Communication method and apparatus

Abstract

Embodiments of the present application relate to the field of communications, and provide a communication method and apparatus, which can solve the problem of insufficient valid data in a wireless communication network. In the method, a synthetic data function may acquire, from a first apparatus and on the basis of a first message sent by a control function and used for triggering generation of synthetic data, data used for generating synthetic data, so as to generate first synthetic data, so that synthetic data can be generated in a wireless communication network on the basis of existing data, thereby expanding a valid data set in the wireless communication network for model training, reasoning, fine-tuning, and the like.

Description

Communication methods and devices

[0001] This application claims priority to Chinese Patent Application No. 202411993728.9, filed with the State Intellectual Property Office of China on December 30, 2024, entitled "Communication Method and Apparatus", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communications, and more particularly to communication methods and apparatus. Background Technology

[0003] Due to issues such as severe data homogenization and user privacy, the amount of effective data that can be obtained by wireless networks for training communication artificial intelligence (AI) models or for sharing with third parties for model training is relatively small. Therefore, how to solve the problem of insufficient effective data in wireless communication networks is a research topic. Summary of the Invention

[0004] This application provides a communication method and apparatus that can generate synthetic data based on existing data in a wireless communication network, expand the effective dataset, and be used for training, inference, fine-tuning, etc. of large communication models.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] In a first aspect, a communication method is provided. This method can be executed by a synthetic data function in a wireless communication network, or by a component of the synthetic data function, such as a processor, chip, or chip system, or by a logic module or software capable of implementing all or part of the synthetic data function. The method includes: receiving a first message from a control function, the first message being used to trigger the generation of synthetic data; receiving first data from a first device, the first device being a means of providing data for generating the synthetic data; and generating first synthetic data based on the first message and the first data, the first synthetic data being used for model training and / or inference.

[0007] In this communication method, the data synthesis function can obtain data for generating synthetic data from the first device based on the first message sent by the control function to trigger the generation of synthetic data, thereby generating the first synthetic data. Thus, synthetic data can be generated from existing data in a wireless communication network, expanding the effective dataset within the network for training, inference, and fine-tuning of large-scale communication models within the network. Alternatively, the synthetic data can be made available to third-party devices or internet applications for use and analysis, addressing the problem of insufficient effective data due to privacy and data homogenization issues.

[0008] In one possible design, the first message includes the data type of the synthetic data, which can be used to determine the method for generating the synthetic data, the first device (providing data for generating the synthetic data), etc. The synthetic data function can generate synthetic data according to the data type of the synthetic data, thereby expanding the effective dataset within the network.

[0009] In one possible design, generating first composite data based on a first message and first data may include: determining a method for generating composite data based on the data type of the composite data, and generating the first composite data based on the method for generating composite data and the first data. Therefore, the composite data function can generate first composite data based on the data type of the composite data and the acquired first data.

[0010] In one possible design, the first message may further include: key performance indicators (KPIs) of the synthetic data, and / or the amount of synthetic data. Based on the data type of the synthetic data, the method for generating the synthetic data is determined, including: determining the method based on at least one of the KPIs and the amount of synthetic data, as well as the data type. Therefore, the synthetic data function can also combine requirements for the KPIs (such as authenticity, diversity, etc.) and / or data volume of the synthetic data to determine the method for generating the synthetic data, thereby improving the reliability and accuracy of the synthetic data.

[0011] In one possible design, the first message may further include a method for generating composite data. Generating the first composite data based on the first message and the first data includes: generating the first composite data based on the method for generating composite data and the first data. Therefore, the method for generating composite data can be carried by the control function in the first message and sent to the composite data function, eliminating the need for the composite data function to generate it itself.

[0012] In one possible design, the communication method may further include: sending a second message to a first device based on a first message, the second message triggering the first device to provide data for generating synthetic data to the data synthesis function; or, sending a second message to a second device based on the first message, the second message triggering the first device to provide data for generating synthetic data. Thus, based on different data types, the data synthesis function can send signaling to either the first or second device to obtain data for generating synthetic data.

[0013] In one possible design, sending a second message to a first device or a second device based on a first message may include: sending a second message to the first device based on information used to instruct the first device; or sending a second message to the second device based on information used to instruct the second device; wherein the first message further includes information used to instruct the first device or information used to instruct the second device. Therefore, the first device or the second device can also be indicated to the data synthesis function by the control function in the first message, without requiring determination by the data synthesis function.

[0014] In one possible design, the first message includes the data type of the synthesized data; sending a second message to a first device based on the first message includes: determining the first device based on the data type of the synthesized data, and sending the second message to the first device; or, sending a second message to a second device based on the first message includes: determining the second device based on the data type of the synthesized data, and sending the second message to the second device. Thus, the synthesized data function can locally determine either the first device providing the data for generating the synthesized data or the second device triggering the first device, based on the data type of the synthesized data.

[0015] In one possible design, the second message includes the data type of the synthetic data, which can be used by the first device to determine the reported data used to generate the synthetic data.

[0016] In one possible design, the second message may further include first information, which corresponds to data used to generate the synthetic data. Thus, the data types of the first information and the synthetic data can index data stored in the first device that can be used to generate the synthetic data.

[0017] In one possible design, the first message includes the data type and data volume of the synthesized data, or the first message includes the data type, method for generating the synthesized data, and data volume of the synthesized data. Based on the first message, sending a second message to the first or second device includes: determining the data volume used to generate the synthesized data based on the data volume and method for generating the synthesized data; or, determining the data volume used to generate the synthesized data based on the data volume, method for generating the synthesized data, and data type of the synthesized data; sending the second message to the first or second device, the second message also including the data volume used to generate the synthesized data. Therefore, the data synthesis function can also determine the data volume used to generate the synthesized data based on the data volume and method for generating the synthesized data, or based on the data volume and method for generating the synthesized data, combined with the data type of the synthesized data.

[0018] In one possible design, the first message also includes KPIs that can be used to synthesize data; determining the amount of data used to generate the synthesized data based on the data volume and the method of generating the synthesized data includes: determining the amount of data used to generate the synthesized data based on the data volume, the method of generating the synthesized data, and the KPIs of the synthesized data; or, determining the amount of data used to generate the synthesized data based on the data volume, the method of generating the synthesized data, and the data type of the synthesized data includes: determining the amount of data used to generate the synthesized data based on the data volume, the method of generating the synthesized data, the data type of the synthesized data, and the KPIs of the synthesized data. Therefore, the amount of data used to generate the synthesized data can also be determined in conjunction with the KPIs of the synthesized data.

[0019] In one possible design scheme, KPIs may include: authenticity and / or diversity. For example, authenticity can be characterized by similarity, which measures how closely the synthesized data resembles real data. The higher the similarity, the higher the authenticity of the synthesized data. By setting a similarity threshold, such as 95% to 98%, the requirement for authenticity of the synthesized data can be represented. Diversity can be characterized by the number of data features. Different data features correspond to data generated under different circumstances. By setting a threshold for the number of data features, the requirement for diversity of the synthesized data can be represented.

[0020] In one possible design, the communication method may further include: sending first synthetic data to a third device, which may be any of the following: a device for storing the first synthetic data, a device for using the first synthetic data for model training and / or inference, or a device for providing the first synthetic data to a third-party device.

[0021] In one possible design, the first device may include a data storage network element.

[0022] In one possible design, the first device may further include at least one of the following: a terminal device, an access network device, a location service network element, or a user plane network element.

[0023] In one possible design, the second device includes a session management network element.

[0024] Secondly, a communication method is provided. This method can be executed by a control function, or by a component of the control function, such as a processor, chip, or chip system, or by a logic module or software capable of implementing all or part of the control function. The method includes: receiving a third message from a first network element, the third message being used to request synthesized data; and, based on the third message, sending a first message to a synthesized data function in the wireless communication network, the first message being used to trigger the generation of synthesized data.

[0025] In one possible design, the third message includes the data type of the synthesized data, and the first message includes the data type of the synthesized data.

[0026] In one possible design, the first message may further include a method for generating synthetic data; according to the third message, sending the first message to the synthetic data function in the wireless communication network includes: determining the method for generating synthetic data based on the data type of the synthetic data, and sending the first message to the synthetic data function.

[0027] In one possible design, the third message may also include the KPI of the synthesized data and / or the data volume of the synthesized data; determining the method for generating the synthesized data based on the data type of the synthesized data includes: determining the method for generating the synthesized data based on at least one of the KPI of the synthesized data and the data volume of the synthesized data, as well as the data type of the synthesized data.

[0028] In one possible design, the third message may also include the KPIs of the synthesized data and / or the amount of synthesized data, and the first message may also include the KPIs of the synthesized data and / or the amount of synthesized data.

[0029] In one possible design, sending a first message to a synthetic data function in a wireless communication network according to a third message includes: determining a first device or a second device based on the data type of the synthetic data, wherein the first device is a device for providing data for generating the synthetic data, and the second device is used to trigger the first device to provide data for generating the synthetic data; sending the first message to the synthetic data function, the first message further including information for instructing the first device or information for instructing the second device.

[0030] In one possible design, the communication method may further include: sending a fourth message to a first device according to a third message, the fourth message being used to control the first device to provide data for generating synthetic data to the synthetic data function, the first device being a device for providing data for generating synthetic data; or, sending a fourth message to a second device according to a third message, the fourth message being used by the second device to trigger the first device to provide data for generating synthetic data.

[0031] In one possible design, sending a fourth message to the first device based on the third message may include: determining the first device based on the data type of the synthesized data, and sending the fourth message to the first device. Alternatively, sending a fourth message to the second device based on the third message may include: determining the second device based on the data type of the synthesized data, and sending the fourth message to the second device.

[0032] In one possible design, the fourth message includes the data type of the synthetic data and second information, the second information being used to instruct the synthetic data function to provide data for generating the synthetic data.

[0033] In one possible design, the fourth message may also include the first information, which corresponds to the data used to generate the synthetic data.

[0034] In one possible design, the third message includes the data type and the amount of the synthesized data. Based on the third message, a fourth message is sent to the first or second device, including: determining a method for generating the synthesized data based on the data type and the amount of the synthesized data, and determining the amount of data used to generate the synthesized data based on the amount of the synthesized data and the method for generating the synthesized data; or, determining the amount of data used to generate the synthesized data based on the amount of the synthesized data, the method for generating the synthesized data, and the data type of the synthesized data. The fourth message is sent to the first or second device, and the fourth message also includes the amount of data used to generate the synthesized data.

[0035] In one possible design, the third message may also include the KPIs for the synthesized data. The method for generating the synthesized data is determined based on its data type and volume, including: determining the method for generating the synthesized data based on its data type, volume, and KPIs. Alternatively, the amount of data used to generate the synthesized data is determined based on its volume and generation method, including: determining the amount of data used to generate the synthesized data based on its volume, generation method, and KPIs. Or, the amount of data used to generate the synthesized data is determined based on its volume, generation method, and data type, including: determining the amount of data used to generate the synthesized data based on its volume, generation method, data type, and KPIs.

[0036] In one possible design approach, KPIs could include: authenticity and / or diversity.

[0037] In one possible design, the first device may include a data storage network element.

[0038] In one possible design, the first device may further include at least one of the following: a terminal device, an access network device, a location service network element, or a user plane network element.

[0039] In one possible design, the second device includes a session management network element.

[0040] Thirdly, a communication method is provided. This method can be executed by a session management network element, or by a component of the session management network element, such as a processor, chip, or chip system of the session management network element, or by a logic module or software capable of implementing all or part of the session management network element. The method includes: receiving a fifth message, which triggers the provision of user plane data for generating synthetic data to a synthetic data function from a terminal device; sending a sixth message to a user plane network element based on the fifth message, which is used by the user plane network element to provide user plane data for generating synthetic data to the synthetic data function from the terminal device; or, sending a Quality of Service (QoS) rule to the terminal device based on the fifth message, the QoS rule including a first QoS Flow Identifier (QFI), the first QFI corresponding to the synthetic data function.

[0041] In one possible design, the correspondence between the first QFI and the synthetic data function is sent to the user plane network element.

[0042] In one possible design, receiving the fifth message includes: receiving a fifth message from the synthetic data function, the fifth message including the data type of the synthetic data, wherein the data type of the synthetic data is user plane data of the terminal device.

[0043] In one possible design, receiving the fifth message includes: receiving a fifth message from a control function, the fifth message including the data type of the synthetic data, first information and second information, wherein the second information is used to instruct the synthetic data function to provide user plane data of the terminal device for generating the synthetic data, and the data type of the synthetic data is user plane data of the terminal device.

