A communication method and device

Abstract

The present application provides a communication method and apparatus, the communication method comprising: a first network device obtains first information from a second network device, the first information comprising a first analysis result of first data of a terminal on the second network device; the first network device obtains second information from a third network device, the second information comprising a second analysis result of the first data of the terminal on the third network device; the first network device determines first experience information of a service of the terminal according to the first information and the second information; the first network device sends the first experience information to a fourth network device, the first experience information being used to determine parameters of the service of the terminal on the fourth network device. The communication method provided by the present application can improve the service experience of the terminal for the service.

Description

Technical Field

[0001] The present application relates to the field of communications, and more specifically, to a communication method and device. Background Art

[0002] During the service process of the terminal, data from three domains, namely, the radio access network (RAN), the core network (CN) and the service provider (e.g., the application function (AF) network element), jointly affect the service experience. In the prior art, when the service experience cannot be satisfied, the radio access network attempts to open some air interface information (such as the available air interface rate of the terminal, the terminal air interface cache status, etc.) to the service provider, thereby assisting the service provider to adjust the application layer parameters (such as the congestion window).

[0003] However, in addition to the above-mentioned air interface information on the access network side, there are many private parameters on the network side that affect the service experience. However, in the prior art, considering data privacy and security reasons, the network cannot provide private data to the service provider, resulting in the service provider being unable to accurately adjust the application layer parameters and unable to guarantee the service experience. Summary of the invention

[0004] The present application provides a communication method and device, which improves the accuracy of a service provider in adjusting application layer parameters, thereby ensuring service experience.

[0005] In a first aspect, an embodiment of the present application provides a communication method, the method comprising: a first network device obtains first information from a second network device, wherein the first information includes a first analysis result of first data of a terminal on the second network device; the first network device obtains second information from a third network device, the second information includes a second analysis result of the first data of the terminal on the third network device; the first network device determines first service experience information of a service of the terminal based on the first information and the second information; the first network device sends the first service experience information to a fourth network device, and the first service experience information is used to determine parameters of the service of the terminal on the fourth network device.

[0006] According to the communication method of an embodiment of the present application, a first network device obtains first information and second information, the first information including a first analysis result of first data of a terminal on the second network device; the second information including a second analysis result of the first data of the terminal on the third network device, and the first network device determines first service experience information of a service of the terminal based on the first information and the second information, and sends the first service experience information to a fourth network device, thereby improving the accuracy of the service provider in adjusting application layer parameters, thereby ensuring the service experience.

[0007] In some embodiments, the service may be a service flow, and the first data may be data of a terminal corresponding to the service flow on a second network device; the first data may also be data of a terminal corresponding to the service flow on a third network device.

[0008] In some embodiments, the first analysis result of the first data may be an analysis result of the business experience, that is, a model reasoning result of the business experience; and the second analysis result of the first data may be a model reasoning result of the business experience.

[0009] In combination with the first aspect, in an implementation of the first aspect, the second network device includes a core network device, and the method also includes: the first network device sends a first request to the core network device, wherein the first request is used to request a first analysis result of the first data of the terminal on the core network device, and the first request includes first identification information of the terminal and at least one of the following information: an analysis identifier and identification information of a first model, wherein the analysis identifier and / or identification information of the first model is used to determine the first model corresponding to the first analysis result of the first data of the terminal on the core network device.

[0010] In some embodiments, the analysis identifier can be an Analytics ID, for example, service experience, network element load, network performance, UE mobility, UE communication, expected UE behavior, UE abnormal behavior, etc.

[0011] In some embodiments, the identification information of the model may be an Internet protocol (IP) address, a uniform resource locator (URL), or a fully qualified domain name (FQDN).

[0012] In combination with the first aspect and any one of the above-mentioned implementation methods, in another implementation method of the first aspect, the third network device includes an access network device, and the method also includes: the first network device sends a second request to the access network device, wherein the second request is used to request a second analysis result of the first data of the terminal on the access network device, and the second request includes second identification information of the terminal and at least one of the following information: identification information of the analysis identification and a second model, wherein the analysis identification and / or the identification information of the second model is used to determine the second model corresponding to the second analysis result of the first data of the terminal on the access network device.

[0013] In combination with the first aspect and any one of the above-mentioned implementation methods, in another implementation method of the first aspect, the method also includes: the first network device obtains third information from the fourth network device, wherein the third information includes a third analysis result of the first data of the terminal on the fourth network device.

[0014] In combination with the first aspect, in some implementations of the first aspect, the fourth network device includes an application function device, and the method also includes: the first network device sends a third request to the application function device, wherein the third request is used to request a third analysis result of the first data of the terminal on the application function device, and the third request includes a third identifier of the terminal and at least one of the following information: identification information of the analysis identifier and a third model, wherein the analysis identifier and / or the identification information of the third model is used to determine the third model corresponding to the third analysis result of the first data of the terminal on the application function device.

[0015] In combination with the first aspect and any one of the above-mentioned implementations, in another implementation of the first aspect, the first information may also include first association information, wherein the first association information is used to associate the second information with the first information; and / or the second information may also include the first association information.

[0016] In some embodiments, the first association information may be association information between the RAN and the AMF. The association information between the RAN and the AMF may be, for example, an identifier of the RAN UE NGAP ID, a globally unique identifier of the RAN, i.e., the Global RANNode ID, and a timestamp when local inference data on the core network side is generated, i.e., Timestamp.

[0017] In combination with the first aspect and some of the above-mentioned implementations, in another implementation of the first aspect, the first information may also include second association information, wherein the second association information is used to associate the first information with the third information; and / or the third information may also include the second association information.

[0018] In some embodiments, the second association information may be association information between the UPF and the AF. The association information between the UPF and the AF may be, for example, an IP quintuple (i.e., source IP address, destination IP address, source port number, destination port number, protocol number), and a Timestamp when local inference data is generated on the UPF on the core network side.

[0019] In combination with the first aspect and any one of the above-mentioned implementation methods, in another implementation method of the first aspect, the first information may also include second data of the terminal on the second network device, and the second information may also include second data of the terminal on the third network device. The method also includes: the first network device obtains a fourth analysis result based on the second data of the terminal on the second network device and the second data of the terminal on the third network device; the first network device determines the first service experience information of the service of the terminal based on the first information and the second information, including: the first network device determines the first service experience information of the service of the terminal based on the first information, the second information and the fourth analysis result.

[0020] In combination with the first aspect, in another implementation of the first aspect, the third information also includes second data of the terminal on the fourth network device, and the first network device obtains a fourth analysis result based on the second data of the terminal on the second network device and the second data of the terminal on the third network device, including: the first network device obtains the fourth analysis result based on the second data of the terminal on the second network device, the second data of the terminal on the third network device, and the second data of the terminal on the fourth network device; the first network device determines the first service experience information of the service of the terminal based on the first information, the second information, and the fourth analysis result, including: the first network device determines the first service experience information of the service of the terminal based on the first information, the second information, the third information, and the fourth analysis result.

[0021] In combination with the first aspect and any one of the above-mentioned implementation methods, in another implementation method of the first aspect, the first network device determines the first service experience information of the service of the terminal based on the first information and the second information, including: the first network device determines the first service experience information based on the first information, the second information and the second service experience information of the service requirement.

[0022] In combination with the first aspect, in another implementation of the first aspect, the first information may also include second data of the terminal on the second network device, and the second information may also include second data of the terminal on the third network device. The method also includes: the first network device obtains a fourth analysis result based on the second data of the terminal on the second network device and the second data of the terminal on the third network device; the first network device determines the first service experience information of the service of the terminal based on the first information, the second information and the second service experience information of the service requirement, including: the first network device determines the first service experience information of the service of the terminal based on the first information, the second information, the fourth analysis result and the second service experience information of the service requirement.

[0023] In combination with the first aspect, in another implementation manner of the first aspect, the third information further includes second data of the terminal on the fourth network device, and the first network device acquires a fourth analysis result according to the second data of the terminal on the second network device and the second data of the terminal on the third network device, including: the first network device acquires the fourth analysis result according to the second data of the terminal on the second network device, the second data of the terminal on the third network device, and the second data of the terminal on the fourth network device;

[0024] The first network device determines the first service experience information of the service of the terminal according to the first information, the second information, the fourth analysis result and the second service experience information of the service requirement, including: the first network device determines the first service experience information of the service of the terminal according to the first information, the second information, the third information, the fourth analysis result and the second service experience information of the service requirement.

[0025] In combination with the first aspect and any one of the above implementations, in another implementation of the first aspect, the first data of the terminal on the second network device includes private data corresponding to the terminal.

[0026] In combination with the first aspect and any one of the above implementations, in another implementation of the first aspect, the first data of the terminal on the third network device includes private data corresponding to the terminal.

[0027] In combination with the first aspect and some of the above implementations thereof, in another implementation of the first aspect, the first data of the terminal on the fourth network device includes private data corresponding to the terminal.

[0028] In combination with the first aspect and some of the above implementations thereof, in another implementation of the first aspect, the second data of the terminal on the second network device includes public data corresponding to the terminal.

[0029] In combination with the first aspect and some of the above implementations, in another implementation of the first aspect, the second data of the terminal on the third network device includes public data corresponding to the terminal.

[0030] In combination with the first aspect and some of the above implementations thereof, in another implementation of the first aspect, the second data of the terminal on the fourth network device includes public data corresponding to the terminal.

[0031] In combination with the first aspect and any one of the above implementations, in another implementation of the first aspect, the first network device includes a data analysis device or a policy control device.

[0032] In combination with the first aspect and any one of the above-mentioned implementations, in another implementation of the first aspect, the first model or the second model or the third model may be a sub-model after distributed training.

[0033] In a second aspect, a communication method is provided, the method comprising: a second network device determines first information, wherein the first information comprises a first analysis result of first data of a terminal on the second network device; and the second network device sends the first information to the first network device.

[0034] In combination with the second aspect, in another implementation method of the second aspect, the second network device sends the first information to the first network device, including: the second network device receives a first request from the first network device, wherein the first request is used to request a first analysis result of the first data of the terminal on the second network device, and the first request includes first identification information of the terminal and at least one of the following information: an analysis identifier and identification information of a first model, model information of the first model, the analysis identifier and / or identification information of the first model is used to determine the first model; the second network device sends a first response to the first network device, and the first response includes the first information.

[0035] In combination with the second aspect and any one of the above implementations, in another implementation of the second aspect, the first information may also include second data of the terminal on the second network device.

[0036] In combination with the second aspect and any one of the above-mentioned implementation methods, in another implementation method of the second aspect, the first information may also include first association information, wherein the first association information is used to associate the second information with the first information; the second information includes a second analysis result of the first data of the terminal on the third network device; and / or the second information may also include the first association information.

[0037] In combination with the second aspect and any one of the above-mentioned implementation methods, in another implementation method of the second aspect, the first information may also include second association information, wherein the second association information is used to associate the first information with the third information; wherein the third information includes a third analysis result of the first data of the terminal on the four network devices; and / or, the third information may also include the second association information.

[0038] In combination with the second aspect and any one of the above implementations, in another implementation of the second aspect, the first data of the terminal on the second network device includes private data corresponding to the terminal.

[0039] In combination with the second aspect and any one of the above implementations, in another implementation of the second aspect, the first data of the terminal on the third network device includes private data corresponding to the terminal.

[0040] In combination with the second aspect and some of the above implementations thereof, in another implementation of the second aspect, the first data of the terminal on the fourth network device includes private data corresponding to the terminal.

[0041] In combination with the second aspect and any one of the above implementations, in another implementation of the second aspect, the second data of the terminal on the second network device includes public data corresponding to the terminal.

[0042] In combination with the second aspect and any one of the above implementations, in another implementation of the second aspect, the first network device includes a data analysis device or a policy control device.

[0043] In combination with the second aspect and any one of the above implementations, in another implementation of the second aspect, the second network device includes a core network device.

[0044] In combination with the second aspect and any one of the above implementations, in another implementation of the second aspect, the third network device includes an access network device.

[0045] In combination with the second aspect and any one of the above implementations, in another implementation of the second aspect, the fourth network device includes an application function device.

[0046] In combination with the second aspect and any one of the above-mentioned implementations, in another implementation of the second aspect, the first model may be a sub-model after distributed training.

[0047] According to a third aspect, a communication method is provided, which includes: a third network device determines second information, where the second information includes a second analysis result of first data of a terminal on the third network device; and the third network device sends the second information to the first network device.

[0048] In combination with the third aspect, in another implementation of the third aspect, the third network device sends the second information to the first network device, including: the third network device receives a second request from the first network device, wherein the second request is used to request a second analysis result of the first data of the terminal on the third network device, and the second request includes the second identification information of the terminal and at least one of the following information: an analysis identification and identification information of a second model, model information of the second model, and the analysis identification and / or the identification information of the second model is used to determine the second model. The third network device sends a second response to the first network device, and the second response includes the second information.

[0049] In combination with the third aspect, and any one of the above implementations, in another implementation of the third aspect, the second information may also include second data of the terminal on the third network device.

