WO2024027577A1

WO2024027577A1 - Data feature analysis method and apparatus, and network device

Info

Publication number: WO2024027577A1
Application number: PCT/CN2023/109769
Authority: WO
Inventors: 程思涵; 吴晓波; 崇卫微; 柯小婉
Original assignee: 维沃移动通信有限公司
Priority date: 2022-08-03
Filing date: 2023-07-28
Publication date: 2024-02-08
Also published as: CN117560290A

Abstract

The present application belongs to the technical field of wireless communications. Disclosed are a data feature analysis method and apparatus, and a network device. The data feature analysis method in the present application comprises: a first device acquiring information related to a service data stream of a first service, the information related to the service data stream comprising first information and second information, the first information being information related to a PDU in the service data stream of the first service, and the second information being information related to data frames in the service data stream of the first service, wherein each data frame comprises at least one PDU set; and the first device determining an analysis model for the first service according to the information related to the service data stream, the analysis model being used for identifying data features of the PDU set in the service data stream of the first service.

Description

Data feature analysis method, device and network equipment

Cross-references to related applications

This application claims priority from Chinese Patent Application No. 202210930432.7 filed in China on August 3, 2022, the entire content of which is incorporated herein by reference.

Technical field

This application belongs to the field of wireless communication technology, and specifically relates to a data feature analysis method, device and network equipment.

Background technique

The data of video streams in Extended Reality (XR) can be divided into I frames, P frames and B frames.

Intra-coded picture (I frame) is also called an independently decoded frame and is usually a complete picture.

Forward predictive-coded picture frame (Predictive-coded Picture, P frame) represents the difference between this frame and the previous I frame or P frame. When decoding, you need to use the previously cached picture to superimpose the difference defined by this frame to generate Final image.

Bidirectionally predicted encoded image frames (Bidirectionally predicted pictures, B frames) are bidirectional difference frames, that is, B frames record the difference between this frame and the previous and next frames. In other words, to decode B frames, not only must the previous cached picture be obtained, but also The decoded picture is obtained by superimposing the previous and next pictures with the data of this frame to obtain the final picture.

P frames and B frames record changes relative to I frames. The I frame is more important than the P frame or the B frame. The transmission error of the I frame will cause the I frame to be incorrectly parsed by the receiver, and further cause the subsequent P frame and B frame to be parsed incorrectly. At present, the industry has proposed methods to optimize the transmission of I frames. The premise of optimization is to correctly identify I frames.

A Protocol Data Unit (PDU) set is a set of data with the same characteristics. A PDU set consists of one or more PDUs. A PDU set can be used to transmit (carry) the contents of a frame (payload), or the contents of a slice of a frame. A frame can be divided into multiple slices (slices), for example, a frame is divided into 9 slices, and each PDU set is used to transmit one of the slices. Each PDU may be an Internet Protocol (IP) packet; alternatively, each PDU may be composed of multiple IP packets; or each PDU may be encapsulated in one or more IP packets, or each PDU may be or multiple IP packets for transmission. The protocol data unit can also be called a packet data unit (Packet Data Unit, PDU). In this application, the two can be replaced with each other.

One method of identifying I frames is that the Application Function (AF) provides the data characteristics of the PDU set when generating XR data, such as the importance level of the frame or the type of the frame (I frame, P frame, B frame, etc. ). Gateway equipment in the operator's core network, such as User Plane Function (UPF), can target different For transmission optimization of the PDU set of the I frame, for example, prioritize transmission of all PDUs in the PDU set of the I frame or use a high quality of service (Quality of Service, QoS) quality of service flow (QoS flow) for transmission, and instruct the base station to All PDUs in the PDU set of the frame are transmitted first. This ensures users a smooth experience when using XR services.

If the AF does not provide the data characteristics of the PDU set to the gateway device, or the AF data is encrypted, for example, the AF data is transmitted using the Hyper Text Transfer Protocol over SecureSocket Layer, HTTPS, then the gateway device The data characteristics of the PDU set cannot be obtained, so the I frame cannot be optimally transmitted, which will affect the user experience.

Contents of the invention

Embodiments of the present application provide a data feature analysis method, device, and network equipment, which can solve the problem of being unable to obtain the data features of a PDU set and thus being unable to optimize the transmission of I frames.

The first aspect provides a data feature analysis method, including:

The first device obtains relevant information of the service data flow of the first service. The relevant information of the service data flow includes first information and second information. The first information is the PDU in the service data flow of the first service. The relevant information, the second information is the relevant information of the data frames in the service data flow of the first service, wherein each of the data frames includes at least one PDU set;

The first device determines an analysis model of the first service based on the relevant information of the service data flow, and the analysis model is used to identify the data characteristics of the PDU set in the service data flow of the first service.

The second aspect provides a data feature analysis method, including:

The second device obtains the analysis model of the first service, where the analysis model is used to identify the data characteristics of the PDU set in the service data flow of the first service;

The second device analyzes the target service data flow of the first service according to the analysis model and obtains an analysis result. The analysis result includes at least one of the following: the boundary of the PDU set in the target service data flow. Information, the type indication information of the PDU set, the sequence number of each PDU in the PDU set, the number of PDUs in the PDU set, and the period of the PDU set;

Wherein, the type indication information includes at least one of the following: frame type, importance level information;

The boundary information of the PDU set in the target service data flow includes at least one of the following: information of the starting PDU of the PDU set, and information of the ending PDU of the PDU set.

The third aspect provides a data feature analysis method, including:

The third device receives the analysis results of the target service data flow of the first service, the analysis results are obtained based on the analysis model, and the analysis model is used to identify the data characteristics of the PDU set in the service data flow of the first service;

The third device determines the transmission mode of the PDU set in the target service data flow based on the analysis result.

In the fourth aspect, a data feature analysis device is provided, including:

The first acquisition module is used to acquire relevant information of the service data flow of the first service. The relevant information includes first information and second information. The first information is the PDU in the service data flow of the first service. The relevant information, the second information is the relevant information of the data frames in the service data flow of the first service, wherein each of the data frames includes at least one PDU set;

The first determination module is configured to determine the analysis model of the first service based on the relevant information of the service data flow. The analysis model is used to identify the data characteristics of the PDU set in the service data flow of the first service. .

In the fifth aspect, a data feature analysis device is provided, including:

The first acquisition module is used to acquire the analysis model of the first service, and the analysis model is used to identify the data characteristics of the PDU set in the service data flow of the first service;

An analysis module, configured to analyze the target service data flow of the first service according to the analysis model and obtain analysis results, where the analysis results include at least one of the following: the boundary of the PDU set in the target service data flow. Information, the type indication information of the PDU set, the sequence number of each PDU in the PDU set, the number of PDUs in the PDU set, and the period of the PDU set;

A sixth aspect provides a data feature analysis device, including:

The first receiving module is configured to receive the analysis results of the target service data flow of the first service. The analysis results are obtained based on the analysis model. The analysis model is used to identify the PDU set in the service data flow of the first service. data characteristics;

The first determination module is configured to determine the transmission mode of the PDU set in the target service data flow according to the analysis result.

In a seventh aspect, a network device is provided. The terminal includes a processor and a memory. The memory stores programs or instructions that can be run on the processor. When the program or instructions are executed by the processor, the following is implemented: The steps of the method described in the first aspect, the second aspect or the third aspect.

In an eighth aspect, a network device is provided, including a processor and a communication interface, wherein the processor is configured to obtain relevant information of the service data flow of the first service, where the relevant information includes first information and second information, The first information is the relevant information of the PDU in the service data flow of the first service, and the second information is the relevant information of the data frame in the service data flow of the first service, wherein each of the The data frame includes at least one PDU set; according to the relevant information of the service data flow, an analysis model of the first service is determined, and the analysis model is used to identify the PDU set in the service data flow of the first service. Data characteristics.

