Data feature analysis method and apparatus, and network device

Abstract

The application discloses a data feature analysis method and device and network equipment, and belongs to the technical field of wireless communication. The data feature analysis method comprises the following steps: a first device acquires related information of a service data stream of a first service, wherein the related information of the service data stream comprises first information and second information, the first information is related information of a PDU in the service data stream of the first service, and the second information is related information of a data frame in the service data stream of the first service, wherein each data frame comprises at least one PDU set; and the first device determines an analysis model of the first service according to the related information of the service data stream, wherein the analysis model is used for identifying data features of the PDU set in the service data stream of the first service.

Description

Technical Field

[0001] This application belongs to the field of wireless communication technology, specifically relating to a data feature analysis method, apparatus, and network device. Background Technology

[0002] In Extended Reality (XR), video stream data can be divided into I-frames, P-frames, and B-frames.

[0003] An I-frame (Intra-coded picture) is also called an independent decoded frame and is usually a complete picture.

[0004] A P-frame (Predictive-coded Picture) represents the difference between the current frame and a previous I-frame or P-frame. During decoding, the previously cached frames are overlaid with the differences defined in the current frame to generate the final image.

[0005] A B-frame (Bidirectionally predicted picture) is a bidirectional difference frame, meaning that a B-frame records the difference between the current frame and the frames before and after it. In other words, to decode a B-frame, you need to obtain not only the previous buffered images but also the subsequent images, and obtain the final image by superimposing the data from the previous and subsequent images with the data of the current frame.

[0006] P-frames and B-frames record changes relative to I-frames. I-frames are more important than P-frames or B-frames; transmission errors in I-frames will prevent them from being correctly parsed by the receiver, further leading to parsing errors in subsequent P-frames and B-frames. Currently, the industry has proposed methods to optimize the transmission of I-frames, but these optimizations are contingent on the correct identification of I-frames.

[0007] A Protocol Data Unit (PDU) set is a collection of data with the same characteristics. A PDU set consists of one or more PDUs. A PDU set can be used to carry the payload of a frame or the payload of a slice of a frame. A frame can be divided into multiple slices, for example, a frame divided into 9 slices, and each PDU set is used to transmit one of those slices. Each PDU can be an Internet Protocol (IP) packet; or, each PDU can consist of multiple IP packets; or each PDU can be encapsulated within one or more IP packets; or, each PDU can be transmitted through one or more IP packets. Protocol Data Units can also be called Packet Data Units (PDUs), and in this application, the two terms are interchangeable.

[0008] One method for identifying I-frames involves the Application Function (AF) providing data characteristics of the PDU set when generating XR data, such as the frame's importance level or frame type (I-frame, P-frame, B-frame, etc.). Gateway devices within the operator's core network, such as the User Plane Function (UPF), can optimize transmission for different PDU sets. For example, they can prioritize the transmission of all PDUs within the I-frame's PDU set or use a high Quality of Service (QoS) flow for transmission, and instruct the base station to prioritize the transmission of all PDUs within the I-frame's PDU set. This ensures a smooth user experience when using XR services.

[0009] If the AF does not provide the gateway device with the data characteristics of the PDU set, or if the AF data is encrypted, for example, if the AF data is transmitted using Hyper Text Transfer Protocol over Secure Socket Layer (HTTPS), the gateway device cannot obtain the data characteristics of the PDU set, and therefore cannot optimize the transmission of I-frames, which will affect the user experience. Summary of the Invention

[0010] This application provides a data feature analysis method, apparatus, and network device that can solve the problem of not being able to obtain the data features of the PDU set, thus making it impossible to optimize the transmission of I-frames.

[0011] Firstly, a data feature analysis method is provided, including:

[0012] The first device acquires relevant information about the service data stream of the first service. The relevant information about the service data stream includes first information and second information. The first information is the relevant information about the PDUs in the service data stream of the first service, and the second information is the relevant information about the data frames in the service data stream of the first service. Each data frame includes at least one set of PDUs.

[0013] The first device determines an analysis model for the first service based on relevant information of the service data stream. The analysis model is used to identify the data characteristics of the PDU set in the service data stream of the first service.

[0014] Secondly, a data feature analysis method is provided, including:

[0015] The second device acquires 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 stream of the first service;

[0016] The second device analyzes the target service data stream of the first service according to the analysis model and obtains the analysis results. The analysis results include at least one of the following: boundary information of the PDU set in the target service data stream, type indication information of the PDU set, sequence number of each PDU in the PDU set, number of PDUs in the PDU set, and period of the PDU set.

[0017] The type indication information includes at least one of the following: frame type, importance level information;

[0018] The boundary information of the PDU set in the target business data stream 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.

[0019] Thirdly, a data feature analysis method is provided, including:

[0020] The third device receives the analysis results of the target service data stream of the first service. The analysis results are obtained based on the analysis model, which is used to identify the data characteristics of the PDU set in the service data stream of the first service.

[0021] The third device determines the transmission method of the PDU set in the target service data stream based on the analysis results.

[0022] Fourthly, a data feature analysis device is provided, comprising:

[0023] The first acquisition module is used to acquire relevant information of the business data stream of the first service. The relevant information includes first information and second information. The first information is the relevant information of PDUs in the business data stream of the first service, and the second information is the relevant information of data frames in the business data stream of the first service. Each data frame includes at least one set of PDUs.

[0024] The first determining module is used to determine the analysis model of the first service based on the relevant information of the service data stream. The analysis model is used to identify the data characteristics of the PDU set in the service data stream of the first service.

[0025] Fifthly, a data feature analysis device is provided, comprising:

[0026] 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 business data stream of the first service;

[0027] The analysis module is used to analyze the target business data stream of the first service according to the analysis model and obtain the analysis results. The analysis results include at least one of the following: boundary information of the PDU set in the target business data stream, type indication information of the PDU set, sequence number of each PDU in the PDU set, number of PDUs in the PDU set, and period of the PDU set.

[0028] The type indication information includes at least one of the following: frame type, importance level information;

[0029] The boundary information of the PDU set in the target business data stream 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.

[0030] Sixthly, a data feature analysis device is provided, comprising:

[0031] The first receiving module is used to receive the analysis results of the target service data stream of the first service. The analysis results are obtained based on the analysis model, which is used to identify the data characteristics of the PDU set in the service data stream of the first service.

[0032] The first determining module is used to determine the transmission method of the PDU set in the target service data stream based on the analysis results.

[0033] A seventh aspect provides a network device, the terminal including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the first, second, or third aspect.

[0034] Eighthly, a network device is provided, including a processor and a communication interface, wherein the processor is configured to acquire relevant information of a service data stream of a first service, the relevant information including first information and second information, the first information being relevant information of PDUs in the service data stream of the first service, and the second information being relevant information of data frames in the service data stream of the first service, wherein each data frame includes at least one set of PDUs; and to determine an analysis model of the first service based on the relevant information of the service data stream, the analysis model being configured to identify data characteristics of the set of PDUs in the service data stream of the first service.

[0035] In a ninth aspect, a network device is provided, including a processor and a communication interface, wherein the processor is configured to acquire an analysis model of a first service, the analysis model being configured to identify data characteristics of a set of PDUs in the service data stream of the first service; and to analyze a target service data stream of the first service according to the analysis model to obtain analysis results, the analysis results including at least one of the following: boundary information of the PDU set in the target service data stream, type indication information of the PDU set, sequence number of each PDU in the PDU set, number of PDUs in the PDU set, and period of the PDU set; wherein the type indication information includes at least one of the following: frame type and importance level information; the boundary information of the PDU set in the target service data stream 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.

[0036] In a tenth aspect, a communication system is provided, comprising: a first device, a second device, and a third device, wherein the first device is configured to perform the steps of the data feature analysis method as described in the first aspect, the second device is configured to perform the steps of the data feature analysis method as described in the second aspect, and the third device is configured to perform the steps of the data feature analysis method as described in the third aspect.

[0037] Eleventhly, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the data feature analysis method as described in the first, second, or third aspects.

[0038] In a twelfth aspect, a chip is provided, the chip including a processor and a communication interface coupled to the processor, the processor being used to run programs or instructions to implement the data feature analysis method as described in the first, second or third aspect.