[0050] In combination with the third aspect, and any one of the above-mentioned implementation methods, in another implementation method of the third aspect, the second information may also include first association information, and the first association information is used to associate the second information with the first information, and the first information includes a first analysis result of the first data of the terminal on the second network device.

[0051] In combination with the third aspect, and any one of the above implementations, in another implementation of the third aspect, the first data of the terminal on the second network device includes private data corresponding to the terminal.

[0052] In combination with the third aspect, and any one of the above implementations, in another implementation of the third aspect, the first data of the terminal on the third network device includes private data corresponding to the terminal.

[0053] In combination with the third aspect, and any one of the above implementations, in another implementation of the third aspect, the second data of the terminal on the third network device includes public data corresponding to the terminal.

[0054] In combination with the third aspect, and any one of the above-mentioned implementations, in another implementation of the third aspect, the first network device includes a data analysis device or a policy control device.

[0055] In combination with the third aspect, and any one of the above implementations, in another implementation of the third aspect, the second network device includes a core network domain device.

[0056] In combination with the third aspect, and any one of the above implementations, in another implementation of the third aspect, the third network device includes an access network device.

[0057] In combination with the third aspect, and any one of the above-mentioned implementations, in another implementation of the third aspect, the second model may be a sub-model after distributed training.

[0058] In a fourth aspect, a communication method is provided, the method comprising: the fourth network device receives first service experience information sent by the first network device, the first service experience information is used to determine parameters of the service of the terminal on the fourth network device, the first service experience information is determined based on first information and second information, the first information includes a first analysis result of first data of the terminal on the second network device, and the second information includes a second analysis result of the first data of the terminal on the third network device; the fourth network device determines the parameters of the service of the terminal on the fourth network device based on the first service experience information.

[0059] In combination with the fourth aspect, in another implementation manner of the fourth aspect, wherein the first information may also include second data of the terminal on the second network device, and the second information may also include second data of the terminal on the third network device, the method also includes: the first service experience information is determined based on the first information and the second information, including: the first service experience information determines the first service experience information of the service of the terminal based on the first information, the second information and a fourth analysis result; the fourth analysis result is determined based on the second data of the terminal on the second network device and the second data of the terminal on the third network device.

[0060] In combination with the fourth aspect, and any one of the above-mentioned implementation methods, in another implementation method of the fourth aspect, the method also includes: the fourth network device determines third information, wherein the third information includes a third analysis result of the first data of the terminal on the fourth network device; the fourth network device sends the third information to the first network device.

[0061] In combination with the fourth aspect, in another implementation method of the fourth aspect, the fourth network device sends the third information to the first network device, including: the fourth network device receives a third request from the first network device, wherein the third request is used to request a third analysis result of the first data of the terminal on the fourth network device, and the third request includes third identification information of the terminal and at least one of the following information: an analysis identifier and identification information of a third model, model information of the third model, and the analysis identifier and / or identification information of the third model are used to determine the third model; the fourth network device sends a third response to the first network device, and the third response includes the third information.

[0062] In combination with the fourth aspect, and some of the above-mentioned implementation methods, in another implementation method of the fourth aspect, the third information also includes second data of the terminal on the fourth network device, and the first service experience information determines the first service experience information of the service of the terminal according to the first information, the second information and the fourth analysis result, including: the first service experience information is determined according to the first information, the second information, the third information and the fourth analysis result; the fourth analysis result is determined according to the second data of the terminal on the second network device and the second data of the terminal on the third network device, including: the fourth analysis result is determined according to the second data of the terminal on the second network device, the second data of the terminal on the third network device and the second data of the terminal on the fourth network device.

[0063] In combination with the fourth aspect, and any one of the above-mentioned implementation methods, in another implementation method of the fourth aspect, the first service experience information is determined based on the first information and the second information, including: the first service experience information is determined based on the first information, the second information and the second service experience information of the service requirement.

[0064] In combination with the fourth aspect, and some of the above-mentioned implementations, in another implementation of the fourth aspect, the third information may also include second data of the terminal on the third network device.

[0065] In combination with the fourth aspect, and some of the above-mentioned implementation methods, in another implementation method of the fourth aspect, the third information may also include the second association information, and the second association information is used to associate the first information with the third information, and the first information includes a first analysis result of the first data of the terminal on the second network device.

[0066] In combination with the fourth aspect, and any one of the above-mentioned implementations, in another implementation of the fourth aspect, the first data of the terminal on the second network device includes private data corresponding to the terminal.

[0067] In combination with the fourth aspect, and any one of the above-mentioned implementations, in another implementation of the fourth aspect, the first data of the terminal on the third network device includes private data corresponding to the terminal.

[0068] In combination with the fourth aspect, and any one of the above implementations, in another implementation of the fourth aspect, the first data of the terminal on the fourth network device includes private data corresponding to the terminal.

[0069] In combination with the fourth aspect, and any one of the above-mentioned implementations, in another implementation of the fourth aspect, the second data of the terminal on the second network device includes public data corresponding to the terminal.

[0070] In combination with the fourth aspect, and any one of the above-mentioned implementations, in another implementation of the fourth aspect, the second data of the terminal on the third network device includes public data corresponding to the terminal.

[0071] In combination with the fourth aspect, and any one of the above-mentioned implementations, in another implementation of the fourth aspect, the second data of the terminal on the fourth network device includes public data corresponding to the terminal.

[0072] In combination with the fourth aspect, and any one of the above-mentioned implementations, in another implementation of the fourth aspect, the first network device includes a data analysis device or a policy control device.

[0073] In combination with the fourth aspect, and any one of the above-mentioned implementations, in another implementation of the fourth aspect, the second network device includes a core network device.

[0074] In combination with the fourth aspect, and any one of the above-mentioned implementations, in another implementation of the fourth aspect, the third network device includes an access network device.

[0075] In combination with the fourth aspect, and any one of the above implementations, in another implementation of the fourth aspect, the fourth network device includes an application function device.

[0076] In combination with the fourth aspect, and any one of the above-mentioned implementations, in another implementation of the fourth aspect, the third model may be a sub-model after distributed training.

[0077] In a fifth aspect, a communication device is provided, which can be used to perform the operations of the communication device in the first aspect and any possible implementation of the first aspect. Specifically, the communication device includes a means for performing the steps or functions described in the first aspect, which can be the first communication device of the first aspect. The steps or functions can be implemented by software, or hardware, or a combination of hardware and software.

[0078] In a sixth aspect, a communication device is provided, which can be used to perform the operations of the communication device in the second aspect and any possible implementation of the second aspect. Specifically, the device may include means for performing the steps or functions corresponding to the steps or functions described in the second aspect. The steps or functions may be implemented by software, or hardware, or a combination of hardware and software.

[0079] In a seventh aspect, a communication device is provided, which can be used to perform the operations of the communication device in the third aspect and any possible implementation of the third aspect. Specifically, the communication device includes a means for performing the steps or functions described in the third aspect, which can be the first communication device of the third aspect. The steps or functions can be implemented by software, hardware, or a combination of hardware and software.

[0080] In an eighth aspect, a communication device is provided, which can be used to perform the operations of the communication device in the fourth aspect and any possible implementation of the fourth aspect. Specifically, the device may include means for performing the steps or functions corresponding to the steps or functions described in the fourth aspect. The steps or functions may be implemented by software, or hardware, or by a combination of hardware and software.

[0081] In the ninth aspect, a communication device is provided, including a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the communication device executes the communication method in any possible implementation of the first to fourth aspects.

[0082] There are one or more processors and one or more memories. The memory may be integrated with the processor, or the memory may be separately arranged from the processor.

[0083] The communication device also includes a transmitter (transmitter) and a receiver (receiver).

[0084] In one possible design, a communication device is provided, including a transceiver, a processor, and a memory. The processor is used to control the transceiver to send and receive signals, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the communication device executes the method in the first to fourth aspects or any possible implementation of the first to fourth aspects.

[0085] In a tenth aspect, a system is provided, wherein the system comprises the above-mentioned communication device.

[0086] In the eleventh aspect, a computer program product is provided, which includes: a computer program (also referred to as code, or instruction), which, when executed, enables a computer to execute a method in any possible implementation of the first to fourth aspects above.

[0087] In the twelfth aspect, a computer-readable medium is provided, which stores a computer program (also referred to as code, or instruction) which, when executed on a computer, enables the computer to execute a method in any possible implementation of the first to fourth aspects above.

[0088] In the thirteenth aspect, a chip system is provided, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that a communication device equipped with the chip system executes a method in any possible implementation of the first to fourth aspects above.

[0089] In a fourteenth aspect, a chip is provided, comprising a processor and a communication interface, wherein the communication interface is used to communicate with an external device or an internal device, and the processor is used to implement a method in any possible implementation of the first to fourth aspects above.

[0090] Optionally, the chip may further include a memory, in which instructions are stored, and the processor is used to execute the instructions stored in the memory or instructions from other sources. When the instructions are executed, the processor is used to implement the method in any possible implementation of the first to fourth aspects above. Optionally, the chip may be integrated on an access network device.

[0091] In the fifteenth aspect, a communication system is provided, which includes a first network device, and the first network device is used to execute the method in any possible implementation of the first to fourth aspects above; the communication system also includes a second network device, and the second network device is used to send first information to the first network device, and the first information includes a first analysis result of the first data of the terminal on the second network device.

[0092] The communication method and communication device of the embodiments of the present invention can improve the accuracy of the service provider in adjusting the application layer parameters, thereby ensuring the service experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0093] Figure 1 A schematic diagram of an application scenario suitable for the method provided in an embodiment of the present application.

[0094] Figure 2 This is a schematic diagram of the framework of the federated learning system in the distributed training of this application.

[0095] Figure 3 It is a schematic flow chart of a communication method provided in an embodiment of the present application.

[0096] Figure 4 Another embodiment of the present application provides a schematic flow chart of a communication method.

[0097] Figure 5 This is a schematic flowchart of a communication method provided in yet another embodiment of the present application.

[0098] Figure 6 It is a schematic block diagram of a communication device provided in an embodiment of the present application.

[0099] Figure 7 It is a schematic block diagram of another communication device provided in an embodiment of the present application.

[0100] Figure 8 It is a schematic block diagram of another communication device provided in an embodiment of the present application.

[0101] Fig. 9It is a structural diagram of a communication device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0102] The technical solution in this application will be described below in conjunction with the accompanying drawings.

[0103] The wireless communication systems mentioned in the embodiments of the present application include but are not limited to: global system of mobile communication (GSM) system, long term evolution (LTE) frequency division duplex (FDD) system, LTE time division duplex (TDD), LTE system, advanced long term evolution (LTE-Advanced, LTE-A) system, next generation communication system (for example, 6G communication system), a fusion system of multiple access systems, or an evolution system.

[0104] The terminal devices involved in the embodiments of the present application may include various access terminals, mobile devices, user terminals or user devices with wireless communication functions. For example, the terminal device may be a mobile phone, a tablet computer, a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal in industrial control, a machine type communication (MTC) terminal, a customer premise equipment (CPE), a wireless terminal in self-driving, a wireless terminal in remote medical, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, etc. The embodiments of the present application do not limit the application scenarios. In the present application, the aforementioned terminal devices and chips that can be set in the aforementioned terminal devices are collectively referred to as terminal devices.

[0105] As an example but not limitation, in the embodiments of the present application, the terminal device may also be a wearable device. Wearable devices may also be referred to as wearable smart devices, which are a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also powerful functions achieved through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include full-featured, large-sized, and fully or partially independent of smartphones, such as smart watches or smart glasses, as well as devices that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various types of smart bracelets and smart jewelry for vital sign monitoring.

[0106] Figure 1 Schematic diagram of a network architecture applicable to the method provided in the embodiment of the present application. The network architecture may specifically include the following network elements:

[0107] 1. Radio access network (RAN): An access network that implements access network functions based on wireless communication technology can be called a radio access network. The radio access network can manage wireless resources, provide access services to terminals, and then complete the forwarding of control signals and user data between terminals and the core network.

[0108] The wireless access network can be, for example, a base transceiver station (BTS) in a global system of mobile communication (GSM) system or a code division multiple access (CDMA), a base station (nodeB, NB) in a wideband code division multiple access (WCDMA) system, an evolutionary nodeB (eNB or eNodeB) in an LTE system, or a wireless controller in a cloud radio access network (CRAN) scenario, or the network device can be a relay station, an access point, a vehicle-mounted device, a wearable device, a network device in a future 5G network, or a network device in a future evolved PLMN network, etc., and the embodiments of the present application are not limited thereto.

[0109] 2. A network data analytics function (NWDAF) has at least one of the following functions: data collection function and data analysis function. The data collection function refers to the function used to collect relevant data from network elements, third-party service servers, terminal devices or network management systems; the data analysis function refers to the analysis and training based on relevant input data to obtain a model, and the data analysis results are determined by reasoning based on the model, and then the data analysis results are provided to the network elements, third-party service servers, terminal devices or network management systems. The analysis results can assist the network in selecting the service quality parameters of the service, or assist the network in executing traffic routing, or assist the network in selecting background traffic transmission strategies, etc. This application mainly involves the data collection function and model training function of NWDAF.