In a ninth aspect, a network device is provided, including a processor and a communication interface, wherein the processor is used to obtain an analysis model of the first service, and the analysis model is used to identify the service data flow of the first service. The data characteristics of the PDU set; analyze the target service data flow of the first service according to the analysis model to obtain analysis results, and the analysis results include at least one of the following: PDU set in the target service data flow boundary information, The type indication information of the PDU set, the sequence number of each PDU in the PDU set, the number of PDUs in the PDU set, and the period of the PDU set; wherein the type indication information includes at least one of the following: Frame type, importance level information; the boundary information of the PDU set in the target service data flow includes at least one of the following: information about the starting PDU of the PDU set, and information about the ending PDU of the PDU set.

In a tenth aspect, a communication system is provided, including: a first device, a second device and a third device. The first device can be used to perform the steps of the data feature analysis method as described in the first aspect. The third device The second device can be used to perform the steps of the data feature analysis method as described in the second aspect, and the third device can be used to perform the steps of the data feature analysis method as described in the third aspect.

In an eleventh aspect, a readable storage medium is provided. Programs or instructions are stored on the readable storage medium. When the programs or instructions are executed by a processor, the programs or instructions are implemented as described in the first aspect, the second aspect or the third aspect. The steps of the data feature analysis method described above.

In a twelfth aspect, a chip is provided. The chip includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the first aspect and the second aspect. The data feature analysis method described in the aspect or the third aspect.

In a thirteenth aspect, a computer program/program product is provided, the computer program/program product is stored in a storage medium, and the computer program/program product is executed by at least one processor to implement the first aspect, the third aspect The steps of data feature analysis described in the second aspect or the third aspect.

In the embodiment of the present application, by training the relevant information of the service data flow of the first service, an analysis model of the first service is obtained. The analysis model can identify the data characteristics of the PDU set in the service data flow of the first service, In this way, all PDUs in the PDU set of the I frame can be transmitted with priority, ensuring a smooth user experience when using the first service.

Description of the drawings

Figure 1 is a block diagram of a wireless communication system applicable to the embodiment of the present application;

Figure 2 is one of the flow diagrams of the data feature analysis method according to the embodiment of the present application;

Figure 3 is a schematic diagram of PDUs in I frames, P frames and B frames in this embodiment of the present application;

Figure 4 is the second schematic flowchart of the data feature analysis method according to the embodiment of the present application;

Figure 5 is the third flowchart of the data feature analysis method according to the embodiment of the present application;

Figure 6 is a schematic flow chart of the data feature analysis method in Embodiment 1 of the present application;

Figure 7 is one of the flow diagrams of the data feature analysis method in Embodiment 2 of the present application;

Figure 8 is the second schematic flow chart of the data feature analysis method in Embodiment 2 of the present application;

Figure 9 is the third schematic flow chart of the data feature analysis method in Embodiment 2 of the present application;

Figure 10 is one of the flow diagrams of the data feature analysis method in Embodiment 3 of the present application;

Figure 11 is the second schematic flow chart of the data feature analysis method in Embodiment 3 of the present application;

Figure 12 is one of the structural schematic diagrams of the data feature analysis device according to the embodiment of the present application;

Figure 13 is the second structural schematic diagram of the data feature analysis device according to the embodiment of the present application;

Figure 14 is the third structural schematic diagram of the data feature analysis device according to the embodiment of the present application;

Figure 15 is a schematic structural diagram of a network device according to an embodiment of the present application;

Figure 16 is one of the schematic diagrams of the hardware structure of the network device according to the embodiment of the present application;

Figure 17 is the second schematic diagram of the hardware structure of the network device according to the embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be clearly described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art fall within the scope of protection of this application.

The terms "first", "second", etc. in the description and claims of this application are used to distinguish similar objects and are not used to describe a specific order or sequence. It is to be understood that the terms so used are interchangeable under appropriate circumstances so that the embodiments of the present application can be practiced in sequences other than those illustrated or described herein, and that "first" and "second" are distinguished objects It is usually one type, and the number of objects is not limited. For example, the first object can be one or multiple. In addition, "and/or" in the description and claims indicates at least one of the connected objects, and the character "/" generally indicates that the related objects are in an "or" relationship.

It is worth pointing out that the technology described in the embodiments of this application is not limited to Long Term Evolution (LTE)/LTE Evolution (LTE-Advanced, LTE-A) systems, and can also be used in other wireless communication systems, such as code Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access, OFDMA), Single-carrier Frequency Division Multiple Access (SC-FDMA) and other systems. The terms "system" and "network" in the embodiments of this application are often used interchangeably, and the described technology can be used not only for the above-mentioned systems and radio technologies, but also for other systems and radio technologies. The following description describes a New Radio (NR) system for example purposes, and NR terminology is used in much of the following description, but these techniques can also be applied to applications other than NR system applications, such as 6th ^generation Generation, 6G) communication system.

Figure 1 shows a block diagram of a wireless communication system to which embodiments of the present application are applicable. The wireless communication system includes a terminal 11 and a network side device 12. The terminal 11 may be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (Laptop Computer), or a notebook computer, a personal digital assistant (Personal Digital Assistant, PDA), a palmtop computer, a netbook, or a super mobile personal computer. (ultra-mobile personal computer, UMPC), mobile Internet device (Mobile Internet Device, MID), augmented reality (AR)/virtual reality (VR) equipment, robots, wearable devices (Wearable Device) , Vehicle User Equipment (VUE), Pedestrian User Equipment (PUE), smart home (home equipment with wireless communication functions, such as refrigerators, TVs, washing machines or furniture, etc.), game consoles, personal computers (personal Terminal-side devices such as computer (PC), teller machine or self-service machine, wearable devices include: smart watches, smart phones, etc. Bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. In addition to the above terminal equipment, it can also be a chip in the terminal, such as a modem chip or a system on chip (SoC). It should be noted that the embodiment of the present application does not limit the specific type of the terminal 11. The network side device 12 may include an access network device or a core network device, where the access network device may also be called a radio access network device, a radio access network (Radio Access Network, RAN), a radio access network function or a wireless access network unit. Access network equipment may include base stations, Wireless Local Area Networks (WLAN) access points or WiFi nodes, etc. The base stations may be called Node B, Evolved Node B (eNB), access point, base transceiver station ( Base Transceiver Station (BTS), radio base station, radio transceiver, Basic Service Set (BSS), Extended Service Set (ESS), home B-node, home evolved B-node, transmitting and receiving point ( Transmitting Receiving Point (TRP) or some other appropriate terminology in the field, as long as the same technical effect is achieved, the base station is not limited to specific technical terms. It should be noted that in the embodiment of this application, only in the NR system The base station is introduced as an example, and the specific type of base station is not limited. The core network equipment may include but is not limited to at least one of the following: core network node, core network function, mobility management entity (Mobility Management Entity, MME), access mobility management function (Access and Mobility Management Function, AMF), session management function (Session Management Function, SMF), User Plane Function (UPF), Policy Control Function (PCF), Policy and Charging Rules Function (PCRF), Edge Application Service Discovery function (Edge Application Server Discovery Function, EASDF), Unified Data Management (UDM), Unified Data Repository (UDR), Home Subscriber Server (HSS), centralized network configuration ( Centralized network configuration (CNC), Network Repository Function (NRF), Network Exposure Function (NEF), Local NEF (Local NEF, or L-NEF), Binding Support Function (Binding Support Function, BSF), application function (Application Function, AF), etc. It should be noted that in the embodiment of this application, only the core network equipment in the NR system is used as an example for introduction, and the specific type of the core network equipment is not limited.

The data feature analysis method, device and network equipment provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings through some embodiments and application scenarios.

Please refer to Figure 2. This embodiment of the present application provides a data feature analysis method, including:

Step 21: The first device obtains relevant information of the service data flow of the first service. The relevant information of the service data flow includes first information and second information. The first information is the service data flow of the first service. The relevant information of the PDUs in the first service, the second information is the relevant information of the data frames in the service data flow of the first service, wherein each of the data frames includes at least one PDU set;

Step 22: The first device determines the analysis model of the first service based on the relevant information of the service data flow. The analysis model is used to identify the data of the PDU set in the service data flow of the first service. feature. This analysis model can also be called a machine learning model (ML model).