[0039] In a thirteenth aspect, a computer program / program product is provided, which is stored in a storage medium and is executed by at least one processor to perform the data feature analysis steps as described in the first, second, or third aspect.

[0040] In this embodiment of the application, an analysis model for the first service is obtained by training on the relevant information of the service data stream of the first service. This analysis model can identify the data characteristics of the PDU set in the service data stream of the first service, thereby prioritizing the transmission of all PDUs in the PDU set of the I-frame to ensure a smooth user experience when using the first service. Attached Figure Description

[0041] Figure 1 This is a block diagram of a wireless communication system applicable to embodiments of this application;

[0042] Figure 2 This is one of the flowcharts illustrating the data feature analysis method according to an embodiment of this application;

[0043] Figure 3 This is a schematic diagram of PDUs in I-frames, P-frames, and B-frames according to an embodiment of this application;

[0044] Figure 4 This is a second schematic flowchart of the data feature analysis method according to an embodiment of this application;

[0045] Figure 5 This is the third flowchart illustrating the data feature analysis method according to an embodiment of this application;

[0046] Figure 6 This is a flowchart illustrating the data feature analysis method of Embodiment 1 of this application;

[0047] Figure 7 This is one of the flowcharts illustrating the data feature analysis method of Embodiment 2 of this application;

[0048] Figure 8 This is the second flowchart illustrating the data feature analysis method of Embodiment 2 of this application;

[0049] Figure 9 This is the third flowchart illustrating the data feature analysis method of Embodiment 2 of this application;

[0050] Figure 10This is one of the flowcharts illustrating the data feature analysis method of Embodiment 3 of this application;

[0051] Figure 11 This is the second flowchart illustrating the data feature analysis method of Embodiment 3 of this application;

[0052] Figure 12 This is one of the structural schematic diagrams of the data feature analysis device according to an embodiment of this application;

[0053] Figure 13 This is a second schematic diagram of the structure of the data feature analysis device according to an embodiment of this application;

[0054] Figure 14 This is the third schematic diagram of the data feature analysis device according to an embodiment of this application;

[0055] Figure 15 This is a schematic diagram of the network device according to an embodiment of this application;

[0056] Figure 16 This is one of the hardware structure diagrams of the network device according to an embodiment of this application;

[0057] Figure 17 This is a second schematic diagram of the hardware structure of the network device according to an embodiment of this application. Detailed Implementation

[0058] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0059] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same class, not limited in number; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0060] It is worth noting that the technologies described in this application are not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be used in other wireless communication systems, such as 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 this application are often used interchangeably, and the described technologies can be used with the systems and radio technologies mentioned above, as well as with other systems and radio technologies. The following description describes New Radio (NR) systems for illustrative purposes, and NR terminology is used in most of the following description; however, these technologies can also be applied to applications beyond NR systems, such as 6th generation (6G) radio systems. th Generation 6G communication system.

[0061] Figure 1This diagram illustrates a block diagram of a wireless communication system applicable to embodiments of this application. The wireless communication system includes a terminal 11 and a network-side device 12. Terminal 11 can be a mobile phone, tablet computer, laptop computer, personal digital assistant (PDA), handheld computer, netbook, ultra-mobile personal computer (UMPC), mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, vehicle-mounted device (VUE), pedestrian terminal (PUE), smart home (home devices with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), game console, personal computer (PC), ATM or self-service machine, etc. Wearable devices include: smartwatches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart chains, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Besides the aforementioned terminal devices, it could also be a chip within the terminal, such as a modem chip or a system-on-chip (SoC). It should be noted that the specific type of terminal 11 is not limited in this application embodiment. The network-side device 12 may include access network equipment or core network equipment. The access network equipment 12 may also be referred to as a radio access network device, radio access network (RAN), radio access network function, or radio access network unit. Access network device 12 may include base stations, WLAN access points, or WiFi nodes, etc. The base station may be referred to as Node B, Evolved Node B (eNB), access point, 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 Receiving Point (TRP), or any other suitable term 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 this application embodiment, only the base station in the NR system is used as an example for introduction, and the specific type of base station is not limited.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 (MME), Access and Mobility Management Function (AMF), Session Management Function (SMF), User Plane Function (UPF), Policy Control Function (PCF), Policy and Charging Rules Function (PCRF), Edge Application Server Discovery Function (EASDF), Unified Data Management (UDM), Unified Data Repository (UDR), Home Subscriber Server (HSS), Centralized network configuration (CNC), Network Repository Function (NRF), Network Exposure Function (NEF), Local NEF (or L-NEF), and Binding Support. Core network functions (BSF), application functions (AF), etc. It should be noted that this application embodiment only uses core network equipment in the NR system as an example for description, and does not limit the specific type of core network equipment.

[0062] The data feature analysis method, apparatus, and network device provided in this application will be described in detail below with reference to the accompanying drawings and through some embodiments and application scenarios.

[0063] Please refer to Figure 2 This application provides a data feature analysis method, including:

[0064] Step 21: The first device obtains relevant information about the service data stream of the first service. The relevant information about the service data stream includes first information and second information. The first information is the relevant information about the PDUs in the service data stream of the first service, and the second information is the relevant information about the data frames in the service data stream of the first service. Each data frame includes at least one set of PDUs.

[0065] Step 22: The first device determines an analysis model for the first service based on the relevant information of the service data stream. This analysis model is used to identify the data characteristics of the PDU set in the service data stream of the first service. This analysis model can also be called a machine learning model (ML model).

[0066] In this embodiment of the application, the first device may be a Network Data Analysis Function (NWDAF) Model Training Logical Function (MTLF), an Application Function (AF), or other network devices.

[0067] In this embodiment of the application, optionally, the first service can be an extended reality (XR) service or other services.

[0068] In this embodiment, the data frame may include at least one of the following: a screen frame corresponding to a service, such as an I-frame, P-frame, or B-frame; a screen frame in the service data stream, such as an I-frame, P-frame, or B-frame; data corresponding to a screen frame in the service data stream; a slice of a screen frame corresponding to a service; a slice of a screen frame in the service data stream; and data corresponding to a slice of a screen frame in the service data stream. A screen frame may include multiple slices, for example, a screen frame divided into 9 slices. The screen frame may also be called an image frame, portrait frame, graphic frame, etc., and this application does not specifically limit its terminology. All descriptions used to describe a frame are within the scope of this application.

[0069] Please refer to Figure 3 , Figure 3 This is a schematic diagram of PDUs in I-frames, P-frames and B-frames in the embodiments of this application. As can be seen from the figure, each frame includes multiple PDUs, and SN is the sequence number of the PDU.

[0070] In this embodiment of the application, an analysis model for the first service is obtained by training on the relevant information of the service data stream of the first service. This analysis model can identify the data characteristics of the PDU set in the service data stream of the first service, thereby prioritizing the transmission of all PDUs in the PDU set of the I-frame to ensure a smooth user experience when using the first service.

[0071] In this embodiment of the 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.

[0072] In this embodiment of the application, the first device can collect the first information from a gateway device (such as a UPF). Optionally, the first information provided by the gateway device is at the IP 5-tuple granularity, that is, at the service data stream granularity. The IP 5-tuple includes: terminal IP address, terminal port number, server IP address, server port number, and protocol number.

[0073] In one embodiment, the first information may be as shown in Table 1:

[0074] Table 1 First Information

[0075]

[0076]

[0077] In this embodiment of the 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, and the type indication information of each data frame; wherein, the type indication information includes at least one of the following: frame type and importance level information.

[0078] In this embodiment of the application, the frame type may optionally include at least one of the following: I-frame, P-frame, and B-frame. Generally, I-frames have a higher importance level than B-frames and P-frames.

[0079] In this embodiment of the application, if the first device is an NWDAF MTLF, the first device can collect the second information from the AF. Optionally, the second information provided by the AF is at the IP 5-tuple granularity, that is, at the service data stream granularity. The IP 5-tuple 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.