[0110] In the embodiment of the present application, the NWDAF may be a separate network element or may be co-located with other core network elements. For example, the NWDAF network element may be co-located with an access and mobility management function (AMF) network element or with a session management function (SMF) network element.

[0111] Typical application scenarios of NWDAF include: customization or optimization of terminal parameters, that is, NWDAF collects information such as user connection management, mobility management, session management, and accessed services, and uses reliable analysis and prediction models to evaluate and analyze different types of users, build user portraits, determine user movement trajectories and service usage habits, and predict user behavior. The 5G network optimizes user mobility management parameters and wireless resource management parameters based on analysis and prediction data; service (path) optimization, that is, NWDAF collects information such as network performance, service load in a specific area, and user service experience, and uses reliable network performance analysis and prediction models to evaluate and analyze different types of services, build service portraits, determine the inherent correlation between service quality of experience (QoE), service experience (service experience), service path, or 5G service quality (QoS) parameters, optimize service paths, service routing, 5G edge computing, and determine the service corresponding to 5G QoS parameters, etc.; AF optimizes service parameters. For example, the Internet of Vehicles is an important technology of the 5G network. In the autonomous driving scenario of the Internet of Vehicles, the prediction of the network performance (such as QoS information and service load) of the base station that the vehicle is about to pass plays an important role in improving the service quality of the Internet of Vehicles. For example, the Internet of Vehicles server can determine whether to continue the unmanned driving mode based on the predicted information of network performance. NWDAF collects information such as network performance and service load in a specific area, and uses reliable network performance analysis and prediction models to realize the statistics and prediction of network performance, and assist AF in optimizing parameters.

[0112] 3. AMF network element: Mainly used for mobility management and access management, etc., and can be used to implement other functions of the mobility management entity (MME) except session management, such as terminal mobility management, terminal registration and deregistration, terminal session access, terminal allowed slice access selection, legal monitoring or access authorization (or authentication), etc. In the embodiment of the present application, it can be used to implement the functions of access and mobility management network elements.

[0113] 4. SMF network element: mainly used for session management, IP address allocation and management of terminal equipment, selection and management of user plane functions, policy control, termination points of charging function interfaces or downlink data notification, etc. In the embodiment of the present application, it can be used to implement the function of session management network element.

[0114] 5. Policy control function (PCF): A unified policy framework used to guide network behavior and provide service policies, charging policy information, etc. to control plane functional network elements (such as AMF, SMF network elements, etc.).

[0115] 6. Application function (AF): used to provide services, or perform data routing affected by applications, access network open function elements, or interact with PCF elements for service data policy control.

[0116] 7. Network exposure function (NEF): used to securely expose the service and capability information (such as terminal location, network congestion status, etc.) provided by 3GPP network function elements to the outside world.

[0117] 8. User plane function (UPF): can be used for packet routing and forwarding, or QoS parameter processing of user plane data, etc. User data can be accessed to the data network (DN) through this network element. In the embodiment of the present application, it can be used to implement the functions of the user plane network element.

[0118] 9. Charging function network element (network data analytics function, CHF): responsible for generating charging data records (CDR), also known as call bills, and transmitting them to the charging gateway function (CGF). Finally, CGF creates CDR files and forwards them to relevant processing devices in the charging domain. At the same time, CHF, as the quota control node for online billing, performs online billing rate processing for various services of users, and completes real-time settlement of user fees through ABMF.

[0119] 10. Unified data repository (UDR): used to store user contract data, business policy data, unstructured data, etc.

[0120] 11. Operation, administration and maintenance (OAM): The main functions of OAM include: network resource (such as wireless access network resources, core network element resources, transmission network resources, etc.) management, fault management and performance management. OAM can effectively improve the network management and maintenance capabilities of Ethernet and ensure the stable operation of the network.

[0121] In this network architecture, the N2 interface is the interface between the RAN and AMF network elements, which is used to send wireless parameters, NAS signaling, etc.; the N3 interface is the interface between the RAN and UPF network elements, which is used to transmit user plane data, etc.; the N4 interface is the interface between the SMF network element and the UPF network element, which is used to transmit information such as service policies, tunnel identification information of the N3 connection, data cache indication information, and downlink data notification messages.

[0122] It should be understood that the above-mentioned network architecture applied to the embodiments of the present application is merely an example of a network architecture described from the perspective of a traditional point-to-point architecture and a service-oriented architecture. The network architecture applicable to the embodiments of the present application is not limited to this. Any network architecture that can realize the functions of the above-mentioned network elements is applicable to the embodiments of the present application.

[0123] It should be understood that Figure 1 The interface name between the network elements is only an example. The interface name in the specific implementation may be other names, and this application does not specifically limit this. In addition, the name of the message (or signaling) transmitted between the above network elements is only an example and does not constitute any limitation on the function of the message itself.

[0124] As the amount of data continues to increase, it often takes a long time for a single machine to train the model, so a distributed machine learning system is needed to support it, and multiple machines are used to jointly complete the model training to shorten the training time. These multiple machines can be connected in series or in parallel according to the performance of the machine, and each completes the part they are responsible for. As an example and not a limitation, the embodiment of the present application is introduced by taking the federated learning model in the distributed machine learning system as an example.

[0125] In order to avoid leaking privacy and affecting data compliance, and to protect data privacy and security, we can consider using model training methods to extract the features of private data and establish a virtual shared model, so as to obtain the features of the data through the model without obtaining the original data on the network side. Federated Learning (FL) is a feasible solution to meet privacy protection and data security. Currently, Federated Learning can ensure that data does not leave the local area, and through parameter exchange under an encryption mechanism, a virtual shared model is established without violating data privacy regulations. This virtual model is like the optimal model established by everyone aggregating data together. However, when establishing a virtual model, the data itself does not move, and does not leak privacy or affect data compliance. In this way, the built models only serve local targets in their respective regions.

[0126] Federated learning is divided into vertical federated learning, horizontal federated learning and federated transfer learning. Vertical federated learning means that when the users (or samples) of two data sets have a lot of overlap but the user features have a little overlap, the data sets are divided vertically (i.e., the feature dimension), and the part of the data where the users of both parties are the same but the user features are not exactly the same is taken out for training. Horizontal federated learning means that when the users of two data sets have a little overlap but the user features overlap a lot, the data sets are divided horizontally (i.e., the user or sample dimension), and the part of the data where the users of both parties are different is taken out for training separately. Federated transfer learning means that when the users and user features of two data sets have little overlap, the model obtained by training one of the data sets is applied to the other data set for training. The present invention only relates to vertical federated learning and horizontal federated learning.

[0127] Figure 2 The following is a schematic diagram of the federated learning system framework. The system architecture consists of two parts: encrypted sample alignment and encrypted model training. After determining the common user group, the data can be used to train the machine learning model. In order to ensure the confidentiality of the data during the training process, encrypted training is required with the help of a third-party collaborator C. Taking the linear regression model as an example, the training process can be divided into the following four steps:

[0128] Step 1: Collaborator C distributes the public key to A and B to encrypt the data that needs to be exchanged during the training process.

[0129] Step 2: A and B exchange the intermediate results of the gradient calculation in encrypted form. The specific process is as follows:

[0130] Client A has a dataset Client B has a data set. where y i is the label data, then the model to be trained is as follows:

[0131]

[0132] Assume that the objective function for linear regression is: min L

[0133] Where L is the loss function, as follows:

[0134]

[0135] Since the original data D on A and B A and D B It is impossible to aggregate them together and cannot be based on the traditional centralized training method. The training method based on vertical federation is as follows:

[0136] make Then the L transformation is as follows:

[0137]

[0138] make So,

[0139] L=L A +L B +L AB Formula 4

[0140] make Then L is about θ A and θ B The gradient is as follows:

[0141]

[0142]

[0143] Accordingly, the model parameters are updated as follows:

[0144]

[0145]

[0146] The training process of vertical federated learning is as follows:

[0147] (1) Client A and Client B initialize model parameters θ respectively A and θ B ;

[0148] (2) Client A based on θ A And local data calculate and L A , and then send it to Client B;

[0149] (3) Client B based on θ B And local data calculate Further based on and i Calculate d i , L AB , L B , and finally based on L A , L AB , L B L is calculated. Client B will i Sent to Client A.

[0150] In step 3, A and B perform calculations based on the encrypted gradient values ​​respectively, while B calculates the loss based on its label data and summarizes these results to C. C calculates the total gradient by summarizing the results and decrypts it.

[0151] Step 4: C sends the decrypted gradients back to A and B respectively, and A and B update the parameters of their respective models based on the gradients.

[0152] Iterate the above steps until the model training end conditions are met, such as the number of iterations reaches a certain threshold (such as 10,000 times) and the loss L is less than a certain threshold (such as 0.00001), thus completing the entire training process.

[0153] After training, in the inference phase, A and B are based on the trained model parameters θ A and θ B Compute local inference results as well as That is, the model inference results of the business are obtained based on the trained model parameters and the private data of the business.

[0154] During the sample alignment and model training process, the data of A and B are retained locally, and the data interaction in the previous training will not lead to data privacy leakage.

[0155] It should be noted that the vertical federated learning model is only a possible training model for implementing the communication method in the embodiment of the present application, and should not constitute any limitation to the present application. The present application does not exclude the use of other distributed training models or the definition of other models in the future or the use of other methods to establish a shared model and jointly use their respective data without violating data privacy regulations. As long as the methods can achieve the same or similar functions mentioned above, they are within the scope of protection of the present application.

[0156] The current 5G network lacks a service experience evaluation mechanism. In the prior art, attempts are made to guarantee rich and varied 5G services through fixed QoS parameters, which makes it impossible to accurately match service experience requirements and network resources. At present, the base station can provide information such as the available rate of the UE air interface and the status of the UE air interface buffer, and send it to the TCP sender through the transmission control protocol acknowledgement (TCP ACK) extension. Then the TCP sender or the TCP receiver can adjust the initial congestion control window or the congestion avoidance interface congestion window of the service according to the wireless status, thereby ensuring the service experience. However, to improve the service experience, the information provided by the current network is not enough for the application layer to optimize the QoS parameters. That is to say, in addition to the above-mentioned air interface information on the access network side, there are many private parameters on the network side that affect the service experience. Due to the protection of data privacy, the network side cannot provide these private data. Therefore, in the prior art, the service provider cannot accurately adjust the application layer parameters and cannot guarantee the service experience.

[0157] Therefore, in order to solve the above problems, an embodiment of the present application provides a communication method, so that the service provider can update local parameters according to the network side service experience model inference results or service requirements.

[0158] Specifically, in the present application, the service experience or service flow experience model parameters can be first obtained according to the above-mentioned vertical federation training model. Then, NWDAF or PCF (i.e., an example of the first network device) obtains the model reasoning result (i.e., an example of the analysis result) of the terminal for the private data (i.e., an example of the first data) of the service or the service flow in each domain. For example, the first network device obtains the model reasoning result of the service experience of the terminal for the service or the service flow in the CN domain (i.e., an example of the second network device) (i.e., an example of the first analysis result), the model reasoning result of the service experience in the RAN domain (i.e., an example of the third network device) (i.e., an example of the second analysis result) or the model reasoning result of the service experience in the AF domain (i.e., an example of the fourth network device) (i.e., an example of the third analysis result). Then, the PCF network element will determine the size relationship between the model reasoning result of the service experience and the service experience or the service flow experience requirement (i.e., an example of the second service experience information). If the service experience model reasoning result of the terminal cannot meet the size of the service or the service flow experience requirement, at this time, the PCF network element will try to calculate new QoS parameters. When PCF cannot calculate the appropriate QoS parameters, it means that the network side has been adjusted to the limit. The first network device will send the network side service experience model inference result or service flow requirement (i.e., an example of the first service experience information) to the application function device (i.e., an example of the fourth network device). The fourth network device determines the local application layer QoS parameters based on the service experience model inference result or service flow requirement. For ease of understanding, the process of determining the QoS parameters is described in detail below.

[0159] As an example but not limitation, a multi-criteria decision-making (MCDM) method is used as an example to introduce that the process of the fourth network device determining the local application layer QoS parameters according to the service experience model reasoning result or the service flow requirement is a process of solving the following equations according to the MCDM algorithm:

[0160]

[0161] The fourth network device solves the above equations to determine The corresponding QoS parameters are used to make the service experience on the fourth network device "as high as possible", the energy consumption "as low as possible", the cost "as low as possible" and other goals as much as possible. This is a typical multi-objective optimization problem. Unlike single-objective optimization, which has only one optimal solution, multi-objective optimization usually has multiple solutions, called Pareto optimal solutions; in principle, the more objectives there are, the fewer the number of optimal solutions.

[0162] It should be noted that in the process of describing the embodiments in conjunction with the accompanying drawings hereinafter, the figures are only for illustration to facilitate understanding and shall not constitute any limitation to the present application. In addition, the figure shows that NWDAF may correspond to the data analysis function network element, CN corresponds to the core network, AMF may correspond to the access and mobility management network element, SMF may correspond to the session management network element, PCF may correspond to the policy control network element, AF represents the application function network element, and RAN represents the radio access network element or the radio access network device. The names of the network elements are defined only to distinguish different functions and shall not constitute any limitation to the present application. The present application does not exclude the possibility of defining other network elements to implement the same or similar functions.

