User plane function data acquisition method, system and device and storage medium

Abstract

The invention discloses a user plane function data acquisition method, system and device and a storage medium. The method comprises the following steps: determining a first protocol link through a protocol selection algorithm set on a network data analysis function according to data information of each protocol link; screening a first small model on the wireless access network according to a model number in the data acquisition request; transmitting the data acquisition request through the first protocol link so as to acquire first data from user equipment; and intelligently analyzing the first data through the first small model to obtain a reply message, and sending the reply message back to a message request end of the data acquisition request. According to the embodiment of the invention, the protocol link of data acquisition is determined through the protocol algorithm, and the data is processed through the small model, so that the data acquisition and processing efficiency is improved. The method can be widely applied to the technical field of 5G data acquisition.

Description

Technical Field

[0001] The present invention relates to the field of 5G data collection technology, and in particular to a method, system, device and storage medium for collecting user plane function data. Background Art

[0002] The service-based architecture in 5G facilitates flexible information exchange between network functions through standardized service-based interfaces (SBIs). This definition provides a suitable framework for 5G systems, especially AI / ML functions (such as NWDAF) to collect required data from various sources. As AI / ML is applied to 5G use cases such as network automation, analytics, etc., a large number of network signaling messages, including event subscription creation / modification / deletion signaling and event reports generated by the corresponding subscriptions, will be generated. This large amount of signaling will consume a lot of processing and memory, which reduces the performance / capability of UPF packet forwarding, which is the main task of UPF.

[0003] With the development of 5G technology, the R-18 version has enhanced 5G in many directions, including the research on AI fusion, and the introduction of network intelligence / automation functions. NWDAF supports user-level and service-level real-time data collection, model training, intelligent analysis, closed-loop control and other capabilities. In detail, NWDAF can collect user service data in real time by connecting to UPF, and continuously collect wireless resource data by connecting to wireless network management, and conduct intelligent analysis on the collected data to achieve real-time self-identification of multiple types of services. However, a large number of real-time data collection requests at the same time will reduce the efficiency of intelligent analysis. Summary of the invention

[0004] The purpose of the present invention is to solve one of the technical problems existing in the prior art to at least a certain extent.

[0005] To this end, an object of the present invention is to provide an efficient user plane function data collection method, system, device and storage medium.

[0006] In order to achieve the above technical objectives, one aspect of an embodiment of the present invention provides a method for collecting user plane function data, comprising the following steps: determining a first protocol link according to the data information of each protocol link through a protocol selection algorithm set on a network data analysis function; screening a first small model on a wireless access network according to a model number in a data collection request; transmitting the data collection request through the first protocol link to collect first data from a user device; performing intelligent analysis on the first data through the first small model to obtain a reply message, and sending the reply message back to the message request end of the data collection request. The embodiment of the present application determines the protocol link for data collection through a protocol algorithm, and processes the data through a small model, which is conducive to improving the efficiency of data collection and processing.

[0007] In some embodiments, in the user plane function data collection method of an embodiment of the present invention, the data information includes several information; the determining the first protocol link according to the data information of each protocol link through the protocol selection algorithm set on the network data analysis function includes:

[0008] Sort the protocol links according to each information, and determine a sorting value of the protocol links based on each information;

[0009] Determine a total value of each of the protocol links according to the ranking value;

[0010] A first protocol link is determined according to the total value.

[0011] In some embodiments, in one embodiment of the present invention, the method further comprises:

[0012] The large model is distilled to obtain a plurality of small models, and the small models are set in a wireless access network; the small models correspond to the model numbers;

[0013] A first interface is set; the first interface is an interface between the wireless access network and the small model, and the first interface is used to send a request for data clustering features from the wireless access network to the small model, and send data clustering features from the small model to the wireless access network.

[0014] In some embodiments, in one embodiment of the present invention, the method further comprises the following steps:

[0015] A second interface is set up; the second interface is an interface between the network data analysis function and the protocol selection algorithm, and the second interface is used to send a first request for selecting an optimal protocol from the network data analysis function to the protocol selection algorithm, and the first request includes the data information.