[0080] In one embodiment, the second information may be as shown in Table 2:

[0081] Table 2 Second Information

[0082]

[0083]

[0084] In this embodiment of the application, optionally, the relevant information of the service data stream also includes fifth information, as shown in Tables 1 and 2. The fifth information includes at least one of the following: duration of the service data stream, uplink bit rate, downlink bit rate, uplink PDU delay, downlink PDU delay, number of uplink PDUs transmitted, and number of downlink PDUs transmitted.

[0085] As can be seen from Tables 1 and 2 above, the first device can obtain the fifth information from the gateway device and / or AF.

[0086] In this embodiment of the application, optionally, the analysis model includes at least one of the following information:

[0087] 1) The time interval between two adjacent PDUs within the PDU set;

[0088] 2) The time interval between two adjacent PDU sets;

[0089] Using 1) and 2), we can distinguish which PDUs belong to a PDU set and identify the boundaries of the PDU set.

[0090] Typically, the time interval between adjacent PDUs within a PDU set is relatively short, for example, 1ms; while the time interval between adjacent PDU sets is longer, for example, 16.67ms.

[0091] 3) Size distribution information of different types of PDU sets;

[0092] For example, the size distribution function f1(x) can be a set of PDUs of different types. The size distribution function f1(x) can be a normal distribution function, a mean distribution function, etc.

[0093] Typically, the PDU set of an I-frame is larger, while the PDU set of a P-frame or B-frame is smaller.

[0094] 4) Periods of different types of PDU sets.

[0095] I-frames typically appear periodically, for example, one I-frame every 8 frames. This periodicity can be used to determine the frame type or importance level of a PDU set.

[0096] In this embodiment of the application, optionally, the relevant information of the business data stream further includes third information, which is relevant information about lost PDUs and / or lost PDU sets; optionally, the analysis model also includes the following information: indication information on whether PDU set packet loss is allowed. This information is mainly used to determine whether other remaining PDUs in the PDU set containing the lost PDU need to be transmitted if PDU loss is detected. For example, under certain 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 in a PDU set is lost, there is no need to transmit other remaining PDUs in the PDU set. In other words, by training the third information, the trained analysis model can include indication information on whether PDU set packet loss is allowed, i.e., it has the function of analyzing whether PDU set packet loss is allowed.

[0097] In this embodiment of the application, optionally, the third information includes at least one of the following: a timestamp of PDU loss, and a timestamp of PDU set being discarded.

[0098] In this embodiment of the application, optionally, the relevant information of the business data stream further includes fourth information, wherein the fourth information is relevant information of out-of-order PDUs and / or out-of-order PDU sets; optionally, the analysis model further includes at least one of the following information:

[0099] 1) The first jitter information of the PDUs in the PDU set;

[0100] For example, it could be the distribution function f2(x) of PDU jitter within the PDU set. The distribution function f2(x) could be, for example, a Gaussian distribution function.

[0101] The first jitter information indicates that the PDU experienced a significant transmission delay during network transmission. This first jitter information can be used to eliminate the impact of jitter on the determination of PDU set boundaries.

[0102] 2) Second jitter information between PDU sets.

[0103] For example, it could be the distribution function f3(x) representing the jitter between PDU sets. The distribution function f3(x) could be, for example, a Gaussian distribution function.

[0104] The second jitter information indicates that the PDU set experienced significant transmission delay during network transmission. This second jitter information can be used to eliminate the impact of jitter on the periodicity determination of the PDU set.

[0105] By using 1) and 2) above, interference can be eliminated for jitter occurring within and between PDU sets.

[0106] In other words, 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 a PDU set and / or the second jitter information between PDU sets.

[0107] In this embodiment of the application, optionally, the fourth information includes at least one of the following: timestamps of out-of-order PDUs; timestamps of the out-of-order PDU set.

[0108] In this embodiment of the application, the first device can collect the third information and / or the fourth information from the terminal (UE). Optionally, the third information and / or the fourth information provided by the terminal is at the IP 5-tuple granularity, that is, at the service data stream granularity. The IP 5-tuple includes: terminal IP address, terminal port number, server IP address, server port number, and protocol number.

[0109] In one embodiment, the third and fourth information may be as shown in Table 3:

[0110] Table 3 Third and Fourth Information

[0111]

[0112] In this embodiment of the application, optionally, the first device sends the analysis model or information of the analysis model to the second device for the second device to analyze the data characteristics of the PDU set in the service data stream of the first service. In this embodiment of the application, optionally, the second device can be an NWDAF AnLF, or other network device. An NWDAF AnLF can also be called an NWDAF containing AnLF.

[0113] The Network Data Analytics Function (NWDAF) in this application embodiment can be divided into the following two functions:

[0114] Model Training Logical Function (MTLF): Used to train and analyze models.

[0115] The Analytics logical function (AnLF) is used to perform logical reasoning (reference) using an analytical model.

[0116] In this embodiment of the application, optionally, the data feature analysis method further includes: the first device receiving a first request, the first request being used to request the analysis model of the first service, the first request including at least one of the following information: a first identifier and first filtering information, the first filtering information may also be called an analytics filter, used to filter service data that meets the conditions;

[0117] 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 business data stream;

[0118] The first filtering information includes at least one of the following: business data flow description identifier, business identifier, application ID, slice identifier, data network name (DNN), network area information, and terminal identifier.

[0119] Optionally, the first identifier can be an Analytics ID, in which case the value corresponding to the Analytics ID indicates that the requested analytics model is an analytics model used to identify the data characteristics of the PDU set in the business data stream. For example,

[0120] Analytics ID = Business Flow Characteristics.

[0121] The APP identifier can also be used as a business identifier, and a business training and analysis model can be specified for the business corresponding to the APP identifier.

[0122] The service data flow descriptor can also replace the APP identifier. The service data flow descriptor can be an IP 5-tuple (terminal IP address, terminal port number, server IP address, server port number, protocol number) or an IP triple (server IP address, server port number, protocol number).

[0123] Slice identifiers, such as Single Network Slice Selection Assistance Information (S-NSSAI), can specify the services within that slice to be analyzed.

[0124] The Data Network Name (DNN) allows you to specify the services within the data network corresponding to the DNN for analysis.

[0125] The Area of ​​Interest (APOI) allows you to specify which services within that area to analyze.

[0126] 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, telephone number, etc.

[0127] In this embodiment of the application, optionally, the data analysis method further includes: the first device sending a second request, the second request being used to request relevant information of the service data stream, the second request including at least one of the following: a first identifier and first filtering information; the first identifier being used to indicate the request for relevant information of the service data stream; the first filtering information including at least one of the following: service data stream description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, and terminal identifier.

[0128] The descriptions of the first identifier and the first filtering information are as described above and will not be repeated here.

[0129] Please refer to Figure 4 This application also provides a data feature analysis method, including:

[0130] Step 41: The second device acquires the analysis model of the first service, the analysis model being used to identify the data characteristics of the PDU set in the service data stream of the first service;

[0131] Step 42: The second device analyzes the target service data stream of the first service according to the analysis model and obtains the analysis results. The analysis results include at least one of the following: boundary information of the PDU set in the target service data stream, type indication information of the PDU set, sequence number of each PDU in the PDU set, number of PDUs in the PDU set, and period of the PDU set.

[0132] The type indication information includes at least one of the following: frame type, importance level information;

[0133] The boundary information of the PDU set in the target business data stream 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.

[0134] In this embodiment of the application, the second device may optionally be an NWDAF AnLF or other network device.

[0135] In this embodiment of the application, optionally, the first service can be an extended reality (XR) service or other services.

[0136] In this embodiment of the application, the frame type may optionally include at least one of the following: I-frame, P-frame, and B-frame. Generally, I-frames have a higher importance level than B-frames and P-frames.

[0137] In this embodiment of the application, each PDU set includes at least one PDU. Each PDU can be an IP packet.

[0138] In this embodiment of the application, the data characteristics of the PDU set in the service data stream of the first service can be identified by the analysis model, so that all PDUs in the PDU set of the I frame can be transmitted first, ensuring a smooth experience for users when using the first service.