[0163] Figure 3 1 is a schematic flow chart of the communication method 100 provided in the present application. As an example and not a limitation, Figure 3 The first network device may be a data analysis device or a policy control device, the second network device may be a core network device, the third network device may be a wireless access network device, and the fourth network device may be an application function device.

[0164] S101: A first network device obtains first information sent by a second network device, where the first information includes a first analysis result of first data of a terminal on the second network device.

[0165] It should be understood that the first information may be an analysis result of the service experience data of the terminal in the core network domain, that is, an inference result corresponding to the service experience model, and the first data includes private data corresponding to the terminal in the core network domain.

[0166] S102: The first network device obtains second information sent by the third network device, where the second information includes a second analysis result of the first data of the terminal on the third network device.

[0167] It should be understood that the second information may be an analysis result of service experience data of the terminal in the wireless access network domain, that is, an inference result corresponding to the service experience model, and the first data includes private data corresponding to the terminal in the wireless access network domain.

[0168] S103: The first network device determines first service experience information of the service of the terminal according to the first information and the second information.

[0169] As an example, if the first network device is a data analysis device, the data analysis device can determine the first service experience information based on the analysis results of the service experience data of the terminal in the core network domain and the analysis results of the service experience data of the terminal in the wireless access network domain. For example, the first service experience information can be the maximum service experience requirement that can be met by the network side, and the first service experience information can also be the minimum service experience requirement that needs to be met by the fourth network device.

[0170] S104: The first network device sends first service experience information to the fourth network device, where the first service experience information is used to determine parameters of the terminal's service on the fourth network device.

[0171] As mentioned above, the fourth network device may utilize a multi-criteria decision algorithm and calculate and update local application layer parameters according to the first service experience information.

[0172] According to the communication method provided in the present application, the first network device obtains the analysis results of the terminal's service experience data for the service on the second network device and the third network device, and sends the data analysis results of the service flow to the application function network element. The application function network element can adjust parameters based on the model inference results of each domain, thereby improving the accuracy of the application function network element's adjustment of application layer parameters, thereby improving the service experience of the terminal for the service.

[0173] Figure 4 It is a schematic flow chart of the communication method 200 of the first specific embodiment of the present application.

[0174] Figure 4 The method 200 may be performed by Figure 1 The radio access network RAN, the core network CN (for example, the access and mobility management function network element AMF, the session management function network element SMF, the user plane function network element UPF), the policy control function network element PCF, the data analysis function network element NWDAF and the application function network element AF in the system shown are executed. As an example and not a limitation, in the method of this embodiment, service A is taken as an example for explanation. It should be noted that in this embodiment, service A can be a certain service or a service flow, and this application does not impose any limitation on the number and type of services.

[0175] In this embodiment, NWDAF (i.e., an example of the first network device) obtains the model reasoning result of the terminal for private data (i.e., an example of the first data) of service A in the CN domain (i.e., an example of the second network device) (i.e., an example of the first data) and the model reasoning result of private data in the RAN domain (i.e., an example of the third network device) (i.e., an example of the second analysis result of the first data); NWDAF determines the model reasoning result of the network-side service experience (i.e., an example of the first service experience information) based on the model reasoning result of the CN domain private data and the model reasoning result of the RAN domain private data, and then the application function network element (i.e., an example of the fourth device) determines the AF local application layer parameters based on the model reasoning result of the network-side service experience.

[0176] like Figure 4 As shown, each step is described in detail below.

[0177] S201, the PCF sends a request #1 to the NWDAF to subscribe to the NWDAF for the analysis result of the service experience data of the terminal when using service A, that is, the inference result corresponding to the service experience model.

[0178] Request #1 may include one or more of the following information: an analytics ID, an application ID, and a UE ID (eg, a subscription permanent identifier (SUPI)).

[0179] Specifically, in a possible implementation, the PCF triggers the Nnwdaf_AnalyticsSubscription_Subscribe service operation to the NWDAF, and subscribes to the NWDAF the service experience data analysis result of the terminal using service A. The Nnwdaf_AnalyticsSubscription_Subscribe service operation includes the following information: For example, AnalyticsID = Service Experience, which is used to indicate that the PCF subscribes to the data analysis result of the service experience type from the NWDAF. In addition, the Analytics ID can also be used to determine the service experience model used to generate the service experience data analysis result; Analytics Filter, which is used to indicate the filtering information of the service experience data analysis result to be requested, such as Application ID, which is used to indicate the service identifier of the service; Target of Analytics Reporting, which is used to indicate the object of the model inference result to be requested, such as SUPI, which is used to indicate the terminal identifier of the terminal.

[0180] It should be understood that in the embodiment of the present application, the request may be for a business model inference result of one or part of the terminals of the service A, or it may be for all the terminals of the service A. The present application does not impose any limitation on the number of terminals.

[0181] S202: NWDAF determines identification information of a service experience model of service A.

[0182] In one possible implementation, NWDAF can determine that the business experience data analysis result of business A needs to be inferred through the business experience model based on the analysis identifier Analytics ID, and determine that the business experience model is based on longitudinal federated learning training based on historical training records. It should be understood that the identification information of the model can be one or more of Model ID, internet protocol address (IP) address, uniform resource locator (URL), and fully qualified domain name (FQDN). In other words, both the analysis identifier and the model identification information can be used to determine the business experience model used in the process of the business experience data analysis result.

[0183] As mentioned before, the vertical federated learning model is as follows:

[0184]

[0185] Among them, x i represents the i-th sample data, where It is a local private data vector distributed on the RAN for service A terminals. It is the local private data vector of the service A terminal distributed on the CN. It is the local private data vector distributed on AF for service A terminal. It is the public data vector actively reported by RNA, CN and AF in the sample data.

[0186] It should be understood that the private data in the embodiment of the present application includes data that cannot be reported on each network element or non-standardized data, wherein the network element can determine which data cannot be reported to the NWDAF based on data privacy or data volume or the equipment vendor policy described by the network element. For example, a base station equipment vendor may be unwilling to report private parameters of the RAN, such as energy-saving parameters, positioning parameters, and radio resource management parameters, in order to protect product interests.

[0187] It should be understood that in the embodiment of the present application, the public data includes data or standardized data that each network element can report to the NWDAF, wherein the network element can determine which data can be reported to the NWDAF based on data privacy or data volume or the equipment vendor policy described by the network element. For example, the public data reported by each network element may include the wireless signal quality reported by the RAN: reference signal received power (reference signal received power, RSRP), reference signal received quality (reference signal received quality, RSRQ), signal to interference plus noise ratio (signal to interference plus noise ratio, SINR), etc.; QoS related parameters reported by the UPF: flow rate (QoS flow bit rate), flow delay (QoS flow packet delay), flow packet error rate (QoS flow packet errorpate), etc.; service flow related parameters reported by the AF: application layer cache size (buffer size) corresponding to the service flow, service experience (service experience) of the service flow, etc.

[0188] It should be understood that A ,θ B ,θ C ,θ D They are The corresponding model parameters are model parameter vectors trained by each domain based on local private data or public data reported by each domain. Each model parameter vector includes one or more model parameters.

[0189] It should be understood that the model parameters of the vertical federated learning model in this application are trained in advance, and the trained model parameters are stored locally in each domain. The business experience model used in the business A model reasoning stage can be determined by analyzing the identification information and / or the model. This application mainly describes the model reasoning process.

[0190] S203, NWDAF sends a request to each domain to request the terminal for the model inference result and / or public data for service A.

[0191] In some embodiments, the NWDAF sends a subscription request to the CN and the RAN, respectively requesting to subscribe to the model inference results for the service A terminal in the core network domain and the access network domain.

[0192] In some embodiments, NWDAF sends a subscription request to CN and RAN, respectively requesting to subscribe to the model inference results and public data (ie, an example of the second data) for the service A terminal in the core network domain and the access network domain.

[0193] In some other embodiments, the NWDAF sends subscription requests to the CN, RAN and AF, respectively requesting to subscribe to the model inference results for the service A terminal in the core network domain, the access network domain and the service provider.

[0194] In some other embodiments, NWDAF sends subscription requests to CN, RAN and AF, respectively for requesting to subscribe to model inference results and public data for service A terminal in the core network domain, access network domain and service provider.

[0195] S203a, NWDAF sends request #2 (ie, an example of the first request) to CN, for subscribing the model inference result of the terminal regarding the service experience of service A in the core network domain to CN.

[0196] In some embodiments, request #2 may also be used to subscribe the terminal to the CN's public data about service A in the core network domain.

[0197] Request #2 includes the following content: the first identifier of the terminal and at least one of the following information: an analysis identifier and identification information of a first model, wherein the analysis identifier and / or identification information of the first model is used to determine the model used by the terminal for service experience model inference on the core network device.

[0198] Specifically, in a possible implementation, NWDAF triggers the Nnf_AnalyticsSubscription_Subscribe service operation of 5GC NF to subscribe to CN for the model inference result of the terminal's service experience in the core network domain for service A. The service operation includes a terminal identifier, such as SUPI or GPSI, and identification information of the service A model, such as one or more of Model ID, IP address, URL, and FQDN.

[0199] In a possible implementation, the NWDAF triggers the Nnf_EventExposure_Subscribe service operation of the 5GC NF to subscribe the public data of the terminal in the core network domain for service A to the 5GC NF. The service operation includes the data type Event ID of the public data in the core network domain and the terminal identifier SUPI.

[0200] S203b, NWDAF sends request #3 (i.e., an example of the second request) to RAN to subscribe to the model inference result of the service experience of the terminal in the RAN domain.

[0201] In some embodiments, request #3 may also be used to subscribe the terminal to the RAN for public data about service A in the access network domain.

[0202] Request #3 also includes the following content: a second identifier of the terminal and at least one of the following information: an analysis identifier and identification information of a second model, wherein the analysis identifier and / or identification information of the second model is used to determine the model used by the terminal for inferring the service experience model on the access network device.

[0203] It should be understood that the identification information of the terminal in the embodiments of the present application can be one or more of the following: internet protocol address (internet protocol, IP), subscription permanent identifier (subscription permanent identifier, SUPI), permanent equipment identifier (permanent equipment identifier, PEI), generic public subscription identifier (generic public subscription identifier, GPSI), international mobile subscriber identifier (international mobile subscriber identifier, IMSI), international mobile equipment identity (international mobile equipment identity, IMEI), IP address and mobile station international integrated service digital network number (mobile station international integrated service digital network number, MSISDN). In the following embodiments, any identification information related to the terminal (such as the first identification of the terminal, the second identification of the terminal, etc.) can refer to the description here, and will not be repeated later.

[0204] Specifically, in a possible implementation, NWDAF sends a subscription message to RAN to subscribe to the service experience model inference result of the service A terminal in the access network domain. The subscription message includes the identification information of the service experience model, such as one or more of Model ID, IP address, URL and FQDN, and the access network allocates the identification RAN UE NGAP ID to the terminal on the NG or N2 interface, wherein the NG or N2 interface is the interface between RAN and AMF.

[0205] In a possible implementation, the NWDAF sends a subscription request to the RAN to subscribe to the public data of the terminal in the access network domain for service A. The subscription message includes the data type RANParameter Type of the public data in the access network domain and the identifier RAN UE NGAP ID allocated by the access network to the terminal on the NG or N2 interface.

[0206] In some embodiments, step S203c may also be included, where the NWDAF sends a request #4 (ie, an example of the third request) to the AF, for subscribing to the AF a model inference result of the terminal regarding the service experience of service A in the AF domain.

[0207] In some embodiments, request #4 may also be used to request the AF for the public data of the terminal regarding service A in the AF domain.

[0208] Request #4 also includes the following content: a third identifier of the terminal and at least one of the following information: an analysis identifier and identification information of a third model, wherein the analysis identifier and / or identification information of the third model is used to determine the model used by the terminal for service experience model reasoning on the AF.

[0209] In some embodiments, as a possible implementation, the NWDAF triggers the Naf_AnalyticsSubscription_Subscribe service operation to the AF to subscribe to the AF for the model inference result of the service experience of the terminal in the AF domain. The service operation includes identification information of the service experience model, such as one or more of Model ID, IP address, URL and FQDN, and the terminal identification may include a user permanent identifier SUPI or a general public user identifier GPSI.

[0210] In some embodiments, as a possible implementation, the NWDAF triggers the Naf_EventExposure_Subscribe service operation to the AF to subscribe to the public data of the terminal in the AF domain. The service operation includes the data type Event ID of the public data in the AF domain, the terminal identifier SUPI or GPSI.

[0211] S204, each domain receives the subscription request from NWDAF, generates a local model inference result of the terminal in each domain for service A, and sends a response to NWDAF, where the response includes the local model inference result of each domain.

[0212] As mentioned above, after the vertical federated learning training is completed, for example, the private data of terminal #1 about service A in each domain is In the inference phase, each domain will be based on the trained model parameters θA ,θ B ,θ C ,θ D Computing terminal #1 local inference results for business A The private data of terminal #2 in each domain is In the inference phase, each domain will be based on the trained model parameters θ A ,θ B ,θ C ,θ D Computing terminal #2 local inference results about business A Similarly, for terminal #n, each domain will be based on the trained model parameters θ A ,θ B ,θ C ,θ D Compute terminal #n about the local inference results of business A That is to say, for multiple terminals, each domain will calculate the model inference results of each terminal locally, and finally each domain will send the model inference results of multiple terminals to NWDAF.