[0044] In one possible design, the fifth message may also include first information, which corresponds to the data used to generate the synthetic data.

[0045] In one possible design, the sixth message includes the data type of the synthetic data and second information; wherein the second information is used to instruct the synthetic data function to provide user plane data of the terminal device for generating synthetic data, and the data type of the synthetic data is user plane data of the terminal device.

[0046] In one possible design, the fifth and sixth messages also include the amount of user plane data for the terminal device used to generate the synthetic data.

[0047] Fourthly, a communication method is provided. This method can be executed by a user plane network element, or by a component of the user plane network element, such as a processor, chip, or chip system of the user plane network element, or by a logic module or software capable of implementing all or part of the user plane network element. The method includes: receiving a sixth message from a session management network element, the sixth message being used by the user plane network element to provide user plane data from a terminal device for generating synthetic data to a synthetic data function; and sending the user plane data from the terminal device to the synthetic data function according to the sixth message. Alternatively, receiving a data packet from a terminal device and sending the data packet to the synthetic data function, wherein the data packet carries a first QFI and the user plane data from the terminal device.

[0048] In one possible design, the process involves receiving the correspondence between the first QFI and the synthetic data function from the session management network element; and sending data packets to the synthetic data function, including sending user plane data of the terminal device to the synthetic data function based on the correspondence between the first QFI and the synthetic data function and the data packets.

[0049] In one possible design, the sixth message includes the data type of the synthetic data and second information; wherein the second information is used to instruct the synthetic data function to provide user plane data of the terminal device for generating synthetic data, and the data type of the synthetic data is user plane data of the terminal device.

[0050] In one possible design, according to the sixth message, sending the user plane data of the terminal device to the synthetic data function includes: determining the user plane data of the terminal device according to the type of synthetic data; and sending the user plane data of the terminal device to the synthetic data function according to the second information.

[0051] In one possible design, the sixth message also includes the amount of user plane data for the terminal device used to generate the synthetic data.

[0052] In one possible design, determining the user plane data of the terminal device based on the type of synthesized data includes: determining the user plane data of the terminal device based on the type of synthesized data and the amount of user plane data of the terminal device used to generate the synthesized data.

[0053] Fifthly, a communication method is provided. This method can be executed by a first device, or by a component of the first device, such as a processor, chip, or chip system of the first device, or by a logic module or software capable of implementing all or part of the first device. The method includes: receiving a fifth message, the fifth message being used to trigger the provision of data for generating synthetic data to a synthetic data function; and sending first data to the synthetic data function according to the fifth message.

[0054] Sixthly, a communication method is provided, which can be executed by a second device, or by a component of the second device, such as a processor, chip, or chip system of the second device, or by a logic module or software capable of implementing all or part of the second device. The method includes: receiving a fifth message, the fifth message being used by the second device to trigger the provision of data for generating synthetic data to a synthetic data function; and, based on the fifth message, sending a sixth message to a first device, the sixth message being used to trigger the first device to provide data for generating synthetic data to the synthetic data function.

[0055] The technical effects of the methods described in the second to sixth aspects can be found in the technical effects of the methods described in the first aspect, and will not be repeated here.

[0056] In a seventh aspect, a communication device is provided for implementing the various methods described above. This communication device may be the function or apparatus described in any one of the first to sixth aspects, or may include the function or apparatus described in any one of the first to sixth aspects, or an apparatus included in the function or apparatus described in any one of the first to sixth aspects, such as a chip. The communication device includes corresponding modules, units, or means for implementing the methods described in any one of the first to sixth aspects. These modules, units, or means may be implemented in hardware, software, or by hardware executing corresponding software. The hardware or software includes one or more modules or units corresponding to the aforementioned functions.

[0057] In some possible designs, the communication device includes a processing module and a transceiver module. The processing module is used to implement the processing function of the method described in any one of the first to sixth aspects, and the transceiver module is used to implement the transceiver function of the method described in any one of the first to sixth aspects.

[0058] In one possible design, the transceiver module may include a receiving module and a sending module. The sending module implements the sending function of the communication device, and the receiving module implements the receiving function of the communication device.

[0059] In one possible design, the communication device may further include a storage module storing programs or instructions. When the processing module executes the program or instructions, the communication device can perform the method described in any of the first to sixth aspects.

[0060] Eighthly, a communication device is provided (e.g., the communication device may be a chip or a chip system). The communication device includes a processor for implementing the functions involved in any of the preceding aspects.

[0061] In one possible design, the communication device may further include a memory for storing necessary program instructions and data. A processor is coupled to the memory and is used to execute the computer program or instructions stored in the memory, causing the communication device to perform the method described in any of the possible implementations of the first to sixth aspects.

[0062] In one possible design, the communication device described in the eighth aspect may further include a transceiver. This transceiver may be a transceiver circuit or an interface circuit. The transceiver can be used for communication between the communication device described in the eighth aspect and other communication devices.

[0063] In one possible design, the processor can be integrated with the memory.

[0064] In some possible designs, when the device is a chip system, it can be composed of chips or contain chips and other discrete components.

[0065] A ninth aspect provides a communication device including a processor and an interface circuit, the interface circuit being configured to receive signals from other communication devices outside the communication device and transmit them to the processor, or to send signals from the processor to other communication devices outside the communication device, the processor being configured to implement the method as described in any one of the possible implementations of the first to sixth aspects via logic circuits or execution code instructions.

[0066] It is understood that when the communication device provided by either the eighth or ninth aspect is a chip, the aforementioned transmitting action / function can be understood as an output, and the aforementioned receiving action / function can be understood as an input.

[0067] In a tenth aspect, a computer-readable storage medium is provided, which stores a computer program or instructions that, when executed on a communication device, enable the communication device to perform the method described in any one of the first to sixth aspects.

[0068] Eleventhly, a computer program product containing instructions is provided, including computer program code, which, when run on a communication device, enables the communication device to perform the method described in any one of the first to sixth aspects.

[0069] In a twelfth aspect, a communication system is provided, comprising: a data synthesis function for implementing the method of the first aspect, a control function for implementing the method of the second aspect, and a first means for implementing the method of the fifth aspect. Optionally, it may further include: a first means for implementing the method of the sixth aspect.

[0070] In a thirteenth aspect, a communication chip is provided, wherein instructions are stored that, when the chip is operated on a communication device, cause the method described in any one of the first to sixth aspects above to be implemented. Attached Figure Description

[0071] Figure 1 is a schematic diagram of a data plane architecture suitable for communication systems;

[0072] Figure 2 is a schematic diagram of the architecture of a non-roaming 5G system based on service-oriented interfaces;

[0073] Figure 3 is a schematic diagram of the architecture of a communication system provided in an embodiment of this application;

[0074] Figure 4 is a flowchart illustrating a communication method provided in an embodiment of this application;

[0075] Figure 5 is a flowchart illustrating another communication method provided in an embodiment of this application;

[0076] Figure 6 is a schematic diagram of generating synthetic location data according to an embodiment of this application;

[0077] Figure 7 is a flowchart illustrating another communication method provided in an embodiment of this application;

[0078] Figure 8 is a schematic diagram of the structure of a communication device provided in an embodiment of this application;

[0079] Figure 9 is a schematic diagram of another communication device provided in an embodiment of this application. Detailed Implementation

[0080] This application will present various aspects, embodiments, or features relating to a system that may include multiple devices, components, modules, etc. It should be understood and appreciated that individual systems may include additional devices, components, modules, etc., and / or may not include all the devices, components, modules, etc. discussed in conjunction with the accompanying drawings. Furthermore, combinations of these approaches may also be used.

[0081] The technical solutions of this application embodiment can be applied to various communication systems, such as: Global System for Mobile Communication (GSM), Universal Mobile Telecommunication System (UMTS), Worldwide Interoperability for Microwave Access (WiMAX) communication system, 4th generation (4G) mobile communication system, such as Long Term Evolution (LTE) system, 5th generation (4G) mobile communication system, such as New Radio (NR) system, and future communication systems.

[0082] To better understand the embodiments of this application, the following points are explained before introducing the embodiments of this application.

[0083] First, in the embodiments of this application, "for indicating" can include both direct and indirect indication. When describing a certain "indication information" for indicating A, it can include whether the indication information directly indicates A or indirectly indicates A, but does not necessarily mean that the indication information carries A.

[0084] The information indicated by the instruction is called the information to be instructed. In the specific implementation process, there are many ways to indicate the information to be instructed, such as, but not limited to, directly indicating the information to be instructed, such as the information to be instructed itself or its index. It can also be indirectly indicated by indicating other information, where there is a relationship between the other information and the information to be instructed. It can also indicate only a part of the information to be indicated, while the other parts are known or pre-agreed upon. For example, the instruction of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) arrangement of various pieces of information, thereby reducing instruction overhead to some extent. At the same time, common parts of various pieces of information can be identified and indicated uniformly to reduce the instruction overhead caused by individually indicating the same information.

[0085] Furthermore, the specific indication method can also be any existing indication method, such as, but not limited to, the above-mentioned indication methods and their various combinations. Specific details of various indication methods can be found in existing technologies, and will not be repeated here. As described above, for example, when multiple pieces of information of the same type need to be indicated, the indication methods for different pieces of information may differ. In the specific implementation process, the required indication method can be selected according to specific needs. This application embodiment does not limit the selected indication method; therefore, the indication methods involved in this application embodiment should be understood to cover various methods that enable the party to be indicated to obtain the information to be indicated.

[0086] Secondly, in the embodiments of this application, the terms "first," "second," and various numerical designations are merely for descriptive convenience and are not intended to limit the scope of the embodiments of this application. For example, "first device" and "second device" are only used to distinguish different devices and do not limit their order. Those skilled in the art will understand that the terms "first," "second," etc., do not limit the quantity or execution order, and that "first," "second," etc., are not necessarily different.

[0087] Third, in the embodiments of this application, descriptions such as "when," "under the circumstances," "if," and "if" all refer to the device making corresponding processing under certain objective circumstances. They are not time limits, nor do they require the device to make a judgment action during implementation, nor do they imply any other limitations.

[0088] Fourth, in the embodiments of this application, the words "exemplary" or "for example" are used to indicate that they are examples, illustrations, or descriptions. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design options. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner to facilitate understanding.

[0089] Fifth, in this application, "sending information" can be understood as one device sending information to another device, or it can also be understood as one logic module within a device sending information to another logic module. For example, "the first network element sending information" can be understood as the first device sending information to another device (such as a community broadcasting center), or it can be understood as logic module 1 in the first network element sending information to logic module 2 in the first network element.

[0090] In this application, "receiving information" can be understood as one device receiving information from another device, or it can also be understood as a logical module within a device receiving information from another logical module. For example, "terminal device receiving information" can be understood as a terminal device receiving information from another device (such as a network device), or it can be understood as logical module 1 in the terminal device receiving information from logical module 2 in the terminal device.

[0091] Sixth, the phrase "sending information to... (e.g., a terminal device)" in this application, or the relevant illustrations in the accompanying drawings, can be understood as the destination of the information being the terminal device. This can include sending information directly or indirectly to the terminal device. The phrase "receiving information from... (e.g., a terminal device)," or "receiving information from... (e.g., a terminal device)," or the relevant illustrations in the accompanying drawings, can be understood as the source of the information being the terminal device. This can include receiving information directly or indirectly from the terminal device. Information may undergo necessary processing between the source and destination, such as format changes, but the destination can understand the valid information from the source. Similar expressions in this application can be understood in a similar way, and will not be elaborated further here.

[0092] For ease of understanding, the following section will first introduce the relevant technologies, concepts, or architectures that may be involved in the embodiments of this application:

[0093] 1. Synthetic data

[0094] Synthetic data, also known as generative or simulated data, refers to data automatically generated by computer programs or algorithms, rather than actually collected from the real world. Synthetic data is not simply a resampling of real data; rather, it is generated through algorithms, making it difficult to trace back to specific samples of the real data.

[0095] Synthetic data is commonly used for various purposes, such as machine learning model training and testing, privacy protection, and data augmentation. Synthetic data provides diversity and a large number of samples, which helps improve the generalization ability of models and avoids privacy leaks when handling sensitive information. For example, in the medical field, synthetic medical records can be created; in autonomous driving, different traffic scenarios can be synthesized. The advantages of synthetic data include:

[0096] 1) High controllability: It can precisely control data features and distribution to meet specific model training requirements;

[0097] 2) Privacy protection: No real personal data is required, reducing legal risks and privacy violations;

[0098] 3) Large data volume: It facilitates rapid expansion of the training set, especially when labeling is difficult or costly.

