysis on the terminal device based on the inference data to obtain the data analysis results. The stage of obtaining the terminal device's data analysis results can occur during the inference stage.
[0113] Specifically, before executing step 204, the second access network device can obtain the second data of the terminal device from the first access network device.
[0114] In one optional implementation, the second access network device determines the model corresponding to the terminal device based on the first association information. Specifically, the second access network device determines the training data corresponding to the terminal device based on the first association information and the second data of the terminal device on the first access network device; the second access network device determines the model based on the training data corresponding to the terminal device.
[0115] For example, the second access network device determines the training data corresponding to the terminal device based on the first association information and the second data of the terminal device on the first access network device. Specifically, the second access device determines the training data corresponding to the terminal device from the second data based on the first association information.
[0116] In one optional implementation, the training data includes sample data corresponding to at least one set of information, any set of information including one or more of the following: time information, an identifier assigned to the terminal device by the first access network device, and an identifier of the first access network device.
[0117] It should be noted that the model of the terminal device can be a data analysis model or a machine learning model, etc., and this application does not limit it.
[0118] Step 205: The second access network device sends the terminal device model and a first identifier to the third access network device, wherein the first identifier of the terminal device is used to identify the terminal device model. Specifically, the third access network device can receive at least one terminal device model and at least one corresponding first identifier of the terminal device from the second access network device, and the first identifier of each terminal device is used to identify the corresponding terminal device model.
[0119] Specifically, the second access network device identifies the model (also known as a trained model or machine learning model) corresponding to the terminal device through the terminal device's first identifier. That is, one Temporary UE ID corresponds to one trained model or machine learning model.
[0120] In one optional implementation, after receiving the model of at least one terminal device, the third access network device deploys and saves the model of at least one terminal device locally, so that the first device can subsequently query the model corresponding to the target terminal device to perform data analysis on the target terminal device. The target terminal device is one of the at least one terminal devices.
[0121] For example, the third access network device can be a RAN-side inference device.
[0122] Step 206: The third access network device obtains the second association information, which is used to associate the third data of the target terminal device on the second device and the fourth data of the target terminal device on the first access network device.
[0123] Specifically, the second associated information may include one or more of the following: time information, an identifier assigned to the terminal device by the first access network device, an identifier assigned to the terminal device by the second device, the identifier of the first access network device, and the identifier of the second device.
[0124] In one alternative implementation, the second associated information and the first associated information have the same type (e.g., data type) but different values. For example, the time information is different.
[0125] In one alternative implementation, the third access network device first obtains the fourth data from the first access network device, and then determines the second association information based on the fourth data.
[0126] It should be noted that the third and / or fourth data can be understood as inference data.
[0127] Step 207: The third access network device determines the data analysis results of the target terminal device based on the model of at least one terminal device and the first identifier and second association information of at least one terminal device.
[0128] Specifically, the method for the third access network device to perform step 207 can be as follows: the third access network device obtains the first identifier of the target terminal device; then, the third access network device determines the target model corresponding to the first identifier of the target terminal device based on the first identifier of the target terminal device, the model of at least one terminal device, and the first identifier of at least one terminal device; finally, the third access network device determines the data analysis result of the target terminal device based on the second association information and the target model.
[0129] The process by which the third access network device determines the target model corresponding to the first identifier of the target terminal device based on the first identifier of the target terminal device and the model of at least one terminal device and the first identifier of at least one terminal device is the process by which the third access network device searches for the target model in the model of at least one terminal device stored locally in the third access network device based on the first identifier of the target terminal device.
[0130] In one optional implementation, the third access network device obtains the first identifier of the target terminal device. Specifically, the third access network device sends a third request to the first device, the third request requesting the first identifier of the target terminal device, and the third request includes second association information; the third access network device receives the first identifier of the target terminal device from the first device. Upon receiving the third request, the first device determines the first identifier of the target terminal device based on the second association information.
[0131] In one optional implementation, the third access network device determines the data analysis result of the target terminal device based on the second association information and the target model. Specifically, the third access network device determines the inference data of the target terminal device based on the second association information, the inference data including the fourth data of the target terminal device on the first access network device; the third access network device determines the data analysis result of the target terminal device based on the inference data of the target terminal device and the target model. Here, the target terminal device is the terminal device in the inference stage.
[0132] In one optional implementation, the third access network device determines the policy information of the target terminal device based on the data analysis results of the target terminal device, and sends the policy information to the first access network device.
[0133] The data association method for terminal devices provided in this application embodiment enables data association between the access network device and the terminal device through the first device, thereby enabling the access network device to perform data analysis on the terminal device.
[0134] Based on the above embodiments, the following will be used as an example. Figures 3-5 The specific examples shown below provide a detailed explanation of the data association method for terminal devices provided in this application. In the following examples, the terminal device is UE, the first access network device is a base station, the second access network device is a RAN-side training device, and the third access network device is a RAN-side inference device.
[0135] like Figure 3 As shown, this application provides an example of a data association method for a terminal device. In this example, the first device is NWDAF and the second device is AMF. The specific process of this example may include:
[0136] Step 301: The RAN-side training device sends a first request to the NWDAF. The first request is used to request the first association information and the first identifier of the UE. The first request includes one or more of the following information: time window and network area.
[0137] Specifically, the RAN-side training device requests the association information between the AMF and the base station for each of one or more UEs on the base station within the access network area within the time window, as well as the first identifier corresponding to that UE. The first association information is used to associate the UE's first data on the AMF with the UE's second data on the base station.
[0138] Specifically, the RAN-side training device can send the first request to NWDAF via Nnwdaf_AnalyticsSubscription_Subscribe.
[0139] Specifically, there can be one or more UEs.
[0140] Specifically, the first associated information of the same UE can be one or more.
[0141] Step 302: NWDAF sends a first message to AMF. The first message is used to request the first data of one or more UEs on AMF.
[0142] Specifically, the first data contains one or more first related information.
[0143] Specifically, NWDAF can send the first message to AMF via Namf_EventExposure_Subscribe.
[0144] For example, the first associated information may include one or more of the following terminal information: the terminal device identifier (SUPI x), the timestamp (Timestamp x), the identifier assigned by the RAN to the terminal device on the NG interface (RAN UE NGAP ID x), and the RAN's globally unique identifier (Global RAN Node ID x).
[0145] Step 303: AMF sends first data containing first association information to NWDAF.
[0146] It should be noted that if the network area in step 301 includes multiple AMFs, then the NWDAF needs to interact for each AMF in steps 302 and 303. In this case, the NWDAF can request the addresses of multiple AMFs within the network area from the network repository function (NRF) element based on the network area in step 301.
[0147] Specifically, AMF can send the first data to NWDAF via Namf_EventExposure_Notify.
[0148] Step 304: The RAN-side training device obtains the UE's second data on the base station from the base station through the X3 interface. The second data includes one or more first association information.
[0149] The base station is the gNB / RAN equipment that serves the UE, and it has an NG / N2 interface with the AMF.
[0150] Specifically, the first associated information that the base station can perceive may include Timestamp x, RAN UE NGAP IDx, and Global RAN Node ID x.
[0151] It should be noted that base stations cannot detect the unique identifiers of terminal devices such as SUPI, IMEI, and GPSI.
[0152] Step 305: NWDAF determines the first identifier of the UE.