[0139] In this embodiment of the application, optionally, the analysis model includes at least one of the following information:

[0140] 1) The time interval between two adjacent PDUs within the PDU set;

[0141] 2) The time interval between two adjacent PDU sets;

[0142] Using 1) and 2), we can distinguish which PDUs belong to a PDU set and identify the boundaries of the PDU set.

[0143] Typically, the time interval between adjacent PDUs within a PDU set is relatively short, for example, 1ms; while the time interval between adjacent PDU sets is longer, for example, 16.67ms.

[0144] 3) Size distribution information of different types of PDU sets;

[0145] For example, the size distribution function f1(x) can be a set of PDUs of different types. The size distribution function f1(x) can be a normal distribution function, a mean distribution function, etc.

[0146] Typically, the PDU set of an I-frame is larger, while the PDU set of a P-frame or B-frame is smaller.

[0147] 4) Periods of different types of PDU sets.

[0148] I-frames typically appear periodically, for example, one I-frame every 8 frames. This periodicity can be used to determine the frame type or importance level of a PDU set.

[0149] Optionally, the analysis model may also include the following information: indication information on whether PDU set packet loss is allowed, and the analysis result may also include: the result of whether to continue transmitting the corresponding PDU set in the target service data stream.

[0150] Optionally, the analysis model further includes at least one of the following: first jitter information of PDUs within the PDU set; second jitter information between PDU sets; and analysis of the target service data stream of the first service based on the analysis model, obtaining analysis results including: the second device determining the boundary of the PDU set in the target service data stream based on the first jitter information and / or the second jitter information. For example, if the jitter of an abnormal PDU within the PDU set is found to match the first jitter information, the jitter of that PDU can be ignored and considered as normal jitter, instead of considering the PDU set as ending, thereby eliminating the influence of the first jitter information on the determination of the PDU combination boundary.

[0151] In this embodiment of the application, optionally, the data feature method further includes:

[0152] The second device sends a third request to the third device. The third request is used to request the service data stream of the first service. The third request includes at least one of the following: service data stream description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, and terminal identifier.

[0153] The second device receives the target service data stream of the first service sent by the third device.

[0154] In this embodiment of the application, the third device may optionally be a gateway device, such as a UPF.

[0155] In this embodiment of the application, optionally, the data feature method further includes:

[0156] The second device receives a fourth request, which is used to request the second device to analyze the service data stream of the first service. The fourth request includes at least one of the following: service data stream description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, terminal identifier, and identifier of the UPF that provides services to the terminal.

[0157] In this embodiment of the application, optionally, the data feature method further includes:

[0158] The second device sends the analysis results to the third device.

[0159] At this time, the third device can be a gateway device, such as a UPF, a base station, or other network devices.

[0160] Please refer to Figure 5 This application also provides a data feature analysis method, including:

[0161] Step 51: The third device receives the analysis results of the target service data stream of the first service. The analysis results are obtained based on the analysis model, which is used to identify the data characteristics of the PDU set in the service data stream of the first service.

[0162] Step 52: The third device determines the transmission method of the PDU set in the target service data stream based on the analysis results.

[0163] The transmission method includes at least one of the following: whether to prioritize transmission, and whether to continue transmission.

[0164] In this embodiment of the application, the third device may optionally be a gateway device, such as a UPF, a base station, or other network device.

[0165] In this embodiment of the application, optionally, the first service can be an extended reality (XR) service or other services.

[0166] In this embodiment of the application, each PDU set includes at least one PDU. Each PDU can be an IP packet.

[0167] In this embodiment of the application, the data characteristics of the PDU set in the service data stream of the first service can be identified by the analysis model, so that all PDUs in the PDU set of the I frame can be transmitted first, ensuring a smooth experience for users when using the first service.

[0168] In this embodiment of the application, optionally, the data feature method further includes:

[0169] The third device receives a third request, which is used to request the service data stream of the first service. The third request includes at least one of the following: service data stream description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, and terminal identifier.

[0170] The third device obtains the target service data stream of the first service according to the third request.

[0171] In this embodiment, optionally, the third device can be a gateway device, such as a UPF.

[0172] In this embodiment of the application, optionally, the data feature method further includes:

[0173] The third device receives a fifth request sent by the fourth device. The fifth request is used to request the analysis of the service data stream of the first service. The fifth request includes at least one of the following: service data stream description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, and terminal identifier.

[0174] 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 stream of the first service. The fourth request includes at least one of the following: service data stream description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, terminal identifier, and identifier of the UPF that provides services to the terminal.

[0175] In this embodiment of the application, optionally, the fourth device can be an SMF or other network device. The second device can be an NWDAF AnLF or other network device.

[0176] The data feature analysis method of this application embodiment will be illustrated below with specific application scenarios.

[0177] Example 1 of this application:

[0178] In this embodiment, the analysis model is trained by the operator's network. Please refer to... Figure 6 The data feature analysis method of this application includes the following steps:

[0179] Step 1: The Network Function (NF) consumer, such as UPF or SMF, sends an Nnwdaf_AnalyticsSubscription_Subscribe message to the NWDAF AnLF, which contains the following information:

[0180] 1) Analytics ID (i.e., the first identifier in the above embodiments) 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 business data stream;

[0181] 2) The first filtering information, also known as the analytics filter, includes at least one of the following: business data flow description identifier, business identifier, application ID, slice identifier, DNN, network area information, and terminal identifier.

[0182] The APP identifier can also be used as a business identifier, and a business training and analysis model can be specified for the business corresponding to the APP identifier.

[0183] The service data flow descriptor can also replace the APP identifier. The service data flow descriptor can be an IP 5-tuple (terminal IP address, terminal port number, server IP address, server port number, protocol number) or an IP triple (server IP address, server port number, protocol number).

[0184] Slice identifiers, such as Single Network Slice Selection Assistance Information (S-NSSAI), can specify the services within that slice to be analyzed.

[0185] The Data Network Name (DNN) allows you to specify the services within the data network corresponding to the DNN for analysis.

[0186] The Area of ​​Interest (APOI) allows you to specify which services within that area to analyze.

[0187] 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, telephone number, etc.

[0188] The NWDAF in this application embodiment can be divided into the following two functions:

[0189] MTLF: Used for training and analyzing models.

[0190] AnLF: Used for logical reasoning (reference) using analytical models.

[0191] Logically, UPF and NWDAF AnLF are two separate entities, but physically they can be a single entity.

[0192] 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. This message contains the Analytics ID and Analytics Filter from Step 1.

[0193] Step 3: The NWDAF MTLF collects first information from the gateway device (such as the UPF). The content of the first information can be found in Table 1 of the above embodiments. It should be noted that the first information provided by the UPF is at the IP 5-tuple granularity (source IP address, destination IP address, protocol number, source port, destination port), that is, at the service data flow granularity. The IP 5-tuple includes: 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 or different from the UPF in Step 1.

[0194] Step 4: The NWDAF MTLF collects second information from the AF. The content of the second information can be found in Table 2 of the above embodiment. The second information provided by the AF is at the IP 5-tuple granularity, that is, at the service data flow granularity. The IP 5-tuple includes the following information: terminal IP address, terminal port number, server IP address, server port number, and protocol number.

[0195] Step 5: The NWDAF MTLF collects third and fourth information from the UE. The contents of the third and fourth information can be found in Table 3 of the above embodiments. The traffic information provided by the UE is at the IP 5-tuple granularity, that is, at the service data flow granularity. The IP 5-tuple includes the following information: terminal IP address, terminal port number, server IP address, server port number, and protocol number.

[0196] Step 6: NWDAF MTLF generates a training dataset based on relevant information from the service data streams received from AF, UPF and UE, and trains the analysis model based on the training dataset.

[0197] The analysis model includes at least one of the following:

[0198] 1) The time interval between two adjacent PDUs within the PDU set;

[0199] 2) The time interval between two adjacent PDU sets;

[0200] Using 1) and 2), we can distinguish which PDUs belong to a PDU set and identify the boundaries of the PDU set.

[0201] Typically, the time interval between adjacent PDUs within a PDU set is relatively short, for example, 1ms; while the time interval between adjacent PDU sets is longer, for example, 16.67ms.

[0202] 3) Size distribution information of different types of PDU sets;

[0203] For example, it can be the size distribution function f1(x) for different types of PDU sets.