[0099] 2. Data plane architecture

[0100] The new capabilities such as communication sensing and AI in future communication networks will generate massive amounts of data. This data can come from terminal devices, edge devices, radio (R) access network (AN) devices, and core network (CN), but the 5G user plane is not suitable for carrying this data.

[0101] Therefore, referring to Figure 1, a schematic diagram of a data plane architecture suitable for a communication system is provided. As shown in Figure 1, this data plane architecture includes a data orchestrator (DO), a data controller (DC), a data agent (DA), a data storage function (DSF), and a trust anchor agent (TAA).

[0102] Among them, DO and DC are data orchestrators divided according to the real-time requirements and cross-domain situations of the tasks. DO is responsible for coarse-grained, non-real-time data orchestration, while DC is responsible for fine-grained, real-time orchestration tasks. The collaboration between DO and DC realizes the elasticity and programmability of the data pipeline.

[0103] The Data Access Provider (DO) acts as a portal receiving data service requests and transforming them into combined requests for data pipelines. Furthermore, DO collaborates with other network services; for example, while computing power network services orchestrate computing power, DO orchestrates data. Based on data service requests and the Data Access Provider's (DA) service capabilities, DO enables coarse-grained cross-domain data pipeline orchestration. Simultaneously, DO incorporates a built-in data protection technology repository (DPTR), including technologies such as differential privacy, homomorphic encryption, secure multi-party computation, and zero-knowledge proofs, providing data security and privacy protection capabilities and enabling DA with data protection technology (DPT) as needed.

[0104] Conversely, the Data Center (DC) implements fine-grained Data Allocation (DA) orchestration, combining data pipelines within the local domain based on DA capabilities and data service requests to achieve real-time and efficient service management. Secondly, the DC receives DA capability reports and implements DA registration and revocation functions, enabling real-time monitoring of DAs by monitoring their heartbeats. Furthermore, the DC incorporates a Trust Anchor Client (TAC) to initiate requests for authentication, authorization, and access control mechanisms to the Data Access Provider (TAP), as well as requesting traceability and auditing services for data access. The DC can be deployed on both the RAN and CN sides.

[0105] The Data Acquisition (DA) performs data acquisition, preprocessing, data storage, data analysis, and data sharing services within the data pipeline. Data storage is responsible for the local storage of small amounts of data, short-term data, or data with privacy protection requirements. It can be built into network functions or deployed independently. The DA reports its data service capabilities to the Data Center (DC), which then selects a suitable DA based on the service request and DA capabilities, and implements orchestration. The DO updates the Data Platform Level (DPT) of the DA as needed. The DA provides data services externally through a service application programming interface (API).

[0106] DSF is primarily used as a storage extension component for DA when storing large-scale or long-term data.

[0107] TAA is an independent component defined in the data plane architecture specifically for ensuring data trustworthiness. It is primarily responsible for protecting data confidentiality, integrity, and reliability.

[0108] 3. 5G mobile communication system

[0109] 5G is a new generation of broadband mobile communication technology characterized by high speed, low latency, and massive connectivity. 5G communication facilities are the network infrastructure for realizing the interconnection of humans, machines, and things. Figure 2 shows a schematic diagram of the architecture of a non-roaming 5G system based on a service-oriented interface. This 5G system includes terminal equipment, (R)AN, and CN. The terminal equipment accesses the data network (DN) through AN and CN.

[0110] Terminal equipment can be a terminal device with transceiver functions, or it can be a chip or chip system installed in the terminal device. This terminal equipment can also be referred to as user equipment (UE), access terminal, subscriber unit, user station, mobile station (MS), mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication equipment, user agent, or user device. The terminal devices in the embodiments of this application may be mobile phones, cellular phones, smartphones, tablets, wireless data cards, personal digital assistants (PDAs), wireless modems, handsets, laptop computers, machine-type communication (MTC) terminals, Internet of Things (IoT) terminals, computers with wireless transceiver capabilities, virtual reality (VR) terminals, augmented reality (AR) terminals, smart home devices (e.g., refrigerators, televisions, air conditioners, electricity meters, etc.), smart robots, robotic arms, workshop equipment, wireless terminals in autonomous driving, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical care, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, and wireless terminals in smart homes. The terminal device in this application can be a wireless terminal in the home, an in-vehicle terminal, a roadside unit (RSU) with terminal function, or an aerial device (e.g., an intelligent robot, a hot air balloon, a drone, or an airplane). The terminal device can also be an in-vehicle module, in-vehicle component, in-vehicle chip, or in-vehicle unit built into a vehicle as one or more components or units. The terminal device can also be other devices with terminal function; for example, it can be a device that performs terminal function in device-to-device (D2D) communication.

[0111] The embodiments of this application do not limit the device form of the terminal device. The device used to implement the function of the terminal device can be the terminal device itself; it can also be a device that supports the terminal device in implementing the function, such as a chip system. The device can be installed in the terminal device or used in conjunction with the terminal device. In the embodiments of this application, the chip system can be composed of chips or can include chips and other discrete components.

[0112] An Access Network (AN) is used to implement access-related functions. It can provide network access for authorized users in a specific area and determine different quality transmission links to transmit user data based on user level, service requirements, etc. The AN forwards control signals and user data between the terminal equipment and the Network Controller (CN). The AN may include: access network equipment, also known as access network nodes, RAN nodes, RAN equipment, RAN entities, or access nodes, located on the network side of the aforementioned communication system. It is used to help terminal equipment achieve wireless access and is a device with wireless transceiver capabilities, or a chip or chip system that can be installed in the device.

[0113] The access network equipment includes, but is not limited to: base stations (BS), evolved Node Bs (eNodeB / eNB), access points (AP), transmit / receive points (TRP), next-generation Node Bs (gNB), base stations in future mobile communication systems, or access nodes in wireless fidelity (Wi-Fi) systems. Access network equipment can be macro base stations, micro base stations or indoor stations, relay nodes or donor nodes, open radio access networks (ORAN), or radio controllers in centralized radio access network (CRAN) scenarios. Access network equipment can also be one or a group of antenna panels (including multiple antenna panels) of a 5G base station, or it can be a network node constituting a gNB, TRP, TP, or transmission measurement function (TMF), such as a central unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), a radio unit (RU), or a roadside unit (RSU) with base station functionality. Optionally, access network equipment can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, the access network equipment in vehicle-to-everything (V2X) technology can be an RSU. All or part of the functions of the access network equipment in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (e.g., a cloud platform). The access network equipment in this application can also be a logical node, logical module, or software capable of implementing all or part of the functions of the access network equipment.

[0114] In this network, CU and DU can be configured separately or included in the same network element, such as a baseband unit (BBU). RU can be included in radio frequency equipment or radio frequency units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs). It is understood that access network equipment can be CU nodes, DU nodes, or equipment including both CU and DU nodes. Furthermore, CUs can be classified as network equipment within the RAN or as network equipment within the CN; no restrictions are placed here.

[0115] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software and hardware modules.

[0116] In this application embodiment, the form of the access network device is not limited. The device used to implement the function of the access network device can be the access network device itself; it can also be a device that supports the access network device in implementing the function, such as a chip system. The device can be installed in the access network device or used in conjunction with the access network device.

[0117] The Network Center (CN) is primarily responsible for maintaining the subscription data of the mobile network and providing terminal devices with functions such as session management, mobility management, policy management, and security authentication. The CN mainly includes the following network elements: User Plane Function (UPF), Authentication Server Function (AUSF), Access and Mobility Management Function (AMF), Session Management Function (SMF), Network Slice Selection Function (NSSF), Network Exposure Function (NEF), Network Repository Function (NRF), Policy Control Function (PCF), Unified Data Management (UDM), Unified Data Repository (UDR), Network Data Analytics Function (NWDAF), and Application Function (AF).

[0118] The following is a brief explanation of the network functions (NFs) included in CN.

[0119] 1. UPF: Primarily responsible for user data processing (forwarding, receiving, billing, etc.). For example, a UPF can receive user data from a DN and forward it to the terminal device through the access network equipment. A UPF can also receive user data from the terminal device through the access network equipment and forward it to the DN. In a Protocol Data Unit (PDU) session, a UPF directly connected to the DN via N6 is also called a Protocol Data Unit Session Anchor (PSA).

[0120] 2. AUSF: Primarily used for performing security authentication of terminal devices.

[0121] 3. AMF: Primarily used for mobility management in mobile networks. Examples include user location updates, user network registration, and user handover.

[0122] 4. SMF: Primarily used for session management in mobile networks. This includes session establishment, modification, and release. Specific functions include assigning Internet Protocol (IP) addresses to users and selecting a UPF (User-Defined Provider) to provide packet forwarding capabilities.

[0123] 5. NSSF: Primarily used to select network slices for terminal devices.

[0124] 6. NEF: Primarily used to support the opening of capabilities and events. For example, NEF can expose some capabilities of the 5G network to third-party applications through APIs. Third-party applications can obtain some capabilities of the 5G network by calling the APIs provided by NEF through AF, enabling them to control certain behaviors of the 5G network and terminal devices.

[0125] 7. NRF: Primarily used to provide network element discovery functionality. Based on requests from other network elements, it provides network element information corresponding to the network element type. It also provides network element management services, such as network element registration, updating, deregistration, and network element status subscription and push.

[0126] 8. PCF: Primarily supports providing a unified policy framework to control network behavior, delivering policy rules to control layer network functions, and acquiring user subscription information related to policy decisions. PCF can provide policies to AMF and SMF, such as Quality of Service (QoS) policies and slice selection policies.

[0127] 9. UDM: Primarily used to store user data, such as contract data, authentication / authorization data, etc.

[0128] 10. UDR: Primarily used to store structured data, including contract data, policy data, externally exposed structured data, and application-related data.

[0129] 11. NWDAF: Primarily used to collect data (including data from terminal devices, access network devices, core network elements, and third-party application devices, or one or more of these). This data can be the data itself of the terminal device, access network device, core network element, or third-party application device, or it can be data from the terminal device on the access network device, core network element, or third-party application device. The collected data is then analyzed, and the analysis results are output for network, network management equipment, and application execution strategy decisions. NWDAF can utilize machine learning models for data analysis. The 3rd Generation Partnership Project (3GPP) separates the training and inference functions of NWDAF. An NWDAF can support only model training, only data inference, or both. An NWDAF supporting model training can also be called a training NWDAF, or an NWDAF supporting model training logical function (MTLF) (abbreviated as MTLF). A training NWDAF can train a model based on the acquired data to obtain a trained model. An NWDAF that supports data inference can also be called an inference NWDAF, or an NWDAF that supports analytics logical function (AnLF) (abbreviated as AnLF). An inference NWDAF can input input data into a trained model to obtain analysis results or inference data. In this embodiment, a training NWDAF refers to an NWDAF that at least supports model training. As a possible implementation, a training NWDAF can also support data inference. An inference NWDAF refers to an NWDAF that at least supports data inference. As a possible implementation, an inference NWDAF can also support model training. If an NWDAF supports both model training and data inference, it can be called a training NWDAF, an inference NWDAF, a training-inference NWDAF, or simply an NWDAF. In this embodiment, an NWDAF can be a separate network element or co-located with other network elements, such as being placed in a PCF or AMF.

[0130] 12. Application Provider (AF): This relays the application's requests to the network, such as QoS requirements or user state event subscriptions. AF can be a third-party functional entity or an application server deployed by the operator.

[0131] It should be understood that the above examples illustrate several core network elements included in the CN. In addition, other core network elements may also be included, such as the unified data repository (UDR), which is mainly used to store structured data. The stored content includes contract data and policy data, externally exposed structured data, and application-related data.

[0132] It is understandable that the aforementioned network elements or functions can be physical entities in hardware devices, software instances running on dedicated hardware, or virtualization functions instantiated on a shared platform (e.g., a cloud platform). Simply put, an NF can be implemented in hardware or software.

[0133] A Data Network (DN) is a network located outside of the carrier's network. A carrier's network can connect to multiple DNs, and various services can be deployed on a DN, providing data and / or voice services to terminal devices. For example, a DN might be the private network of a smart factory. Sensors installed in the workshop can act as terminal devices, and a control server for these sensors is deployed within the DN. The control server provides services to the sensors. Sensors can communicate with the control server, receive instructions from it, and transmit the collected sensor data back to the control server accordingly. Another example is a DN serving as the internal office network of a company. Employees' mobile phones or computers can act as terminal devices, accessing information and data resources on the company's internal office network.