In this embodiment of the present application, the first device may be a network data analysis function (Network Data Analytics). Function, NWDAF) model training logical function (MTLF), or it can be an application function (Application Function, AF), or other network devices.

In this embodiment of the present application, optionally, the first service may be an extended reality (Extended Reality, XR) service or other services.

In this embodiment of the present application, the data frame may include at least one of the following: a picture frame corresponding to the service, such as an I frame, a P frame or a B frame; a picture frame in the service data stream, such as an I frame, P frame or B frame; data corresponding to a picture frame in the service data flow; a slice of a picture frame corresponding to the service; a slice of a picture frame in the service data flow; a slice of a picture frame in the service data flow Data corresponding to a shard. The one picture frame may include multiple slices, for example, one picture frame is divided into 9 slices. The picture frame may also be called an image frame, a portrait frame, a picture frame, a picture frame, etc. This application does not specifically limit it, and all the above descriptions used to describe a frame are within the scope of this application.

Please refer to Figure 3. Figure 3 is a schematic diagram of PDUs in I frames, P frames and B frames in this embodiment of the present application. It can be seen from the figure that each picture frame includes multiple PDUs, and SN is the sequence number of the PDU.

In this embodiment of the present application, optionally, the first information includes at least one of the following: the reception time of each PDU, the time interval between two adjacent PDUs, and the size of each PDU.

In this embodiment of the present application, the first device may collect the first information from a gateway device (such as UPF). Optionally, the first information provided by the gateway device is IP five-tuple granularity, that is, service Data flow granularity, where the IP five-tuple includes: terminal IP address, terminal port number, server IP address, server port number and protocol number.

In one embodiment, the first information may be as shown in Table 1:

Table 1 first information

In this embodiment of the present application, optionally, the second information includes at least one of the following: the start time of each data frame, the end time of each data frame, the number of PDUs in each data frame, each Type indication information of a data frame; wherein the type indication information includes at least one of the following: frame type, importance level information.

In this embodiment of the present application, optionally, the frame type may include at least one of the following: I frame, P frame, and B frame. Normally, I frames have a higher importance level than B frames and P frames.

In the embodiment of this application, if the first device is NWDAF MTLF, the first device can collect the second information from the AF. Optionally, the second information provided by the AF is IP five-tuple granularity. , that is, the granularity of business data flow, in which the IP quintuple includes: terminal IP address, terminal port number, server IP address, server port number and protocol number. NWDAF MTLF can also be called NWDAF containing MTLF.

In one embodiment, the second information may be as shown in Table 2: Table 2 Second information

In this embodiment of the present application, optionally, the relevant information of the service data flow also includes fifth information. As shown in Table 1 and Table 2, the fifth information includes at least one of the following: the duration of the service data flow. , uplink bit rate, downlink bit rate, uplink PDU delay, downlink PDU delay, number of uplink PDU transmissions, number of downlink PDU transmissions.

It can be seen from the above Table 1 and Table 2 that the first device can obtain the fifth information from the gateway device and/or AF.

In this embodiment of the present application, optionally, the analysis model includes at least one of the following information:

1) The time interval between two adjacent PDUs in the PDU set;

2) The time interval between two adjacent PDU sets;

Using 1) and 2), you can distinguish which PDUs belong to a PDU set and distinguish the boundaries of the PDU set.

Normally, the time interval between adjacent PDU sets within a PDU set is relatively short, for example, 1 ms; the time interval between adjacent PDU sets is relatively long, for example, 16.67 ms.

3) Size distribution information of different types of PDU sets;

For example, it can be the size distribution function f1(x) of different types of PDU sets. The size distribution function f1(x) may be a normal distribution function, an average distribution function, etc.

Generally, the size of the PDU set of I frame is larger, and the size of PDU set of P frame and B frame is smaller.

4) Periods of different types of PDU sets.

Usually I frames appear periodically, for example, one I frame every 8 frames. The frame type or importance level of the PDU set can be determined through the period.

In the embodiment of this application, optionally, the relevant information of the service data flow also includes third information, and the third information is the relevant information of lost PDUs and/or lost PDU sets; optionally, the analysis model It also contains the following information: Instruction information on whether to allow packet loss in the PDU set. This information is mainly used to determine whether the remaining PDUs in the PDU set where the PDU is located need to be transmitted when a PDU loss is detected. For example, in some video encoding formats, the loss of one PDU in a PDU set will affect the parsing of the entire PDU set. Therefore, if one PDU is lost in the PDU set, there is no need to transmit the other remaining PDUs in the PDU set. . That is to say, by training the third information, the trained analysis model can be made to include indication information of whether the PDU set is allowed to lose packets, that is, it has the function of analyzing whether the PDU set is allowed to lose packets.

In this embodiment of the present application, optionally, the third information includes at least one of the following: a timestamp when PDU loss occurs, and a timestamp when PDU set discard occurs.

In the embodiment of this application, optionally, the relevant information of the service data flow also includes fourth information, and the fourth information is the relevant information of out-of-order PDUs and/or out-of-order PDU sets; optionally, the The analytical model also contains at least one of the following information:

1) The first jitter information of the PDU in the PDU set;

For example, it may be the distribution function f2(x) of PDU jitter within the PDU set. The distribution function f2(x) may be, for example, a Gaussian distribution function.

The first jitter information represents that a large transmission delay occurs during the network transmission of the PDU. The impact of jitter on PDU set boundary determination can be eliminated based on the first jitter information.

2) Second jitter information between PDU sets.

For example, it can be the distribution function f3(x) of jitter between PDU sets. The distribution function f3(x) may be, for example, a Gaussian distribution function.

The second jitter information represents that a large transmission delay occurs during network transmission of the PDU set. The influence of jitter on the period judgment of the PDU set can be eliminated according to the second jitter information.

Through the above 1) and 2), the interference that occurs within a PDU set and between PDU sets can be eliminated.

That is to say, by training the fourth information, the trained analysis model can be made to have the function of analyzing the first jitter information of PDUs within the PDU set and/or the second jitter information between PDU sets.

In this embodiment of the present application, optionally, the fourth information includes at least one of the following: a timestamp of an out-of-order PDU; a timestamp of an out-of-order PDU set.

In this embodiment of the present application, the first device may collect the third information and/or the fourth information from a terminal (UE). Optionally, the third information and/or the fourth information provided by the terminal is IP. Five-tuple granularity, that is, business data flow granularity. Among them, the IP five-tuple includes: terminal IP address, terminal port number, server IP address, server port number, and protocol number.

In one embodiment, the third information and the fourth information may be as shown in Table 3:

Table 3 Third information and fourth information

In this embodiment of the present application, optionally, the first device sends the analysis model or the information of the analysis model to the second device, so that the second device can analyze the service data flow of the first service. Data characteristics of the PDU set in . In this embodiment of the present application, optionally, the second device may be NWDAF AnLF, or other network device. NWDAF AnLF can also be called NWDAF containing AnLF.

The Network Data Analytics Function (NWDAF) in the embodiment of this application can be divided into the following two functions:

Model Training logical function (MTLF): used to train analysis models.

Analytical logical function (AnLF): used for logical reasoning (reference) using analytical models.

In this embodiment of the present application, optionally, the data feature analysis method further includes: the first device receiving a first request, the first request being used to request an analysis model of the first service, the first The request includes at least one of the following information: a first identification and first filtering information. The first filtering information may also be called an analytics filter (Analytics Filter) and is used to filter business data that meets the conditions;

The first identifier is used to indicate that the requested analysis model is an analysis model used to identify the data characteristics of the PDU set in the service data flow;

The first filtering information includes at least one of the following: service data flow description identification, service identification, APP identification (Application ID), slice identification, data network name (Data Network Name, DNN), network area information, and terminal identification.