[0204] Typically, the PDU set of an I-frame is larger, while the PDU set of a P-frame or B-frame is smaller.

[0205] 4) Periods of different types of PDU sets.

[0206] I-frames typically appear periodically, for example, one I-frame every 8 frames. This periodicity can be used to determine the frame type or importance level of a PDU set.

[0207] 5) Indication information on whether PDU set packet loss is allowed.

[0208] This information is primarily used to determine whether, in the event of a detected PDU loss, the remaining PDUs within the same PDU set need to be transmitted. For example, in certain video encoding formats, the loss of one PDU in a PDU set will affect the parsing of the entire set. Therefore, if one PDU is lost, there is no need to transmit the remaining PDUs within that set. In other words, by training with this third information, the trained analysis model can include indications of whether PDU set packet loss is permissible, thus possessing the function of analyzing whether PDU set packet loss is allowed.

[0209] 6) The first jitter information of the PDUs in the PDU set;

[0210] For example, the jitter distribution function f2(x) within the PDU set can be used. This first jitter information represents a significant transmission delay during PDU transmission over the network. The impact of jitter on the PDU set boundary determination can be eliminated based on this first jitter information.

[0211] 7) Second jitter information between PDU sets.

[0212] For example, it could be the distribution function f3(x) of jitter among PDU sets. This second jitter information represents a significant transmission delay in the PDU set during network transmission. The impact of jitter on the periodicity determination of the PDU set can be eliminated based on this second jitter information.

[0213] Step 7: NWDAF MTLF sends the trained analysis model to NWDAF AnLF via Nnwdaf_MLModelProvision_Notify or Nnwdaf_MLModelInfo_Response.

[0214] Step 8: NWDAF AnLF sends a Nupf_eventExposure_Subscibe message (i.e., the third request mentioned above) to UPF to request the service data stream. The request includes at least one of the following: service data stream description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, and terminal identifier.

[0215] Step 9: The UPF obtains the business data stream from the AF. Based on the third request mentioned above, the UPF sends the determined business data stream to the NWDAF AnLF.

[0216] Step 10: NWDAF AnLF uses an analysis model to analyze the received service data stream and obtains the analysis results, which are shown in Table 4.

[0217] Table 4 Analysis Results

[0218]

[0219] For details on how to obtain the analysis results based on the analysis model, please refer to the above embodiments, which will not be repeated here.

[0220] Step 11: NWDAF AnLF sends the analysis results to UPF;

[0221] Step 12: The UPF notifies the base station of the analysis results via the GPRS Tunneling Protocol (GTP) header;

[0222] Step 13: The base station sends the service data stream to the UE and transmits the PDU set according to the above analysis results during the transmission process.

[0223] Example 2 of this application:

[0224] Please refer to Figure 7 The data feature analysis method of this application includes the following steps:

[0225] Step 1: The NWDAF AnLF sends either Nnwdaf_MLModelProvision_Subscribe or Nnwdaf_MLModelInfo_Request (equivalent to the first request in the above embodiment) to the NWDAF MTLF to request the analysis model. This message contains:

[0226] 1) Analytics ID (i.e., the first identifier in the above embodiments) 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 business data stream;

[0227] 2) The first filtering information, also known as the analytics filter, includes at least one of the following: business data flow description identifier, business identifier, application ID, slice identifier, DNN, network area information, and terminal identifier.

[0228] The APP identifier can also be used as a business identifier, and a business training and analysis model can be specified for the business corresponding to the APP identifier.

[0229] The service data flow descriptor can also replace the APP identifier. The service data flow descriptor can be an IP 5-tuple (terminal IP address, terminal port number, server IP address, server port number, protocol number) or an IP triple (server IP address, server port number, protocol number).

[0230] Slice identifiers, such as Single Network Slice Selection Assistance Information (S-NSSAI), can specify the services within that slice to be analyzed.

[0231] The Data Network Name (DNN) allows you to specify the services within the data network corresponding to the DNN for analysis.

[0232] The Area of ​​Interest (APOI) allows you to specify which services within that area to analyze.

[0233] 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, telephone number, etc.

[0234] 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 trained without being triggered by other network elements; in other embodiments of this application, AnLF can be triggered by NFComsumer (UPF or SMF) to train the analysis model.

[0235] Please participate Figure 8 In some embodiments, prior to step 1, the following steps are also included:

[0236] Step 01a: When the SMF determines that the user is using the XR service, the SMF sends an N4 session establishment request or N4 session 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 stream description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, and terminal identifier;

[0237] Step 02a: The UPF sends an 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 stream 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.

[0238] Please participate Figure 9 In some embodiments, prior to step 1, the following steps are also included:

[0239] Step 01b: When the SMF determines that the user is using the XR service, the SMF sends an Nnwdaf_Analyticsription_Subscribe message (i.e., the fourth request in the above embodiment) to the AnLF. The message includes at least one of the following: service data stream description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, terminal identifier, and identifier of the UPF that provides services to the terminal.

[0240] Step 2: The NWDAF MTLF collects first information from the gateway device (such as the UPF). The content of the first information can be found in Table 1 of the above embodiments. It should be noted that the first information provided by the UPF is at the IP 5-tuple granularity (source IP address, destination IP address, protocol number, source port, destination port), that is, at the service data flow granularity. The IP 5-tuple includes: 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 or different from the UPF in Step 1.

[0241] Step 3: The NWDAF MTLF collects second information from the AF. The content of the second information can be found in Table 2 of the above embodiment. The second information provided by the AF is at the IP 5-tuple granularity, that is, at the service data flow granularity. The IP 5-tuple includes the following information: terminal IP address, terminal port number, server IP address, server port number, and protocol number.

[0242] Step 4: The NWDAF MTLF collects third and fourth information from the UE. The contents of the third and fourth information can be found in Table 3 of the above embodiments. The traffic information provided by the UE is at the IP 5-tuple granularity, that is, at the service data flow granularity. The IP 5-tuple includes the following information: terminal IP address, terminal port number, server IP address, server port number, and protocol number.

[0243] Step 5: NWDAF MTLF generates a training dataset based on relevant information from the service data streams received from AF, UPF and UE, and trains the analysis model based on the training dataset.

[0244] The analysis model includes at least one of the following:

[0245] 1) The time interval between two adjacent PDUs within the PDU set;

[0246] 2) The time interval between two adjacent PDU sets;

[0247] Using 1) and 2), we can distinguish which PDUs belong to a PDU set and identify the boundaries of the PDU set.

[0248] Typically, the time interval between adjacent PDUs within a PDU set is relatively short, for example, 1ms; while the time interval between adjacent PDU sets is longer, for example, 16.67ms.

[0249] 3) Size distribution information of different types of PDU sets;

[0250] For example, it can be the size distribution function f1(x) for different types of PDU sets.

[0251] Typically, the PDU set of an I-frame is larger, while the PDU set of a P-frame or B-frame is smaller.

[0252] 4) Periods of different types of PDU sets.

[0253] I-frames typically appear periodically, for example, one I-frame every 8 frames. This periodicity can be used to determine the frame type or importance level of a PDU set.

[0254] 5) Indication information on whether PDU set packet loss is allowed.

[0255] This information is primarily used to determine whether, in the event of a detected PDU loss, the remaining PDUs within the same PDU set need to be transmitted. For example, in certain video encoding formats, the loss of one PDU in a PDU set will affect the parsing of the entire set. Therefore, if one PDU is lost, there is no need to transmit the remaining PDUs within that set. In other words, by training with this third information, the trained analysis model can include indications of whether packet loss is permissible for a PDU set, thus possessing the function of analyzing whether packet loss is allowed for a PDU set.

[0256] 6) The first jitter information of the PDUs in the PDU set;

[0257] For example, the jitter distribution function f2(x) within the PDU set can be used. This first jitter information represents a significant transmission delay during PDU transmission over the network. The impact of jitter on the PDU set boundary determination can be eliminated based on this first jitter information.

[0258] 7) Second jitter information between PDU sets.