[0134] In Figure 2, Nnef, Nnrf, Npcf, Nudm, Nudr, Nnwdaf, Naf, Nausf, Namf, Nsmf, N1, N2, N3, N4, and N6 are interface sequence numbers. For example, the meaning of these interface sequence numbers can be found in the 3GPP standard protocol; this application does not limit the meaning of these interface sequence numbers. It should be noted that the interface names between the various network functions in Figure 2 are merely examples. In specific implementations, the interface names of this system architecture may be other names, which this application does not limit. Furthermore, the names of the messages (or signaling) transmitted between the various network elements are also merely examples and do not constitute any limitation on the function of the messages themselves.

[0135] It should be noted that in the architecture shown in Figure 2, the interface between (R)AN and CN can also be called the NG interface (not shown in Figure 2). (R)AN and CN are connected through the NG interface. The NG interface can include the NG-C interface and the NG-U interface. The NG-C interface is the control plane interface, connecting (R)AN and AMF, and is used to transmit control plane data. The NG-U interface is the user plane interface, connecting (R)AN and UPF, and is used to transmit user plane data.

[0136] It should be understood that AMF, SMF, UPF, NEF, AUSF, NRF, PCF, and UDM shown in Figure 2 can be understood as network elements in the core network used to implement different functions, such as network slices that can be combined as needed. These core network elements can be independent devices or integrated into the same device to implement different functions. This application does not limit the specific form of the above network elements.

[0137] It should also be understood that the above naming is defined solely for the purpose of distinguishing different functions and should not constitute any limitation on this application. This application does not preclude the possibility of using other naming conventions in 5G networks and other future networks.

[0138] In wireless networks, acquiring data faces numerous challenges. Data is the foundation for training wireless models, but wireless scenarios are complex, and the data used for training wireless models is diverse, requiring data from different devices in the network, such as terminal devices, access network devices, and network elements. However, wireless data acquisition is difficult. For example, user data is difficult to obtain and use due to privacy issues; access network device-level data is proprietary and difficult to obtain; network-level southbound data has poor standardization, making acquisition difficult; and a large amount of data generated in the network is highly homogeneous.

[0139] This shows that due to severe data homogenization and user privacy issues, the amount of effective data that the network can obtain for training communication AI models or for sharing with third parties for model training, such as user, network device, and network functions, is relatively small. Therefore, how to solve the problem of insufficient effective data in wireless communication networks is a research topic.

[0140] It should be understood that in the embodiments of this application, the model can be an AI model or a machine learning (ML) model. In some scenarios, AI models and ML models can be used interchangeably. For example, an ML model can also be called an AI model, and this is not a limitation.

[0141] Therefore, this application provides a communication method and apparatus that can generate synthetic data based on existing data in a wireless communication network, expand the effective dataset, and use it for model training, inference, fine-tuning, etc. It can also provide datasets of hidden users for Internet applications (over-the-top, OTT) to use and analyze, in order to create specific data analysis, etc.

[0142] Referring to Figure 3, which is a schematic diagram of the architecture of a communication system provided in an embodiment of this application, it can be applied to the architecture shown in Figures 1 and 2 above. As shown in Figure 3, the communication system includes a first network element, a control function, a data synthesis function, and a first device. The devices can communicate directly or indirectly with each other, and there is no limitation on this.

[0143] In this embodiment, the first network element, acting as the requester of the synthetic data, is used to issue service requirements to the control function and can perform model training, inference, and other related operations based on the requested synthetic data. In this application embodiment, the first network element can be an NF, RAN, or similar element in a wireless communication network; for example, the first network element is an AF.

[0144] The control function is deployed in the wireless communication network to issue control signaling to relevant network elements according to service requirements, triggering each network element to perform actions such as data transmission, storage, collection, and generation of synthetic data, enabling efficient service management of data services. In the embodiments of this application, the control function may also be referred to as a control network element, data control function, data control network element, etc., without limitation. As an example, the control function can be the DC shown in Figure 1 above.

[0145] The synthetic data function is deployed in the wireless communication network to collect data and generate synthetic data based on control signaling issued by the control function, and then provides the synthetic data to relevant network elements. In the embodiments of this application, the synthetic data function may be referred to as a synthetic data network element, synthetic data generation function (SDGF), SDGF network element, data synthesis function, data synthesis network element, etc., and is not limited thereto.

[0146] In one possible design, the data synthesis function can be deployed independently or co-located with a network element (NF) in the network; there is no limitation on this. For example, the data synthesis function can be co-located with a data storage network element (such as the DSF shown in Figure 1 above). In this case, the data storage network element can be considered to include the data synthesis function, or in other words, the data storage network element has the data synthesis function, used to receive data from its own storage repository or data obtained from other NFs, RANs, etc., and can support multiple data synthesis methods, selecting different data synthesis methods according to the data type. Another example is the data synthesis function combined with a network data analysis function (such as the NWDAF mentioned above). In this case, the network data analysis function can be considered to include the data synthesis function, or in other words, it has the data synthesis function, can generate synthetic data based on the data synthesis function, and the network data analysis function can perform model training, inference, and other processing locally based on the synthetic data.

[0147] The first device is an apparatus for providing data for generating synthetic data. It provides the synthetic data function with the data for generating synthetic data according to signaling from a control function or a synthetic data function. In embodiments of this application, the first device can be an NF, RAN, or terminal device in a wireless communication network, and the first device is determined based on the data type of the synthetic data. For example, if the data type of the synthetic data is location data of a terminal device, then the first device can be a data storage network element (such as DSF), a location service network element (such as location-based service (LBS), a terminal device, an access network device, etc.).

[0148] Optionally, the communication system may further include a second device, which can trigger the first device to provide data for generating the composite data based on control signaling issued by the control function or the composite data function. It can be considered that in this scenario, the control function or the composite data function cannot directly trigger the first device to provide data for generating the composite data, but requires the second device to trigger it. In this embodiment, the second device can be an NF, RAN, etc., in the wireless communication network, and the second device is determined according to the type of composite data. For example, if the data type of the composite data is user plane data of the terminal device, then the second device can be a session management network element (such as the SMF in the aforementioned 5G network), and the first device can be a user plane network element (such as the UPF in the aforementioned 5G network).

[0149] The communication method provided in the embodiments of this application will be described in detail below with reference to Figures 4-7.

[0150] For example, Figure 4 is a flowchart illustrating a communication method provided in an embodiment of this application. The communication method is illustrated using the communication between the first network element, control function, data synthesis function, and first device shown in Figure 3 as an example.

[0151] As shown in Figure 4, the communication method includes:

[0152] S401, the first network element sends a third message to the control function.

[0153] Correspondingly, the control function receives a third message from the first network element.

[0154] The third message is used to request synthesized data; that is, the third message is used by the first network element to request synthesized data from the control function.

[0155] For example, the first network element can send a third message to the control function based on business requirements. For instance, if the business requirement is a model training requirement, the first network element can send a third message to the control function to request synthetic data of a specific data type for model training, based on the functionality and accuracy of the model to be trained.

[0156] Optionally, the third message may be a message that has the function of requesting synthetic data. For example, the third message may be a synthetic data request message, or it may be based on an existing message and add a synthetic data request / acquisition instruction to request synthetic data. There is no limitation on this.

[0157] In this embodiment of the application, the third message may include the first network element's requirement information for the requested synthetic data. Specifically, the first network element's requirement information for the requested synthetic data includes the data type of the synthetic data, that is, the third message includes the data type of the synthetic data.

[0158] It should be understood that the third message may also include the identifier of the first network element.

[0159] In wireless communication networks, different types of synthetic data can be generated based on different data types. Different types of synthetic data can be used to train or validate different or the same models. The model can be a wireless model deployed in the wireless communication network or a model deployed outside the wireless communication network, without limitation.

[0160] For example, the data types of the synthesized data include, but are not limited to, the following types: data types related to terminal devices, data types related to access network devices, and data types related to network nodes (NFs).

[0161] Among them, the data types related to terminal devices can further include terminal device location data, terminal device network traffic data, terminal device service experience data, terminal device communication data (including session type, duration, data communication volume, etc.), terminal device network performance data (including signal strength, network latency, throughput, etc.), and so on.

[0162] The data types related to access network equipment can further include reference signal receiving power (RSRP), signal to interference plus noise ratio (SINR), measurement report (MR), minimized drive tests (MDT), load conditions, etc.

[0163] Among them, NF-related data types can further include user session data (including 5-tuples, QoS, etc.), user location data, user authentication information, billing and traffic data, load status, etc.

[0164] Among them, AF-related data types can further include user application data.

[0165] Optionally, the third message may also include key performance indicators (KPIs) of the synthetic data and / or the amount of synthetic data.

[0166] The KPIs for the synthetic data can be used to indicate the data quality requirements of the first network element for the requested synthetic data. For example, the KPIs may include: authenticity and / or diversity.

[0167] The authenticity of synthetic data, also known as the simulation degree or unrealistic degree of synthetic data, is used to characterize how closely the generated synthetic data is statistically close to the real data and can reflect the mathematical or statistical characteristics of the real data. For example, the authenticity requirements / needs for synthetic data can be set by setting thresholds for different dimensions of authenticity. The generated synthetic data is then compared with these thresholds from different dimensions to ensure that the acquired synthetic data meets the threshold requirements for characterizing authenticity.

[0168] The diversity of synthetic data is used to characterize its ability to reflect data features or distributions under various conditions. For example, if the data type of synthetic data is location data from terminal devices, the generated synthetic data can reflect the characteristics of location data under changes in weather, time (morning / evening), etc. Alternatively, a threshold parameter can be set to measure the diversity of synthetic data, and the generated synthetic data can be compared with this threshold to ensure that the acquired synthetic data meets the threshold requirements.

[0169] For example, authenticity can be characterized by similarity, which measures how close synthetic data is to real data. The higher the similarity, the higher the authenticity of the synthetic data. By setting a similarity threshold, such as 95% to 98%, the authenticity requirement for synthetic data can be represented. Diversity can be characterized by the number of data features. Different data features correspond to data generated under different circumstances. By setting a threshold for the number of data features, the diversity requirement for synthetic data can be represented.

[0170] The data volume of the synthesized data is used to indicate the first network element's requirement for the amount of synthesized data requested or the size of the dataset. For example, the data volume requirement for the synthesized data can also be indicated by setting a data volume threshold, and the synthesized data generation function can generate synthesized data that meets the threshold requirement based on the data volume threshold.

[0171] In this embodiment of the application, the synthetic data may also be referred to as the synthetic dataset, and there is no limitation thereto.

[0172] It should be understood that the above examples illustrate several types of first network element requirements for synthetic data. In addition, the requirements information may also include other requirements for synthetic data, such as the required time from requesting synthetic data to receiving feedback synthetic data, which is not limited thereto.

[0173] S402, The control function sends a first message to the synthetic data function based on the third message.

[0174] Correspondingly, the data synthesis function receives the first message from the control function.

[0175] Furthermore, after receiving the third message, the control function can determine whether to generate synthetic data based on the third message. Then, the control function sends the first message to the synthetic data function to trigger the synthetic data function to generate synthetic data.

[0176] The first message is used to trigger the generation of synthetic data.

[0177] Optionally, the first message can be a message that itself has the function of triggering the generation of synthetic data. For example, the first message can be a message used to request the generation of synthetic data or a message used to notify the generation of synthetic data; or the first message can be based on an existing message with an instruction to generate synthetic data, which is not limited.

[0178] The first message can be determined based on the third message. For example, if the third message includes the data type of the synthesized data, then the first message also includes the data type of the synthesized data.

[0179] Optionally, the control function further determines the method for generating the synthetic data based on the data type of the synthetic data in the third message. In this case, the first message may also include the method for generating the synthetic data.

[0180] The method for generating synthetic data can be understood as a method determined or recommended by the control function for generating synthetic data.

[0181] For example, methods for generating synthetic data include, but are not limited to, the following: recurrent neural network (RNN), generative adversarial network (GAN), large language model (LLM), etc.

[0182] It should be noted that the control function can determine the method for generating synthetic data based on the data type in various ways. This application does not limit this method, and only two possible implementation methods are given below as examples.

[0183] Implementation Method 1: The control function has a local configuration that corresponds to the data types and the methods for generating synthetic data. That is, different data types are configured with different methods for generating synthetic data. The control function determines the method for generating synthetic data of that data type based on the correspondence and the data type of the received synthetic data.