Optionally, the first identifier may be an Analytics ID. In this case, the value corresponding to the Analytics ID indicates that the requested analysis model is an analysis model used to identify the data characteristics of the PDU set in the business data flow. For example,

Analytics ID = business flow characteristics.

The APP identifier can also be used as a business identifier, and a business training analysis model corresponding to the APP identifier can be specified;

The service data flow descriptor can also replace the APP identifier. The service data flow descriptor can be an IP five-tuple (terminal IP address, terminal port number, server IP address, server port number, protocol number) or IP triplet (server IP address, server port number, protocol number).

Slice identification, such as Single Network Slice Selection Assistance Information (S-NSSAI) for a single network slice, can specify the analysis of services within the slice.

Data network name (DNN), you can specify the business in the data network corresponding to the DNN to be analyzed.

Network area information (Area of Interest), you can specify the business in the area to be analyzed.

The terminal identifier may be the identifier of one or more terminals, and the terminal identifier may include at least one of the following: the UE's IP address, IMSI, GUTI, phone number, etc.

In this embodiment of the present application, optionally, the data analysis method further includes: the first device sends a second request, The second request is used to request to obtain relevant information of the service data flow. The second request includes at least one of the following information: a first identification and a first filtering information; the first identification is used to indicate Request relevant information of the service data flow; the first filtering information includes at least one of the following: service data flow description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, and terminal identifier.

For descriptions of the first identifier and the first filtering information, refer to the above content, and will not be described again.

Please refer to Figure 4. This embodiment of the present application also provides a data feature analysis method, including:

Step 41: The second device obtains the analysis model of the first service, where the analysis model is used to identify the data characteristics of the PDU set in the service data flow of the first service;

Step 42: The second device analyzes the target service data flow of the first service according to the analysis model, and obtains analysis results. The analysis results include at least one of the following: PDU in the target service data flow. The boundary information of the set, the type indication information of the PDU set, the sequence number of each PDU in the PDU set, the number of PDUs in the PDU set, and the period of the PDU set;

In this embodiment of the present application, optionally, the second device may be NWDAF AnLF, or other network device.

In this embodiment of the present application, each PDU set includes at least one PDU. Each PDU can be an IP packet.

In the embodiment of the present application, the data characteristics of the PDU set in the service data stream of the first service can be identified through the analysis model, so that all PDUs in the PDU set of the I frame can be transmitted preferentially, ensuring that when the user uses the first service smooth experience.

1) The time interval between two adjacent PDUs in the PDU set;

2) The time interval between two adjacent PDU sets;

3) Size distribution information of different types of PDU sets;

4) Periods of different types of PDU sets.

Optionally, the analysis model also includes the following information: indication information of whether to allow packet loss in a PDU set, and the analysis results also include: a result of whether to continue transmitting the corresponding PDU set in the target service data flow.

Optionally, the analysis model also includes at least one of the following information: first jitter information of PDUs within the PDU set; second jitter information between PDU sets; analysis of the first service according to the analysis model. Analyzing the target service data flow and obtaining the analysis result includes: the second device determines the boundary of the PDU set in the target service data flow according to the first jitter information and/or the second jitter information. For example, if it is found that the jitter of an abnormal PDU in the PDU set matches the first jitter information, the jitter of the PDU can be ignored and considered to be normal jitter, and the PDU set is not considered to be over, thereby eliminating the first jitter information. Impact on the determination of the PDU binding boundary.

In this embodiment of the present application, optionally, the data characterization method also includes:

The second device sends a third request to the third device. The third request is used to request the service data flow of the first service. The third request includes at least one of the following: service data flow description identifier, service Identity, APP identification, slice identification, data network name, network area information, terminal identification;

The second device receives the target service data stream of the first service sent by the third device.

In this embodiment of the present application, optionally, the third device may be a gateway device, such as a UPF.

The second device receives a fourth request. The fourth request is used to request the second device to analyze the service data flow of the first service. The fourth request includes at least one of the following: service data flow. Description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, terminal identifier, and the identifier of the UPF that provides services for the terminal.

The second device sends the analysis result to a third device.

At this time, the third device may be a gateway device, such as a UPF, a base station, or other network equipment.

Please refer to Figure 5. This embodiment of the present application also provides a data feature analysis method, including:

Step 51: The third device receives the analysis result of the target service data flow of the first service. The analysis result is obtained based on the analysis model. The analysis model is used to identify the PDU set in the service data flow of the first service. data characteristics;

Step 52: The third device determines the transmission mode of the PDU set in the target service data flow based on the analysis result.

The transmission method includes at least one of the following: whether to prioritize transmission and whether to continue transmission.

In this embodiment of the present application, optionally, the third device may be a gateway device, such as a UPF, a base station, or other network device.

The third device receives a third request. The third request is used to request the service data flow of the first service. The third request includes at least one of the following: service data flow description identifier, service identifier, and APP identifier. , slice identification, data network name, network area information, terminal identification;

The third device obtains the target service data stream of the first service according to the third request.

In this embodiment, optionally, the third device may be a gateway device, such as UPF.

The third device receives a fifth request sent by the fourth device. The fifth request is used to request analysis of the service data flow of the first service. The fifth request includes at least one of the following: service data flow. Description identification, service identification, APP identification, slice identification, data network name, network area information, terminal identification;

The third device sends a fourth request to the second device. The fourth request is used to request the second device to analyze the service data flow of the first service. The fourth request includes at least one of the following: : Service data flow description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, terminal identifier, and the identifier of the UPF that provides services for the terminal.

In this embodiment of the present application, optionally, the fourth device may be an SMF or other network device. The second device may be NWDAF AnLF, or other network device.

Below, the data feature analysis method in the embodiment of the present application will be described with examples based on specific application scenarios.

Example 1 of this application:

In the embodiment of this application, the operator network performs analysis model training. Please refer to Figure 6. The data feature analysis method in the embodiment of this application includes the following steps:

Step 1: Network Function (NF) consumer (Consumer), such as UPF or SMF, sends Nnwdaf_AnalyticsSubscription_Subscribe message to NWDAF AnLF, containing the following information in the message:

1) Analytics ID (i.e., the first identifier in the above embodiment), used to indicate that the requested analysis model is an analysis model used to identify the data characteristics of the PDU set in the business data flow;

2) The first filtering information, which may also be called an Analytics Filter, includes at least one of the following: business data flow description identification, business identification, APP identification (Application ID), and slice identification, DNN, network area information, terminal identification.

The APP identifier can also be used as a service identifier, and the service corresponding to the APP identifier can be specified. train analytical models;

The NWDAF in the embodiment of this application can be divided into the following two functions:

MTLF: used to train analytical models.

AnLF: used for logical reasoning (reference) using analytical models.

Among them, UPF and NWDAF AnLF are two entities logically and can be one entity physically.

Step 2: NWDAF AnLF sends Nnwdaf_MLModelProvision_Subscribe or Nnwdaf_MLModelInfo_Request (equivalent to the first request in the above embodiment) to NWDAF MTLF to request the analysis model. The message contains the Analytics ID and Analytics Filter in step 1.

Step 3: NWDAF MTLF collects the first information from the gateway device (such as UPF). For the content of the first information, please refer to Table 1 in the above embodiment. It should be noted that the first information provided by UPF is at the granularity of IP five-tuple (source IP address, destination IP address, protocol number, source port, destination port), that is, at the granularity of business data flow. Among them, the IP five-tuple The information included in the group is: terminal IP address, terminal port number, server IP address, server port number, and protocol number. The UPF in this step can be the same as the UPF in step 1, or it can be different.

Step 4: NWDAF MTLF collects the second information from the AF. For the content of the second information, please refer to Table 2 in the above embodiment. The second information provided by AF is at the granularity of IP quintuple, which is the granularity of business data flow. The information included in the IP quintuple is: terminal IP address, terminal port number, server IP address, server port number, protocol Number.