[0213] Exemplarily, in a possible implementation, for service A, RAN calculates and obtains the model inference results of n terminals, that is, RAN aggregates the model inference results of multiple terminals and sends them to NWDAF. In other words, RAN sends the model inference results to NWDAF. In fact, it includes the model inference results of multiple terminals in the RAN domain. For the convenience of expression, the embodiment of the present application uses the model inference results of multiple or one terminal as The model inference results of the terminal in other domains later also represent the model inference results of multiple or one terminal, which will not be repeated here.

[0214] It should be understood that in some embodiments, when public data exists in each domain, each domain will also simultaneously send local public data corresponding to the inference data results of each terminal in each domain, and the public data can be matched through associated information.

[0215] S204a, CN sends a response #1 (ie, an example of a first response) to the NWDAF.

[0216] Response #1 is used for CN to report the terminal's model inference results about service A in the core network domain (i.e., an example of the first information). Response information a also includes association information, i.e., the association information between the terminal and RAN and AMF (i.e., an example of the first association information), and the association information between the terminal and UPF and AF (i.e., an example of the second association information).

[0217] It should be understood that the association information between RAN and AMF and the association information between UPF and AF are intended to distinguish each terminal and its source, that is, each terminal will be assigned a unique identifier on the corresponding interface, so that each terminal and its source can be distinguished.

[0218] In a possible implementation, the CN triggers the Nnf_AnalyticsSubscription_Notify service operation to the NWDAF to send the model inference result of the service experience of the terminal in the core network domain to the NWDAF, for example, The service operation also includes: the association information between the terminal and the RAN and AMF, such as the RAN UE NGAP ID, the global unique identifier of the RAN, the timestamp when the data used for inference in the core network domain is generated on the core network element, that is, Timestamp, and the association information between the terminal and the UPF and AF, such as,

[0219] IP quintuple (i.e., source IP address, destination IP address, source port number, destination port number, protocol number), and the timestamp of the data generated by the UPF on the core network side for inference;

[0220] In some embodiments, when public data exists on the CN, the response information a is used to indicate to the CN the public data of the terminal in the core network domain. In one possible implementation, the CN triggers the Nnf_EventExposure_Notify service operation to the NWDAF to send the public data of the terminal in the core network domain and the association information between the terminal in the RAN and the AMF, and the association information between the terminal in the UPF and the AF to the NWDAF.

[0221] S204b: RAN sends a response #2 (ie, an example of a second response) to the NWDAF.

[0222] Response #2 is used by RAN to indicate to NWDAF the model inference result of the terminal regarding service A in the access network domain (i.e., an example of the second information). Response #2 may also include the association information between the terminal and the AMF.

[0223] In a possible implementation, the RAN sends a RAN side data analysis result notification message to the NWDAF, where the message includes a model inference result of the service experience of the terminal in the access network domain. For example, And the association information between the terminal and the AMF, including the RAN UE NGAP ID, the RAN's globally unique identifier Global RAN Node ID, and the timestamp when the data used for inference on the access network side is generated on the access network;

[0224] In some embodiments, when public data exists on the RAN, response #2 is also used for the RAN to send the public data of the terminal in the access network domain to the NWDAF. In a possible implementation, the RAN sends a RAN side data notification message to the NWDAF, which includes the public data of the terminal in the access network domain and the corresponding association information between the terminal in the RAN and the AMF, for example, the RAN UE NGAP ID, the global unique identifier of the RAN Global RAN Node ID, and the timestamp when the data used for inference locally on the access network side is generated on the access network.

[0225] In some embodiments, the method further includes step S204c, where the AF sends a response #3 (ie, an example of a third response) to the NWDAF.

[0226] Response #3 is used for AF to send the terminal the model inference result of service A in the AF domain (ie, an example of the third information). Response #3 may also include the association information between the UPF and AF of the terminal.

[0227] In some embodiments, as a possible implementation, the AF triggers the Naf_AnalyticsSubscription_Notify service operation to the NWDAF to send the model inference result of the service experience of the terminal in the application domain to the NWDAF, for example, And the corresponding association information between the UPF and AF of the terminal, for example, the IP five-tuple, the Timestamp when the public data on the AF domain of the third-party application is generated;

[0228] In some embodiments, as a possible implementation, when public data exists on the AF, response #3 is also used for the AF to report the public data of the terminal in the application domain. In a possible implementation, the AF triggers the Naf_EventExposure_Notify service operation to the NWDAF to send the public data of the terminal in the AF domain and the corresponding association information between the UPF and the AF of the terminal to the NWDAF.

[0229] S205 , the NWDAF receives the response information and determines the inference result of the service experience data model of the terminal regarding each domain of service A.

[0230] Specifically, NWDAF may determine the inference result of the service experience data model of the terminal regarding each domain of service A through the association information.

[0231] Normally, when NWDAF needs to perform end-to-end data analysis of each terminal between RAN, CN, and AF, it needs to consider associating the data of each terminal distributed on RAN, CN, and AF. Generally, NWDAF associates the data of terminals in each domain with each other through association identifiers, thereby finally determining the data of each terminal in each domain.

[0232] It should be understood that in the embodiment of the present application, RAN, CN and AF all report the model inference results and associated information of each terminal in each domain to NWDAF. According to the associated information reported by each domain, NWDAF can aggregate the model inference results of each terminal in the RAN domain, CN domain and AF domain, that is, NWDAF obtains the model inference results of the service experience of each terminal in each domain through the associated information aggregation.

[0233] In a possible implementation, NWDAF may adopt the following association method:

[0234] NWDAF associates the model inference results of the terminal in the core network domain based on the association information between RAN and AMF And the model inference results of the terminal in the access network domain Finally, the terminal obtains the local model inference results in each domain

[0235] In some embodiments, as a possible implementation, NWDAF may adopt the following association method:

[0236] NWDAF associates the model inference results of the terminal in the core network domain based on the association information between RAN and AMF And the model inference results of the terminal in the access network domain Then, the model inference results of the terminal in the core network domain are further associated with the association information between UPF and AF. And the model inference results of the terminal in the AF domain Finally, the terminal obtains the local model inference results in each domain

[0237] It should be understood that the association method in the embodiments of the present application is merely an example and should not constitute any limitation to the present application. The present application does not exclude the possibility of using other association methods between network elements to achieve the same or similar functions.

[0238] In some embodiments, when each domain sends public data, NWDAF will infer the public data. For example, in an embodiment of the present application, if each domain sends public data, then, as a possible implementation method, NWDAF associates the public data of the terminal in the core network domain and the public data of the terminal in the access network domain according to the association information between RAN and AMF, for example, Then NWDAF is based on the local model parameters θ D Determine inference results for public data

[0239] In some other embodiments, when each domain sends public data, NWDAF will infer the public data. For example, as a possible implementation, NWDAF associates the public data of the terminal in the core network domain and the public data of the terminal in the access network domain according to the association information between RAN and AMF, and then further associates the public data of the terminal in the core network domain and the public data of the terminal in the AF domain according to the association information between UPF and AF, and finally obtains the public data of the terminal in each domain, for example, Then NWDAF is based on the local model parameters θ D Determine inference results for public data

[0240] It should be understood that the NWDA local reasoning result may include one or more of the core network domain, access network domain, and application domain, depending on whether each domain reports its own public data. The situation described in the embodiment of the present application is that the core network domain, access network domain, and application domain all report their own public data, so the NWDA local reasoning result is the common reasoning result of the public data of the three parties, but this situation is only an example and should not be used to limit the embodiment of the present application.

[0241] Exemplarily, when the model reasoning results of each domain are linear results, NWDAF can summarize the service experience model reasoning results of the terminal in each domain by summing them; Exemplarily, when the model reasoning results of each domain are logical quantities, NWDAF can first summarize the service experience model reasoning results of the terminal in each domain by summing them, and then obtain the final service experience model reasoning results by logarithmic operation. It should be understood that the above is only an example, and this application does not impose any restrictions on the way NWDAF summarizes the service experience model reasoning results. According to the actual situation, NWDAF can flexibly calculate and obtain the model reasoning results of the terminal's service experience in each domain.

[0242] In some embodiments, the model inference result of the terminal service experience finally summarized by NWDAF may be:

[0243] In some embodiments, the model inference result of the terminal service experience finally summarized by NWDAF may be:

[0244] In some other embodiments, the model inference result of the terminal service experience finally summarized by NWDAF may be:

[0245] In some other embodiments, the model inference result of the terminal service experience finally summarized by NWDAF may be:

[0246] It should be noted that NWDAF finally summarizes the model inference results of the terminal in each domain, which may be the average value or variance value of the model inference results of multiple terminals in each domain.

[0247] S206, NWDAF sends a response #4 to PCF.

[0248] Response #4 is used by NWDAF to send the data analysis results of the terminal's service experience to PCF, that is, the above-mentioned model inference results. As a possible implementation method, NWDAF triggers the Nnwdaf_AnalyticsSubscript ion_Notify service to PCF and sends the terminal's service A model inference results to PCF.

[0249] In some other embodiments, as another possible implementation, NWDAF triggers the Nnwdaf_AnalyticsSubscription_Notify service to PCF and provides the terminal's service A model inference result to PCF.

[0250] S207, PCF determines QoS parameters of service A.

[0251] The PCF receives response #4 and determines the QoS parameters.

[0252] As a possible implementation method, PCF calculates new QoS parameters for service A based on the response information d. As mentioned above, PCF can calculate QoS parameters based on the terminal service model inference results and service experience requirements through a multi-criteria decision algorithm. If PCF can calculate appropriate QoS parameters, the network side adjusts the application layer parameters based on the new QoS parameters to improve the terminal's service experience for service A.

[0253] It should be noted that the experience requirement of service A in this embodiment (ie, an example of the second service experience information) may be pre-configured or pre-set by the network. For example, the experience requirement of service A is N (N>0), where N is a positive integer.

[0254] It should be noted that in the prior art, although PCF also calculates QoS parameters based on the "service experience data analysis results", the "service experience model data analysis results" in the prior art are different from the service experience model inference results of the embodiments of the present application. The terminal service model inference results in all embodiments of the present application refer to the model inference results of the private data of the service terminal in each domain, that is, NWDAF obtains information on the network side including private data and public data.

[0255] Based on the inference results of the terminal service experience model and the service experience requirements, PCF attempts to calculate new QoS parameters for the service and finds that it is no longer possible to calculate appropriate QoS parameters, indicating that the network side can no longer make adjustments.

[0256] S208, PCF sends first indication information to NWDAF.

[0257] The PCF sends the first indication information to the NWDAF, indicating that the network side adjustment of the NWDAF for the service of the terminal has reached the limit, but still cannot meet the service experience requirement.

[0258] S209, the NWDAF receives the first indication information and determines first service experience information, where the first service experience information is used to determine application parameters on the AF.

[0259] In some embodiments, the NWDAF determines the first service experience information based on the above indication information, the service experience requirements pre-configured by the network, the core network domain, the access network domain, and the inference result of public data.

[0260] In some embodiments, the first service experience information includes the sum of the service experience model reasoning results of the terminal in the core network domain and the access network domain:

[0261] As another example, when the service experience requirement pre-configured on the PCF network element or the NWDAF network element is a service experience MOS score greater than or equal to 3.0 points, and the service experience requirement that the RAN and the CN can meet at most is a MOS score less than or equal to 2.0 points, then the NWDAF sends the maximum service experience requirement MOS score that the network side can meet to the AF, that is, the value of 2.0 of the maximum service experience requirement that the network side can meet.

[0262] In some embodiments, the first service experience information includes the sum of the common data model inference results of the terminal in the core network domain, the access network domain and the NWDAF:

[0263] In some embodiments, the first service experience information includes the sum of model inference results of the service experience of the terminal in the core network domain, the access network domain, and the application domain:

[0264] In some embodiments, the first service experience information includes the sum of the model reasoning results of the terminal's public data service experience in the core network domain, the access network domain, the application domain, and the NWDAF:

[0265] In some other embodiments, the first service experience information includes a service experience requirement that needs to be met by the AF side:

[0266] As an example, when the service experience requirement pre-set by the network is that the service experience MOS score is greater than or equal to 3.0 points, and the service experience requirement that can be met by RAN and CN is at most MOS score less than or equal to 2.0 points, then for the AF side, the service experience requirement must at least meet a MOS score greater than or equal to 1.0 points, that is, NWDAF directly sends the calculated value of 1.0 that the AF side needs to meet the service experience requirement to the AF.

[0267] In some other embodiments, the first service experience information includes a service experience requirement that needs to be met by the AF side:

[0268] In some other embodiments, the first service experience information includes a service experience requirement that needs to be met by the AF side:

[0269] In some other embodiments, the first service experience information includes a service experience requirement that needs to be met by the AF side:

[0270] It should be understood that when each domain fails to report its own public data, the first service experience information here does not include the inference result of the public data, that is, does not include the NWDA local inference result.