[0259] For example, it could be the distribution function f3(x) of jitter among PDU sets. This second jitter information represents a significant transmission delay in the PDU set during network transmission. The impact of jitter on the periodicity determination of the PDU set can be eliminated based on this second jitter information.

[0260] Step 6: NWDAF MTLF sends the trained analysis model to NWDAF AnLF via Nnwdaf_MLModelProvision_Notify or Nnwdaf_MLModelInfo_Response.

[0261] Step 7: NWDAF AnLF sends a Nupf_eventExposure_Subscibe message (i.e., the third request mentioned above) to UPF to request the service data stream. The request includes at least one of the following: service data stream description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, and terminal identifier.

[0262] Step 8: The UPF obtains the business data stream from the AF. Based on the third request mentioned above, the UPF sends the determined business data stream to the NWDAF AnLF.

[0263] Step 9: NWDAF AnLF uses an analysis model to analyze the received service data stream and obtains the analysis results, which can be shown in Table 4 of Example 1.

[0264] For details on how to obtain the analysis results based on the analysis model, please refer to the above embodiments, which will not be repeated here.

[0265] Step 10: NWDAF AnLF sends the analysis results to UPF;

[0266] Step 11: The UPF notifies the base station of the analysis results via the GPRS Tunneling Protocol (GTP) header;

[0267] Step 12: The base station sends the service data stream to the UE and transmits the PDU set according to the above analysis results during the transmission process.

[0268] Example 3 of this application:

[0269] In this embodiment, the analysis model is trained by AF.

[0270] Please refer to Figure 10 The data feature analysis method of this application includes the following steps:

[0271] Step 1: The AF collects first information from the gateway device (such as the UPF). The content of the first information can be found in Table 1 of the above embodiment. It should be noted that the first information provided by the UPF is at the IP 5-tuple granularity (source IP address, destination IP address, protocol number, source port, destination port), that is, at the service data flow granularity. The IP 5-tuple includes: 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 or different from the UPF in Step 1.

[0272] Step 2: The AF collects third and fourth information from the UE. The contents of the third and fourth information can be found in Table 3 of the above embodiment. The traffic information provided by the UE is at the IP 5-tuple granularity, that is, at the service data flow granularity. The IP 5-tuple includes the following information: terminal IP address, terminal port number, server IP address, server port number, and protocol number.

[0273] Step 3: Based on the first information collected from the UPF, the third and fourth information collected from the UE, and the second information stored locally, AF generates a training dataset and trains the analysis model based on the training dataset.

[0274] The analysis model includes at least one of the following:

[0275] 1) The time interval between two adjacent PDUs within the PDU set;

[0276] 2) The time interval between two adjacent PDU sets;

[0277] Using 1) and 2), we can distinguish which PDUs belong to a PDU set and identify the boundaries of the PDU set.

[0278] Typically, the time interval between adjacent PDUs within a PDU set is relatively short, for example, 1ms; while the time interval between adjacent PDU sets is longer, for example, 16.67ms.

[0279] 3) Size distribution information of different types of PDU sets;

[0280] For example, it can be the size distribution function f1(x) for different types of PDU sets.

[0281] Typically, the PDU set of an I-frame is larger, while the PDU set of a P-frame or B-frame is smaller.

[0282] 4) Periods of different types of PDU sets.

[0283] I-frames typically appear periodically, for example, one I-frame every 8 frames. This periodicity can be used to determine the frame type or importance level of a PDU set.

[0284] 5) Indication information on whether PDU set packet loss is allowed.

[0285] This information is primarily used to determine whether, in the event of a detected PDU loss, the remaining PDUs within the same PDU set need to be transmitted. For example, in certain video encoding formats, the loss of one PDU in a PDU set will affect the parsing of the entire set. Therefore, if one PDU is lost, there is no need to transmit the remaining PDUs within that set. In other words, by training with this third information, the trained analysis model can include indications of whether packet loss is permissible for a PDU set, thus possessing the function of analyzing whether packet loss is allowed for a PDU set.

[0286] 6) The first jitter information of the PDUs in the PDU set;

[0287] For example, the jitter distribution function f2(x) within the PDU set can be used. This first jitter information represents a significant transmission delay during PDU transmission over the network. The impact of jitter on the PDU set boundary determination can be eliminated based on this first jitter information.

[0288] 7) Second jitter information between PDU sets.

[0289] For example, it could be the distribution function f3(x) of jitter among PDU sets. This second jitter information represents a significant transmission delay in the PDU set during network transmission. The impact of jitter on the periodicity determination of the PDU set can be eliminated based on this second jitter information.

[0290] Step 4: AF sends the trained analysis model to the integrated device of UPF and NWDAF AnLF.

[0291] Step 5: AF sends the service data stream to the integrated device of UPF and NWDAF AnLF.

[0292] Step 6: NWDAF AnLF uses an analysis model to analyze the received service data stream and obtain the analysis results, which can be shown in Table 4 of Example 1.

[0293] For details on how to obtain the analysis results based on the analysis model, please refer to the above embodiments, which will not be repeated here.

[0294] Step 7: The integrated UPF and NWDAF AnLF device notifies the base station of the analysis results via the GPRS Tunneling Protocol (GTP) header;

[0295] Step 8: The base station sends the service data stream to the UE and transmits the PDU set according to the above analysis results during the transmission process.

[0296] Please refer to Figure 11 In this embodiment of the application, steps 1 and 2 above can be implemented in the following way:

[0297] Step 111: The AF sends an Nnwdaf_Analyticsription_Subscribe message to the NWDAF, which carries the following information:

[0298] 1) Analytics ID (i.e., the first identifier in the above embodiments) 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 business data stream;

[0299] 2) The first filtering information, also known as the analytics filter, includes at least one of the following: business data flow description identifier, business identifier, application ID, slice identifier, DNN, network area information, and terminal identifier.

[0300] Step 112: NWDAF subscribes to UE data from SMF;

[0301] Step 113: SMF obtains the first information from UFP through N4 session, as shown in Table 1;

[0302] Step 114: SMF provides initial information to NWDAF;

[0303] Step 115: NWDAF collects third and fourth information from the UE, as shown in Table 3;

[0304] Step 116: NWDAF provides AF with data obtained from UPF and UE.

[0305] The data feature analysis method provided in this application can be executed by a data feature analysis device. This application uses an example of a data feature analysis device executing the data feature analysis method to illustrate the data feature analysis device provided in this application.

[0306] Please refer to Figure 12 This application embodiment also provides a data feature analysis device 120, including:

[0307] The first acquisition module 121 is used to acquire relevant information of the service data stream of the first service. The relevant information includes first information and second information. The first information is the relevant information of PDUs in the service data stream of the first service, and the second information is the relevant information of data frames in the service data stream of the first service. Each data frame includes at least one set of PDUs.

[0308] The first determining module 122 is used to determine the analysis model of the first service based on the relevant information of the service data stream. The analysis model is used to identify the data characteristics of the PDU set in the service data stream of the first service.

[0309] In this embodiment of the application, an analysis model for the first service is obtained by training on the relevant information of the service data stream of the first service. This analysis model can identify the data characteristics of the PDU set in the service data stream of the first service, thereby prioritizing the transmission of all PDUs in the PDU set of the I-frame to ensure a smooth user experience when using the first service.

[0310] 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;

[0311] and / or

[0312] 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 and importance level information.

[0313] Optionally, the analysis model includes at least one of the following: the time interval between two adjacent PDUs within a PDU set; the time interval between two adjacent PDU sets; the size distribution information of different types of PDU sets; and the period of different types of PDU sets.

[0314] Optionally, the relevant information of the business data stream may also include third information, which is information related to lost PDUs and / or sets of lost PDUs;

[0315] The analysis model also includes the following information: indication information on whether PDU set packet loss is allowed.

[0316] Optionally, the third information includes at least one of the following: a timestamp indicating that a PDU was lost, and a timestamp indicating that a PDU set was discarded.

[0317] Optionally, the relevant information of the business data stream may also include fourth information, which is the relevant information of out-of-order PDUs and / or out-of-order PDU sets;

[0318] The analysis model also includes at least one of the following: first jitter information of PDUs within a PDU set; second jitter information between PDU sets.