Step 5: NWDAF MTLF collects the third information and the fourth information from the UE. For the contents of the third information and the fourth information, please refer to Table 3 in the above embodiment. The traffic information provided by the UE is at the granularity of IP quintuple, that is, the granularity of service data flow. The information included in the IP quintuple is: terminal IP address, terminal port number, server IP address, server port number, and protocol number. .

Step 6: NWDAF MTLF generates a training data set based on the relevant information of the service data flow received from AF, UPF and UE, and trains the analysis model based on the training data set.

Analytical models include at least one of the following information:

1) The time interval between two adjacent PDUs in the PDU set;

2) The time interval between two adjacent PDU sets;

3) Size distribution information of different types of PDU sets;

For example, it can be the size distribution function f1(x) of different types of PDU sets.

4) Periods of different types of PDU sets.

5) Indication information of whether to allow PDU aggregation packet loss.

This information is mainly used to determine whether the remaining PDUs in the PDU set where the PDU is located need to be transmitted when a PDU loss is detected. For example, in some video encoding formats, the loss of one PDU in a PDU set will affect the parsing of the entire PDU set. Therefore, if one PDU is lost in the PDU set, there is no need to transmit the other remaining PDUs in the PDU set. . That is to say, by training the third information, the trained analysis model can be made to include indication information of whether the PDU set is allowed to lose packets, that is, it has the function of analyzing whether the PDU set is allowed to lose packets.

6) The first jitter information of the PDU in the PDU set;

For example, it may be the distribution function f2(x) of PDU jitter within the PDU set. The first jitter information represents that a large transmission delay occurs during the network transmission of the PDU. The impact of jitter on PDU set boundary determination can be eliminated based on the first jitter information.

7) Second jitter information between PDU sets.

For example, it can be the distribution function f3(x) of jitter between PDU sets. The second jitter information represents that a large transmission delay occurs during network transmission of the PDU set. The influence of jitter on the period judgment of the PDU set can be eliminated according to the second jitter information.

Step 7: NWDAF MTLF sends the trained analysis model to NWDAF AnLF through Nnwdaf_MLModelProvision_Notify or Nnwdaf_MLModelInfo_Response.

Step 8: NWDAF AnLF sends the Nupf_eventExposure_Subscibe message (the third request above) to UPF to request the business data flow. The request contains at least one of the following: business data flow description identification, business identification, APP identification, slice identification, Data network name, network area information, terminal identification;

Step 9: UPF obtains the service data flow from AF, and UPF sends the determined service data flow to NWDAF AnLF based on the above third request.

Step 10: NWDAF AnLF uses the analysis model to analyze the received business data flow and obtains the analysis results. The analysis results can be shown in Table 4:

Table 4 analysis results

For details on how to obtain the analysis results based on the analysis model, please refer to the above embodiments, and the description will not be repeated again.

Step 11: NWDAF AnLF sends the analysis results to UPF;

Step 12: UPF notifies the base station of the analysis results through the GPRS Tunneling Protocol (GTP) header;

Step 13: The base station sends the service data stream to the UE, and during the transmission process, the PDU set is transmitted based on the above analysis results.

Embodiment 2 of this application:

Please refer to Figure 7. The data feature analysis method in the embodiment of this application includes the following steps:

Step 1: NWDAF AnLF sends Nnwdaf_MLModelProvision_Subscribe or Nnwdaf_MLModelInfo_Request (equivalent to the first request in the above embodiment) to NWDAF MTLF to request the analysis model. The message contains:

The terminal identification may be the identification of one or more terminals, and the terminal identification may include at least one of the following: the Internet Protocol (IP) address of the user equipment (User Equipment, UE), the International Mobile Subscriber Identity Code (International Mobile Subscriber Identity, IMSI), Globally Unique Temporary UE Identity (GUTI), phone number, etc.

In some embodiments of this application, AnLF in step 1 can actively initiate the training process of the analysis model, that is, the analysis model is not trained based on the trigger of other network elements; in some other embodiments of this application, NF Comsumer ( UPF or SMF) triggers AnLF to train the analysis model.

Please refer to Figure 8. In some embodiments, before step 1, it also includes:

Step 01a: When the SMF determines that the user uses the XR service, the SMF sends an N4session establishment request or N4session modification request message (i.e., the fifth request in the above embodiment) to the UPF corresponding to the XR service, carrying at least one of the following: service data flow description identifier , service identification, APP identification, slice identification, data network name, network area information, terminal identification;

Step 02a: The UPF initiates the Nnwdaf_Analyticsription_Subscribe message (i.e., the fourth request in the above embodiment) to AnLF. The message includes at least one of the following: service data flow description identifier, service identifier, APP identifier, slice identifier, data network name, network Area information, terminal identification, and identification of the UPF that provides services to the terminal.

Please refer to Figure 9. In some embodiments, before step 1, it also includes:

Step 01b: When the SMF determines that the user uses the XR service, the SMF sends the Nnwdaf_Analyticsription_Subscribe message (i.e., the fourth request in the above embodiment) to AnLF. The message includes at least one of the following: service data flow description identifier, service identifier, APP identifier, Slice identification, data network name, network area information, terminal identification, and identification of the UPF that provides services to the terminal.

Step 2: NWDAF MTLF collects the first information from the gateway device (such as UPF). For the content of the first information, please refer to Table 1 in the above embodiment. It should be noted that the first information provided by UPF is at the granularity of IP five-tuple (source IP address, destination IP address, protocol number, source port, destination port), that is, at the granularity of business data flow. Among them, the IP five-tuple The information included in the group is: terminal IP address, terminal port number, server IP address, server port number, and protocol number. The UPF in this step can be the same as the UPF in step 1, or it can be different.

Step 3: NWDAF MTLF collects the second information from the AF. For the content of the second information, please refer to Table 2 in the above embodiment. The second information provided by AF is at the granularity of IP quintuple, which is the granularity of business data flow. The information included in the IP quintuple is: terminal IP address, terminal port number, server IP address, server port number, protocol Number.

Step 4: NWDAF MTLF collects the third information and the fourth information from the UE. For the contents of the third information and the fourth information, please refer to Table 3 in the above embodiment. The traffic information provided by the UE is at the granularity of IP quintuple, that is, the granularity of service data flow. The information included in the IP quintuple is: terminal IP address, terminal port number, server IP address, server port number, and protocol number. .

Step 5: NWDAF MTLF generates a training data set based on the relevant information of the service data flow received from AF, UPF and UE, and trains the analysis model based on the training data set.

Analytical models include at least one of the following information:

1) The time interval between two adjacent PDUs in the PDU set;

2) The time interval between two adjacent PDU sets;

3) Size distribution information of different types of PDU sets;

4) Periods of different types of PDU sets.

5) Indication information of whether to allow PDU aggregation packet loss.

This information is mainly used to determine whether the remaining PDUs in the PDU set where the PDU is located need to be transmitted when a PDU loss is detected. For example, in some video encoding formats, the loss of one PDU in a PDU set will affect the parsing of the entire PDU set. Therefore, if one PDU is lost in the PDU set, there is no need to transmit the other remaining PDUs in the PDU set. . That is to say, by training the third information, the trained analysis model can include indication information of whether the PDU set allows packet loss, that is, it has the function of analyzing whether the PDU set allows packet loss.

6) The first jitter information of the PDU in the PDU set;

7) Second jitter information between PDU sets.

Step 6: NWDAF MTLF sends the trained analysis model to NWDAF AnLF through Nnwdaf_MLModelProvision_Notify or Nnwdaf_MLModelInfo_Response.

Step 7: NWDAF AnLF sends the Nupf_eventExposure_Subscibe message (the third request mentioned above) to UPF to request the business data flow. The request contains at least one of the following: business data flow description identification, business identification, APP identification, slice identification, Data network name, network area information, terminal identification;

Step 8: UPF obtains the service data flow from AF. UPF transfers the determined service data flow according to the above third request. Send to NWDAF AnLF.

Step 9: NWDAF AnLF uses the analysis model to analyze the received service data flow and obtains the analysis results. The analysis results can be as shown in Table 4 of Embodiment 1.