[0184] For example, the correspondence between data types and methods for generating synthetic data is configured in the form of a list, which may include: the correspondence between location data and RNN, the correspondence between traffic data and GNN, and so on.

[0185] In some implementations, a data type of synthetic data can correspond to multiple (two or more) methods for generating synthetic data of that data type. In this case, the control function can carry all the methods for generating synthetic data of the corresponding data type in the first message, or it can select one or more of the methods for generating synthetic data of that data type and carry the selected method for generating synthetic data in the first message. There is no limitation on this.

[0186] Implementation Method 2: The control function is locally configured with a model for determining the method of generating synthetic data. By inputting the data type of the synthetic data into the model, the method for generating synthetic data of that data type is obtained.

[0187] It should be noted that when the third message also includes the KPI of the synthetic data and / or the data volume of the synthetic data, the control function can determine the method for generating the synthetic data not only based on the data type of the synthetic data, but also by combining at least one of the KPI and the data volume of the synthetic data. In other words, the control function can determine the method for generating the synthetic data based on at least one of the KPI and the data volume of the synthetic data, as well as the data type of the synthetic data. Similar to determining the method for generating synthetic data based on the data type, the control function can also be configured with a correspondence between the data type, KPI, data volume, and the method for generating the synthetic data, or it can take the data type, KPI, and data volume as model inputs and output the method for generating the synthetic data; the specific implementation is not limited.

[0188] It should be noted that, in cases where the third message also includes the KPI of the synthetic data and / or the amount of synthetic data, in some implementations, the method for generating synthetic data may not depend on the data type of the synthetic data, but may be determined based on at least one of the KPI and the amount of synthetic data. No limitation is imposed on this.

[0189] Optionally, the control function carries the KPIs of the synthesized data, and / or the amount of synthesized data, as well as the method of generating the synthesized data, in the first message. In this case, in addition to the data type of the synthesized data and the method of generating the synthesized data, the first message may also include the KPIs of the synthesized data and / or the amount of synthesized data.

[0190] Furthermore, the first message may not include a method for generating the synthetic data. In this case, the method for generating the synthetic data can be determined by the synthetic data function, for example, by the synthetic data function based on the first message. The first message may also include parameters for determining the method for generating the synthetic data, such as the KPI of the synthetic data and / or the amount of synthetic data. Specifically, if the third message also includes the KPI of the synthetic data and / or the amount of synthetic data, the first message may also include the KPI of the synthetic data and / or the amount of synthetic data.

[0191] Furthermore, the control function can also determine the first or second device based on the data type of the synthetic data in the third message.

[0192] The first device is a means for providing data for generating synthetic data to a synthetic data function in a wireless communication network, and the second device is a means for providing data for generating synthetic data to the synthetic data function based on a message triggered by a control function. For example, the device types of the first and second devices can be network equipment (NF), terminal devices, or access network devices, etc., and there is no limitation thereto.

[0193] For example, the control function can be locally configured with a correspondence between the data types of the synthesized data and the first and second devices, and this correspondence can also be stored in the form of a list. That is, for each data type of synthesized data, there is a first device capable of providing data of the corresponding data type for generating the synthesized data, and a second device that triggers the first device to provide data of the corresponding data type for generating the synthesized data. Thus, the control function can determine from which first device to request data, or through which second device to trigger the first device to provide data, based on the data type. It should be understood that one data type can correspond to multiple first devices or multiple second devices. The control function can select at least one first device from multiple first devices, or at least one second device from multiple second devices, to collect data for generating the synthesized data.

[0194] Data of any type in a wireless communication network (including data used to generate composite data and data not used to generate composite data) can be stored in a data storage network element (such as the DSF shown in Figure 1 above). Therefore, the first device can be a data storage network element. Depending on the data type, the first device can also be a terminal device, an access network device, a location service network element, or a user plane network element. For example, if the composite data is location data of a terminal device, then the first device can be a data storage network element, a terminal device, a location service network element (such as LBS mentioned above), or an access network device accessed by the terminal device. As another example, if the composite data is user traffic data, then the first device can be a data storage network element, a terminal device, or a user plane network element.

[0195] For the second device, when the control function cannot directly request data for generating the composite data from the first device, the control function can indirectly trigger the first device to provide data for generating the composite data through the second device. For example, when the data type of the composite data is user plane data of the terminal device (such as user traffic data), and the user plane data of the terminal device includes data types transmitted by the terminal device through user plane network elements, the control function cannot directly request user plane data for generating the composite data from the user plane network elements. Instead, it triggers the user plane network elements to provide data for generating the composite data to the composite data function through a session management network element (such as the aforementioned SMF). In this case, the second device can be a session management network element, and the first device can be a user plane network element or a terminal device.

[0196] After determining the first device or the second device, the control function may also carry information for instructing the first device or the second device in the first message. Further, the data synthesis function may trigger the first device to provide data for generating the synthesized data based on the information for instructing the first device, or trigger the second device based on the information for instructing the second device, which in turn triggers the first device to provide data for generating the synthesized data.

[0197] For example, the information used to indicate the first device can be the identifier of the first device, and the information used to indicate the second device can be the identifier of the second device.

[0198] In other words, the first message may also include information for instructing the first device or information for instructing the second device.

[0199] In a possible design where the control function does not carry information for instructing the first device or the second device in the first message, the control function may send a fourth message to the first device or the second device based on the third message, and the first device or the second device shall receive the third message from the control function accordingly.

[0200] Specifically, when a fourth message is sent to the first device, the fourth message is used to trigger the first device to provide data for generating synthetic data to the synthetic data function; when a fourth message is sent to the second device, the fourth message is used to trigger the second device to trigger the first device to provide data for generating synthetic data to the synthetic data function.

[0201] For the design of the fourth message, please refer to the descriptions of the first and third messages above. For example, the fourth message is a message used to request the first device to provide data for generating synthetic data to the synthetic data function.

[0202] In this design, after determining the first or second device based on the data type of the synthesized data in the third message, the control function directly sends a fourth message to the first or second device. At this point, the synthesized data function can directly receive the first data from the first device used to generate the synthesized data, without needing to request it from the first or second device. In other words, the control function can directly trigger the first or second device through the fourth message to provide the synthesized data function with the data used to generate the synthesized data, without requiring the synthesized data function to trigger it. After receiving the first message, the synthesized data function simply waits for the data from the first device to generate the synthesized data and then generates the synthesized data.

[0203] The fourth message may include the data type of the synthesized data and second information, the second information being used to indicate that data for generating the synthesized data should be provided to the synthesized data function. Optionally, the fourth message may also include first information, which corresponds to the data used to generate the synthesized data. The first information may be determined based on the first device, as described below.

[0204] The first information can be used to index the data used to generate synthetic data of the corresponding data type. Whether the fourth message carries the first information is determined by the control function based on the type or function of the first device. For example, for a first device with data storage function, it collects various types of data storage from various devices or NFs in the network and needs to distinguish the stored data through the first information. For a first device that generates data, it can be understood as the data generator, so it can distinguish the reported data based on the data type and does not need the first information to distinguish it.

[0205] For example, for a first device with data storage functionality, such as a data storage network element, the first device can locally store a correspondence between data used to generate synthetic data and first information. Different data types of data used to generate synthetic data are associated with different first information; for example, the first information might be an index of the synthetic data. Furthermore, since some data locally stored in the first device may not be usable for generating synthetic data, while some data may be usable but of the same data type, a correspondence also exists between the data type of the synthetic data and the first information, as well as the data used to generate the synthetic data. Therefore, the first device can uniquely determine the data that can generate the corresponding data type and is used to generate the synthetic data based on the data type of the synthetic data and the first information. For example, the correspondence stored locally in the first device includes the data type (key1), the index of the synthetic data (i.e., the first information, key2), and the data used to generate the synthetic data. It should be understood that this correspondence may also include other parameters, which are not limited thereto.

[0206] The second information can be used to instruct the data receiver or data consumer to use the data synthesis function. Specifically, the second information may include an identifier for the data synthesis function, such as its IP address or port number, for transmitting data to the data synthesis function.

[0207] Optionally, if the third message includes the data type and volume of the synthesized data, or if the third message includes the data type, volume, and KPIs of the synthesized data, the fourth message may also include the amount of data used to generate the synthesized data. The amount of data used to generate the synthesized data may refer to the size of the data requested from the first device for generating the synthesized data; specifically, the amount of data used to generate the synthesized data may be a range or a threshold. Further, the first device may provide data within the range or satisfying the threshold for generating the synthesized data; this is not limited.

[0208] When the third message includes the data type and data volume of the synthetic data, the control function can determine the method for generating the synthetic data based on the data type and data volume of the synthetic data, and thus determine the data volume used to generate the synthetic data based on the data volume and the method for generating the synthetic data, or determine the data volume used to generate the synthetic data based on the data volume, the method for generating the synthetic data, and the data type of the synthetic data.

[0209] For example, similar to the implementation of the method for determining the generation of synthetic data described above, the control function is locally configured with a correspondence between the amount of synthetic data, the method for generating synthetic data, and the amount of data used to generate synthetic data; or it is locally configured with a correspondence between the amount of synthetic data, the method for generating synthetic data, the data type of synthetic data, and the amount of data used to generate synthetic data. Thus, the control function can determine the amount of data used to generate synthetic data based on this correspondence, the determined method for generating synthetic data, and the received amount of synthetic data and / or the data type of synthetic data. As another example, the control function is locally configured with a model for determining the amount of data to generate synthetic data. By inputting the method for generating synthetic data, the amount of synthetic data, and / or the data type of synthetic data into this model, the amount of data used to generate synthetic data is obtained.

[0210] When the third message includes the data type, data volume, and KPIs of the synthesized data, the control function can determine the method for generating the synthesized data based on these parameters. Conversely, it can determine the amount of data used to generate the synthesized data based on the data volume, generation method, and KPIs. For a detailed implementation example, please refer to the above example; further details will not be provided here.

[0211] It should be understood that the mandatory parameters for determining the amount of data used to generate the synthetic data are the amount of data used to generate the synthetic data and the method for generating the synthetic data. For other optional parameters, it depends on the parameter type carried in the third message.

[0212] S403, The first device sends the first data to the synthetic data function.

[0213] Correspondingly, the data synthesis function receives first data from the first device.

[0214] There are three possible designs for how the first device triggers the sending of the first data to the synthetic data function:

[0215] Design 1: The first device sends first data to the synthetic data function based on the triggering of the control function.

[0216] As described in S402 above, after receiving the third message, the control function can determine the first device based on the third message and send the fourth message to the first device, which will not be elaborated here. In this design 1, after receiving the fourth message, the first device can determine the first data that can generate the corresponding data type of synthetic data based on the data type of the synthetic data in the fourth message and the first information, and then send the first data to the synthetic data function based on the second information.

[0217] Optionally, the first data is carried in the response message of the fourth message and sent.

[0218] Design 2: The first device sends first data to the synthetic data function based on the triggering of the synthetic data function.

[0219] In this design 2, after receiving the first message, the data synthesis function can determine the first device based on the first message. For example, the data synthesis function can determine the first device based on the data type of the synthesized data in the first message; the implementation process is similar to that of the control function determining the first device described above, and will not be repeated here. As another example, if the first message includes information indicating the first device, the data synthesis function can determine the first device based on that information.

[0220] Therefore, the data synthesis function can send a second message to the first device, and correspondingly, the first device receives the second message from the data synthesis function. The second message can be used to trigger the first device to provide data to the data synthesis function for generating the synthesized data. Specifically, the second message may include the data type of the synthesized data. Optionally, the second message may also include first information and / or second information. Specific descriptions of the first and second information can be found in the first and second information in the fourth message described above, and will not be repeated here.

[0221] Optionally, the second message may also include the amount of data used to generate the synthetic data.

[0222] When the first message includes the data type and volume of the synthesized data, the data synthesis function can determine the method for generating the synthesized data based on the data type and volume of the synthesized data, and thus determine the amount of data used to generate the synthesized data based on the volume of the synthesized data and the method for generating the synthesized data. Alternatively, when the first message includes the data type, method for generating the synthesized data, and volume of the synthesized data, the data synthesis function can determine the amount of data used to generate the synthesized data based on the volume of the synthesized data, the method for generating the synthesized data, and the data type of the synthesized data.

[0223] If the first message also includes the KPIs for the synthesized data, the data synthesis function can further determine the amount of data used to generate the synthesized data based on these KPIs. In other words, the data synthesis function can determine the amount of data used to generate the synthesized data based on the data volume, the method used to generate the synthesized data, and the KPIs for the synthesized data. Alternatively, the data synthesis function can determine the amount of data used to generate the synthesized data based on the data volume, the method used to generate the synthesized data, the data type of the synthesized data, and the KPIs for the synthesized data.