[0153] Specifically, based on the first data obtained in step 303, NWDAF can determine the association information of each UE among one or more UEs accessing the network area within the time window. The first data includes the UE's SUPI, and NWDAF can assign a Temporary UE ID (i.e., a first identifier) to each UE's SUPI x. Through this step, the Temporary UE ID is equivalent to anonymizing SUPI x, but it can uniquely correspond to SUPI x. This facilitates subsequent RAN-side data analysis for each UE based on SUPI x, without revealing which specific terminal device the UE belongs to.
[0154] Based on the above, the first association information for each UE among one or more UEs determined by NWDAF can be as follows:
[0155] Temporary UE ID 1, List of<Timestamp,RAN UE NGAP ID,Global RAN Node ID> 1;
[0156] Temporary UE ID 2, List of<Timestamp,RAN UE NGAP ID,Global RAN Node ID> 2;
[0157] ...;
[0158] Temporary UE ID N, List of<Timestamp,RAN UE NGAP ID,Global RAN Node ID> N, where N is the number of UEs, and N is greater than or equal to 1.
[0159] Step 306: NWDAF sends the first association information and the UE's first identifier to the RAN-side training equipment.
[0160] For example, NWDAF sends Temporary UE ID X, List of to the RAN-side training device.<Timestamp,RAN UE NGAP ID,Global RAN Node ID> X, X = 1, 2, 3…N.
[0161] Specifically, NWDAF can send the first association information and the UE's first identifier to the RAN-side training device via Nnwdaf_AnalyticsSubscription_Notify.
[0162] Step 307: The RAN-side training device determines the UE model based on the first association information.
[0163] Step 307 is the model training process. Specifically, the RAN-side training device uses the initial association information of each UE in one or more UEs, namely Temporary UE ID X, List of<Timestamp,RANUE NGAP ID,Global RAN Node ID> X, X = 1, 2, 3…N, and the second data corresponding to Timestamp x, RAN UENGAP ID x, and Global RAN Node ID x in step 304, determine the training data corresponding to each UE in one or more UEs. Each training data belongs to one UE, and the training data may include sample data corresponding to one or more sets of information (Timestamp x, RAN UE NGAP ID x, and Global RAN Node ID x).
[0164] Then, the RAN-side training equipment trains the corresponding model based on the training data of each UE in one or more UEs. This model is identified by the Temporary UE ID, which can be in the following format:
[0165] Temporary UE ID 1, Trained Model 1;
[0166] Temporary UE ID 2, Trained Model 2;
[0167] ...;
[0168] Temporary UE ID N, Trained Model N, where N is the number of UEs.
[0169] Step 308: The RAN-side training device sends the model and corresponding first identifier of each UE in one or more UEs to the RAN-side inference device; wherein, the first identifier of a UE is used to identify the model of the UE.
[0170] Step 309: The RAN-side inference device deploys and saves the model of one or more UEs locally.
[0171] The model deployment can refer to existing methods, which will not be described in detail in this application.
[0172] Step 310: The RAN-side inference device obtains the second association information, which is used to associate the third data of the target UE on the AMF and the fourth data of the target UE on the base station.
[0173] The target UE is one of the aforementioned UEs.
[0174] Specifically, the RAN-side inference device can first obtain the fourth data of the target UE on the base station, and then obtain the second association information from the fourth data.
[0175] Specifically, the fourth type of data can be understood as inference data.
[0176] For example, the second associated information could be Timestamp y, RAN UE NGAP ID y, and Global RANNode ID y.
[0177] Step 311: The RAN-side inference device sends a third request to the NWDAF. The third request is used to request the first identifier of the target UE and includes second association information.
[0178] That is, the RAN-side inference device queries the NWDAF for the first identifier of the target UE, Temporary UE ID Y, based on the second association information.
[0179] Step 312: NWDAF determines (searches for) the first identifier of the target UE based on the second association information.
[0180] Step 313: The NWDAF sends the first identifier of the target UE to the RAN-side inference device.
[0181] It should be noted that during steps 311-313 above, NWDAF needs to continuously obtain the SUPI y corresponding to the Timestamp y, RAN UE NGAP ID y, and Global RAN Node ID y from AMF, and then determine the Temporary UE ID y.
[0182] Step 314: The RAN-side inference device searches for the corresponding target model locally based on the first identifier (Temporary UE ID Y) of the target UE, and determines the data analysis results of the target UE based on the second association information and the target model.
[0183] Specifically, the RAN-side inference device inputs the inference data (i.e., the fourth data) corresponding to Timestamp y, RAN UE NGAP ID y, and Global RAN NodeID y (i.e., the second association information) into the target analysis model to obtain the data analysis results.
[0184] Step 315: The RAN-side inference device determines the policy information of the target UE based on the data analysis results of the target UE.
[0185] Step 316: The RAN-side inference device sends the policy information to the base station.
[0186] Based on the above example, the RAN side can leverage the core network to achieve per-UE data association, which can assist the RAN side in performing per-UE data analysis.
[0187] In an optional implementation, the following method can be used instead of the method described in steps 302-305 above, where the NWDAF determines the association information of the same UE (SUPI) when accessing different base stations: The NWDAF collects data of the UE on the RAN, including the UE's association identification information on the RAN (Timestamp x), RAN UE NGAP ID x (or AMF UE NGAP IDX), and Global RAN Node ID x; the NWDAF collects data of the UE on the AMF, including the aforementioned association identification information of the UE on the AMF and the UE ID (e.g., SUPI); the NWDAF associates the information of the UE on all the base stations and the core network (i.e., RAN, AMF) to obtain the association information of the UE when accessing different base stations, that is...<Timestamp,RAN UE NGAPID,Global RAN Node ID> List; NWDAF assigns a temporary terminal identifier to the associated information of the UE when it accesses different base stations.
[0188] like Figure 4 As shown, this application provides an example of a data association method for a terminal device. In this example, the first device is a UE, and the second device is a UE. The specific process of this example may include:
[0189] Step 401: The RAN-side training device sends a first request to the UE. The first request is used to request the first association information and the UE's first identifier. The first request includes one or more of the following information: time window and network area.
[0190] The first association information is used to associate the first data of the UE on the UE with the second data of the UE on the base station.
[0191] Specifically, the first piece of related information can be one or more.
[0192] Specifically, the RAN-side training device requests the UE from the base station in the network area within the time window, which is the first association information between the UE and the base station.
[0193] Step 402: The RAN-side training device obtains the UE's second data on the base station from the base station through the X3 interface. The second data includes one or more first association information.
[0194] The base station is the gNB / RAN equipment that serves the UE, and there is a Uu interface between the base station and the UE.
[0195] The base station can sense one or more first association information, including Timestamp x1, C-RNTI x1, and Global RAN Node ID x1.
[0196] Step 403: The UE obtains the first data stored locally.
[0197] Specifically, the UE stores one or more first association information (Timestamp x1, C-RNTI x1, and Global RAN Node ID x1) on all base stations within the access network area within the time window.
[0198] Step 404: The UE sends a second request to the third device. The second request is used to request the third device to generate or assign a first identifier for the UE. The second request includes the second identifier of the UE, SUPI X.
[0199] The third device can be an AF or a specific server.
[0200] Step 405: The third device generates the UE's first identifier (Temporary UEID X) based on the UE's second identifier (SUPI X).