[0016] In some embodiments, in an embodiment of the present invention, the transmitting the data collection request through the first protocol link includes:

[0017] If the first protocol link is the PFCP protocol, sending the data collection request to the session management function; the session management function receives the data collection request and forwards the data collection request to the user plane function through the N4 interface;

[0018] Alternatively, if the first protocol link is the HTTP protocol, the data collection request is sent to the user plane function through the Nupf interface.

[0019] In some embodiments, in one embodiment of the present invention, the data collection request carries an event number, an event type, and a collection duration; the transmitting the data collection request through the first protocol link includes:

[0020] The user equipment receives the data collection request and determines whether the data collection operation is allowed according to the event number and the event type;

[0021] If data collection is allowed to be started, data collection is started and a first duration is obtained; the first duration is the cumulative duration starting from the current data collection start time;

[0022] If the first duration is greater than or equal to the collection duration, data collection is terminated and the collected data is used as the first data.

[0023] In some embodiments, in an embodiment of the present invention, the data collection request carries a network function number and a network function type; the transmitting the data collection request through the first protocol link includes:

[0024] The access and mobility management function receives the data collection request and authenticates the network function according to the network function number and the network function type;

[0025] If the network function does not have the authority to subscribe to the user equipment data collection event, the data collection process is terminated.

[0026] On the other hand, an embodiment of the present invention provides a user plane function data collection system, including:

[0027] The first module is used to determine the first protocol link according to the data information of each protocol link through the protocol selection algorithm set on the network data analysis function;

[0028] The second module is used to screen the first small model on the wireless access network according to the model number in the data collection request;

[0029] A third module, configured to transmit the data collection request through the first protocol link to collect first data from the user equipment;

[0030] The fourth module is used to perform intelligent analysis on the first data through the first small model, obtain a reply message, and send the reply message back to the message request end of the data collection request.

[0031] On the other hand, an embodiment of the present invention provides a user plane function data collection device, including:

[0032] at least one processor;

[0033] at least one memory for storing at least one program;

[0034] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned user plane function data collection method.

[0035] On the other hand, an embodiment of the present invention provides a storage medium, in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to implement the above-mentioned user plane function data collection method.

[0036] The embodiments of the present application include at least the following beneficial effects: The method provided by the embodiments of the present invention includes: determining the first protocol link according to the data information of each protocol link through the protocol selection algorithm set on the network data analysis function; screening the first small model on the wireless access network according to the model number in the data collection request; transmitting the data collection request through the first protocol link to collect the first data from the user device; performing intelligent analysis on the first data through the first small model to obtain a reply message, and sending the reply message back to the message request end of the data collection request. The embodiments of the present application determine the protocol link for data collection through a protocol algorithm, and process the data through a small model, which is conducive to improving the efficiency of data collection and processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the embodiments of the present invention or the drawings of related technical solutions in the prior art are introduced below. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0038] Figure 1 A flowchart of an embodiment of a method for collecting user plane function data provided by the present invention;

[0039] Figure 2 A flowchart of another embodiment of the method for collecting user plane function data provided by the present invention;

[0040] Figure 3 A schematic diagram of the structure of an embodiment of the interface setting provided by the present application;

[0041] Figure 4 A structural diagram of an embodiment of a user plane function data collection system provided by the present invention;

[0042] Figure 5A schematic structural diagram of an embodiment of a user plane function data collection device provided by the present invention. DETAILED DESCRIPTION

[0043] The embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and are not to be construed as limitations of the present invention. For the step numbers in the following embodiments, they are only provided for the convenience of explanation, and the order between the steps is not limited in any way, and the execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

[0044] This application relates to the field of AI / ML and 5G UPF data collection technology. First, the terms involved in this application are explained:

[0045] Access and Mobility Management Function (AMF);

[0046] 3rd Generation Partnership Project (3GPP);

[0047] User Equipment (UE);

[0048] Radio Access Network (RAN);

[0049] Unified Data Management (UDM);

[0050] Network Data Analytics Function (NWDAF);

[0051] Store and Forward (S&F);

[0052] Network Function (NF);

[0053] Uplink (UL);

[0054] Short Messaging Service (SMS);

[0055] User Plane Function (UPF);

[0056] Data Network (DN);

[0057] Policy Control Function (PCF):

[0058] Session Management Function (SMF);

[0059] PDU session anchor (PSA);

[0060] Network Exposure Function (NEF);

[0061] Dedicated Short Range Communications (DSRC).