Step 10: NWDAF AnLF sends the analysis results to UPF;

Step 11: UPF notifies the base station of the analysis results through the GPRS Tunneling Protocol (GTP) header;

Step 12: The base station sends the service data flow to the UE, and during the transmission process, the PDU set is transmitted based on the above analysis results.

Embodiment 3 of this application:

In this embodiment, AF performs training of the analysis model.

Please refer to Figure 10. The data feature analysis method in this embodiment of the present application includes the following steps:

Step 1: AF collects first information from a gateway device (such as UPF). For the content of the first information, see Table 1 in the above embodiment. It should be noted that the first information provided by UPF is at the granularity of IP five-tuple (source IP address, destination IP address, protocol number, source port, destination port), that is, at the granularity of business data flow. Among them, the IP five-tuple The information included in the group is: terminal IP address, terminal port number, server IP address, server port number, and protocol number. The UPF in this step can be the same as the UPF in step 1, or it can be different.

Step 2: The AF collects the third information and the fourth information from the UE. For the contents of the third information and the fourth information, please refer to Table 3 in the above embodiment. The traffic information provided by the UE is at the IP quintuple granularity, which is the service data flow granularity. The IP quintuple includes the following information: terminal IP address, terminal port number, server IP address, server port number, and protocol number. .

Step 3: The AF generates a training data set based on the first information collected from the UPF, the third information and the fourth information collected from the UE, and the locally saved second information, and trains the analysis model according to the training data set.

Analytical models include at least one of the following information:

1) The time interval between two adjacent PDUs in the PDU set;

2) The time interval between two adjacent PDU sets;

3) Size distribution information of different types of PDU sets;

4) Periods of different types of PDU sets.

Usually I frames appear periodically, for example, one I frame every 8 frames. The period can be used to determine the PDU set Frame type or importance level.

5) Indication information of whether to allow PDU aggregation packet loss.

6) The first jitter information of the PDU in the PDU set;

7) Second jitter information between PDU sets.

Step 4: AF sends the trained analysis model to the integrated equipment of UPF and NWDAF AnLF.

Step 5: AF sends service data flow to the integrated equipment of UPF and NWDAF AnLF.

Step 6: NWDAF AnLF uses the analysis model to analyze the received service data flow and obtains the analysis results. The analysis results can be as shown in Table 4 of Embodiment 1.

Step 7: The integrated equipment of UPF and NWDAF AnLF notifies the base station of the analysis results through the GPRS Tunneling Protocol (GTP) header;

Step 8: The base station sends the service data flow to the UE, and during the transmission process, the PDU set is transmitted based on the above analysis results.

Please refer to Figure 11. In this embodiment of the present application, the above steps 1 and 2 can be implemented in the following manner:

Step 111: AF sends an Nnwdaf_Analyticsription_Subscribe message to NWDAF. The message carries the following information:

Step 112: NWDAF subscribes to SMF for UE data;

Step 113: SMF obtains the first information from UFP through N4session, as shown in Table 1;

Step 114: SMF provides the first information to NWDAF;

Step 115: NWDAF collects the third information and the fourth information from the UE, as shown in Table 3;

Step 116: NWDAF provides the data obtained from UPF and UE to AF.

For the data feature analysis method provided by the embodiments of the present application, the execution subject may be a data feature analysis device. In the embodiment of the present application, the data characteristic analysis device executed by the data characteristic analysis method is used as an example to illustrate the data characteristic analysis device provided by the embodiment of the present application.

Please refer to Figure 12. This embodiment of the present application also provides a data feature analysis device 120, which includes:

The first acquisition module 121 is used to acquire relevant information of the service data flow of the first service. The relevant information includes first information and second information. The first information is the service data flow of the first service. PDU-related information, the second information is data frame-related information in the service data flow of the first service, wherein each of the data frames includes at least one PDU set;

The first determination module 122 is configured to determine the analysis model of the first service based on the relevant information of the service data flow. The analysis model is used to identify the data of the PDU set in the service data flow of the first service. feature.

Optionally, the first information includes at least one of the following: the reception time of each PDU, the time interval between two adjacent PDUs, and the size of each PDU;

and / or

The second information includes at least one of the following: the start time of each data frame, the end time of each data frame, the number of PDUs in each data frame, and the type indication information of each data frame; wherein, The type indication information includes at least one of the following: frame type, importance level information.

Optionally, the analysis model includes at least one of the following information: the time interval between two adjacent PDUs in the PDU set; the time interval between two adjacent PDU sets; size distribution information of different types of PDU sets. ;Periods of different types of PDU collections.

Optionally, the relevant information of the service data flow also includes third information, and the third information is the relevant information of lost PDUs and/or lost PDU sets;

The analysis model also includes the following information: indication information of whether packet loss in the PDU set is allowed.

Optionally, the third information includes at least one of the following: a timestamp when PDU loss occurs, and a timestamp when PDU set discard occurs.

Optionally, the relevant information of the service data flow also includes fourth information, and the fourth information is relevant information of out-of-order PDUs and/or out-of-order PDU sets;

The analysis model also includes at least one of the following information: first jitter information of the PDU in the PDU set; Second jitter information between PDU sets.

Optionally, the fourth information includes at least one of the following: a timestamp of an out-of-order PDU; a timestamp of an out-of-order PDU set.

Optionally, the relevant information of the service data flow also includes fifth information, and the fifth information includes at least one of the following: duration of the service data flow, uplink bit rate, downlink bit rate, uplink PDU delay, downlink PDU delay, number of uplink PDU transmissions, and number of downlink PDU transmissions.

Optionally, the data feature analysis device 120 also includes:

The first sending module is configured to send the analysis model or the information of the analysis model to the second device, so that the second device can analyze the data characteristics of the PDU set in the service data flow of the first service.

Optionally, the data feature analysis device 120 also includes:

A receiving module, configured to receive a first request, the first request being used to request an analysis model of the first business, the first request including at least one of the following information: a first identification and a first filtering information. ;

The first filtering information includes at least one of the following: service data flow description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, and terminal identifier.

Optionally, the data feature analysis device 120 also includes:

The second sending module is configured to send a second request. The second request is used to request to obtain relevant information of the service data flow. The second request includes at least one of the following information: a first identifier and a third 1. Filter information;

The first identifier is used to indicate relevant information of the requested service data flow;

The data feature analysis device in the embodiment of the present application may be an electronic device, such as an electronic device with an operating system, or may be a component in the electronic device, such as an integrated circuit or chip.

The data feature analysis device provided by the embodiment of the present application can implement each process implemented by the method embodiment in Figure 2 and achieve the same technical effect. To avoid duplication, the details will not be described here.

Please refer to Figure 13. This embodiment of the present application also provides a data feature analysis device 130, which includes:

The first acquisition module 131 is used to acquire the analysis model of the first service, where the analysis model is used to identify the data characteristics of the PDU set in the service data flow of the first service;

The analysis module 132 is configured to analyze the target service data flow of the first service according to the analysis model and obtain analysis results, where the analysis results include at least one of the following: Boundary information, type indication information of the PDU set, the sequence number of each PDU in the PDU set, the number of PDUs in the PDU set, and the period of the PDU set;

The boundary information of the PDU set in the target service data flow includes at least one of the following: Information about the starting PDU and information about the ending PDU of the PDU set.

In the embodiment of the present application, the data characteristics of the PDU set in the service data flow of the first service can be identified through the analysis model, so that all PDUs in the PDU set of the I frame can be transmitted preferentially, ensuring that when the user uses the first service smooth experience.

Optionally, the analysis model also includes at least one of the following information: first jitter information of PDUs within the PDU set; second jitter information between PDU sets; the analysis module 132 is configured to perform jitter according to the first One jitter information and/or second jitter information determines the boundary of the PDU set in the target service data flow.