[0201] Step 406: The third device sends the UE's first identifier to the UE.
[0202] Step 407: The UE sends the first association information and the UE's first identifier to the RAN-side training equipment.
[0203] For example, the UE sends a Temporary UE ID X and a list of corresponding associated information (Timestamp x1, C-RNTI x1, and Global RAN Node ID x1) to the RAN-side training device.
[0204] Step 408: The RAN-side training device determines the UE model based on the first association information.
[0205] Step 408 is the model training process. Specifically, the RAN-side training device determines the training data corresponding to the UE based on the Temporary UE ID X from the UE and the corresponding list of associated information (Timestamp x1, C-RNTI x1, and Global RAN Node ID x1) (i.e., one or more first associated information), and the second data corresponding to one or more of the associated information (Timestamp x, C-RNTI x, and Global RAN Node ID x) from step 402. Each training data set may include sample data corresponding to one or more sets of information (Timestamp x1, C-RNTI x1, and Global RAN Node ID x1).
[0206] Then, the RAN-side training equipment trains the corresponding model (Trained Model X) based on the UE's training data. This model can be identified by the Temporary UE ID X, which can be in the following format:
[0207] Temporary UE ID X, Trained Model X.
[0208] Step 409: The RAN-side training device sends the model and corresponding first identifier of each UE in one or more UEs to the RAN-side inference device; wherein, the first identifier of a UE is used to identify the model of the UE.
[0209] Step 410: The RAN-side inference device deploys and saves the model of one or more UEs locally.
[0210] The model deployment can refer to existing methods, which will not be described in detail in this application.
[0211] Step 411: The RAN-side inference device obtains the second association information, which is used to associate the third data of the target UE on the target UE and the fourth data of the target UE on the base station.
[0212] Specifically, the RAN-side inference device can first obtain the fourth data of the target UE on the base station, and then obtain the second association information from the fourth data.
[0213] The target UE is one of the aforementioned UEs.
[0214] Specifically, the fourth type of data can be understood as inference data.
[0215] For example, the second associated information could be Timestamp x2, C-RNTI x2, and Global RAN NodeID x2.
[0216] Step 412: The RAN-side inference device sends a third request to the UE. The third request is used to request the first identifier of the target UE and includes second association information.
[0217] That is, the RAN-side inference device queries the UE for the first identifier of the target UE, Temporary UE ID X, based on the second association information (Timestamp x2, C-RNTI x2 and GlobalRAN Node ID x2).
[0218] Step 413: The UE determines (searches for) the first identifier of the target UE based on the second association information.
[0219] Step 414: The UE sends the first identifier of the target UE to the RAN-side inference device.
[0220] Step 415: The RAN-side inference device finds the corresponding target data sub-model locally based on the first identifier (Temporary UE ID X) of the target UE, and determines the data analysis result of the target UE based on the second association information and the target model.
[0221] Specifically, the RAN-side inference device inputs the inference data (i.e., the fourth data) corresponding to Timestamp x2, C-RNTI x2, and Global RAN Node ID x2 (i.e., the second association information) into the target model to obtain the data analysis results.
[0222] Step 416: The RAN-side inference device determines the policy information of the target UE based on the data analysis results of the target UE.
[0223] Step 417: The RAN-side inference device sends the policy information to the base station.
[0224] Based on the above example, the RAN side can use the UE to achieve per-UE data association, which can assist the RAN side in performing per-UE data analysis.
[0225] like Figure 5 As shown, this application provides an example of a data association method for a terminal device. In this example, the first device is an NWDAF and the second device is a UPF. The specific process of this example may include:
[0226] Step 501: The RAN-side training device sends a first request to the NWDAF. The first request is used to request the first association information and the first identifier of the UE. The first request includes one or more of the following information: time window and network area.
[0227] Specifically, there can be one or more UEs.
[0228] Specifically, the first associated information of the same UE can be one or more.
[0229] Specifically, the RAN-side training device requests the association information between the UPF and the base station for each of one or more UEs on the base station in the access network area within the time window, as well as the first identifier corresponding to one or more UEs.
[0230] For example, the RAN-side training device can send a first request to NWDAF via Nnwdaf_AnalyticsSubscription_Subscribe.
[0231] Step 502: The NWDAF sends a second message to the SMF. The second message is used to request data of one or more UEs on the SMF. The data of one or more UEs on the SMF includes association information. The association information is used to associate the first data of one or more UEs on the UPF with the data of one or more UEs on the SMF.
[0232] The association information refers to the association information between the SMF and UPF of each UE among one or more UEs on the base station in the network area within the time window.
[0233] Specifically, NWDAF can send a second message to SMF via Nsmf_EventExposure_Subscribe.
[0234] For example, the associated information may include SUPI x, timestamp x, and the terminal's IP address (UEIP x).
[0235] Step 503: NWDAF receives data from one or more UEs on the SMF.
[0236] Specifically, SMF can send this data to NWDAF via Nsmf_EventExposure_Subscribe.
[0237] Step 504: NWDAF sends a first message to UPF. The first message is used to request the first data of one or more UEs on UPF.
[0238] Specifically, the first data contains one or more first related information.
[0239] Specifically, NWDAF can send the first message to UPF via Nupf_EventExposure_Subscribe.
[0240] For example, the first associated information may include: timestamp (Timestamp x), the terminal's IP address (UE IPx), and tunnel information (AN Tunnel Info x) assigned by the RAN for the terminal's session on the N3 interface.
[0241] Optionally, the NWDAF can send subscription information to the UPF via the SMF. The subscription information is used to request the first data of one or more UEs on the UPF.
[0242] Step 505: UPF sends first data containing first association information to NWDAF.
[0243] Specifically, UPF can send the first data to NWDAF via Nupf_EventExposure_Subscribe.
[0244] Optionally, the UPF can send notification information to the NWDAF via the SMF. The notification information is used to send the first data of one or more UEs on the UPF to the NWDAF.
[0245] Step 506: The RAN-side training device obtains the UE's second data on the base station from the base station through the X3 interface. The second data includes one or more first association information.
[0246] The base station is the gNB / RAN equipment that serves the UE, and it has an N3 interface with the UPF.
[0247] Specifically, the first associated information that the base station can sense may include Timestamp x and AN Tunnel Infox.
[0248] Step 507: NWDAF determines the first identifier of the UE.
[0249] Specifically, based on the data obtained in steps 503 and 505, NWDAF can obtain the association information between the UE and the RAN and UPF for each UE through the UE IP x. Then, it further summarizes and determines the association information of each UE among one or more UEs accessing the network area within the time window. The first data includes the UE's SUPI, and NWDAF assigns a Temporary UE ID (i.e., the first identifier) to each UE's SUPI x. Through this step, the Temporary UEID is equivalent to anonymizing SUPI x, but it can uniquely correspond to SUPI x. This facilitates subsequent per-UE data analysis by the RAN side based on SUPI x, without revealing which specific terminal device the UE belongs to.
[0250] Based on the above, the first association information for each UE among one or more UEs determined by NWDAF can be as follows:
[0251] Temporary UE ID 1, List of<Timestamp,AN Tunnel Info> 1;
[0252] Temporary UE ID 2, List of<Timestamp,AN Tunnel Info> 2;
[0253] ...;
[0254] Temporary UE ID N, List of<Timestamp,AN Tunnel Info> N, where N is the number of UEs.