[0062] The service-based architecture in 5G facilitates flexible information exchange between network functions through standardized service-based interfaces (SBIs). This definition provides a suitable framework for 5G systems, especially AI / ML functions (such as NWDAF) to collect required data from various sources. As AI / ML is applied to 5G use cases such as network automation, analytics, etc., a large number of network signaling messages, including event subscription creation / modification / deletion signaling and event reports generated by the corresponding subscriptions, will be generated. This large amount of signaling will consume a lot of processing and memory, which reduces the performance / capability of UPF packet forwarding, which is the main task of UPF.

[0063] With the freezing of 3GPP R-18 version, its freezing indicates that 5G technology has ushered in another important milestone, which will accelerate the maturity and deployment of 5G-A industry. The R-18 version has enhanced 5G in many directions, including the research of AI fusion, and introduced functions such as network intelligence / automation. NWDAF supports a series of capabilities such as user-level and service-level real-time data collection, model training, intelligent analysis, and closed-loop control. In detail, NWDAF can collect user service data in real time by connecting to UPF, and continuously collect wireless resource data by connecting to wireless network management, and conduct intelligent analysis on the collected data to achieve real-time self-identification of multiple types of services. However, a large number of real-time data collection requests at the same time will reduce the efficiency of intelligent analysis.

[0064] That is, the prior art introduces a simplified report instruction information to identify and reduce the impact of intensive data collection from UPF on network performance, so that the NF service consumer can instruct the NF service producer, i.e., UPF, to skip sending event reports according to the reduced report instruction information, thereby avoiding additional or unnecessary network signaling to send these meaningless event reports, as well as the additional processing load of UPF and NF consumers sending and receiving these signal messages, and additional energy consumption, but cannot process a large number of data collection requests at the same time.

[0065] In this regard, in order to reduce the impact of intensive data collection from UPF on network performance, the present invention discloses a protocol selection algorithm and a mechanism for sending small models to base stations to select the optimal protocol link, pre-extract the characteristics of business data collected by UPF from users, and complete the collection of business data on a periodic basis.

[0066] The following describes in detail a method and system for collecting user plane function data according to an embodiment of the present invention with reference to the accompanying drawings. First, a method for collecting user plane function data according to an embodiment of the present invention will be described with reference to the accompanying drawings.

[0067] Reference Figure 1 In an embodiment of the present invention, a method for collecting user plane function data is provided. The method for collecting user plane function data in an embodiment of the present invention can be applied to a terminal, a server, or software running in a terminal or a server. The terminal can be a tablet computer, a laptop computer, a desktop computer, etc., but is not limited to this. The server can be an independent physical server, or a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The method for collecting user plane function data in an embodiment of the present invention mainly includes the following steps:

[0068] S100: Determine a first protocol link according to data information of each protocol link through a protocol selection algorithm set on a network data analysis function;

[0069] S200: Filtering the first small model on the wireless access network according to the model number in the data collection request;

[0070] S300: transmitting the data collection request through the first protocol link to collect first data from the user equipment;

[0071] S400: Perform intelligent analysis on the first data through the first small model to obtain a reply message, and send the reply message back to the message request end of the data collection request.

[0072] Optionally, in one embodiment of the present invention, the data information includes several pieces of information; the determining the first protocol link according to the data information of each protocol link by a protocol selection algorithm set on a network data analysis function includes:

[0073] Sort the protocol links according to each information, and determine a sorting value of the protocol links based on each information;

[0074] Determine a total value of each of the protocol links according to the ranking values;

[0075] A first protocol link is determined according to the total value.