Optionally, the data feature analysis device 130 also includes:

A first sending module, configured to send a third request to a third device. The third request is used to request a service data flow of the first service. The third request includes at least one of the following: a service data flow description identifier. , service identification, APP identification, slice identification, data network name, network area information, terminal identification;

The first receiving module is configured to receive the target service data stream of the first service sent by the third device.

Optionally, the data feature analysis device 130 also includes:

The second receiving module is configured to receive a fourth request. The fourth request is used to request the second device to analyze the service data flow of the first service. The fourth request includes at least one of the following: Service Data flow description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, terminal identifier, and the identifier of the UPF that provides services for the terminal.

Optionally, the data feature analysis device 130 also includes:

The second sending module is used to send the analysis result to the third device.

The data feature analysis device provided by the embodiment of the present application can implement each process implemented by the method embodiment in Figure 4 and achieve the same technical effect. To avoid duplication, the details will not be described here.

Please refer to Figure 14. This embodiment of the present application also provides a data feature analysis device 140, which includes:

The first receiving module 141 is used to receive the analysis results of the target service data flow of the first service. The analysis results are obtained based on the analysis model. The analysis model is used to identify PDUs in the service data flow of the first service. Collection data characteristics;

The first determination module 142 is configured to determine the transmission mode of the PDU set in the target service data flow according to the analysis result.

In this embodiment of the present application, the analysis model can be used to identify the PDU set in the service data flow of the first service. Data characteristics, so that all PDUs in the PDU set of the I frame can be prioritized for transmission, ensuring a smooth user experience when using the first service.

Optionally, the data feature analysis device 140 also includes:

The second receiving module is configured to receive a fifth request sent by the fourth device. The fifth request is used to request analysis of the service data flow of the first service. The fifth request includes at least one of the following: Service Data flow description identification, service identification, APP identification, slice identification, data network name, network area information, terminal identification;

A sending module, configured to send a fourth request to the second device. The fourth request is used to request the second device to analyze the service data flow of the first service. The fourth request includes at least one of the following: : Service data flow description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, terminal identifier, and the identifier of the UPF that provides services for the terminal.

The data feature analysis device provided by the embodiment of the present application can implement each process implemented by the method embodiment in Figure 5 and achieve the same technical effect. To avoid duplication, the details will not be described here.

Optionally, as shown in Figure 15, this embodiment of the present application also provides a network device 150, which includes a processor 151 and a memory 152. The memory 152 stores programs or instructions that can be run on the processor 151. When the program or instruction is executed by the processor 151, each step of the above-mentioned data feature analysis method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, the details will not be described here.

Embodiments of the present application also provide a network device, including a processor and a communication interface. The communication interface is used to receive an analysis result of the target service data flow of the first service. The analysis result is obtained based on an analysis model. The analysis model is To identify the data characteristics of the PDU set in the service data flow of the first service; the processor is configured to determine the transmission mode of the PDU set in the target service data flow according to the analysis result. This network device embodiment corresponds to the method embodiment executed by the above-mentioned third device. Each implementation process and implementation manner of the above-mentioned method embodiment can be applied to this network device embodiment, and can achieve the same technical effect.

Specifically, the embodiment of the present application also provides a network device. As shown in FIG. 16 , the network device 160 includes: an antenna 161 , a radio frequency device 162 , a baseband device 163 , a processor 164 and a memory 165 . The antenna 161 is connected to the radio frequency device 162 . In the uplink direction, the radio frequency device 162 receives information through the antenna 161 and sends the received information to the baseband device 163 for processing. In the downlink direction, the baseband device 163 processes the information to be sent and sends it to the radio frequency device 162. The radio frequency device 162 processes the received information and then sends it out through the antenna 161.

The method performed by the network device in the above embodiment can be implemented in the baseband device 163, which includes a baseband processor.

The baseband device 163 may include, for example, at least one baseband board on which multiple chips are disposed, as shown in FIG. Program to perform the network device operations shown in the above method embodiments.

The network side device may also include a network interface 166, which is, for example, a common public wireless interface. public radio interface (CPRI).

Specifically, the network device 160 in the embodiment of the present application also includes: instructions or programs stored in the memory 165 and executable on the processor 164. The processor 164 calls the instructions or programs in the memory 165 to execute the modules shown in Figure 14 The implementation method and achieve the same technical effect will not be repeated here to avoid repetition.

Specifically, the embodiment of the present application also provides a network device. As shown in FIG. 17 , the network device 170 includes: a processor 171 , a network interface 172 and a memory 173 . Among them, the network interface 172 is, for example, a common public radio interface (CPRI).

Specifically, the network device 170 in the embodiment of the present application also includes: instructions or programs stored in the memory 173 and executable on the processor 171. The processor 171 calls the instructions or programs in the memory 173 to execute FIG. 12 or FIG. 13 or Figure 14 shows the execution method of each module and achieves the same technical effect. To avoid repetition, it will not be described again here.

Embodiments of the present application also provide a readable storage medium. Programs or instructions are stored on the readable storage medium. When the program or instructions are executed by a processor, each process of the above-mentioned data feature analysis method embodiment is implemented, and can achieve The same technical effects are not repeated here to avoid repetition.

Wherein, the processor is the processor in the terminal described in the above embodiment. The readable storage medium includes computer readable storage media, such as computer read-only memory ROM, random access memory RAM, magnetic disk or optical disk, etc.

An embodiment of the present application further provides a chip. The chip includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the above embodiment of the data feature analysis method. Each process can achieve the same technical effect. To avoid repetition, we will not go into details here.

It should be understood that the chips mentioned in the embodiments of this application may also be called system-on-chip, system-on-a-chip, system-on-chip or system-on-chip, etc.

Embodiments of the present application further provide a computer program/program product. The computer program/program product is stored in a storage medium. The computer program/program product is executed by at least one processor to implement the above data feature analysis method. Each process in the example can achieve the same technical effect. To avoid repetition, we will not repeat it here.

Embodiments of the present application also provide a communication system, including: a first device, a second device and a third device. The first device can be used to perform the steps of the data feature analysis method performed by the first device. The second device may be configured to perform the steps of the data characteristic analysis method performed by the above-mentioned second device, and the third device may be configured to perform the steps of the data characteristic analysis method performed by the above-mentioned third device.

It should be noted that, in this document, the terms "comprising", "comprises" or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article or device that includes a series of elements not only includes those elements, It also includes other elements not expressly listed or inherent in the process, method, article or apparatus. Without further limitation, an element defined by the statement "comprises a..." does not exclude the presence of additional identical elements in a process, method, article or apparatus that includes that element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, but may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved. Functions can be executed, for example, by different The described methods are performed in the order described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus the necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is better. implementation. Based on this understanding, the technical solution of the present application can be embodied in the form of a computer software product that is essentially or contributes to the existing technology. The computer software product is stored in a storage medium (such as ROM/RAM, disk , CD), including several instructions to cause a terminal (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in various embodiments of this application.

The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above-mentioned specific implementations. The above-mentioned specific implementations are only illustrative and not restrictive. Those of ordinary skill in the art will Inspired by this application, many forms can be made without departing from the purpose of this application and the scope protected by the claims, all of which fall within the protection of this application.