[0255] Step 508: The NWDAF sends the first association information and the UE's first identifier to the RAN-side training equipment.
[0256] For example, NWDAF sends Temporary UE ID X, List of to the RAN-side training device.<Timestamp,AN Tunnel Info> X, X = 1, 2, 3…N.
[0257] Specifically, NWDAF can send the first association information and the UE's first identifier to the RAN-side training device via Nnwdaf_AnalyticsSubscription_Notify.
[0258] Step 509: The RAN-side training device determines the UE model based on the first association information.
[0259] Step 5097 is the model training process. Specifically, the RAN-side training device uses the first association information of each UE from one or more UEs in the NWDAF, namely the Temporary UE ID X, List of<Timestamp,AN Tunnel Info> X, X = 1, 2, 3…N, and the second data corresponding to Timestamp x and AN TunnelInfo x obtained in step 506, determine the training data corresponding to each UE in one or more UEs. Each training data belongs to one UE, and the training data may include sample data corresponding to one or more sets of information (Timestamp x, AN Tunnel Info x).
[0260] Then, the RAN-side training equipment trains the corresponding model based on the training data of each UE in one or more UEs. This model can be identified by the Temporary UE ID, which can be in the following format:
[0261] Temporary UE ID 1, Trained Model 1;
[0262] Temporary UE ID 2, Trained Model 2;
[0263] ...;
[0264] Temporary UE ID N, Trained Model N, where N is the number of UEs.
[0265] Step 510: The RAN-side training device sends the model and the corresponding first identifier for each UE in one or more UEs to the RAN-side inference device.
[0266] Step 511: The RAN-side inference device deploys and saves the model of one or more UEs locally.
[0267] The model deployment can refer to existing methods, which will not be described in detail in this application.
[0268] Step 512: The RAN-side inference device obtains the second association information, which is used to associate the third data of the target UE on the UPF and the fourth data of the target UE on the base station.
[0269] Specifically, the RAN-side inference device can first obtain the fourth data of the target UE on the base station, and then obtain the second association information from the fourth data.
[0270] Specifically, the fourth type of data can be understood as inference data.
[0271] For example, the second associated information could be Timestamp y or AN Tunnel Info y.
[0272] Step 513: The RAN-side inference device sends a third request to the NWDAF. The third request is used to request the first identifier of the target UE and includes second association information.
[0273] That is, the RAN-side inference device queries the NWDAF for the first identifier of the target UE, Temporary UE ID Y, based on the second association information.
[0274] Step 514: NWDAF determines (searches for) the first identifier of the target UE based on the second association information.
[0275] Step 515: The NWDAF sends the first identifier of the target UE to the RAN-side inference device.
[0276] It should be noted that during steps 513-515 above, NWDAF needs to continuously obtain SUPI y, Timestamp y, and UE IP y from SMF, and also needs to continuously obtain Timestamp y, UE IP y, and AN Tunnel Info y from UPF. Then, it needs to associate and determine the SUPI y corresponding to Timestamp y and AN Tunnel Info y, and then further query locally to determine Temporary UE ID Y.
[0277] Step 516: The RAN-side inference device searches for the corresponding target model locally based on the first identifier (Temporary UE ID Y) of the target UE, and determines the data analysis results of the target UE based on the second association information and the target model.
[0278] Specifically, the RAN-side inference device inputs the inference data (i.e., the fourth data) corresponding to Timestamp y, RAN UE NGAP ID y, and Global RAN NodeID y (i.e., the second association information) into the target model to obtain the data analysis results.
[0279] Step 517: The RAN-side inference device determines the policy information of the target UE based on the data analysis results of the target UE.
[0280] Step 518: The RAN-side inference device sends the policy information to the base station.
[0281] Based on the above example, the RAN side can leverage the core network to achieve per-UE data association, which can assist the RAN side in performing per-UE data analysis.
[0282] In an optional implementation, the following method can be used instead of the method described in steps 502-507 above for NWDAF to determine the association information of the same UE (SUPI) when accessing different base stations: NWDAF collects data of the UE on the RAN, including the UE's association identification information Timestamp x and AN Tunnel Info x on the RAN; NWDAF collects data of the UE on the UPF, including the aforementioned association identification information and UE IP x on the UPF; NWDAF collects data of the UE on the SMF, including the UE IP x and UE ID (such as SUPI) on the SMF; NWDAF associates the information of the UE on all the base stations and core networks (i.e., RAN, UPF / SMF) to obtain the association information of the UE when accessing different base stations, that is...<Timestamp,AN Tunnel Info> List.
[0283] like Figure 6 As shown, this application embodiment also provides an example of a data association method for a terminal device. In this example, relative to... Figure 3 The difference in the illustrated embodiment is that the base station directly provides the first association information to the RAN-side training device, and the base station requests the first identifier of the UE corresponding to the first association information from the NWDAF on behalf of the RAN-side training device, so that the NWDAF does not need to transmit the association information to the NWDAF subsequently, thereby reducing the transmission pressure between the NWDAF and the RAN-side training device. Specifically, the specific process of this example may include:
[0284] Step 601: The base station sends a fourth request to the NWDAF. The fourth request is used to request the first identifier of the UE corresponding to the first association information for the RAN-side training equipment.
[0285] Specifically, the base station requests the UE's first identifier from the NWDAF for the RAN-side training equipment based on the first association information (Timestamp x, RAN UE NGAP ID x, Global RANNode ID x). The first association information is used to associate the UE's first data on the AMF with the UE's second data on the base station.
[0286] Specifically, the fourth request includes the address information of the RAN-side training device.
[0287] Specifically, there can be one or more UEs.
[0288] Specifically, there is only one first association information for the same UE.
[0289] Step 602: The base station sends the first association information to the RAN-side training equipment.
[0290] The base station is the gNB / RAN equipment that serves the UE, and it has an NG / N2 interface with the AMF.
[0291] Specifically, the first associated information that the base station can perceive may include Timestamp x, RAN UE NGAP IDx, and Global RAN Node ID x.
[0292] It should be noted that base stations cannot detect the unique identifiers of terminal devices such as SUPI, IMEI, and GPSI.
[0293] Step 603: NWDAF sends a first message to AMF. The first message is used to request the first data of one or more UEs on AMF.
[0294] Specifically, the first data contains a first related information.
[0295] Specifically, NWDAF can send the first message to AMF via Namf_EventExposure_Subscribe.
[0296] For example, the first associated information may include one or more of the following: the identifier of the terminal device (SUPI x), the timestamp (Timestamp x), the identifier assigned by the RAN to the terminal device on the NG interface (RAN UE NGAP ID x), and the globally unique identifier of the RAN (Global RAN Node ID x).
[0297] Step 604: AMF sends first data containing first association information to NWDAF.
[0298] Specifically, AMF can send the first data to NWDAF via Namf_EventExposure_Notify.
[0299] Step 605: NWDAF determines the first identifier of the UE.
[0300] Specifically, based on the first data obtained in step 604, NWDAF can determine the association information of each UE among one or more UEs accessing the network area within the time window. The first data includes the UE's SUPI, and NWDAF can assign a Temporary UE ID (i.e., a first identifier) to each UE's SUPI x. Through this step, the Temporary UE ID is equivalent to anonymizing SUPI x, but it can uniquely correspond to SUPI x. This facilitates subsequent RAN side data analysis for each UE based on SUPI x, without being aware of which specific terminal device the UE belongs to.