[0076] In the embodiment of the present application, according to the evaluation rule of each information, the protocol links are sorted according to the current information to obtain a sorting value based on the current information. In addition, for each information, there is a sorting value; multiple sorting values ​​corresponding to the protocol links are added (or weighted averaged) to obtain a total value. The total values ​​are sorted to obtain the optimal first protocol link.

[0077] Optionally, in one embodiment of the present invention, the method further comprises:

[0078] The large model is distilled to obtain a plurality of small models, and the small models are set in a wireless access network; the small models correspond to the model numbers;

[0079] A first interface is set; the first interface is an interface between the wireless access network and the small model, and the first interface is used to send a request for data clustering features from the wireless access network to the small model, and send data clustering features from the small model to the wireless access network.

[0080] Optionally, in one embodiment of the present invention, the method further comprises:

[0081] A second interface is set up; the second interface is an interface between the network data analysis function and the protocol selection algorithm, and the second interface is used to send a first request for selecting an optimal protocol from the network data analysis function to the protocol selection algorithm, and the first request includes the data information.

[0082] Optionally, in one embodiment of the present invention, the transmitting the data collection request through the first protocol link includes:

[0083] If the first protocol link is the PFCP protocol, sending the data collection request to the session management function; the session management function receives the data collection request and forwards the data collection request to the user plane function through the N4 interface;

[0084] Alternatively, if the first protocol link is the HTTP protocol, the data collection request is sent to the user plane function through the Nupf interface.

[0085] It is understandable that if the first protocol link is the PFCP protocol, the network data analysis function sends the data collection request to the session management function. If the first protocol link is the HTTP protocol, the network data analysis function sends the data collection request to the user plane function through the Nupf interface.

[0086] Optionally, in an embodiment of the present invention, the data collection request carries an event number, an event type, and a collection duration; and the transmitting the data collection request through the first protocol link includes:

[0087] The user equipment receives the data collection request and determines whether the data collection operation is allowed according to the event number and the event type;

[0088] If data collection is allowed to be started, data collection is started and a first duration is obtained; the first duration is the cumulative duration starting from the current data collection start time;

[0089] If the first duration is greater than or equal to the collection duration, data collection is terminated and the collected data is used as the first data.

[0090] Optionally, in an embodiment of the present invention, the data collection request carries a network function number and a network function type; and the transmitting the data collection request through the first protocol link includes:

[0091] The access and mobility management function receives the data collection request and authenticates the network function according to the network function number and the network function type;

[0092] If the network function does not have the authority to subscribe to the user equipment data collection event, the data collection process is terminated.

[0093] The method provided by this application is described in detail below with a specific embodiment:

[0094] Reference Figure 2As shown in the figure, the optimization flow chart of UPF data collection, when other NFs send intelligent analysis requests to NWDAF, carrying the NF ID (network function identifier) ​​and NF Type (network function type), NWDAF will send a data collection request to UPF, requesting to obtain the corresponding intelligent analysis data as input (for example, other NFs request intelligent model training for the autonomous driving service of the vehicle UE, then it is necessary to obtain the location and road conditions of the vehicle UE and other related information. Due to the huge amount of data and limited channel resources, if multiple data collection operations are performed, it will have a huge impact on network performance. Therefore, it is necessary to deploy a protocol selection algorithm. In addition, it is also necessary to deploy a small model obtained by model distillation of the large model in NWDAF in RAN). Specifically, the optimization process includes the following steps:

[0095] 1a. The protocol selection algorithm deployed on NWDAF selects a suitable protocol to send a data collection request. If the PFCP protocol is selected, a data collection request is sent to SMF, carrying UE ID (SUPI) (i.e. user equipment number), Event ID (i.e. event number), NF ID (i.e. network function number), NF Type (i.e. network function type), Event Type (i.e. event type), Duration (collection duration), and Model ID (i.e. model number);

[0096] 1b. SMF receives the data collection request sent by NWDAF, and forwards the Nupf_EventExposure_Notify request to UPF through the N4 interface using the PFCP protocol, carrying UE ID (SUPI), Event ID, Event Type, NF ID, NFType, Duration (collection duration), and model ID;