[0271] S210, NWDAF sends the first service experience information to AF.

[0272] As a possible implementation manner, the NWDAF triggers the Nnwdaf_AnalyticsSubscription_Notify service operation to the AF, and sends the first service experience information to the AF.

[0273] S211, AF receives first service experience information, and determines a local application layer QoS parameter configuration for service A according to the first service experience information.

[0274] In some embodiments, the AF receives the first service experience information, that is, And a multi-criteria decision algorithm determines the local application layer QoS parameter configuration.

[0275] In some other embodiments, the AF firstly receives the first service experience information Determine the service experience requirements that need to be met on the AF side: Then, the local application layer QoS parameter configuration is further determined based on the service experience requirements that need to be met on the AF side and the MCDM algorithm.

[0276] In some embodiments, the AF receives the first service experience information, that is, And based on the MCDM algorithm, the local application layer QoS parameter configuration is determined.

[0277] In some other embodiments, the AF performs the following operations according to the first service experience information: Determine the service experience requirements that the AF network element needs to meet: Then, the local application layer QoS parameter configuration is further determined based on the service experience requirements that the AF network element needs to meet and the MCDM algorithm.

[0278] Through the method of this embodiment, NWDAF obtains the model inference results of the terminal for each domain of service A, and sends the model inference results of the service flow to the application function network element. The application function network element can adjust parameters based on the model inference results of each domain, thereby improving the accuracy of the application function network element's adjustment of application layer parameters, thereby improving the service experience of the terminal for the service.

[0279] Figure 5 It is a schematic flow chart of the communication method 300 of the second specific embodiment of the present application. Figure 5 The method 300 may be composed of Figure 1The RAN, core network elements (eg, AMF network element, UPF network element, SMF network element), PCF network element, NWDAF network element, and AF network element in the system shown are executed. In the method of this embodiment, service B is taken as an example for description as an example but not a limitation.

[0280] It should be understood that in the method of this embodiment, PCF is an example of a first network device, CN is an example of a second network device, RAN is an example of a third network device, and AF is an example of a fourth network device. It should be noted that this embodiment is merely exemplary and should not constitute any limitation to the present application. The first network device may also be other network elements, and the second network device, the third network device, and the fourth network device may also be other network elements.

[0281] like Figure 5 As shown, each step is described in detail below.

[0282] S301, during the establishment of service B initiated by the terminal or AF, the PCF activates the reasoning of the service experience model obtained based on the vertical federation training.

[0283] S301a, the UE triggers the service B establishment process, that is, the PDU Session Modification process initiated by the UE.

[0284] In some embodiments, the AF triggers the service B establishment process, which is the PDU Session Modification process initiated by the AF.

[0285] It should be understood that the embodiment of the present application does not impose any limitation on the subject of the process of triggering the service establishment, and the subject of the process of triggering the service establishment is only an example.

[0286] S301b, SMF sends request #5 to PCF.

[0287] Request #5 is used by the SMF to request the PCF for QoS parameters when the terminal uses service B in the session. Request #5 also includes one or more of the terminal identifier SUPI, the session identifier PDU Session ID, and the service identifier Application ID.

[0288] As a possible implementation, SMF triggers the Npcf_SMPolicyControl_UpdateRequest service operation to PCF, requesting PCF for QoS parameters for the terminal when using service B in the session. The service operation carries one or more of the following identifiers: terminal identifier SUPI, session identifier PDU Session ID, and service identifier Application ID.

[0289] S301c, PCF receives request #5 and determines to activate the model reasoning process corresponding to service B.

[0290] As a possible implementation, PCF receives request #5, and determines that it needs to request the service experience model inference result of service B from NWDAF according to the service identifier and local operator policy, so as to adjust the QoS parameters of the service. Then, PCF requests NWDAF to activate the service experience model corresponding to service B, and determines from NWDAF the identification information of the service experience model (one or more of Model ID, IP address, URL, and FQDN) and that the model is a vertical federation model. Finally, PCF decides to activate the inference process of the service experience model for the service of the terminal in the remaining PDU Session Modification process.

[0291] S301d, the PCF sends a request #6 to the CN, for requesting a model inference result of the service experience of the service B terminal in the CN domain.

[0292] In some embodiments, request #6 is also used to request public data for service B terminal in the CN domain.

[0293] Request #6 includes the first identification information of the terminal and at least one of the following information: an analysis identification and identification information of the first model. In some embodiments, request #6 may also include indication information a and indication information b.

[0294] In some embodiments, as a possible implementation, the PCF triggers the Npcf_SMPplicyControl_Update Response service operation to the CN, and the service operation includes the first identification information of the terminal, the identification Model ID of the service B model, the indication information a, and the indication information b. The indication information a is used to instruct the CN to report the service experience model inference result of the terminal for service B in the CN domain, and the indication information b is used to instruct the CN to report the public data of the terminal in the CN domain.

[0295] S301e, CN sends request #7 to RAN, for requesting the model inference result of the service experience of the service B terminal in the RAN domain.

[0296] In some embodiments, request #7 is also used to request public data for service B terminal in the RAN domain.

[0297] Request #7 includes the second identification information of the terminal and at least one of the following information: an analysis identification and identification information of the second model. In some embodiments, request #7 may also include indication information e and indication information f.

[0298] In some embodiments, as a possible implementation manner, the CN sends an N2PDU SessionRequest request to the RAN, the request including the identification information of the terminal, the identification Model ID of the service experience model of service B, indication information c and indication information d. The indication information c is used to instruct the RAN to report the model inference result of the service experience of the terminal for service B in the RAN domain, and the indication information f is used to instruct the RAN to report the public data of the terminal for service B in the RAN domain.

[0299] In some other embodiments, step S301f may be further included, where the PCF sends a request #8 to the AF to request a model inference result of the service experience of the service B terminal in the AF domain.

[0300] In some other embodiments, request #8 is also used to request public data for service B terminal in the AF domain.

[0301] Request #8 includes the third identification information of the terminal and at least one of the following information: an analysis identification and identification information of a third model. In some embodiments, request #8 may also include indication information e and indication information f.

[0302] In some embodiments, as a possible implementation, the PCF sends an Event Reporting service operation to the AF, which includes the identification information of the terminal (for example, the terminal identification SUPI or GPSI), the identification information of the model (one or more of ModelID, IP address, URL, and FQDN), indication information e, and indication information f. The indication information e is used to instruct the AF to report the model reasoning result of the terminal for the service B service experience in the AF domain, and the indication information f is used to instruct the AF to report the public data of the terminal on the AF.

[0303] S301g, RAN sends NAS signaling to UE to complete the service establishment process.

[0304] As a possible implementation manner, the RAN sends a NAS signaling of the PDU Session Modification Command type to the UE to complete the service establishment process.

[0305] S302, each domain receives the request from the PCF, and sends the model inference result of its own local business experience to the PCF.

[0306] In some embodiments, when public data exists in each domain, each domain will also send local public data at the same time.

[0307] S302a, RAN sends a response #5 to CN.

[0308] Response #5 is used by RAN to send the model inference results of the service experience of the service B terminal in the access network domain to CN. Response #5 may also include associated information.

[0309] As a possible implementation, the RAN sends an N2 message to the CN, which includes the model inference result of the terminal in the access network domain, for example, The N2 message also includes the association information between the terminal and the AMF, such as the RAN UE NGAP ID, the RAN's globally unique identifier Global RAN Node ID, and the timestamp when the local inference data on the access network side is generated.

[0310] In some other embodiments, when public data exists on the RAN, response #5 is used for the RAN to send public data for the service B terminal in the access network domain to the CN.

[0311] In some other embodiments, as a possible implementation method, the RAN sends an N2 message to the CN, which includes the public data of the terminal in the access network domain and the corresponding association information of the terminal between the RAN and the AMF.

[0312] S302b, CN receives response #5, and determines response #6 based on response #5.

[0313] In some embodiments, the CN determines response #6 according to response #5. Response #6 is used by the CN to send the model inference results of the access network domain and the core network domain service experience to the PCF, and response #6 also includes the association information between the UPF and the AF.

[0314] As a possible implementation method, CN first determines the inference data required for the local service experience in the CN domain and the association information between UPF and AF in the core network domain based on the association information between RAN and AMF, and further determines the model inference result of the CN domain service experience based on the local vertical federation model Model ID. Finally, the model inference results of the access domain and core domain service experience and the association information between UPF and AF are sent to PCF.

[0315] S302c, CN sends a response #6 to PCF.

[0316] As a possible implementation, the CN triggers the Npcf_SMPolicy Control_UpdateRequest service operation of the PCF, which includes the model reasoning results for the service experience of the service terminal in the RAN domain and the model reasoning results for the service experience of the service terminal in the CN domain. Response #6 may also include the association information between the UPF and the AF.

[0317] It should be understood that when the access network domain and the core network domain have public data, the response #6 also includes the public data of the terminal in the access network domain and the core network domain.

[0318] In some other embodiments, step S302d is also included, where the AF sends a response #7 to the PCF.

[0319] Response #7 is used by AF to send the model inference result of the terminal's service experience in the AF domain to PCF. Response #7 also includes the association information between UPF and AF.

[0320] As a possible implementation method, the AF sends the model inference result of the service experience of the service B terminal in the AF domain to the PCF, for example, And the corresponding association information between the UPF and AF of the terminal includes: IP quintuple, and Timestamp of the data used for reasoning in the AF domain when it is generated on the AF.

[0321] In some other embodiments, when public data exists on the AF, response #7 also includes the public data of the terminal in the AF domain. As a possible implementation, the AF sends the public data of the service B terminal in the AF and the corresponding association information between the terminal in the UPF and the AF to the PCF.

[0322] In some embodiments, when a domain reports local public data, step S303 is also included, where the PCF sends a request #9 to the NWDAF to request the NWDAF for the model inference results of the service B terminal in the RAN domain public data, the core network public data, or the AF public data.

[0323] It should be understood that when one or more domains in each domain report public data, NWDAF can infer the public data. As an example, in this embodiment, CN, RAN and AF all report public data, and NWDAF will infer the public data.

[0324] As a possible implementation method, NWDAF associates the public data of the terminal in the core network domain and the public data of the terminal in the AF domain according to the association information between UPF and AF, and finally obtains the public data of the terminal in each domain. Then NWDAF determines the inference result of the public data according to the local model parameters, for example,

[0325] It should be understood that in this embodiment, the public data of the terminal in CN, RAN and AF can be obtained according to the association information between UPF and AF. This is because CN has already summarized the local public data of CN domain and RAN domain in steps S320b and S320c.

[0326] In some embodiments, S304, the NWDAF sends a response #8 to the PCF, which is used to send the inference result of the public data on the NWDAF.

[0327] S305, PCF determines the model reasoning results of the service experience of each domain of service B.

[0328] In a possible implementation, PCF may determine the model inference results of the terminal in each domain in the following association manner:

[0329] PCF associates the terminal with the access network domain model inference result based on the association information between UPF and AF Model inference results for core domains And the model inference results of the terminal in the AF domain Finally, PCF obtains the model inference results of the terminal in each domain.

[0330] Optionally, when each domain sends public data, as a possible implementation method, PCF finally determines the service experience model inference result of the terminal

[0331] It should be noted that the embodiment of the present application does not impose any limitation on the way in which PCF aggregates the service experience model inference results. According to the actual situation, PCF can flexibly calculate and obtain the model inference results of the terminal's service experience in each domain.

[0332] It should be noted that PCF finally summarizes the model inference results of the terminal in each domain, which can be the average value or variance value of the model inference results of multiple terminals in each domain.

[0333] S306: PCF calculates QoS parameters according to the service experience model inference result of the terminal.

[0334] As a possible implementation method, PCF calculates the new QoS parameters of the service based on the inference results of the terminal's service experience model. As mentioned above, through the multi-criteria decision-making algorithm, based on the inference results of the terminal's service experience model and the service experience requirements, PCF attempts to calculate the new QoS parameters of the service and finds that it is no longer possible to calculate the appropriate QoS parameters, indicating that the network side can no longer make adjustments.

[0335] S307, the PCF determines first service experience information, where the first service experience information is used to determine parameters of service B on the AF.

[0336] In some embodiments, the PCF determines the service experience requirements that need to be met on the AF side according to the service experience requirements and the inference results of the core network domain service experience model and the access network domain service experience model:

[0337] As an example, when the network pre-configured service experience requirement is that the service experience MOS score is greater than or equal to 4.0 points, and the service experience requirement that the RAN domain and the CN domain can meet at most is a MOS score less than or equal to 3.0 points, then for the AF side, the service experience requirement must at least meet a MOS score greater than or equal to 1.0 points, that is, the PCF directly sends the calculated value of 1.0 of the service experience requirement that the AF domain needs to meet to the AF.