[0224] It should be understood that the process by which the synthetic data function determines the amount of data used to generate the synthetic data is similar to the process by which the control function determines the amount of data used to generate the synthetic data, and will not be elaborated upon here.

[0225] Therefore, the first device can determine the first data that can generate the corresponding data type of the synthesized data based on the data type of the synthesized data in the second message, or it can determine the first data that can generate the corresponding data type of the synthesized data based on the data type of the synthesized data and the first information, and then send the first data to the synthesized data function.

[0226] Optionally, the first data may be sent in the response message of the second message.

[0227] Design 3: The first device sends first data to the synthetic data function based on the triggering of the second device.

[0228] In this design 3, the control function or the data synthesis function determines that it cannot directly request data from the first device based on the data type of the synthesized data. At this time, the control function or the data synthesis function can determine the second device based on the data type of the synthesized data, and send information to the second device so that the second device triggers the first device to provide data for generating the synthesized data based on the information. That is, the control function indirectly triggers the first device to provide data for generating the synthesized data through the second device.

[0229] When the control function indirectly triggers the first device to provide data for generating synthetic data through the second device, the control function can send a fourth message to the second device, and the second device receives the fourth message from the control function. In this case, the fourth message is used by the second device to trigger the first device to provide data for generating synthetic data to the synthetic data function. The fourth message may include the data type of the synthetic data and second information. Optionally, the fourth message may also include first information and / or the amount of data used to generate the synthetic data; for details, please refer to the foregoing description, which will not be repeated here.

[0230] Therefore, the second device can determine the first device based on the data type of the synthesized data in the fourth message, and send a sixth message to the first device. Correspondingly, the first device receives the sixth message from the second device. The sixth message triggers the first device to provide data for generating the synthesized data to the synthesized data function. The sixth message includes the data type of the synthesized data and second information. Optionally, if the fourth message includes the first information and / or the amount of data used to generate the synthesized data, the sixth message may also include the first information and / or the amount of data used to generate the synthesized data.

[0231] When the data synthesis function indirectly triggers the first device to provide data for generating the synthesized data via the second device, similar to the implementation of the control function described above, the data synthesis function can send a second message to the second device, and correspondingly, the second device receives the second message from the data synthesis function. In this case, the second message can be used by the second device to trigger the first device to provide data for generating the synthesized data to the data synthesis function. Specifically, the second message may include the data type of the synthesized data and second information. Optionally, the second message may also include first information and / or the amount of data used to generate the synthesized data.

[0232] Therefore, the second device can determine the first device based on the data type of the synthesized data in the second message, and send a sixth message to the first device. Correspondingly, the first device receives the sixth message from the second device. The sixth message triggers the first device to provide data for generating the synthesized data to the synthesized data function. The sixth message includes the data type of the synthesized data and second information. Optionally, if the second message includes the first information and / or the amount of data used to generate the synthesized data, the sixth message may also include the first information and / or the amount of data used to generate the synthesized data.

[0233] In both of the above cases, the first device can determine the first data that can generate the corresponding data type of the synthesized data based on the data type of the synthesized data in the sixth message, or it can determine the first data that can generate the corresponding data type of the synthesized data based on the data type of the synthesized data and the first information, and then send the first data to the synthesized data function based on the second information.

[0234] For Design 3, in a specific example scenario where the data type of the synthesized data is user plane data of the terminal device, the second device is a session management network element and the first device is a user plane network element. In this case, how the session management network element triggers the user plane network element to provide user plane data from the terminal device used to generate the synthesized data, based on control functions or the synthesized data function, is implemented as follows:

[0235] The session management network element receives a fifth message, which triggers the provision of user plane data of the terminal device used to generate synthetic data to the synthetic data function. The fifth message includes the data type of the synthetic data, wherein the data type of the synthetic data is the user plane data of the terminal device.

[0236] Optionally, the fifth message may further include at least one of the following: first information, second information, or the amount of data used to generate synthetic data, wherein there is a correspondence between the first information and the data used to generate synthetic data, and the second information is used to instruct the synthetic data function to provide user plane data of the terminal device used to generate synthetic data.

[0237] When the session management network element receives the fifth message from the synthetic data function, the fifth message is the second message mentioned above. When the session management network element receives the fifth message from the control function, the fifth message is the fourth message mentioned above. Therefore, for a detailed description of the fifth message, please refer to the relevant descriptions of the second or fourth message mentioned above, which will not be repeated here.

[0238] After the session management network element receives the fifth message, there are two possible design schemes:

[0239] In one possible design scheme 1, the session management network element sends a sixth message to the user plane network element based on the fifth message, and the user plane network element receives the sixth message from the session management network element accordingly.

[0240] The sixth message is used to trigger the user plane network element to provide the user plane data of the terminal device used to generate the synthetic data to the synthetic data function.

[0241] In other words, based on the fifth message, the session management network element can determine that the first device capable of providing data for generating synthetic data to the synthetic data function is a user plane network element. Then, the session management network element can send a sixth message to the user plane network element to trigger it to provide the corresponding data to the synthetic data function. For example, the sixth message is an open subscription message, used to instruct the user plane network element to open a subscription for the corresponding data type used to generate synthetic data to the synthetic data function.

[0242] In this design scheme 1, the sixth message includes the data type of the synthesized data and second information. Therefore, the user plane network element can determine the user plane data of the terminal device based on the data type of the synthesized data, and then send the user plane data of the terminal device to the synthesized data function according to the second information. At this time, the user plane data of the terminal device provided by the user plane network element to the synthesized data function for generating the synthesized data can be offline cached data.

[0243] Optionally, the sixth message also includes the amount of data used to generate the composite data. Then, the user plane network element can determine the user plane data of the terminal device based on the type of composite data and the amount of user plane data used by the terminal device to generate the composite data.

[0244] In one possible design scheme 2, the session management network element sends QoS rules to the terminal device according to the fifth message. Correspondingly, the terminal device receives the QoS rules from the session management network element. The QoS rules include a first QoS flow ID (QFI), which corresponds to a synthetic data function. Then, the terminal device sends data packets to the user plane network element, which receives the data packets from the terminal device. These data packets carry the first QFI and the terminal device's user plane data.

[0245] This QoS rule instructs the terminal device to encapsulate data from the first QFI and the first IP together. The first IP refers to the application IP accessed by the terminal device. According to this QoS rule, the terminal device can encapsulate data with the application IP as the first IP and the first QFI together into a data packet for transmission. The data packet includes the first QFI, the first IP, and the terminal device's user plane data (application access data). It should be understood that the QoS rule also includes 5-tuple information, which includes the source IP, destination IP, data transmission protocol type, source port, and destination port.

[0246] For example, the correspondence between the first QFI and the synthetic data function is the correspondence between the identifier or IP of the first QFI and the synthetic data function.

[0247] In this design scheme 2, the session management network element can send the mapping relationship between the first QFI and the composite data function to the user plane network element. Correspondingly, the user plane network element receives the mapping relationship between the first QFI and the composite data function from the session management network element. For example, the session management network element can send the mapping relationship between the first QFI and the composite data function to the user plane network element during session establishment. This mapping relationship can be carried in the forwarding action rule (FAR). It should be understood that, in addition to sending user plane data from the terminal device to the composite data function, the user plane network element can also send data to the application server located in the DN accessed by the terminal device.

[0248] The correspondence between the first QFI and the synthetic data function is used to instruct the user plane network element to provide the synthetic data function with user plane data of the terminal device used to generate synthetic data, or in other words, to instruct the user plane network element to send the data packet carrying the first QFI to the synthetic data function.

[0249] After receiving the data packet, the user plane network element can determine, based on the correspondence between the first QFI and the synthetic data function, whether the data in the data packet is the data to be sent to the synthetic data function for generating synthetic data, and thus send the data packet, or the user plane data of the terminal device in the data packet, to the synthetic data function.

[0250] It should be understood that there is also a correspondence between the first QFI and the data type of the synthesized data. In other words, the first QFI is used to instruct the synthesized data function to send data of a specified data type used to generate the synthesized data. At this time, the user plane data provided by the user plane network element to the synthesized data from the terminal device used to generate the synthesized data can be the user's online data.

[0251] S404. The data synthesis function generates first synthesized data based on the first message and the first data.

[0252] The first synthetic data can be used for model training and / or inference. For example, it can be used for model training and inference in network NFs, access network devices, etc., or it can be made available to third-party devices for model training and inference. There are no restrictions here.

[0253] In this embodiment of the application, the data synthesis function can determine the method for generating data synthesis based on the first message, and generate the first data synthesis based on the method for generating data synthesis and the first data.

[0254] The data synthesis function determines the method for generating synthesized data based on the first message. Based on the design of the first message in S402 above, there are several possible implementations:

[0255] If the first message includes a method for generating synthetic data, the synthetic data function can process the received first data and generate first synthetic data according to the method for generating synthetic data indicated in the first message.

[0256] If the first message includes the data type of the synthesized data but not the method for generating the synthesized data, the data synthesis function can determine the method for generating the synthesized data based on the data type of the synthesized data in the first message. The specific implementation is similar to the implementation of the control function described above, and will not be elaborated further. If the first message also includes the KPI of the synthesized data and / or the data volume of the synthesized data, the data synthesis function can determine the method for generating the synthesized data based on at least one of the KPI and the data volume of the synthesized data, as well as the data type of the synthesized data. The specific implementation is similar to the implementation of the control function described above, and will not be elaborated further.

[0257] It should be understood that the first synthetic data of the corresponding data type generated based on the determined method for generating synthetic data should meet the requirements of the KPIs and the amount of synthetic data.

[0258] Optionally, the data synthesis function also sends first synthesized data to the third device, and correspondingly, the third device receives the first synthesized data from the data synthesis function.

[0259] The third device may be any of the following: a device for storing the first synthetic data, a device for using the first synthetic data for model training and / or inference, or a device for providing the first synthetic data to a third-party device.

[0260] For example, the means for storing the first synthetic data can be a data storage network element, the means for using the first synthetic data for model training and / or inference can be a first network element requesting synthetic data, or other network elements in the wireless communication network, such as a data analysis network element (such as the NWDAF mentioned above), and the means for opening the first synthetic data to a third-party device can be a network opening network element (such as the NEF mentioned above).

[0261] In the communication method shown in Figure 4, the data synthesis function can obtain data for generating synthetic data from the first device based on the first message sent by the control function to trigger the generation of synthetic data, thereby generating the first synthetic data. Thus, synthetic data can be generated from existing data in a wireless communication network, expanding the effective dataset in the wireless communication network for training, inference, and fine-tuning of large-scale communication models within the network. Alternatively, the synthetic data can be made available to third-party devices or internet applications for use and analysis, addressing the problem of insufficient effective data due to privacy concerns.

[0262] The communication method shown in Figure 4 will be illustrated with specific examples in the following scenarios.

[0263] Taking the data type of the synthesized data as UE location data, the first network element as AF, the control function as DC, the data synthesis function as SDGF, and the first device as DSF, LBS, or UE, as an example, Figure 5 shows a flowchart of an example communication method provided by an embodiment of this application.

[0264] As shown in Figure 5, the communication method includes:

[0265] S501 and AF send a request for composite data to DC.

[0266] Correspondingly, the DC receives a request for synthesized data from the AF.

[0267] Among them, the synthetic data request is an example message of the third message mentioned above. The synthetic data request is used to request synthetic data. The synthetic data request includes the data type of the synthetic data (UE location data), the KPI of the synthetic data, and the data volume of the synthetic data.

[0268] Please refer to the third message above; it will not be repeated here.

[0269] S502 and DC send a request to SDGF to generate synthetic data.

[0270] Correspondingly, SDGF receives requests for generated synthetic data from DC.

[0271] The "Generate Synthetic Data Request" is an example message of the first message mentioned above. The "Generate Synthetic Data Request" is used to request the generation of synthetic data. The request includes the data type of the synthetic data (UE location data), the method for generating the synthetic data (RNN), and the amount of synthetic data. If the first device is a UE, the amount of synthetic data can be replaced by a duration. The duration indicates the amount of data used to generate the synthetic data (i.e., the amount of UE location data), referring to the amount of data the UE is required to report within that duration for generating the synthetic data. The amount of data reported within that duration is the amount of data used to generate the synthetic data.

[0272] DC can determine the method for generating synthetic data based on the data type (UE location data), KPIs, and data volume of the synthetic data in the synthetic data request. For example, for UE location data, the method for generating synthetic data can be RNN.