[0097] 2a. If the HTTP protocol is selected, the HTTP protocol is used to send a data collection request to the UPF through the Nupf interface, carrying UE ID (SUPI), Event ID, NF ID, NF Type, Event Type, Duration (collection duration), and model ID;

[0098] 3.UPF receives the data collection request sent by NWDAF, and sends a UPF data collection request to SMF through Nsmf_EventExposure_Notify, carrying Event ID, UE ID (SUPI), NF ID, NF Type, Event Type, Duration (collection duration), and model ID;

[0099] 4. SMF receives the data collection request from UPF and forwards the request message to AMF through Namf_EventExposure_Notify, including Event ID, UE ID (SUPI), NF ID, NF Type, Event Type, Duration (collection duration), and Model ID;

[0100] 5. After receiving the request forwarded by SMF, AMF needs to authenticate NF to ensure that the NF is a legal and authorized entity. It determines whether the NF has the authority to subscribe to UE data collection event notifications based on NF ID and NF Type. If the NF does not have the authority, AMF rejects or terminates the data collection process. If the NF has the authority, it forwards the request to RAN through the N2 interface after completing the authentication, including Event ID, UE ID (SUPI), Event Type, Duration (collection duration), and Model ID.

[0101] 6. After receiving the request, RAN forwards the data collection request to the corresponding UE, carrying Event ID, Event Type, UEID (SUPI), Duration (collection duration), and downloads the small model of the corresponding model ID;

[0102] 7. The UE receives the data collection request and determines whether the data collection operation is allowed based on the Event ID and Event Type. If allowed, data collection is started and a timer starts based on the Duration. Data is collected every 5 seconds (customizable). After the timer stops, data collection ends and the collected data is forwarded to the RAN.

[0103] 8. RAN receives the collected data sent by UE and uses it as the input of the small model. The small model extracts features from the collected data to obtain clustering features of the collected data. RAN forwards the reply message of UE data collection (carrying the features of the collected data) to AMF.

[0104] 9.AMF forwards the reply message to SMF;

[0105] 10.SMF forwards the reply message to UPF;

[0106] 11. After receiving the data collection response, UPF directly sends a response to NWDAF through the HTTP protocol, carrying the data features collected from the UE.

[0107] For the protocol selection algorithm of this application, please refer to the following introduction:

[0108]

[0109] Table 1

[0110] Table 1 shows the data information of each protocol link, in which each column represents (from left to right): protocol link ID (i.e., available protocol link), link delay (delay), link packet loss rate (loss), link throughput (TP), and availability (ava).

[0111] In Algorithm 1, it is necessary to calculate the link with the lowest cost as the optimal protocol choice. Take link delay as an example:

[0112] First, the link delay of each protocol link is stored as input into list a: delay =[[0,10],[1,100],[2,55],[3,38]]; (see the Input line of Algorithm 1);

[0113] Sorting the link delays in ascending order yields: a delay =[[0,10],[3,38],[2,55],[1,100]]; (see line 2 of Algorithm 1);

[0114] Then the score is calculated based on the sorting result: the sorting R(a delay ) = [4, 3, 2, 1]; (see line 7 of Algorithm 1);

[0115] Then sum all the column scores of each link d(a(t)); (see line 14 of Algorithm 1); for the specific code of Algorithm 1, see Table 2. Table 3 shows the meaning of the characters in Algorithm 1. It can be understood that the data given in Table 1 is data in an embodiment. In actual applications, corresponding data information is provided according to different devices and networks. Specifically, the first request sent by the second interface can carry the data information. In addition, for Figure 2 The specific example shown corresponds to 1a+1b (PFCP protocol) or 2a (HTTP protocol), the same protocol but may have different links, such as links between multiple NWDAF network elements and the same SMF / UPF. Therefore, the number of protocol links is set according to actual needs.