[0338] In some embodiments, the PCF determines the service experience requirements that the AF domain needs to meet based on the service experience requirements, the model reasoning results of the core network domain service experience, the model reasoning results of the access network domain service experience, and the reasoning results of the public data on the NWDAF:

[0339] In some embodiments, the PCF determines the service experience requirements that the AF domain needs to meet based on the service experience requirements, the model reasoning results of the core network domain service experience, the model reasoning results of the access network domain service experience, and the model reasoning results of the application domain service experience:

[0340] In some embodiments, the PCF determines the service experience requirements that need to be met in the AF domain based on the service experience requirements, the model reasoning results of the core network domain service experience, the model reasoning results of the access network domain service experience, the model reasoning results of the application domain service experience, and the public data model reasoning results on the NWDAF:

[0341] In some other embodiments, the PCF calculates the sum of the model inference results of the core network domain service experience and the model inference results of the access network domain service experience. Determine the first service experience information.

[0342] As another example, when the network pre-configured service experience requirement is a service experience MOS score greater than or equal to 3.0 points, and the service experience requirement that the RAN domain and the CN domain can meet at most is a MOS score less than or equal to 2.0 points, the PCF sends the maximum service experience requirement value of 2.0 that the network side can meet to the AF.

[0343] In some other embodiments, the PCF sums the model inference results of the core network domain service experience, the model inference results of the access network domain service experience, and the public data inference results on the NWDAF. Determine the first service experience information.

[0344] In some other embodiments, the PCF calculates the sum of the model inference results of the core network domain service experience, the model inference results of the access network domain service experience, and the model inference results of the AF domain service experience. Determine the first service experience information.

[0345] In some other embodiments, the PCF sums the model reasoning results of the core network domain service experience, the model reasoning results of the access network domain service experience, the model reasoning results of the AF domain service experience, and the public data model reasoning results on the NWDAF. Determine the first service experience information.

[0346] It should be understood that when each domain does not report its own public data, the first service experience information here does not include the public data reasoning result, that is, it does not include the local reasoning result on the NWDA, for example,

[0347] S308: The PCF sends the first service experience information to the AF.

[0348] As a possible implementation manner, the PCF triggers the EventReporting operation of the AF to send the first service experience information to the AF.

[0349] S309: The AF receives the first service experience information, and determines the AF domain application layer QoS parameter configuration of service B according to the first service experience information.

[0350] In some embodiments, the AF performs the following operations based on the first service experience information: And a multi-criteria decision algorithm determines the local application layer QoS parameter configuration.

[0351] In some embodiments, the AF performs the following operations based on the first service experience information: And a multi-criteria decision algorithm determines the local application layer QoS parameter configuration.

[0352] In some other embodiments, the AF firstly receives the first service experience information Determine the service experience requirements that need to be met on the AF side: Then, the local application layer QoS parameter configuration is further determined based on the service experience requirements that need to be met on the AF side and the multi-criteria decision algorithm.

[0353] In some other embodiments, the AF performs the following operations according to the first service experience information: And based on the multi-criteria decision-making algorithm, the local application layer QoS parameter configuration is determined.

[0354] In some other embodiments, the AF performs the following operations according to the first service experience information: Determine the service experience requirements that the AF domain needs to meet: Then, the local application layer QoS parameter configuration is further determined according to the service experience requirements that need to be met in the AF domain and the multi-criteria decision algorithm.

[0355] Through the method of this embodiment, PCF obtains the model inference results of the terminal for each domain of service B, and sends the model inference results of the service flow to the application function network element. The application function network element can adjust parameters based on the model inference results of each domain, thereby improving the accuracy of the application function network element's adjustment of application layer parameters, thereby improving the service experience of the terminal service.

[0356] It should be understood that the various embodiments described in the present application may be independent solutions or may be combined according to internal logic, and these solutions all fall within the protection scope of the present application.

[0357] It should be understood that the network devices in the embodiments of the present application are only RAN, CN, AF and related network elements, and should not constitute any limitation to the present application. The present application does not exclude the possibility of using one or more of them to achieve the same or similar functions in other application scenarios, and the present application does not exclude the possibility of using other one or more network elements to achieve the same or similar functions in other application scenarios.

[0358] It should also be noted that in the embodiments of the present application, "pre-setting", "pre-configuration", etc. can be achieved by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in a device (for example, a network device). The present application does not limit its specific implementation method, such as the preset rules and preset constants in the embodiments of the present application.

[0359] It should also be understood that in the various embodiments of the present application, the size of the serial number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0360] Combined with the above Figures 3 to 5 The communication method provided in the embodiment of the present application is introduced from the execution actions of a single device and the interaction behaviors between various devices. Figures 6 to 9 The communication device provided in the embodiment of the present application is introduced. It should be understood that the description of the device embodiment corresponds to the description of the method embodiment, so the contents not described in detail can be referred to the method embodiment above, and will not be repeated here for the sake of brevity.

[0361] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the interaction between various network elements. It can be understood that, in order to realize the above functions, each network element includes a hardware structure and / or software module corresponding to the execution of each function. Those skilled in the art should be aware that, in combination with the units and algorithm steps of each example described in the embodiments disclosed in this document, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0362] The embodiment of the present application can divide the functional modules of the transmitting end device or the receiving end device according to the above method example. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation. The following is an example of dividing each functional module corresponding to each function.

[0363] Figure 6 A schematic diagram of the structure of a communication device 100 is provided. The communication device includes a receiving unit 110, a processing unit 120, and a sending unit 130. The communication device 100 may be the first network device in the above method embodiment, that is, a data analysis device or a policy control device, or may be a chip for implementing the functions of the data analysis device or the policy control device in the above method embodiment.

[0364] It should be understood that the communication device 100 may correspond to the first network device in the method 100, the data analysis device in the method 200, and the policy control device in the method 300 according to the embodiment of the present application, and the communication device 100 may include a Figure 3 The method 100 in the first network device is performed by a unit of the method, Figure 4 The unit of the method performed by the data analysis device in the method 200, Figure 5 The units of the method executed by the policy control device in the method 300 in the communication device 100 are respectively for implementing Figure 3 Method 100 in Figure 4 Method 200, Figure 5 The corresponding process of method 300 in FIG.

[0365] The communication device 100 can realize Figure 1 The first network device in Figure 4 Data analysis equipment NWDAF and Figure 5 The communication method of each embodiment shown in the policy control device PCF includes:

[0366] The receiving unit 110 is configured to obtain first information from a second network device, where the first information includes a first analysis result of first data of the terminal on the second network device;

[0367] The receiving unit 110 is configured to obtain second information from a third network device, where the second information includes a second analysis result of the first data of the terminal on the third network device;

[0368] A processing unit 120, configured to determine first experience information of the service of the terminal according to the first information and the second information;

[0369] The sending unit 130 is configured to send the first experience information to a fourth network device, where the first experience information is used to determine a parameter of the service of the terminal on the fourth network device.

[0370] In a possible design, the specific implementation also includes:

[0371] A sending unit 130 is used to send a first request to the second network device, where the first request is used to request a first analysis result of the first data of the terminal on the core network device, and the first request includes first identification information of the terminal and at least one of the following information: an analysis identifier and identification information of a first model, where the analysis identifier and / or identification information of the first model is used to determine the first model corresponding to the first analysis result of the first data of the terminal on the core network device.

[0372] In a possible design, the specific implementation also includes:

[0373] A sending unit 130 is used to send a second request to the third network device, where the second request is used to request a second analysis result of the first data of the terminal on the third network device, and the second request includes second identification information of the terminal and at least one of the following information: identification information of the analysis identifier and the second model, where the analysis identifier and / or identification information of the second model is used to determine the second model corresponding to the second analysis result of the first data of the terminal on the third network device, and the third network device includes an access network device.

[0374] In another possible design, the specific implementation also includes:

[0375] The receiving unit 110 is configured to acquire, by the fourth network device, third information including a third analysis result of the first data of the terminal on the fourth network device.

[0376] In a possible design, the specific implementation also includes:

[0377] A sending unit 130 is used to send a third request to the fourth network device, where the third request is used to request a third analysis result of the first data of the terminal on the fourth network device, and the third request includes a third identifier of the terminal and at least one of the following information: identification information of the analysis identifier and a third model, where the analysis identifier and / or the identification information of the third model is used to determine the third model corresponding to the third analysis result of the first data of the terminal on the fourth network device, and the fourth network device includes an application function device.

[0378] In one possible design, the first information may also include first association information, wherein the first association information is used to associate the second information with the first information; and / or the second information may also include the first association information.

[0379] In one possible design, the first information may also include second association information, wherein the second association information is used to associate the first information with the third information; and / or the third information may also include the second association information.

[0380] In a possible design, the specific implementation also includes:

[0381] The first information may further include second data of the terminal on the second network device, and the second information may further include second data of the terminal on the third network device;

[0382] The processing unit 120 is configured to obtain a fourth analysis result according to the second data of the terminal on the second network device and the second data of the terminal on the third network device;

[0383] The processing unit 120 is configured to determine first service experience information of the service of the terminal according to the first information, the second information and the fourth analysis result.

[0384] In a possible design, a specific implementation also includes: the third information also includes second data of the terminal on the fourth network device.

[0385] The processing unit 120 is configured to determine first service experience information of the service of the terminal according to the first information, the second information, the third information and the fourth analysis result.

[0386] In a possible design, the specific implementation also includes:

[0387] The processing unit 120 is configured to determine the first experience information according to the first information, the second information, and second experience information required by the service.

[0388] Figure 7 A schematic diagram of the structure of a communication device 200 is provided. The communication device includes a receiving unit 210, a processing unit 220, and a sending unit 230. The communication device 100 may be a second network device in the above method embodiment, for example, a core network device or a third network device, for example, an access network device. It may also be a chip for implementing the functions of the core network device or the access network device in the above method embodiment.

[0389] It should be understood that the communication device 200 may correspond to the second network device or the third network device in the method 100 according to the embodiment of the present application, the core network device or the access network device in the method 200, and the core network device or the access network device in the method 300. The communication device 200 may include a Figure 3 A unit of the method performed by the second network device or the third network device in the method 100, Figure 4 The unit of the method performed by the core network device or the access network device in the method 200, Figure 5 The core network device or access network device in the method 300 in the method 300 is a unit of the method performed. In addition, each unit in the communication device 200 and the above-mentioned other operations and / or functions are respectively for implementing Figure 3 Method 100 in Figure 4 Method 200, Figure 5 It should be understood that the specific process of each unit executing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0390] Figure 8 A schematic diagram of the structure of a communication device 300 is provided. The communication device includes a receiving unit 310 and a processing unit 320. The communication device 300 may be the fourth network device in the above method embodiment, that is, the application function device, or may be a chip for implementing the function of the application function device in the above method embodiment.

[0391] It should be understood that the communication device 300 may correspond to the fourth network device in the method 100, the application function device in the method 200, and the application function device in the method 300 according to the embodiment of the present application, and the communication device 300 may include a Figure 3 The method 100 in which the fourth network device performs the method unit, Figure 4The unit of the method performed by the application function device in the method 200, Figure 5 The units of the method performed by the application function device in the method 300. In addition, the units in the communication device 300 and the above-mentioned other operations and / or functions are respectively for implementing Figure 3 Method 100 in Figure 4 Method 200, Figure 5 It should be understood that the specific process of each unit executing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0392] Fig. 9 It is a structural block diagram of a communication device 400 provided according to an embodiment of the present application. Fig. 9 The communication device 400 shown includes: a processor 410, a memory 420 and a transceiver 430. The processor 410 is coupled to the memory and is used to execute instructions stored in the memory to control the transceiver 430 to send and / or receive signals.

[0393] It should be understood that the processor 410 and the memory 430 can be combined into one processing device, and the processor 410 is used to execute the program code stored in the memory 430 to implement the above functions. In specific implementation, the memory 430 can also be integrated into the processor 410, or independent of the processor 410. It should be understood that the processor 410 can also correspond to each processing unit in the above communication device, and the transceiver 430 can correspond to each receiving unit and each sending unit in the above communication device.

[0394] It should also be understood that the transceiver 420 may include a receiver (or receiver) and a transmitter (or transmitter). The transceiver may further include an antenna, and the number of antennas may be one or more. The transceiver 420 may also be a communication interface or interface circuit.

[0395] In one possible design, the communication device 400 may be the first network device in the above method embodiment, or may be a chip for implementing the functions of the first network device in the above method embodiment.

[0396] Specifically, the communication device 400 may correspond to the first network device in the method 100, the data analysis device in the method 200, and the policy control device in the method 300 according to the embodiment of the present application. The communication device 400 may include a Figure 3 The unit of the method performed by the first network device in the method 100, Figure 4 The unit of the method performed by the data analysis device in the method 200, Figure 5The policy control device in the method 300 in the method 300 is a unit of the method executed by the policy control device. In addition, the units in the communication device 400 and the above-mentioned other operations and / or functions are respectively for implementing Figure 3 Method 100 in Figure 4 Method 200, Figure 5 It should be understood that the specific process of each unit executing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0397] In one possible design, the communication device 400 may be the second network device, the third network device or the fourth network device in the above method embodiment, or may be a chip for implementing the functions of the second network device, the third network device or the fourth network device in the above method embodiment.