[0301] Based on the above, the first association information for each UE among one or more UEs determined by NWDAF can be as follows:
[0302] Temporary UE ID x, Timestamp x, RAN UE NGAP ID x, Global RAN Node ID x.
[0303] Step 606: NWDAF sends the UE's first identifier to the RAN-side training equipment.
[0304] For example, NWDAF sends Temporary UE ID x, Timestamp x, RAN UE NGAP ID x, and Global RAN Node ID x to the RAN-side training device.
[0305] Specifically, NWDAF can send the first association information and the UE's first identifier to the RAN-side training device via Nnwdaf_AnalyticsSubscription_Notify.
[0306] It should be noted that steps 601 to 606 can be executed cyclically to ultimately determine the first associated information corresponding to a terminal device, namely, Temporary UE ID X, List of<Timestamp,RAN UE NGAP ID,GlobalRAN Node ID> X, X = 1, 2, 3…N, where N represents the number of first association information items for the same terminal device. In subsequent steps, the RAN-side training device can determine the training data for the terminal device based on the first association information corresponding to the terminal device, see step 607.
[0307] Step 607: The RAN-side training device determines the UE model based on the first association information.
[0308] Step 607 is the model training process. Specifically, the RAN-side training device uses the first association information of each UE in one or more UEs, namely Temporary UE ID X, List of<Timestamp,RANUE NGAP ID,Global RAN Node ID> X, X = 1, 2, 3…N, and the second data corresponding to Timestamp x, RAN UENGAP ID x, and Global RAN Node ID x in step 604, determine the training data corresponding to each UE in one or more UEs. Each training data belongs to one UE, and the training data may include sample data corresponding to one or more sets of information (Timestamp x, RAN UE NGAP ID x, and Global RAN Node ID x).
[0309] Then, the RAN-side training equipment trains the corresponding model based on the training data of each UE in one or more UEs. This model is identified by the Temporary UE ID, which can be in the following format:
[0310] Temporary UE ID 1, Trained Model 1;
[0311] Temporary UE ID 2, Trained Model 2;
[0312] ...;
[0313] Temporary UE ID N, Trained Model N, where N is the number of UEs.
[0314] Step 608: The RAN-side training device sends the model and corresponding first identifier of each UE in one or more UEs to the RAN-side inference device; wherein, the first identifier of a UE is used to identify the model of the UE.
[0315] Step 609: The RAN-side inference device deploys and saves the model of one or more UEs locally.
[0316] The model deployment can refer to existing methods, which will not be described in detail in this application.
[0317] Step 610: The RAN-side inference device obtains the second association information, which is used to associate the third data of the target UE on the AMF and the fourth data of the target UE on the base station.
[0318] The target UE is one of the aforementioned UEs.
[0319] Specifically, the RAN-side inference device can first obtain the fourth data of the target UE on the base station, and then obtain the second association information from the fourth data.
[0320] Specifically, the fourth type of data can be understood as inference data.
[0321] For example, the second associated information could be Timestamp y, RAN UE NGAP ID y, and Global RANNode ID y.
[0322] Step 611: The RAN-side inference device sends a third request to the NWDAF. The third request is used to request the first identifier of the target UE and includes second association information.
[0323] That is, the RAN-side inference device queries the NWDAF for the first identifier of the target UE, Temporary UE ID Y, based on the second association information.
[0324] Step 612: NWDAF determines (searches for) the first identifier of the target UE based on the second association information.
[0325] Step 613: The NWDAF sends the first identifier of the target UE to the RAN-side inference device.
[0326] It should be noted that during steps 311-313 above, NWDAF needs to continuously obtain the SUPI y corresponding to the Timestamp y, RAN UE NGAP ID y, and Global RAN Node ID y from AMF, and then determine the Temporary UE ID y.
[0327] Step 614: The RAN-side inference device searches for the corresponding target model locally based on the first identifier (Temporary UE ID Y) of the target UE, and determines the data analysis results of the target UE based on the second association information and the target model.
[0328] Specifically, the RAN-side inference device inputs the inference data (i.e., the fourth data) corresponding to Timestamp y, RAN UE NGAP ID y, and Global RAN NodeID y (i.e., the second association information) into the target analysis model to obtain the data analysis results.
[0329] Step 615: The RAN-side inference device determines the policy information of the target UE based on the data analysis results of the target UE.
[0330] Step 616: The RAN-side inference device sends the policy information to the base station.
[0331] In the embodiments provided above, the various schemes of the data association method for terminal devices provided in the embodiments of this application have been described from the perspectives of each functional module or device itself and the interaction between each functional module or device. It is understood that each functional module or device, such as the first device, the second access network device, and the third access network device described above, includes corresponding hardware structures and / or software modules to perform each function in order to achieve the above functions. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the various examples described in the embodiments disclosed in this application, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0332] For example, when the aforementioned functional modules or devices implement their corresponding functions through software modules, a communication device provided in this application embodiment can be referred to. Figure 7 As shown, the communication device 700 may include a transceiver unit 701 and a processing unit 702. The transceiver unit 701 is used for receiving or sending information (messages or data), while the processing unit 702 is used for controlling and managing the operations of the communication device 700. The processing unit 702 can also control the steps performed by the transceiver unit 701.
[0333] For example, the communication device 700 may be the first device in the above embodiments, specifically a processor, chip, chip system, or functional module in the first device; or, the communication device 700 may be the second access network device in the above embodiments, specifically a processor, chip, chip system, or functional module in the second access network device; or, the communication device 700 may be the third access network device in the above embodiments, specifically a processor, chip, chip system, or functional module in the third access network device.
[0334] In one embodiment, when the communication device 700 is used to implement the functions of the first device in the above embodiment, it may specifically include:
[0335] Processing unit 702 is used to acquire first data of terminal device on second device; wherein, the first data includes first association information, the first association information is used to associate the first data with second data of terminal device on first access network device, the second data includes the first association information, and there are one or more terminal devices; and to determine the first identifier of terminal device; transceiver unit 701 is used to send the first association information and the first identifier of terminal device to second access network device.
[0336] In one optional implementation, the first association information may include one or more of the following: time information, an identifier assigned to the terminal device by the first access network device, an identifier assigned to the terminal by the second device, an identifier of the first access network device, and an identifier of the second device.
[0337] In an optional implementation, the transceiver unit 701 is further configured to receive a first request from the second access network device, the first request being used to request first association information and a first identifier of the terminal device.
[0338] Specifically, the first request may include one or more of the following information: time window, network region.
[0339] In one example, the first device is a data analysis network element, and the second device is an access and mobility management function network element.
[0340] In another example, the first device is a data analysis network element, and the second device is a user plane function network element.
[0341] In another example, the first and second devices are terminal devices.
[0342] Specifically, the first data of the terminal device on the second device also includes the second identifier of the terminal device; when the first device is a data analysis network element and the second device is an access and mobility management function network element or a user plane function network element, the processing unit 702 is specifically used to: determine the first identifier of the terminal device based on the second identifier of the terminal device when determining the first identifier of the terminal device.