[0273] Optionally, the DC also determines a first device, such as DSF, LBS, or UE, for providing data to generate the synthetic location data of the UE, based on the data type of the synthetic data (UE location data). Therefore, the request to generate synthetic data may also include an identifier of the first device (corresponding to the information used to indicate the first device as described above).

[0274] To determine which UE's location data to generate the composite location data from, the Data Center (DC) can send a consent request to each UE in the network based on the composite data request. This consent request requests the UE to allow / agree to provide its location data. The consent request may include the data type (UE's location data), expected incentives, and risk level. Expected incentives indicate the reward for agreeing to provide data to the UE, such as points or call credit rewards. The risk level indicates the extent to which the object requesting the UE's consent can obtain the data. For example, risk levels include A, B, and C, with risk increasing sequentially. A indicates the object can obtain the specific content of the data, B indicates the object can see the data's metadata—basic attributes, and C indicates the object can only obtain the data type.

[0275] Therefore, the UE can determine whether to agree to provide location data based on the UE consent request, and send a UE consent response to the DC. If consent is granted, the DC can request to obtain the UE's location data.

[0276] Alternatively, the results regarding whether a UE agrees to provide location data can be stored in a UDR, UDM, or unstructured data storage function (UDSF). The DC can also directly obtain information from the UDR or UDSF about which UEs agree to provide location data, without any limitation.

[0277] Therefore, the DC can choose which UE's location data to obtain in order to acquire composite data.

[0278] The following describes how the DC triggers the first device to send the UE's location data to the SDGF:

[0279] The location data of the UE triggered by the DC will be explained with DSF, LBS and UE as the first devices respectively.

[0280] S503-A1, DC sends UE data transmission request to DSF.

[0281] Accordingly, the DSF receives data transmission requests from the DC for the UE.

[0282] The UE data transmission request is an example of the fourth message mentioned above. The UE data transmission request is used to request the UE's location data for generating synthetic data. The UE data transmission request includes the UE ID, synthetic data ID, data type of synthetic data (UE's location data), data consumer (SDGF ID), and the amount of data used to generate the synthetic data. The UE ID can be a subscription concealed identifier (SUCI) or a subscription permanent identifier (SUPI). There is a correspondence between the synthetic data ID, the data type of synthetic data, and the data used to generate the synthetic data. The synthetic data ID is used to index the data used to generate the synthetic data and corresponds to the first information mentioned above. The data consumer is used to instruct the DSF or LBS to provide data to the SDGF and corresponds to the second information mentioned above.

[0283] S504-A1 and DSF send UE location data to SDGF.

[0284] Correspondingly, SDGF receives UE location data from DSF.

[0285] The UE's location data corresponds to the first data mentioned above. The data stored locally by the DSF can be in the form of: key1 for the synthetic data ID, key2 for the data type, key3 for the UE ID, and the payload is the data content that the UE transmits according to its own privacy level, that is, the data part that can be used to generate synthetic data. Therefore, the DSF can determine the UE's location data used to generate synthetic data based on the data type and synthetic data ID of the synthetic data, and then determine the UE's location data to be sent to the SDGF for generating synthetic data based on the data consumer.

[0286] At this time, the UE location data reported by DSF can be offline data.

[0287] Alternatively, S503-A1 to S504-A1 can be replaced with S503-A2 to S504A2:

[0288] S503-A2 and DC send UE data transmission requests to LBS.

[0289] Accordingly, LBS receives UE data transmission requests from DC.

[0290] S504-A2 and LBS send UE location data to SDGF.

[0291] Correspondingly, SDGF receives location data from LBS for the UE.

[0292] The implementation process of S503-A2 to S504A2 is similar to that of S503-A1 to S504-A1, except that the UE data transmission request may or may not carry the composite data ID, and there is no restriction on this.

[0293] Alternatively, S503-A1 to S504-A1 can be replaced with S503-A3 to S504-A3:

[0294] S503-A3, DC sends a UE data transmission request to the UE.

[0295] Accordingly, the UE receives a UE data transmission request from the DC.

[0296] The UE data transmission request may include the UE ID, the data type of the synthesized data (UE location data), the data consumer (SDGF ID), and the duration. The duration can be found in the relevant description in S502 above.

[0297] It should be understood that the DC can send UE data transmission requests to the UE through the RAN equipment.

[0298] S504-A3, the UE sends its location data to the SDGF.

[0299] Accordingly, SDGF receives UE location data from the UE.

[0300] The UE can report online real-time or offline location data to the SDGF based on the type of synthetic data in the UE data transmission request.

[0301] It should be understood that the UE can also send location data to the LBS and DSF for storage, and the SDGF can obtain the UE's location data from the DSF as described in S503-A1 to S504-A1, or obtain the UE's location data from the LBS as described in S503-A2 to S504A2.

[0302] Of course, the SDGF can also trigger the first device to send the UE's location data to the SDGF. The implementation process for the SDGF to trigger the request for UE data is similar to that of the DC. The difference from the DC is that since the SDGF directly triggers the request, the UE's data transmission request does not need to carry the data consumer. This will not be elaborated further.

[0303] S505 and SDGF generate location-related synthetic data based on the method for generating synthetic data and the UE's location data.

[0304] The SDGF processes the received UE location data according to the method for generating synthetic data (RNN) indicated in the request to generate synthetic data in S502, and generates location-related synthetic data (corresponding to the first synthetic data mentioned above).

[0305] For example, as shown in Figure 6, the UE's location data (D) includes dwell trajectory data marked by home and work locations. By inputting the UE's location data into an RNN model, synthetic location data (S) can be generated, which includes more dwell trajectory data.

[0306] S506 and SDGF send location-related synthetic data to AF via NEF.

[0307] Accordingly, AF receives location-related synthetic data from SDGF via NEF.

[0308] Therefore, SDGF can generate location-related synthetic data based on existing online or offline location data that can be obtained within the network, thereby expanding the effective dataset.

[0309] Taking the data type of the synthesized data as UE traffic data, the first network element as AF, the control function as DC, the data synthesis function as SDGF, the first device as UPF, and the second device as SMF as an example, Figure 7 shows a schematic flowchart of an example communication method provided in an embodiment of this application.

[0310] As shown in Figure 7, the communication method includes:

[0311] S701 and AF send a request for composite data to DC.

[0312] Correspondingly, the DC receives a request for synthesized data from the AF.

[0313] S702 and DC send a request to SDGF to generate synthetic data.

[0314] Correspondingly, SDGF receives requests for generated synthetic data from DC.

[0315] The difference between this and S501 and S502 is that the data type of the synthesized data carried in the synthesized data request and the synthesized data generation request is UE traffic data. The method for generating synthesized data in the synthesized data generation request also varies depending on the data type, such as GAN. The implementation of S701 and S702 can be found in the relevant implementation descriptions in S501 and S502 above, and will not be repeated here.

[0316] The SDGF can determine the UPF that provides traffic data to the UE based on the data type of the synthetic data in the synthetic data request. However, the SDGF cannot directly request the UE's traffic data from the UPF and needs to be triggered by the SMF. Therefore, the SDGF indirectly triggers the UPF to provide the UE's traffic data through the SMF.

[0317] S703 and SDGF send UE data transmission requests to SMF.

[0318] Correspondingly, the SMF receives UE data transmission requests from the SDGF.

[0319] The UE data transmission request is an example of the second message mentioned above. The UE data transmission request includes the UE ID, the data type of the synthetic data (UE traffic data), and the amount of data used to generate the synthetic data.

[0320] S704, SMF sends an event open subscription (Nupf_EventExposure_Subscribe) to UPF.

[0321] Correspondingly, UPF receives open subscriptions to events from SMF.

[0322] Based on the UE's data transmission request, the SMF determines that the SDGF needs to subscribe to the UE's traffic data from the UPF, and thus sends an event open subscription to the UPF. The event open subscription is an example of the sixth message mentioned above, and includes the UE ID, the subscribed NF ID (SDGF ID), the subscribed data type (UE's traffic data), and the subscribed data volume. The subscribed data type is the data type used to generate the composite data, and the subscribed data volume is the amount of data used to generate the composite data.

[0323] S705, UPF sends an event exposure notification (Nupf_EventExposure_Notify) to SDGF.

[0324] Correspondingly, SDGF receives event open notifications from UPF.

[0325] The event open notification includes traffic data from the UE used to generate the synthetic data.

[0326] UPF can determine the UE traffic data used to generate composite data based on the data type (UE traffic data) and the amount of data subscribed in the event open subscription, and send an event open notification carrying the UE traffic data used to generate composite data to SDGF based on the subscribed NF ID (SDGF ID).

[0327] The traffic data transmitted in S704 to S705 above can be online or offline traffic data.

[0328] The above S704 to S705 can be replaced by the following S706 to S709:

[0329] S706 and SMF send the correspondence between the first QFI and SDGF to UPF.

[0330] Correspondingly, the UPF receives the correspondence between the first QFI and the SDGF from the SMF.

[0331] The correspondence between the first QFI and SDGF is used to instruct the UPF to send traffic data packets carrying the first QFI to the synthetic data function, or to instruct traffic data packets carrying the first QFI to be used by the SDGF to generate synthetic data, without limitation.

[0332] S707 and SMF send QoS rules to the UE.

[0333] Accordingly, the UE receives QoS rules from the SMF.

[0334] Among them, QoS rules are used to indicate how to map traffic data of a specific application IP (such as the first IP) to a specific QFI (such as the first QFI). The QoS rules include the first IP and the first QFI.

[0335] S708, the UE sends traffic data packets to the UPF. Correspondingly, the UPF receives traffic data packets from the UE.

[0336] The traffic data packets include the traffic data from the first IP address, the first QFI, and the UE. In other words, the UE can send the accessed traffic data to the UPF according to QoS rules.

[0337] S709 and UPF send traffic data packets to SDGF.

[0338] Correspondingly, SDGF receives traffic data packets from UPF.

[0339] UPF can determine whether the UE's traffic data in the current traffic data packet is the traffic data that generates the composite data based on the correspondence between the first QFI and SDGF and the QFI in the traffic data packet. If the QFI of the traffic data packet is the first QFI, then the UPF sends the traffic data packet to SDGF.

[0340] The traffic data transmitted in S706 to S709 above can be online real-time traffic data.

[0341] Of course, the SDGF / DC can also request UE traffic data from the DSF. The implementation process is similar to that of the SDGF / DC requesting UE location data, and will not be elaborated further. Alternatively, the DC can also trigger the SMF to request UE traffic data by executing S704-S705 or S706-S709 as described above, just as the SDGF does. The implementation process is similar, and will not be elaborated further.

[0342] S710 and SDGF generate traffic-related synthetic data based on the method for generating synthetic data and the UE's traffic data.

[0343] SDGF can use the UE's traffic data reported by UPF and the method for generating synthetic data (such as GAN) indicated in the synthetic data generation request in S702 as input to the GAN model, and the GAN output generates traffic-related synthetic data.

[0344] S711 and SDGF send traffic-related synthetic data to AF via NEF.

[0345] Correspondingly, AF receives traffic-related synthetic data from SDGF via NEF.

[0346] Therefore, SDGF can generate synthetic traffic-related data based on existing online or offline traffic data that can be obtained within the network, thereby expanding the effective dataset.

[0347] It is understood that, in the above embodiments, the methods and / or steps implemented by the data synthesis function can also be implemented by components (e.g., processors, chips, chip systems, circuits, logic modules, or software) that can be used for the data synthesis function; the methods and / or steps implemented by the control function can also be implemented by components (e.g., processors, chips, chip systems, circuits, logic modules, or software) that can be used for the control function; the methods and / or steps implemented by the first device can also be implemented by components (e.g., processors, chips, chip systems, circuits, logic modules, or software) that can be used for the first device; and the methods and / or steps implemented by the second device can also be implemented by components (e.g., processors, chips, chip systems, circuits, logic modules, or software) that can be used for the second device.

[0348] The foregoing mainly describes the solutions provided in this application. Accordingly, this application also provides a communication device for implementing various methods in the above method embodiments. This communication device can be a data synthesis function in the above method embodiments, or a device containing a data synthesis function, or a component that can be used for a data synthesis function, such as a chip or chip system. Alternatively, the communication device can be a control function in the above method embodiments, or a device containing a control function, or a component that can be used for a control function, such as a chip or chip system. Alternatively, the communication device can be a first device in the above method embodiments, or a device containing a first device, or a component that can be used for a first device, such as a chip or chip system. Alternatively, the communication device can be a second device in the above method embodiments, or a device containing a second device, or a component that can be used for a second device, such as a chip or chip system.