[0398] It should be understood that the communication device 400 may correspond to the second network device or the third network device or the fourth network device in the method 100 according to the embodiment of the present application, the core network device, the access network device or the application function device in the method 200, the core network device, the access network device or the application function device in the method 300, and the communication device 200 may include a Figure 3 A unit of the method performed by the second network device or the third network device or the fourth network device in the method 100, Figure 4 The unit of the method performed by the core network device, access network device or application function device in the method 200, Figure 5 The core network device, access network device or application function device in the method 300 in the method 300 is a unit of the method performed. In addition, each unit in the communication device 400 and the above-mentioned other operations and / or functions are respectively for implementing Figure 3 Method 100 in Figure 4 Method 200, Figure 5 It should be understood that the specific process of each unit executing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0399] When the communication device 400 is a chip, the chip includes a transceiver unit and a processing unit. The transceiver unit may be an input / output circuit or a communication interface; the processing unit may be a processor or a microprocessor or an integrated circuit integrated on the chip. The embodiment of the present application also provides a processing device including a processor and an interface. The processor may be used to execute the method in the above method embodiment.

[0400] It should be understood that the above-mentioned processing device can be a chip. For example, the processing device can be a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on chip (SoC), a central processor unit (CPU), a network processor (NP), a digital signal processor (DSP), a micro controller unit (MCU), a programmable logic device (PLD) or other integrated chips.

[0401] In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software. The steps of the method disclosed in conjunction with the embodiment of the present application can be directly embodied as a hardware processor for execution, or a combination of hardware and software modules in a processor for execution. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in conjunction with its hardware. To avoid repetition, it is not described in detail here.

[0402] It should be noted that the processor in the embodiment of the present application can be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method embodiment can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to perform, or the hardware and software modules in the decoding processor can be combined and performed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0403] It can be understood that the memory in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus RAM (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0404] According to the method provided in the embodiment of the present application, the present application also provides a computer program product, which includes: a computer program code, when the computer program code is run on a computer, the computer executes Figure 3 or Figure 4 or Figure 5 A method according to any one of the embodiments shown.

[0405] According to the method provided in the embodiment of the present application, the present application also provides a computer-readable medium, which stores a program code, and when the program code is run on a computer, the computer executes Figure 3 or Figure 4 or Figure 5 A method according to any one of the embodiments shown.

[0406] According to the method provided in the embodiments of the present application, the present application also provides a system, which includes the aforementioned device or equipment.

[0407] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a high-density digital video disc (DVD)), or a semiconductor medium (eg, a solid state disc (SSD)).

[0408] The network side devices in the above-mentioned various device embodiments correspond to the network side devices or terminal devices in the terminal devices and method embodiments, and the corresponding modules or units perform the corresponding steps. For example, the communication unit (transceiver) performs the steps of receiving or sending in the method embodiment, and other steps except sending and receiving can be performed by the processing unit (processor). The functions of the specific units can refer to the corresponding method embodiments. Among them, the processor can be one or more.

[0409] The terms "component", "module", "system", etc. used in this specification are used to represent computer-related entities, hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program and / or a computer. By way of illustration, both applications running on a computing device and a computing device can be components. One or more components may reside in a process and / or an execution thread, and a component may be located on a computer and / or distributed between two or more computers. In addition, these components may be executed from various computer-readable media having various data structures stored thereon. Components may, for example, communicate through local and / or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component between a local system, a distributed system and / or a network, such as the Internet interacting with other systems through signals).

[0410] It should also be understood that the term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0411] It should also be understood that the numbers "first" and "second" are introduced in the embodiments of the present application only to distinguish different objects, such as different "devices" or "units", and do not constitute a limitation on the embodiments of the present application.

[0412] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example 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 performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0413] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0414] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0415] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0416] In addition, each functional unit in each embodiment of the present 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.

[0417] If the functions are implemented in the form of 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 the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0418] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A communication method, characterized in that: include: The first network device acquires first information from the second network device, where the first information includes a first analysis result of first data of the terminal on the second network device, where the first analysis result is obtained based on a parameter of a first model and the first data, and the first model corresponds to the first analysis result; The first network device acquires second information from a third network device, where the second information includes a second analysis result of the first data of the terminal on the third network device, where the second analysis result is obtained based on a parameter of a second model and the first data, and the second model corresponds to the second analysis result; The first network device determines first service experience information of the service of the terminal according to the first information and the second information; The first network device sends the first service experience information to a fourth network device, where the first service experience information is used to determine a parameter of the service of the terminal on the fourth network device, and the fourth network device includes an application function device.

2. The method according to claim 1, characterized in that The second network device includes a core network device, and the method further includes: The first network device sends a first request to the core network device, the first request is used to request a first analysis result of the first data of the terminal on the core network device, the first request includes first identification information of the terminal and at least one of the following information: an analysis identifier and identification information of a first model, the analysis identifier and identification information of the first model are used to determine the first model corresponding to the first analysis result of the first data of the terminal on the core network device.

3. The method according to claim 1, characterized in that The third network device includes an access network device, and the method further includes: The first network device sends a second request to the access network device, the second request is used to request a second analysis result of the first data of the terminal on the access network device, the second request includes second identification information of the terminal and at least one of the following information: analysis identification and identification information of a second model, the analysis identification and identification information of the second model are used to determine the second model corresponding to the second analysis result of the first data of the terminal on the access network device.

4. The method according to claim 1, characterized in that: The method further comprises: The first network device obtains third information from the fourth network device, where the third information includes a third analysis result of the first data of the terminal on the fourth network device.

5. The method according to claim 4, characterized in that The first data of the terminal on the fourth network device includes private data corresponding to the terminal.

6. The method according to claim 4, characterized in that The method further comprises: The first network device sends a third request to the application function device, wherein the third request is used to request a third analysis result of the first data of the terminal on the application function device, and the third request includes a third identifier of the terminal and at least one of the following information: an analysis identifier and identification information of a third model, wherein the analysis identifier and identification information of the third model are used to determine the third model corresponding to the third analysis result of the first data of the terminal on the application function device.

7. The method according to claim 4, characterized in that The first information may further include second association information, wherein the second association information is used to associate the first information with the third information; and / or, The third information may further include the second associated information.

8. The method according to claim 1, characterized in that The first information may also include first associated information, wherein: The first association information is used to associate the second information with the first information; and / or, The second information may further include the first associated information.

9. The method according to claim 4, characterized in that The first information may further include second data of the terminal on the second network device, the second information may further include second data of the terminal on the third network device, and the method may further include: The first network device acquires a fourth analysis result according to the second data of the terminal on the second network device and the second data of the terminal on the third network device; The first network device determines first service experience information of the service of the terminal according to the first information and the second information, including: The first network device determines first service experience information of the service of the terminal according to the first information, the second information and the fourth analysis result.

10. The method according to claim 9, characterized in that The second data of the terminal on the second network device includes the public data corresponding to the terminal, and the second data of the terminal on the third network device includes the public data corresponding to the terminal.

11. The method according to claim 9, characterized in that The third information also includes second data of the terminal on the fourth network device, The first network device acquires a fourth analysis result according to the second data of the terminal on the second network device and the second data of the terminal on the third network device, including: The first network device acquires the fourth analysis result according to the second data of the terminal on the second network device, the second data of the terminal on the third network device, and the second data of the terminal on the fourth network device; The first network device determines first service experience information of the service of the terminal according to the first information, the second information, and the fourth analysis result, including: The first network device determines first service experience information of the service of the terminal according to the first information, the second information, the third information and the fourth analysis result.

12. The method according to claim 11, characterized in that The second data of the terminal on the fourth network device includes public data corresponding to the terminal.

13. The method according to any one of claims 1 to 12, characterized in that The first network device determines first service experience information of the service of the terminal according to the first information and the second information, including: The first network device determines the first service experience information according to the first information, the second information and second service experience information of the service requirement.

14. The method according to any one of claims 1 to 12, characterized in that The first data of the terminal on the second network device includes private data corresponding to the terminal, and the first data of the terminal on the third network device includes private data corresponding to the terminal.

15. The method according to any one of claims 1 to 12, characterized in that The first network device includes a data analysis device or a policy control device.

16. The method according to claim 6, characterized in that The first model, the second model, or the third model is a sub-model after distributed training.

17. A communication device, characterized in that: include: a receiving unit, the receiving unit being configured to obtain first information from a second network device, the first information comprising a first analysis result of first data of a terminal on the second network device, the first analysis result being obtained based on a parameter of a first model and the first data, the first model corresponding to the first analysis result; The receiving unit is used to obtain second information from a third network device, where the second information includes a second analysis result of the first data of the terminal on the third network device, where the second analysis result is obtained based on a parameter of a second model and the first data, and the second model corresponds to the second analysis result; a processing unit, configured to determine first service experience information of the service of the terminal according to the first information and the second information; A sending unit, wherein the sending unit is used to send the first service experience information to a fourth network device, wherein the first service experience information is used to determine a parameter of the service of the terminal on the fourth network device, and the fourth network device includes an application function device.

18. The communication device according to claim 17, characterized in that: The sending unit is used to send a first request to the second network device, the first request is used to request a first analysis result of the first data of the terminal on the second network device, the first request includes first identification information of the terminal and at least one of the following information: an analysis identifier and identification information of a first model, the analysis identifier and identification information of the first model are used to determine the first model corresponding to the first analysis result of the first data of the terminal on the second network device, and the second network device includes a core network device.

19. The communication device according to claim 17, characterized in that: The sending unit is used to send a second request to the third network device, the second request is used to request a second analysis result of the first data of the terminal on the third network device, the second request includes second identification information of the terminal and at least one of the following information: analysis identification and identification information of a second model, the analysis identification and identification information of the second model are used to determine the second model corresponding to the second analysis result of the first data of the terminal on the third network device, and the third network device includes an access network device.

20. The communication device according to claim 17, characterized in that: The receiving unit is used to obtain third information from the fourth network device, where the third information includes a third analysis result of the first data of the terminal on the fourth network device.

21. The communication device according to claim 20, characterized in that: The first data of the terminal on the fourth network device includes private data corresponding to the terminal.

22. The communication device according to claim 20, characterized in that The sending unit is used to send a third request to the fourth network device, the third request is used to request a third analysis result of the first data of the terminal on the fourth network device, the third request includes a third identifier of the terminal and at least one of the following information: an analysis identifier and identification information of a third model, the analysis identifier and identification information of the third model are used to determine the third model corresponding to the third analysis result of the first data of the terminal on the fourth network device.

23. The communication device according to claim 20, characterized in that The first information may further include second association information, wherein the second association information is used to associate the first information with the third information; and / or, The third information may further include the second associated information.

24. The communication device according to claim 17, characterized in that: The first information may also include first associated information, wherein: The first association information is used to associate the second information with the first information; and / or, The second information may further include the first associated information.

25. The communication device according to claim 20, characterized in that The first information may further include second data of the terminal on the second network device, and the second information may further include second data of the terminal on the third network device. The processing unit is used to determine a fourth analysis result according to the second data of the terminal on the second network device and the second data of the terminal on the third network device; The processing unit is configured to determine first service experience information of a service of the terminal according to the first information and the second information, including: The processing unit is used to determine first service experience information of the service of the terminal according to the first information, the second information and the fourth analysis result.

26. The communication device according to claim 25, characterized in that The second data of the terminal on the second network device includes the public data corresponding to the terminal; the second data of the terminal on the third network device includes the public data corresponding to the terminal.

27. The communication device according to claim 25, characterized in that The third information also includes second data of the terminal on the fourth network device, The processing unit is configured to obtain a fourth analysis result according to the second data of the terminal on the second network device and the second data of the terminal on the third network device, including: The processing unit is used to obtain the fourth analysis result according to the second data of the terminal on the second network device, the second data of the terminal on the third network device, and the second data of the terminal on the fourth network device; The processing unit is configured to determine first service experience information of the service of the terminal according to the first information, the second information, and the fourth analysis result, including: The processing unit is used to determine first service experience information of the service of the terminal according to the first information, the second information, the third information and the fourth analysis result.

28. The communication device according to claim 27, characterized in that The second data of the terminal on the fourth network device includes public data corresponding to the terminal.

29. The communication device according to any one of claims 17 to 28, characterized in that: The processing unit is configured to determine first experience information of the service of the terminal according to the first information and the second information, including: The processing unit is used to determine the first experience information according to the first information, the second information and second experience information required by the service.

30. The communication device according to any one of claims 17 to 28, characterized in that: The first data of the terminal on the second network device includes the private data corresponding to the terminal; the first data of the terminal on the third network device includes the private data corresponding to the terminal.

31. The communication device according to claim 22, characterized in that: The first model, the second model, or the third model is a sub-model after distributed training.

32. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed on a computer, the computer is caused to execute the method according to any one of claims 1 to 16.

33. A communication chip, characterized in that: Instructions are stored in the communication chip, and when the instructions are executed on the device, the device executes the method according to any one of claims 1 to 16.

34. A communication device, characterized in that: The communication device comprises a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the communication device executes the method according to any one of claims 1 to 16.

35. A communication system, characterized in that: include: A first network device, wherein the first network device is used to perform the method according to any one of claims 1 to 16; as well as, The second network device is used to send first information to the first network device, where the first information includes a first analysis result of first data of the terminal on the second network device.

Images