[0343] Specifically, when the first device and the second device are terminal devices, the processing unit 702, when determining the first identifier of the terminal device, is specifically used to: control the transceiver unit 701 to send a second request to the third device and receive the first identifier of the terminal device from the third device; the second request is used to request the first identifier of the terminal device, and the second request includes the second identifier of the terminal device.
[0344] In an optional implementation, the transceiver unit 701 is further configured to receive a third request from the third access network device, the third request being used to request a first identifier of the target terminal device, the third request including second association information, the second association information being used to associate third data of the target terminal device on the second device and fourth data of the target terminal device on the first access network device; the processing unit 702 is further configured to determine the first identifier of the target terminal device based on the second association information; the transceiver unit 701 is further configured to send the first identifier of the target terminal device to the third access network device.
[0345] In another embodiment, when the communication device 700 is used to implement the functions of the second access network device in the above embodiments, it may specifically include:
[0346] The transceiver unit 701 is used to receive first association information and a first identifier of the terminal device from the first device; the first association information is used to associate first data of the terminal device on the second device with second data of the terminal device on the first access network device, the second data includes the first association information, and there are one or more terminal devices; the processing unit 702 is used to determine the model of the terminal device according to the first association information, wherein the model of the terminal device is used to determine the data analysis result of the terminal device; the transceiver unit 701 is also used to send the model of the terminal device and the first identifier of the terminal device to the third access network device, wherein the first identifier of the terminal device is used to identify the model of the terminal device.
[0347] In one optional implementation, the first associated information includes one or more of the following: time information, an identifier assigned to the terminal device by the first access network device, an identifier assigned to the terminal by the second device, an identifier of the first access network device, and an identifier of the second device.
[0348] Specifically, when the processing unit 702 determines the model corresponding to the terminal device based on the first association information, it is specifically used to: determine the training data corresponding to the terminal device based on the first association information and the second data of the terminal device on the first access network device; and determine the model of the terminal device based on the training data corresponding to the terminal device.
[0349] In another embodiment, when the communication device 700 is used to implement the functions of the third access network device in the above embodiments, it may specifically include:
[0350] The transceiver unit 701 is used to receive a model of at least one terminal device and a first identifier of at least one terminal device from the second access network device, wherein the first identifier of each terminal device is used to identify the model of the corresponding terminal device, and the model of each terminal device is used to determine the data analysis result of the corresponding terminal device; the processing unit 702 is used to obtain second association information, which is used to associate the third data of the target terminal device on the second device and the fourth data of the target terminal device on the first access network device; and to determine the data analysis result of the target terminal device based on the model of at least one terminal device, the first identifier of at least one terminal device and the second association information; the target terminal device is one of the at least one terminal device.
[0351] In an optional implementation, the processing unit 702 is further configured to determine the policy information of the target terminal device based on the data analysis results of the target terminal device; the transceiver unit 701 is further configured to send the policy information to the first access network device.
[0352] For example, when the processing unit 702 determines the data analysis result of the target terminal device based on the model of at least one terminal device, the first identifier of at least one terminal device, and the second association information, it is specifically used to: obtain the first identifier of the target terminal device; determine the target model corresponding to the first identifier of the target terminal device based on the first identifier of the target terminal device, the model of at least one terminal device, and the first identifier of at least one terminal device; and determine the data analysis result of the target terminal device based on the second association information and the target model.
[0353] Specifically, when the processing unit 702 obtains the first identifier of the target terminal device, it is specifically used to: control the transceiver unit 701 to send a third request to the first device, the third request being used to request the first identifier of the target terminal device, the third request including second association information; and receive the first identifier of the target terminal device from the first device.
[0354] In one optional implementation, when the processing unit 702 determines the data analysis result of the target terminal device based on the second association information and the target model, it is specifically used to: determine the inference data of the target terminal device based on the second association information, wherein the inference data includes the fourth data of the target terminal device on the first access network device; and determine the data analysis result of the target terminal device based on the inference data of the target terminal device and the target model.
[0355] In one optional implementation, the second associated information includes one or more of the following: time information, an identifier assigned to the terminal device by the first access network device, and an identifier of the first access network device.
[0356] It should be noted that the division of units in the embodiments of this application is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods. The functional units in the embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units described above can be implemented in hardware or as software functional units.
[0357] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0358] For example, when the aforementioned functional modules or devices implement their respective functions through hardware, the communication device provided in this application embodiment can also be referred to... Figure 8 As shown, the communication device 800 may include a transceiver 801 and a processor 802. Optionally, the communication device 800 may also include a memory 803. The memory 803 may be located inside or outside the communication device 800. The processor 802 can control the transceiver 801 to receive and send data or information, etc.
[0359] Specifically, processor 802 can be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and an NP. Processor 802 may further include hardware chips. These hardware chips can be application-specific integrated circuits (ASICs), programmable logic devices (PLDs), or combinations thereof. The PLDs can be complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), generic array logic (GALs), or any combination thereof.
[0360] The transceiver 801, processor 802, and memory 803 are interconnected. Optionally, the transceiver 801, processor 802, and memory 803 are interconnected via bus 804; bus 804 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 7 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.
[0361] In one alternative implementation, memory 803 is used to store programs, etc. Specifically, the program may include program code, which includes computer operation instructions. Memory 803 may include RAM, and may also include non-volatile memory, such as one or more disk storage devices. Processor 802 executes the application program stored in memory 803 to implement the above functions, thereby realizing the functions of communication device 800.
[0362] For example, the communication device 800 may be the first device, the second access network device, or the third access network device described above.
[0363] In one embodiment, when the communication device 800 is used to implement the functions of the first device in the above embodiment, it may specifically include:
[0364] The processor 802 is used to acquire first data of the terminal device on the second device; wherein the first data includes first association information, the first association information is used to associate the first data with the second data of the terminal device on the first access network device, the second data includes the first association information, and the terminal device is one or more; and to determine the first identifier of the terminal device; the transceiver 801 is used to send the first association information and the first identifier of the terminal device to the second access network device.
[0365] In one optional implementation, the first association information may include one or more of the following: time information, an identifier assigned to the terminal device by the first access network device, an identifier assigned to the terminal by the second device, an identifier of the first access network device, and an identifier of the second device.
[0366] In an optional implementation, transceiver 801 is further configured to receive a first request from a second access network device, the first request being used to request first association information and a first identifier of the terminal device.
[0367] Specifically, the first request may include one or more of the following information: time window, network region.
[0368] In one example, the first device is a data analysis network element, and the second device is an access and mobility management function network element.
[0369] In another example, the first device is a data analysis network element, and the second device is a user plane function network element.
[0370] In another example, the first and second devices are terminal devices.
[0371] Specifically, the first data of the terminal device on the second device also includes the second identifier of the terminal device; when the first device is a data analysis network element and the second device is an access and mobility management function network element or a user plane function network element, the processor 802, when determining the first identifier of the terminal device, is specifically used to: generate the first identifier of the terminal device for the terminal device based on the second identifier of the terminal device.
[0372] Specifically, when the first device and the second device are terminal devices, the processor 802, when determining the first identifier of the terminal device, is specifically used to: control the transceiver 801 to send a second request to the third device and receive the first identifier of the terminal device from the third device; the second request is used to request the first identifier of the terminal device, and the second request includes the second identifier of the terminal device.