[0319] Optionally, the fourth information includes at least one of the following: timestamps of out-of-order PDUs; timestamps of the out-of-order PDU set.

[0320] Optionally, the relevant information of the service data stream may also include fifth information, which includes at least one of the following: duration of the service data stream, uplink bit rate, downlink bit rate, uplink PDU latency, downlink PDU latency, number of uplink PDU transmissions, and number of downlink PDU transmissions.

[0321] Optionally, the data feature analysis device 120 further includes:

[0322] The first sending module is used to send the analysis model or 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 stream of the first service.

[0323] Optionally, the data feature analysis device 120 further includes:

[0324] A receiving module is configured to receive a first request, the first request being used to request an analysis model for the first service, the first request including at least one of the following: a first identifier and first filtering information;

[0325] 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 business data stream;

[0326] The first filtering information includes at least one of the following: business data flow description identifier, business identifier, APP identifier, slice identifier, data network name, network area information, and terminal identifier.

[0327] Optionally, the data feature analysis device 120 further includes:

[0328] The second sending module is used to send a second request, the second request being used to request the acquisition of relevant information of the business data stream, the second request including at least one of the following: a first identifier and first filtering information;

[0329] The first identifier is used to indicate relevant information about the requested business data stream;

[0330] The first filtering information includes at least one of the following: business data flow description identifier, business identifier, APP identifier, slice identifier, data network name, network area information, and terminal identifier.

[0331] The data feature analysis device in this application embodiment can be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or a chip.

[0332] The data feature analysis device provided in this application embodiment can achieve... Figure 2 The various processes implemented in the method embodiments achieve the same technical effect, and will not be described again here to avoid repetition.

[0333] Please refer to Figure 13 This application embodiment also provides a data feature analysis device 130, including:

[0334] The first acquisition module 131 is used to acquire the analysis model of the first service, the analysis model being used to identify the data characteristics of the PDU set in the business data stream of the first service;

[0335] Analysis module 132 is used to analyze the target business data stream of the first service according to the analysis model and obtain analysis results. The analysis results include at least one of the following: boundary information of the PDU set in the target business data stream, type indication information of the PDU set, sequence number of each PDU in the PDU set, number of PDUs in the PDU set, and period of the PDU set.

[0336] The type indication information includes at least one of the following: frame type, importance level information;

[0337] The boundary information of the PDU set in the target business data stream 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.

[0338] In this embodiment of the application, the data characteristics of the PDU set in the service data stream of the first service can be identified by the analysis model, so that all PDUs in the PDU set of the I frame can be transmitted first, ensuring a smooth experience for users when using the first service.

[0339] Optionally, the analysis model includes at least one of the following: the time interval between two adjacent PDUs within a PDU set; the time interval between two adjacent PDU sets; the size distribution information of different types of PDU sets; and the period of different types of PDU sets.

[0340] Optionally, the analysis model may also include the following information: indication information on whether PDU set packet loss is allowed, and the analysis result may also include: the result of whether to continue transmitting the corresponding PDU set in the target service data stream.

[0341] Optionally, the analysis model further includes at least one of the following: first jitter information of PDUs within the PDU set; second jitter information between PDU sets; the analysis module 132 is used to determine the boundary of the PDU set in the target service data stream based on the first jitter information and / or the second jitter information.

[0342] Optionally, the data feature analysis device 130 further includes:

[0343] The first sending module is used to send a third request to a third device. The third request is used to request the service data stream of the first service. The third request includes at least one of the following: service data stream description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, and terminal identifier.

[0344] The first receiving module is used to receive the target service data stream of the first service sent by the third device.

[0345] Optionally, the data feature analysis device 130 further includes:

[0346] The second receiving module is used to receive a fourth request, which is used to request the second device to analyze the service data stream of the first service. The fourth request includes at least one of the following: service data stream description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, terminal identifier, and identifier of the UPF that provides services to the terminal.

[0347] Optionally, the data feature analysis device 130 further includes:

[0348] The second sending module is used to send the analysis results to the third device.

[0349] The data feature analysis device in this application embodiment can be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or a chip.

[0350] The data feature analysis device provided in this application embodiment can achieve... Figure 4 The various processes implemented in the method embodiments achieve the same technical effect, and will not be described again here to avoid repetition.

[0351] Please refer to Figure 14 This application embodiment also provides a data feature analysis device 140, including:

[0352] The first receiving module 141 is used to receive the analysis results of the target service data stream of the first service. The analysis results are obtained based on the analysis model, which is used to identify the data characteristics of the PDU set in the service data stream of the first service.

[0353] The first determining module 142 is used to determine the transmission mode of the PDU set in the target service data stream based on the analysis results.

[0354] In this embodiment of the application, the data characteristics of the PDU set in the service data stream of the first service can be identified by the analysis model, so that all PDUs in the PDU set of the I frame can be transmitted first, ensuring a smooth experience for users when using the first service.

[0355] Optionally, the data feature analysis device 140 further includes:

[0356] The second receiving module is used to receive a fifth request sent by the fourth device. The fifth request is used to request the analysis of the service data stream of the first service. The fifth request includes at least one of the following: service data stream description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, and terminal identifier.

[0357] The sending module is used to send a fourth request to the second device. The fourth request is used to request the second device to analyze the service data stream of the first service. The fourth request includes at least one of the following: service data stream description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, terminal identifier, and identifier of the UPF that provides services to the terminal.

[0358] The data feature analysis device in this application embodiment can be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or a chip.

[0359] The data feature analysis device provided in this application embodiment can achieve... Figure 5 The various processes implemented in the method embodiments achieve the same technical effect, and will not be described again here to avoid repetition.

[0360] Optional, such as Figure 15 As shown, this application embodiment also provides a network device 150, including a processor 151 and a memory 152. The memory 152 stores a program or instructions that can run on the processor 151. When the program or instructions are executed by the processor 151, they implement the various steps of the above-described data feature analysis method embodiment and can achieve the same technical effect. To avoid repetition, they will not be described again here.

[0361] This application embodiment also provides a network device, including a processor and a communication interface. The communication interface is used to receive the analysis results of a target service data stream of a first service. The analysis results are obtained based on an analysis model, which is used to identify the data characteristics of a set of PDUs in the service data stream of the first service. The processor is used to determine the transmission mode of the set of PDUs in the target service data stream based on the analysis results. This network device embodiment corresponds to the method embodiment executed by the third device described above. All implementation processes and methods of the above method embodiments can be applied to this network device embodiment and achieve the same technical effects.

[0362] Specifically, embodiments of this application also provide a network device. For example... Figure 16As shown, the network device 160 includes: an antenna 161, a radio frequency (RF) device 162, a baseband device 163, a processor 164, and a memory 165. The antenna 161 is connected to the RF device 162. In the uplink direction, the RF device 162 receives information through the antenna 161 and transmits the received information to the baseband device 163 for processing. In the downlink direction, the baseband device 163 processes the information to be transmitted and sends it to the RF device 162. The RF device 162 processes the received information and transmits it through the antenna 161.

[0363] The methods executed by the network device in the above embodiments can be implemented in the baseband device 163, which includes a baseband processor.

[0364] Baseband device 163 may include, for example, at least one baseband board on which multiple chips are disposed, such as Figure 16 As shown, one of the chips is, for example, a baseband processor, which is connected to the memory 165 via a bus interface to call the program in the memory 165 and execute the network device operation shown in the above method embodiment.

[0365] The network-side backup may also include a network interface 166, such as a common public radio interface (CPRI).

[0366] Specifically, the network device 160 in this embodiment further includes: instructions or programs stored in memory 165 and executable on processor 164, wherein processor 164 calls the instructions or programs in memory 165 to execute. Figure 14 The methods executed by each module shown achieve the same technical effect, and to avoid repetition, they will not be described in detail here.

[0367] Specifically, embodiments of this application also provide a network device. For example... Figure 17 As shown, the network device 170 includes a processor 171, a network interface 172, and a memory 173. The network interface 172 is, for example, a common public radio interface (CPRI).