[0116]

[0117]

[0118] Table 2

[0119] character definition N Number of protocol channels M The number of list elements <![CDATA[a delay ]]> Link delay list, eg [[1,10],[2,100],[3,55],[4,38]] <![CDATA[a loss ]]> Link packet loss rate list <![CDATA[a TP ]]> Link Throughput List <![CDATA[a ava ]]> Link Availability List

[0120] In another embodiment of Table 3, the present application provides an interface design, the specific design is as follows Figure 3 For specific functions, see Table 4.

[0121]

[0122]

[0123] Table 4

[0124] The embodiments of the present application provide a protocol selection algorithm: the present invention proposes an algorithm for selecting the optimal protocol link; regarding the process of sending small models to base stations: the present invention proposes a process in which a large model on NWDAF outputs a small model through model distillation and sends it to the base station, in preparation for data collection optimization; regarding the collection of service data in a periodic manner: the present invention proposes a method for completing periodic data collection by setting a timer for periodic data collection of the service through the Duration (collection duration) sent by the network side, so as to reduce the signaling of data collection; regarding the data collection optimization mechanism: the present invention proposes a mechanism in which a small model will perform feature extraction on the collected data, so as to reduce the resource occupation during the upload of intermediate data collection; regarding interface design: the present invention proposes an interface design for model deployment and algorithm deployment.

[0125] The embodiments of the present application are beneficial to reducing resource usage during intermediate data collection and uploading; and reducing redundant signaling interactions.

[0126] In summary, the method provided by the embodiment of the present application includes: determining the first protocol link according to the data information of each protocol link through the protocol selection algorithm set on the network data analysis function; screening the first small model on the wireless access network according to the model number in the data collection request; transmitting the data collection request through the first protocol link to collect the first data from the user device; performing intelligent analysis on the first data through the first small model to obtain a reply message, and sending the reply message back to the message request end of the data collection request. The embodiment of the present application determines the protocol link for data collection through a protocol algorithm, and processes the data through a small model, which is conducive to improving the efficiency of data collection and processing.

[0127] Secondly, refer to the attached Figure 4 A user plane function data collection system proposed according to an embodiment of the present invention is described.

[0128] Figure 4 : is a schematic diagram of the structure of a user plane function data collection system according to an embodiment of the present invention, wherein the system specifically comprises:

[0129] The first module 310 is used to determine the first protocol link according to the data information of each protocol link through the protocol selection algorithm set on the network data analysis function;

[0130] The second module 320 is used to filter the first small model on the wireless access network according to the model number in the data collection request;

[0131] A third module 330, configured to transmit the data collection request through the first protocol link to collect first data from the user equipment;

[0132] The fourth module 340 is used to perform intelligent analysis on the first data through the first small model, obtain a reply message, and send the reply message back to the message request end of the data collection request.

[0133] Optionally, in one embodiment of the present invention, the system further includes a fifth module, configured to:

[0134] The large model is distilled to obtain a plurality of small models, and the small models are set in a wireless access network; the small models correspond to the model numbers;

[0135] A first interface is set; the first interface is an interface between the wireless access network and the small model, and the first interface is used to send a request for data clustering features from the wireless access network to the small model, and send data clustering features from the small model to the wireless access network.

[0136] Optionally, in one embodiment of the present invention, the system also includes a sixth module, used to set up a second interface; the second interface is an interface between the network data analysis function and the protocol selection algorithm, and the second interface is used to send a first request for selecting the optimal protocol from the network data analysis function to the protocol selection algorithm, and the first request carries the data information.

[0137] It can be seen that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0138] Reference Figure 5 , an embodiment of the present invention provides a user plane function data collection device, comprising:

[0139] at least one processor 410;

[0140] At least one memory 420, used to store at least one program;

[0141] When the at least one program is executed by the at least one processor 410, the at least one processor 410 implements the user plane function data collection method.

[0142] Similarly, the contents of the above method embodiments are all applicable to the present device embodiments. The functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0143] An embodiment of the present invention further provides a computer-readable storage medium, in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to execute the above-mentioned user plane function data collection method.

[0144] Similarly, the contents of the above method embodiments are all applicable to the present storage medium embodiments. The functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0145] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part for which is described as a larger operation is performed independently.