[0373] In an optional implementation, transceiver 801 is further configured to receive a third request from a third access network device, the third request being for requesting a first identifier of a target terminal device, the third request including second association information, the second association information being for associating third data of the target terminal device on a second device and fourth data of the target terminal device on a first access network device; processor 802 is further configured to determine the first identifier of the target terminal device based on the second association information; transceiver 801 is further configured to send the first identifier of the target terminal device to the third access network device.
[0374] In another embodiment, when the communication device 800 is used to implement the functions of the second access network device in the above embodiments, it may specifically include:
[0375] Transceiver 801 is used to receive first association information and a first identifier of terminal device from a first device; the first association information is used to associate first data of terminal device on a second device with second data of terminal device on a first access network device, the second data including the first association information, and there are one or more terminal devices; processor 802 is used to determine the model of terminal device according to the first association information, wherein the model of terminal device is used to determine the data analysis result of terminal device; transceiver 801 is also used to send the model of terminal device and the first identifier of terminal device to a third access network device, wherein the first identifier of terminal device is used to identify the model of terminal device.
[0376] In one optional implementation, the first associated information includes one or more of the following: time information, an identifier assigned to the terminal device by the first access network device, an identifier assigned to the terminal by the second device, an identifier of the first access network device, and an identifier of the second device.
[0377] Specifically, when the processor 802 determines the model corresponding to the terminal device based on the first association information, it is specifically used to: determine the training data corresponding to the terminal device based on the first association information and the second data of the terminal device on the first access network device; and determine the model of the terminal device based on the training data corresponding to the terminal device.
[0378] In another embodiment, when the communication device 800 is used to implement the functions of the third access network device in the above embodiments, it may specifically include:
[0379] Transceiver 801 is used to receive a model of at least one terminal device and a first identifier of at least one terminal device from a second access network device, wherein the first identifier of each terminal device is used to identify the model of the corresponding terminal device, and the model of each terminal device is used to determine the data analysis result of the corresponding terminal device; processor 802 is used to acquire second association information, which is used to associate third data of the target terminal device on the second device and fourth data of the target terminal device on the first access network device; and to determine the data analysis result of the target terminal device based on the model of at least one terminal device, the first identifier of at least one terminal device and the second association information; the target terminal device is one of the at least one terminal device.
[0380] In an optional implementation, the processor 802 is further configured to determine the policy information of the target terminal device based on the data analysis results of the target terminal device; the transceiver 801 is further configured to send the policy information to the first access network device.
[0381] For example, when the processor 802 determines the data analysis result of the target terminal device based on the model of at least one terminal device, the first identifier of at least one terminal device, and the second association information, it is specifically used to: obtain the first identifier of the target terminal device; determine the target model corresponding to the first identifier of the target terminal device based on the first identifier of the target terminal device, the model of at least one terminal device, and the first identifier of at least one terminal device; and determine the data analysis result of the target terminal device based on the second association information and the target model.
[0382] Specifically, when the processor 802 obtains the first identifier of the target terminal device, it is specifically used to: control the transceiver 801 to send a third request to the first device, the third request being used to request the first identifier of the target terminal device, the third request including second association information; and receive the first identifier of the target terminal device from the first device.
[0383] In one optional implementation, when the processor 802 determines the data analysis result of the target terminal device based on the second association information and the target model, it is specifically used to: determine the inference data of the target terminal device based on the second association information, wherein the inference data includes the fourth data of the target terminal device on the first access network device; and determine the data analysis result of the target terminal device based on the inference data of the target terminal device and the target model.
[0384] In one optional implementation, the second associated information includes one or more of the following: time information, an identifier assigned to the terminal device by the first access network device, and an identifier of the first access network device.
[0385] Figure 9This is a structural schematic diagram of an access network device provided in an embodiment of this application, such as a structural schematic diagram of a base station. Figure 9 As shown, this access network device can be applied to, for example... Figure 1 In the communication system shown, the functions of any one of the access network devices in the above method embodiments are performed. Base station 900 may include one or more distributed units (DUs) 901 and one or more centralized units (CUs) 902. DU 901 may include at least one antenna 9011, at least one radio frequency unit 9012, at least one processor 9017, and at least one memory 9014. DU 901 is mainly used for transmitting and receiving radio frequency signals, converting radio frequency signals to baseband signals, and performing some baseband processing. CU 902 may include at least one processor 9022 and at least one memory 9021. CU 902 and DU 901 can communicate via an interface, where the control plane interface can be Fs-C, such as F1-C, and the user plane interface can be Fs-U, such as F1-U.
[0386] The CU 902 is primarily used for baseband processing and base station control. The DU 901 and CU 902 can be physically installed together or separately, i.e., a distributed base station. The CU 902 serves as the base station's control center, also known as a processing unit, and is mainly used to perform baseband processing functions. For example, the CU 902 can be used to control the base station to perform the aforementioned tasks. Figure 4 or Figure 6 The method embodiment describes the operation process of the network device.
[0387] Specifically, the baseband processing on the CU and DU can be divided according to the protocol layer of the wireless network. For example, the functions of the PDCP layer and above are set in the CU, while the functions of the protocol layers below PDCP, such as the RLC layer and MAC layer, are set in the DU. For another example, the CU implements the functions of the RRC and PDCP layers, while the DU implements the functions of the RLC, MAC, and physical (PHY) layers.
[0388] Additionally, optionally, the base station 900 may include one or more radio frequency units (RUs), one or more DUs, and one or more CUs. A DU may include at least one processor 9017 and at least one memory 9014, an RU may include at least one antenna 9011 and at least one radio frequency unit 9012, and a CU may include at least one processor 9022 and at least one memory 9021.
[0389] In one example, the CU902 can be composed of one or more single boards. Multiple single boards can collectively support a single access indication wireless access network (such as a 5G network), or they can each support wireless access networks with different access standards (such as LTE, 5G, or other networks). The memory 9021 and processor 9022 can serve one or more single boards. That is, each single board can have its own memory and processor, or multiple single boards can share the same memory and processor. Furthermore, each single board can also have necessary circuitry. Similarly, the DU901 can be composed of one or more single boards. Multiple single boards can collectively support a single access indication wireless access network (such as a 5G network), or they can each support wireless access networks with different access standards (such as LTE, 5G, or other networks). The memory 9014 and processor 9017 can serve one or more single boards. That is, each single board can have its own memory and processor, or multiple single boards can share the same memory and processor. Furthermore, each single board can also have necessary circuitry.
[0390] Based on the above embodiments, this application provides a communication system, which may include the first device, the second access network device, and the third access network device (master station or auxiliary station) involved in the above embodiments.
[0391] This application also provides a computer-readable storage medium for storing a computer program. When the computer program is executed by a computer, the computer can implement the data association method for terminal devices provided in the above method embodiments.
[0392] This application also provides a computer program product for storing a computer program. When the computer program is executed by a computer, the computer can implement the data association method for terminal devices provided in the above method embodiments.
[0393] This application also provides a chip coupled to a memory, which is used to implement the data association method for terminal devices provided in the above method embodiments.
[0394] This application also provides a chip system including a processor for supporting the communication device in implementing the functions involved in the above aspects. In one possible design, the chip system further includes a memory for storing necessary program instructions and data for the communication device. This chip system can be composed of chips or may include chips and other discrete devices.