[0368] Specifically, the network device 170 in this embodiment further includes: instructions or programs stored in memory 173 and executable on processor 171, wherein processor 171 calls the instructions or programs in memory 173 to execute. Figure 12 or Figure 13 or Figure 14 The methods executed by each module shown achieve the same technical effect, and to avoid repetition, they will not be described in detail here.

[0369] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described data feature analysis method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0370] The processor is the processor in the terminal described in the above embodiments. 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.

[0371] This application embodiment also provides a chip, which 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 various processes of the above-described data feature analysis method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0372] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0373] This application also provides a computer program / program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the above-described data feature analysis method embodiments, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0374] This application also provides 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 as described above. The second device can be used to perform the steps of the data feature analysis method performed by the second device as described above. The third device can be used to perform the steps of the data feature analysis method performed by the third device as described above.

[0375] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0376] 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 necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0377] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A data feature analysis method, characterized in that, include: The first device acquires relevant information about the service data stream of the first service. The relevant information about the service data stream includes first information and second information. The first information is the relevant information about Protocol Data Units (PDUs) in the service data stream of the first service. The second information is the relevant information about data frames in the service data stream of the first service. Each data frame includes at least one set of PDUs. The first device determines an analysis model for the first service based on relevant information of the service data stream. The analysis model is used to identify the data characteristics of the PDU set in the service data stream of the first service.

2. The method according to claim 1, characterized in that, 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 and importance level information.

3. The method according to claim 1 or 2, characterized in that, The analysis model includes at least one of the following: the time interval between two adjacent PDUs within a PDU set; the time interval between two adjacent PDU sets; the size distribution information of different types of PDU sets; and the period of different types of PDU sets.

4. The method according to claim 1, characterized in that, The relevant information of the business data stream also includes third information, which is information related to lost PDUs and / or sets of lost PDUs; The analysis model also includes the following information: indication information on whether PDU set packet loss is allowed.

5. The method according to claim 4, characterized in that, The third information includes at least one of the following: a timestamp indicating that a PDU was lost, or a timestamp indicating that a PDU set was discarded.

6. The method according to claim 1 or 4, characterized in that, The relevant information of the business data stream also includes a fourth piece of information, which is the 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: first jitter information of PDUs within a PDU set; second jitter information between PDU sets.

7. The method according to claim 6, characterized in that, The fourth piece of information includes at least one of the following: timestamps of out-of-order PDUs; timestamps of the out-of-order PDU set.

8. The method according to claim 1, characterized in that, The relevant information of the service data stream also includes a fifth piece of information, which includes at least one of the following: the duration of the service data stream, the uplink bit rate, the downlink bit rate, the uplink PDU latency, the downlink PDU latency, the number of uplink PDU transmissions, and the number of downlink PDU transmissions.

9. The method according to claim 1, characterized in that, The method further includes: The first device sends the analysis model or information about the analysis model to the second device for the second device to analyze the data characteristics of the PDU set in the business data stream of the first service.

10. The method according to claim 1, characterized in that, The method further includes: The first device receives a first request, which is used to request the analysis model of the first service. The first request includes at least one of the following: a first identifier and 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 business data stream; The first filtering information includes at least one of the following: business data flow description identifier, business identifier, APP identifier, slice identifier, data network name, network area information, and terminal identifier.

11. The method according to claim 1, characterized in that, The method further includes: The first device sends a second request, which is used to request relevant information of the service data stream. The second request includes at least one of the following: a first identifier and first filtering information. The first identifier is used to indicate relevant information about the requested business data stream; The first filtering information includes at least one of the following: business data flow description identifier, business identifier, APP identifier, slice identifier, data network name, network area information, and terminal identifier.

12. The method according to claim 1, characterized in that, The first device is a network data analysis function model training logic function (NWDAF) or application function (AF).

13. A data feature analysis method, characterized in that, include: The second device acquires 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 stream of the first service; The second device analyzes the target service data stream of the first service according to the analysis model and obtains the analysis results. The analysis results include at least one of the following: boundary information of the PDU set in the target service data stream, type indication information of the PDU set, sequence number of each PDU in the PDU set, number of PDUs in the PDU set, and period of the PDU set. 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 business data stream 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.

14. The method according to claim 13, characterized in that, The analysis model includes at least one of the following: the time interval between two adjacent PDUs within a PDU set; the time interval between two adjacent PDU sets; the size distribution information of different types of PDU sets; and the period of different types of PDU sets.

15. The method according to claim 13, characterized in that, The analysis model also includes the following information: indication information on whether PDU set packet loss is allowed, and the analysis result also includes: the result on whether to continue transmitting the corresponding PDU set in the target service data stream.

16. The method according to claim 13, characterized in that, The analysis model also includes at least one of the following: first jitter information of PDUs within a PDU set; second jitter information between PDU sets; The analysis results obtained by analyzing the target business data flow of the first service based on the analysis model include: The second device determines the boundary of the PDU set in the target service data stream based on the first jitter information and / or the second jitter information.

17. The method according to claim 13, characterized in that, 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 stream of the first service. The third request includes at least one of the following: service data stream description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, and terminal identifier. The second device receives the target service data stream of the first service sent by the third device.

18. The method according to claim 13, characterized in that, The method further includes: The second device receives a fourth request, which is used to request the second device to analyze the service data stream of the first service. The fourth request includes at least one of the following: service data stream description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, terminal identifier, and identifier of the UPF that provides services to the terminal.

19. The method according to claim 13, characterized in that, The method further includes: The second device sends the analysis results to the third device.

20. A data feature analysis method, characterized in that, include: The third device receives the analysis results of the target service data stream of the first service. The analysis results are obtained based on the analysis model, which is used to identify the data characteristics of the PDU set in the service data stream of the first service. The third device determines the transmission method of the PDU set in the target service data stream based on the analysis results.

21. The method according to claim 20, characterized in that, Also includes: The third device receives a third request, which is used to request the service data stream of the first service. The third request includes at least one of the following: service data stream description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, and terminal identifier. The third device obtains the target service data stream of the first service according to the third request.

22. The method according to claim 20, characterized in that, Also includes: The third device receives a fifth request sent by the fourth device. The fifth request is used to request the analysis of the service data stream of the first service. The fifth request includes at least one of the following: service data stream description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, and terminal identifier. 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 stream of the first service. The fourth request includes at least one of the following: service data stream description identifier, service identifier, APP identifier, slice identifier, data network name, network area information, terminal identifier, and identifier of the UPF that provides services to the terminal.

23. A data feature analysis device, characterized in that, include: The first acquisition module is used to acquire relevant information of the business data stream of the first service. The relevant information includes first information and second information. The first information is the relevant information of PDUs in the business data stream of the first service, and the second information is the relevant information of data frames in the business data stream of the first service. Each data frame includes at least one set of PDUs. The first determining module is used to determine the analysis model of the first service based on the relevant information of the service data stream. The analysis model is used to identify the data characteristics of the PDU set in the service data stream of the first service.

24. A data feature analysis device, characterized in that, include: 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 business data stream of the first service; The analysis module is used to analyze the target business data stream of the first service according to the analysis model and obtain the analysis results. The analysis results include at least one of the following: boundary information of the PDU set in the target business data stream, type indication information of the PDU set, sequence number of each PDU in the PDU set, number of PDUs in the PDU set, and period of the PDU set. 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 business data stream 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.

25. A data feature analysis device, characterized in that, include: The first receiving module is used to receive the analysis results of the target service data stream of the first service. The analysis results are obtained based on the analysis model, which is used to identify the data characteristics of the PDU set in the service data stream of the first service. The first determining module is used to determine the transmission method of the PDU set in the target service data stream based on the analysis results.

26. A network device, characterized in that, The method includes a processor and a memory, the memory storing a program or instructions executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the data feature analysis method as described in any one of claims 1 to 12; or, the program or instructions, when executed by the processor, implement the steps of the data feature analysis method as described in any one of claims 13 to 19; or, the program or instructions, when executed by the processor, implement the steps of the data feature analysis method as described in any one of claims 20 to 22.

27. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the data feature analysis method as described in any one of claims 1 to 12, or implement the steps of the data feature analysis method as described in any one of claims 13 to 19, or implement the steps of the data feature analysis method as described in any one of claims 20 to 22.

Images