[0146] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional skills of the engineer. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0147] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several programs to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0148] The logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable programs for implementing the logical functions, and may be embodied in any computer-readable medium for use by a program execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch and execute a program from a program execution system, device or apparatus), or in conjunction with such program execution systems, devices or apparatuses. For purposes of this specification, a "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by a program execution system, device or apparatus, or in conjunction with such program execution systems, devices or apparatuses.

[0149] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0150] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable program execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0151] In the above description of this specification, the description with reference to the terms "one embodiment / example", "another embodiment / example" or "certain embodiments / examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0152] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0153] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A method for collecting user plane function data, characterized in that: The following steps are involved: According to the data information of each protocol link, the first protocol link is determined by the protocol selection algorithm set on the network data analysis function; Filtering the first small model on the wireless access network according to the model number in the data collection request; transmitting the data collection request through the first protocol link to collect first data from the user equipment; The first data is intelligently analyzed by the first small model to obtain a reply message, and the reply message is sent back to the message request end of the data collection request.

2. The user plane function data collection method according to claim 1, characterized in that: The data information includes several pieces of information; the first protocol link is determined according to the data information of each protocol link through the protocol selection algorithm set on the network data analysis function, including: Sort the protocol links according to each information, and determine a sorting value of the protocol links based on each information; Determine a total value of each of the protocol links according to the ranking value; A first protocol link is determined according to the total value.

3. The user plane function data collection method according to claim 1, characterized in that: The method further comprises: The large model is distilled to obtain a plurality of small models, and the small models are set in a wireless access network; the small models correspond to the model numbers; A first interface is set; the first interface is an interface between the wireless access network and the small model, and the first interface is used to send a request for data clustering features from the wireless access network to the small model, and send data clustering features from the small model to the wireless access network.

4. The user plane function data collection method according to claim 1, characterized in that: The method further comprises: A second interface is set up; the second interface is an interface between the network data analysis function and the protocol selection algorithm, and the second interface is used to send a first request for selecting an optimal protocol from the network data analysis function to the protocol selection algorithm, and the first request carries the data information.

5. The user plane function data collection method according to claim 1, characterized in that: The transmitting the data collection request through the first protocol link includes: If the first protocol link is the PFCP protocol, sending the data collection request to the session management function; the session management function receives the data collection request and forwards the data collection request to the user plane function through the N4 interface; Alternatively, if the first protocol link is the HTTP protocol, the data collection request is sent to the user plane function through the Nupf interface.

6. The user plane function data collection method according to claim 1, characterized in that: The data collection request carries the event number, event type, and collection duration; The transmitting the data collection request through the first protocol link includes: The user equipment receives the data collection request and determines whether the data collection operation is allowed according to the event number and the event type; If data collection is allowed to be started, data collection is started and a first duration is obtained; the first duration is the cumulative duration starting from the current data collection start time; If the first duration is greater than or equal to the collection duration, data collection is terminated and the collected data is used as the first data.

7. The user plane function data collection method according to claim 1, characterized in that: The data collection request carries a network function number and a network function type; The transmitting the data collection request through the first protocol link includes: The access and mobility management function receives the data collection request and authenticates the network function according to the network function number and the network function type; If the network function does not have the authority to subscribe to the user equipment data collection event, the data collection process is terminated.

8. A user plane function data collection system, characterized in that: include: The first module is used to determine the first protocol link according to the data information of each protocol link through the protocol selection algorithm set on the network data analysis function; The second module is used to screen the first small model on the wireless access network according to the model number in the data collection request; A third module, configured to transmit the data collection request through the first protocol link to collect first data from the user equipment; The fourth module is used to perform intelligent analysis on the first data through the first small model, obtain a reply message, and send the reply message back to the message request end of the data collection request.

9. A user plane function data collection device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the user plane function data collection method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a program executable by a processor, characterized in that: The processor-executable program is used to implement the user plane function data collection method according to any one of claims 1 to 7 when executed by the processor.

Images