Claims

A data feature analysis method, including:

The first device obtains relevant information of the service data flow of the first service. The relevant information of the service data flow includes first information and second information. The first information is a protocol in the service data flow of the first service. Relevant information of the data unit PDU, the second information is the relevant information of the data frames in the service data flow of the first service, wherein each of the data frames includes at least one PDU set;

The first device determines an analysis model of the first service based on the relevant information of the service data flow, and the analysis model is used to identify the data characteristics of the PDU set in the service data flow of the first service.
The method of claim 1, wherein,

The first information includes at least one of the following: the reception time of each PDU, the time interval between two adjacent PDUs, and the size of each PDU;

and / or

The second information includes at least one of the following: the start time of each data frame, the end time of each data frame, the number of PDUs in each data frame, and the type indication information of each data frame; wherein, The type indication information includes at least one of the following: frame type, importance level information.
The method according to claim 1 or 2, wherein,

The analysis model includes at least one of the following information: the time interval between two adjacent PDU sets within the PDU set; the time interval between two adjacent PDU sets; size distribution information of different types of PDU sets; different types of The period of PDU collection.
The method of claim 1, wherein,

The relevant information of the service data flow also includes third information, and the third information is the relevant information of lost PDUs and/or lost PDU sets;

The analysis model also includes the following information: indication information of whether packet loss in the PDU set is allowed.
The method of claim 4, wherein

The third information includes at least one of the following: a timestamp when PDU loss occurs, and a timestamp when PDU set discard occurs.
The method according to any one of claims 1, 2, and 4, wherein,

The relevant information of the service data flow also includes fourth information, and the fourth information is relevant information of out-of-order PDUs and/or out-of-order PDU sets;

The analysis model also includes at least one of the following information: first jitter information of PDUs within the PDU set; second jitter information between PDU sets.
The method of claim 6, wherein

The fourth information includes at least one of the following: the timestamp of the out-of-order PDU; the timestamp of the out-of-order PDU set.
The method according to any one of claims 1, 2, and 4, wherein the relevant information of the service data flow It also includes fifth information, which includes at least one of the following: duration of service data flow, uplink bit rate, downlink bit rate, uplink PDU delay, downlink PDU delay, uplink PDU transmission number, downlink PDU transmission quantity.
The method according to any one of claims 1, 2, and 4, wherein the method further includes:

The first device sends the analysis model or the information of the analysis model to the second device, so that the second device can analyze the data characteristics of the PDU set in the service data flow of the first service.
The method according to any one of claims 1, 2, and 4, wherein the method further includes:

The first device receives a first request, the first request is used to request an analysis model of the first service, and the first request includes at least one of the following information: a first identification and a first filtering information. ;

The first identifier is used to indicate that the requested analysis model is an analysis model used to identify the data characteristics of the PDU set in the service data flow;

The first filtering information includes at least one of the following: service data flow description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, and terminal identifier.
The method according to any one of claims 1, 2, and 4, wherein the method further includes:

The first device sends a second request. The second request is used to request to obtain relevant information of the service data flow. The second request includes at least one of the following information: a first identification and a first filter. information;

The first identifier is used to indicate relevant information of the requested service data flow;

The first filtering information includes at least one of the following: service data flow description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, and terminal identifier.
The method according to any one of claims 1, 2, and 4, wherein the first device is a network data analysis function model training logic function NWDAF MTLF or an application function AF.
A data feature analysis method, including:

The second device obtains the analysis model of the first service, where the analysis model is used to identify the data characteristics of the PDU set in the service data flow of the first service;

The second device analyzes the target service data flow of the first service according to the analysis model and obtains an analysis result. The analysis result includes at least one of the following: the boundary of the PDU set in the target service data flow. Information, the type indication information of the PDU set, the sequence number of each PDU in the PDU set, the number of PDUs in the PDU set, and the period of the PDU set;

Wherein, the type indication information includes at least one of the following: frame type, importance level information;

The boundary information of the PDU set in the target service data flow includes at least one of the following: information of the starting PDU of the PDU set, and information of the ending PDU of the PDU set.
The method of claim 13, wherein

The analysis model includes at least one of the following information: the time interval between two adjacent PDU sets within the PDU set; the time interval between two adjacent PDU sets; size distribution information of different types of PDU sets; different types of The period of PDU collection.
The method according to claim 13 or 14, wherein the analysis model further includes the following information: whether Instruction information indicating that packet loss of the PDU set is allowed, and the analysis results also include: the result of whether to continue transmitting the corresponding PDU set in the target service data flow.
The method according to claim 13 or 14, wherein the analysis model further includes at least one of the following information: first jitter information of PDUs within a PDU set; second jitter information between PDU sets; according to the The analysis model analyzes the target service data flow of the first service, and the analysis results obtained include:

The second device determines the boundary of the PDU set in the target service data flow according to the first jitter information and/or the second jitter information.
The method according to claim 13 or 14, wherein the method further includes:

The second device sends a third request to the third device. The third request is used to request the service data flow of the first service. The third request includes at least one of the following: service data flow description identifier, service Identity, APP identification, slice identification, data network name, network area information, terminal identification;

The second device receives the target service data stream of the first service sent by the third device.
The method according to claim 13 or 14, wherein the method further includes:

The second device receives a fourth request. The fourth request is used to request the second device to analyze the service data flow of the first service. The fourth request includes at least one of the following: service data flow. Description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, terminal identifier, and the identifier of the UPF that provides services for the terminal.
The method according to claim 13 or 14, wherein the method further includes:

The second device sends the analysis result to a third device.
A data feature analysis method, including:

The third device receives the analysis results of the target service data flow of the first service, the analysis results are obtained based on the analysis model, and the analysis model is used to identify the data characteristics of the PDU set in the service data flow of the first service;

The third device determines the transmission mode of the PDU set in the target service data flow based on the analysis result.
The method of claim 20, further comprising:

The third device receives a third request. The third request is used to request the service data flow of the first service. The third request includes at least one of the following: service data flow description identifier, service identifier, and APP identifier. , slice identification, data network name, network area information, terminal identification;

The third device obtains the target service data stream of the first service according to the third request.
The method according to claim 20 or 21, further comprising:

The third device receives a fifth request sent by the fourth device. The fifth request is used to request analysis of the service data flow of the first service. The fifth request includes at least one of the following: service data flow. Description identification, service identification, APP identification, slice identification, data network name, network area information, terminal identification;

The third device sends a fourth request to the second device. The fourth request is used to request the second device to analyze the service data flow of the first service. The fourth request includes at least one of the following: : Business data flow description identifier, Service identifier, APP identifier, slice identifier, data network name, network area information, terminal identifier, and the identifier of the UPF that provides services to the terminal.
A data feature analysis device, including:

The first acquisition module is used to acquire relevant information of the service data flow of the first service. The relevant information includes first information and second information. The first information is the PDU in the service data flow of the first service. The relevant information, the second information is the relevant information of the data frames in the service data flow of the first service, wherein each of the data frames includes at least one PDU set;

The first determination module is configured to determine the analysis model of the first service based on the relevant information of the service data flow. The analysis model is used to identify the data characteristics of the PDU set in the service data flow of the first service. .
A data feature analysis device, including:

The first acquisition module is used to acquire the analysis model of the first service, and the analysis model is used to identify the data characteristics of the PDU set in the service data flow of the first service;

An analysis module, configured to analyze the target service data flow of the first service according to the analysis model and obtain analysis results, where the analysis results include at least one of the following: the boundary of the PDU set in the target service data flow. Information, the type indication information of the PDU set, the sequence number of each PDU in the PDU set, the number of PDUs in the PDU set, and the period of the PDU set;

Wherein, the type indication information includes at least one of the following: frame type, importance level information;

The boundary information of the PDU set in the target service data flow includes at least one of the following: information of the starting PDU of the PDU set, and information of the ending PDU of the PDU set.
A data feature analysis device, including:

The first receiving module is configured to receive the analysis results of the target service data flow of the first service. The analysis results are obtained based on the analysis model. The analysis model is used to identify the PDU set in the service data flow of the first service. data characteristics;

The first determination module is configured to determine the transmission mode of the PDU set in the target service data flow according to the analysis result.
A network device, including a processor and a memory, the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, any one of claims 1 to 12 is implemented. The steps of the data characteristic analysis method; or, when the program or instruction is executed by the processor, the steps of the data characteristic analysis method according to any one of claims 13 to 19 are implemented; or, the program or When the instructions are executed by the processor, the steps of the data feature analysis method according to any one of claims 20 to 22 are implemented.
A readable storage medium that stores programs or instructions that, when executed by a processor, implement the steps of the data feature analysis method according to any one of claims 1 to 12, or , the steps of implementing the data feature analysis method as described in any one of claims 13 to 19, or the steps of implementing the data feature analysis method as described in any one of claims 20 to 22.