[0349] It is understood that, in order to achieve the aforementioned functions, the communication device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in 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.

[0350] This application embodiment can divide the communication device into functional modules according to the above method embodiment. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0351] Taking the data synthesis function, control function, first device, or second device in the above method embodiments as an example, Figure 8 is a schematic diagram of the structure of a communication device provided in an embodiment of this application. As shown in Figure 8, the communication device 800 includes a processing module 801 and a transceiver module 802. The processing module 801 is used to execute the data synthesis function, control function, first device, or second device processing function in the above method embodiments. The transceiver module 802 is used to execute the data synthesis function, control function, first device, or second device transceiver function in the above method embodiments. All relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here.

[0352] In one possible design, in this embodiment of the application, the transceiver module 802 may include a receiving module and a sending module (not shown in FIG8). The sending module and the receiving module are respectively used to implement the sending and receiving functions of the communication device 800.

[0353] In one possible design, the communication device 800 may further include a storage module (not shown in FIG8) that stores programs or instructions. When the processing module 801 executes the program or instructions, the communication device 800 can perform the data synthesis function, control function, or function of the first or second device in the method shown in any of FIG4, FIG5, or FIG7.

[0354] In some embodiments, the processing module 801 involved in the communication device 800 may be implemented by a processor or processor-related circuit components, and may be a processor or processing unit; the transceiver module 802 may be implemented by a transceiver or transceiver-related circuit components, and may be a transceiver or transceiver unit.

[0355] For example, FIG9 is a schematic diagram of another communication device provided in an embodiment of this application. This communication device may be the data synthesis function or control function, or the first device or the second device in the above method embodiments, or it may be a chip (system) or other component or assembly that can be disposed in the data synthesis function, control function, first device, or second device. As shown in FIG9, the communication device 900 may include a processor 901, a bus 902, a communication interface 903, and a memory 904. The processor 901, the memory 904, and the communication interface 903 communicate via the bus 902. It should be understood that this application does not limit the number of processors and memories in the communication device 900.

[0356] Bus 902 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, only one line is used in Figure 9, but this does not indicate that there is only one bus or one type of bus. Bus 902 can include pathways for transmitting information between various components of communication device 900 (e.g., memory 904, processor 901, communication interface 903).

[0357] Processor 901 may include any one or more processors such as a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0358] The memory 904 may include volatile memory, such as random access memory (RAM). The processor 901 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0359] The communication interface 903 uses transceiver modules such as, but not limited to, network interface cards and transceivers to enable communication between the communication device 900 and other devices or communication networks.

[0360] The memory 904 stores executable program code, which the processor 901 executes to implement the functions of the network device or the terminal device in the aforementioned method embodiments. That is, the memory 904 stores instructions for executing the aforementioned communication methods.

[0361] In another aspect, embodiments of this application also provide a computer program product containing instructions, including computer program code, which, when run on a communication device, enables the communication device to execute the methods described in the above embodiments.

[0362] Furthermore, embodiments of this application also provide a computer-readable storage medium. This computer-readable storage medium stores a computer program or instructions that, when executed on a communication device, enable the communication device to perform the methods described in the above embodiments.

[0363] Furthermore, embodiments of this application also provide a communication system, which includes the aforementioned data synthesis function, control function, and first device. Optionally, the communication system may further include the aforementioned second device.

[0364] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software programs, implementation can be, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device containing one or more servers, data centers, etc., that can be integrated with the medium. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video disks, DVDs), or semiconductor media (e.g., SSDs), etc.

[0365] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software 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.

[0366] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0367] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0368] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, the functional units in the various embodiments of this application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0369] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they 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 a portion 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.) to execute all or part of the steps of the methods described in 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, ROM, RAM, magnetic disks, or optical disks.

[0370] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, the disclosure, and the appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple instances. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0371] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of this application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and modifications of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include such modifications and modifications.

Claims

1. A communication method, characterized in that, A method for synthesizing data functions applied in wireless communication networks includes: Receive a first message from the control function, the first message being used to trigger the generation of synthetic data; Receive first data from a first device, wherein the first device is a means of providing data for generating synthetic data; Based on the first message and the first data, first synthetic data is generated, and the first synthetic data is used for model training and / or inference.

2. The method according to claim 1, characterized in that, The first message includes the data type of the synthesized data.

3. The method according to claim 2, characterized in that, The step of generating the first synthesized data based on the first message and the first data includes: The method for generating the synthetic data is determined based on the data type of the synthetic data; The first synthetic data is generated according to the method for generating synthetic data and the first data.

4. The method according to claim 3, characterized in that, The first message also includes: key performance indicators (KPIs) of the synthetic data, and / or the amount of data in the synthetic data; The method for determining the method for generating synthetic data based on the data type of the synthetic data includes: The method for generating the synthetic data is determined based on at least one of the KPIs of the synthetic data, the data volume of the synthetic data, and the data type of the synthetic data.

5. The method according to claim 2, characterized in that, The first message also includes the method for generating synthetic data; Based on the first message and the first data, first composite data is generated, including: The first synthetic data is generated according to the method for generating synthetic data and the first data.

6. The method according to any one of claims 1-5, characterized in that, The method further includes: Based on the first message, a second message is sent to the first device, the second message being used to trigger the first device to provide data for generating synthetic data to the synthetic data function; Based on the first message, a second message is sent to the second device, the second message being used by the second device to trigger the first device to provide the data for generating the synthetic data.

7. The method according to claim 6, characterized in that, Sending a second message to the first device or the second device according to the first message includes: Based on the information used to instruct the first device, the second message is sent to the first device; Alternatively, the second message may be sent to the second device based on the information used to instruct the second device; wherein the first message may further include information used to instruct the first device or information used to instruct the second device.

8. The method according to claim 6, characterized in that, The first message includes the data type of the synthesized data; Sending a second message to the first device based on the first message includes: The first device is determined based on the data type of the synthesized data; Send the second message to the first device; Alternatively, sending a second message to the second device based on the first message includes: The second device is determined based on the data type of the synthesized data; Send the second message to the second device.

9. The method according to any one of claims 6-8, characterized in that, The second message includes the data type of the synthesized data and first information, wherein the first information corresponds to the data used to generate the synthesized data.

10. The method according to claim 9, characterized in that, The first message includes the data type of the synthesized data and the data volume of the synthesized data, or the first message includes the data type of the synthesized data, the method for generating the synthesized data, and the data volume of the synthesized data; Sending a second message to the first device or the second device according to the first message includes: The amount of data used to generate the synthetic data is determined based on the amount of data in the synthetic data and the method for generating the synthetic data; or, the amount of data used to generate the synthetic data is determined based on the amount of data in the synthetic data, the method for generating the synthetic data, and the data type of the synthetic data. The second message is sent to the first device or the second device, and the second message further includes the amount of data used to generate the synthetic data.

11. The method according to claim 10, characterized in that, The first message also includes the KPIs of the synthesized data; Determining the amount of data used to generate the synthetic data based on the amount of synthetic data and the method for generating the synthetic data includes: The amount of data used to generate the synthetic data is determined based on the data volume of the synthetic data, the method for generating the synthetic data, and the KPIs of the synthetic data; or, Determining the amount of data used to generate the synthetic data based on the amount of synthetic data, the method for generating the synthetic data, and the data type of the synthetic data includes: The amount of data used to generate the synthetic data is determined based on the amount of synthetic data, the method for generating the synthetic data, the data type of the synthetic data, and the KPIs of the synthetic data.

12. The method according to claim 4 or 11, characterized in that, The KPIs include: authenticity and / or diversity.

13. The method according to any one of claims 1-12, characterized in that, The method further includes: The first synthetic data is sent to a third device, which is any one of the following: a device for storing the first synthetic data, a device for using the first synthetic data to train and / or infer the model, or a device for making the first synthetic data available to a third-party device.

14. A communication method, characterized in that, The method, which applies control functions in a wireless communication network, includes: Receive a third message from the first network element, the third message being used to request synthesized data; According to the third message, a first message is sent to the synthetic data function in the wireless communication network, the first message being used to trigger the generation of synthetic data.

15. The method according to claim 14, characterized in that, The third message includes the data type of the synthesized data, and the first message includes the data type of the synthesized data.

16. The method according to claim 15, characterized in that, The first message also includes the method for generating synthetic data; Sending the first message to the synthetic data function in the wireless communication network according to the third message includes: The method for generating the synthetic data is determined based on the data type of the synthetic data; Send the first message to the synthetic data function.

17. The method according to claim 16, characterized in that, The third message also includes the KPIs of the synthesized data, and / or the data volume of the synthesized data; The method for determining the method for generating synthetic data based on the data type of the synthetic data includes: The method for generating the synthetic data is determined based on at least one of the KPIs of the synthetic data, the data volume of the synthetic data, and the data type of the synthetic data.

18. The method according to claim 15, characterized in that, The third message also includes the KPIs of the synthesized data and / or the data volume of the synthesized data, and the first message also includes the KPIs of the synthesized data and / or the data volume of the synthesized data.

19. The method according to any one of claims 15-18, characterized in that, Sending the first message to the synthetic data function in the wireless communication network according to the third message includes: Based on the data type of the synthetic data, a first device or a second device is determined; the first device is a device for providing data for generating the synthetic data, and the second device is used to trigger the first device to provide the data for generating the synthetic data. The first message is sent to the synthetic data function, and the first message further includes information for instructing the first device or information for instructing the second device.

20. The method according to any one of claims 15-18, characterized in that, The method further includes: According to the third message, a fourth message is sent to the first device. The fourth message is used to trigger the control function to provide the first device with data for generating synthetic data to the synthetic data function. The first device is a device that provides data for generating synthetic data. According to the third message, a fourth message is sent to the second device, the fourth message being used by the second device to trigger the first device to provide the data for generating the synthetic data.

21. The method according to claim 20, characterized in that, Sending a fourth message to the first device according to the third message includes: The first device is determined based on the data type of the synthesized data; Send the fourth message to the first device; Alternatively, sending a fourth message to the second device based on the third message includes: The second device is determined based on the data type of the synthesized data; The fourth message is sent to the second device.

22. The method according to claim 20 or 21, characterized in that, The fourth message includes the data type of the synthetic data, first information, and second information. The first information corresponds to the data used to generate the synthetic data, and the second information is used to indicate that the synthetic data function should be provided with the data used to generate the synthetic data.

23. The method according to claim 22, characterized in that, The third message includes the data type of the synthesized data and the data volume of the synthesized data; Sending a fourth message to the first device or the second device according to the third message includes: The method for generating the synthetic data is determined based on the data type and the data volume of the synthetic data; The amount of data used to generate the synthetic data is determined based on the amount of data in the synthetic data and the method for generating the synthetic data. Alternatively, the amount of data used to generate the synthetic data may be determined based on the amount of synthetic data, the method for generating the synthetic data, and the data type of the synthetic data. The fourth message is sent to the first device or the second device, the fourth message further including the amount of data used to generate the synthetic data.

24. The method according to claim 23, characterized in that, The third message also includes the KPIs of the synthesized data. The method for determining the generated synthetic data based on the data type and data volume of the synthetic data includes: The method for generating synthetic data is determined based on the data type, data volume, and KPI of the synthetic data. Determining the amount of data used to generate the synthetic data based on the amount of synthetic data and the method for generating the synthetic data includes: The amount of data used to generate the synthetic data is determined based on the amount of synthetic data, the method for generating the synthetic data, and the KPIs of the synthetic data. Alternatively, determining the amount of data used to generate the synthetic data based on the amount of synthetic data, the method for generating the synthetic data, and the data type of the synthetic data includes: The amount of data used to generate the synthetic data is determined based on the amount of synthetic data, the method for generating the synthetic data, the data type of the synthetic data, and the KPIs of the synthetic data.

25. The method according to any one of claims 17, 18 or 24, characterized in that, The KPIs include: authenticity and / or diversity.

26. A communication device, characterized in that, Includes modules for performing the method as described in any one of claims 1-13 or 14-25.

27. A communication device, characterized in that, include: processor; The processor is configured to run computer programs or instructions to implement the method as described in any one of claims 1-13 or 14-25.

28. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program or instructions that, when executed by a communication device, implement the method as described in any one of claims 1-13 or 14-25.

29. A computer program product, characterized in that, It includes computer program code, which, when run on a communication device, implements the method as described in any one of claims 1-13 or 14-25.

Images