[0395] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0396] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0397] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0398] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0399] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the scope of protection of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.
Claims
1. A data association method for a terminal device, characterized in that, include: The first device acquires first data from the terminal device on the second device; wherein, the first data includes first association information, the first association information is used to associate the first data with the second data of the terminal device on the first access network device, the second data includes the first association information, and the terminal device is one or more; The first device determines the first identifier of the terminal device; The first device sends the first association information and the first identifier of the terminal device to the second access network device; The first identifier of the terminal device is determined based on the second identifier of the terminal device. The first identifier of the terminal device is a temporary terminal device identifier, and the first identifier is used to protect the second identifier.
2. The method as described in claim 1, characterized in that, The first associated information includes one or more of the following: time information, the identifier assigned to the terminal device by the first access network device, the identifier assigned to the terminal by the second device, the identifier of the first access network device, and the identifier of the second device.
3. The method according to any one of claims 1-2, characterized in that, The method further includes: The first device receives a first request from the second access network device, the first request being used to request the first association information and the first identifier of the terminal device.
4. The method according to any one of claims 1-2, characterized in that, The first device is a data analysis network element, and the second device is an access and mobility management function network element.
5. The method according to any one of claims 1-2, characterized in that, The first device is a data analysis network element, and the second device is a user plane function network element.
6. The method according to any one of claims 1-2, characterized in that, The first device and the second device are the terminal devices.
7. The method as described in claim 4, characterized in that, The first data of the terminal device on the second device also includes the second identifier of the terminal device; The first device determines the first identifier of the terminal device, including: The first device determines the first identifier of the terminal device based on the second identifier of the terminal device.
8. The method as described in claim 5, characterized in that, The first data of the terminal device on the second device also includes the second identifier of the terminal device; The first device determines the first identifier of the terminal device, including: The first device determines the first identifier of the terminal device based on the second identifier of the terminal device.
9. The method as described in claim 6, characterized in that, The first device determines the first identifier of the terminal device, including: The first device sends a second request to the third device, the second request being used to request the first identifier of the terminal device, the second request including the second identifier of the terminal device; The first device receives the first identifier of the terminal device from the third device.
10. The method according to any one of claims 1-2, characterized in that, The method further includes: The first device receives a third request from the third access network device. The third request is used to request a first identifier of the target terminal device. The third request includes second association information, which is used to associate third data of the target terminal device on the second device and fourth data of the target terminal device on the first access network device. The first device determines the first identifier of the target terminal device based on the second association information; The first device sends the first identifier of the target terminal device to the third access network device.
11. A data association method for a terminal device, characterized in that, include: The second access network device receives first association information and the first identifier of the terminal device from the first device; The first association information is used to associate the first data of the terminal device on the second device with the second data of the terminal device on the first access network device. The second data includes the first association information. The terminal device can be one or more. The first identifier of the terminal device is determined based on the second identifier of the terminal device. The first identifier of the terminal device is a temporary terminal device identifier. The first identifier is used to protect the second identifier. The second access network device determines the model of the terminal device based on the first association information, wherein the model of the terminal device is used to determine the data analysis results of the terminal device; The second access network device sends the model of the terminal device and the first identifier of the terminal device to the third access network device, wherein the first identifier of the terminal device is used to identify the model of the terminal device.
12. The method as described in claim 11, characterized in that, The first associated information includes one or more of the following: time information, the identifier assigned to the terminal device by the first access network device, the identifier assigned to the terminal by the second device, the identifier of the first access network device, and the identifier of the second device.
13. The method as described in claim 11 or 12, characterized in that, The second access network device determines the model corresponding to the terminal device based on the first association information, including: The second access network device determines the training data corresponding to the terminal device based on the first association information and the second data of the terminal device on the first access network device; The second access network device determines the model of the terminal device based on the training data corresponding to the terminal device.
14. A data association method for a terminal device, characterized in that, include: The third access network device receives a model of at least one terminal device and a first identifier of the at least one terminal device from the second access network device. The first identifier of each terminal device is used to identify the model of the corresponding terminal device, and the model of each terminal device is used to determine the data analysis result of the corresponding terminal device. The first identifier of each terminal device is determined based on a second identifier of each terminal device. The first identifier of each terminal device is a temporary terminal device identifier, and the first identifier is used to protect the second identifier. The third access network device acquires second association information, which is used to associate the third data of the target terminal device on the second device with the fourth data of the target terminal device on the first access network device; the target terminal device is one of the at least one terminal device. The third access network device determines the data analysis result of the target terminal device based on the model of the at least one terminal device, the first identifier of the at least one terminal device, and the second association information.
15. The method as described in claim 14, characterized in that, The method further includes: The third access network device determines the strategy information of the target terminal device based on the data analysis results of the target terminal device; The third access network device sends the policy information to the first access network device.
16. The method as described in claim 14 or 15, characterized in that, The third access network device determines the data analysis results of the target terminal device based on the model of the at least one terminal device, the first identifier of the at least one terminal device, and the second association information, including: The third access network device obtains the first identifier of the target terminal device; The third access network device determines the target model corresponding to the first identifier of the target terminal device based on the first identifier of the target terminal device, the model of the at least one terminal device, and the first identifier of the at least one terminal device. The third access network device determines the data analysis results of the target terminal device based on the second association information and the target model.
17. The method as described in claim 16, characterized in that, The third access network device obtains the first identifier of the target terminal device, including: The third access network device sends a third request to the first device, the third request being used to request the first identifier of the target terminal device, the third request including the second association information; The third access network device receives the first identifier of the target terminal device from the first device.
18. The method as described in claim 16, characterized in that, The third access network device determines the data analysis results of the target terminal device based on the second association information and the target model, including: The third access network device determines the inference data of the target terminal device based on the second association information, and the inference data includes the fourth data of the target terminal device on the first access network device; The third access network device determines the data analysis results of the target terminal device based on the inference data of the target terminal device and the target model.
19. The method according to any one of claims 14-15, characterized in that, The second associated information includes one or more of the following: time information, the identifier assigned to the terminal device by the first access network device, and the identifier of the first access network device.
20. A communication device, characterized in that, Includes units or modules for performing the method as described in any one of claims 1-10.
21. A communication device, characterized in that, Includes units or modules for performing the method as described in any one of claims 11-13.
22. A communication device, characterized in that, Includes units or modules for performing the method as described in any one of claims 14-19.
23. A communication device, characterized in that, Includes a processor and a transceiver, wherein: The transceiver is used to send and receive data or information; The processor, coupled to a memory, is used to invoke a program in the memory to cause the communication device to perform the method as described in any one of claims 1-10.
24. A communication device, characterized in that, Includes a processor and a transceiver, wherein: The transceiver is used to send and receive data or information; The processor, coupled to a memory, is used to invoke a program in the memory to cause the communication device to perform the method as described in any one of claims 11-13.
25. A communication device, characterized in that, Includes a processor and a transceiver, wherein: The transceiver is used to send and receive data or information; The processor, coupled to a memory, is used to invoke a program in the memory to cause the communication device to perform the method as described in any one of claims 14-19.
26. A computer-readable storage medium, characterized in that, Includes instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1-10, or the method as described in any one of claims 11-13, or the method as described in any one of claims 14-19.
Citation Information
Patent Citations
Information processing method and device
CN110650034A