Business data detection method and device, computer program product and electronic equipment

Abstract

The invention provides a service data detection method and device, a computer program product and electronic equipment, and relates to the technical field of communication. The service data detection method comprises the following steps: in response to a received user service request having an AI detection requirement, querying UPF supporting the AI detection capability, and determining a target UPF meeting the user service request from the UPF supporting the AI detection capability; and sending access information corresponding to the user service request to the target UPF, so that the target UPF adopts the AI detection capability to detect user message data matched with the access information. According to the invention, intelligent detection is carried out on the user message data needing AI detection based on the AI detection capability of the UPF, the message detection capability of a communication network can be improved, a targeted differentiation strategy is realized, and the service experience of a user is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of communication technology, and in particular to a service data detection method, a service data detection device, a computer program product, and an electronic device. Background Art

[0002] In the policy management framework of mobile networks, the policy management functional entity usually sends relevant policies to the policy execution functional entity so that the policy control functional entity supports the execution of corresponding policy controls based on the detection results of service flows. Service flow detection is a key link in the process of achieving differentiated service management control.

[0003] In related technologies, when performing service flow detection, deep packet inspection technology is usually used to analyze the packet header to identify service characteristics. With the continuous refinement of service detection at the granularity level, the continuous increase in the number of requirements, and the increasing encryption capabilities of service flows, the difficulty of service flow detection has increased significantly, and traditional deep packet inspection technology has been difficult to meet the communication needs of user services.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The present disclosure provides a business data detection method, a business data detection device, a computer program product and an electronic device, so as to at least to some extent solve the problem in the related art that the detection of business flows is difficult and thus it is difficult to adapt to user business communication needs.

[0006] According to a first aspect of the present disclosure, a service data detection method is provided, which is applied to a first network element, wherein the first network element provides a UPF selection decision service, and the method includes: in response to receiving a user service request with an artificial intelligence (AI) detection requirement, querying the UPF that supports the AI detection capability, and determining a target UPF that meets the user service request from the UPF that supports the AI detection capability; and sending access information corresponding to the user service request to the target UPF, so that the target UPF uses the AI detection capability to detect user message data that matches the access information.

[0007] According to a second aspect of the present disclosure, there is provided a service data detection device, which is applied to a first network element that provides a UPF selection decision service. The device includes: a UPF screening module, configured to query UPFs supporting AI detection capabilities in response to receiving a user service request with an AI detection requirement, and determine a target UPF that meets the user service request from the UPFs supporting AI detection capabilities; an access control module, configured to send access information corresponding to the user service request to the target UPF, so that the target UPF uses the AI detection capabilities to detect user packet data matching the access information.

[0008] According to a third aspect of the present disclosure, there is provided a computer program product, including a computer program, which when executed by a processor, implements the service data detection method according to the first aspect and its possible implementation manners.

[0009] According to a fourth aspect of the present disclosure, there is provided an electronic device, including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the service data detection method according to the first aspect and its possible implementation manners by executing the executable instructions.

[0010] The technical solution of the present disclosure has the following beneficial effects:

[0011] During the above service data detection process, in response to receiving a user service request with an AI (Artificial Intelligence) packet detection requirement, query UPFs (User Plane Function) supporting AI detection capabilities, and determine a target UPF that meets the user service request from the UPFs supporting AI detection capabilities; send access information corresponding to the user service request to the target UPF, so that the target UPF uses the AI detection capabilities to detect user packet data matching the access information. By querying UPFs supporting AI detection capabilities in response to receiving a user service request with an AI detection requirement, in order to select a target UPF from the UPFs supporting AI detection capabilities for intelligent detection of user packet data, the present disclosure can not only achieve differentiated service management and control, but also improve the packet detection ability of the communication network to a certain extent, making the packet data detection more intelligent, thereby meeting the more complex communication requirements of user services and improving the user's service experience. In addition, since the UPF is a network element in the core network mainly responsible for routing and forwarding user plane data packets, the present disclosure endows the UPF with AI detection capabilities for intelligent packet detection, which is implemented on the basis of the existing communication architecture and is relatively convenient to deploy. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 The flowchart of a service data detection method in this exemplary embodiment is shown;

[0013] Figure 2 The interaction flowchart of a user interface path selection in this exemplary embodiment is shown;

[0014] Figure 3 The interaction flowchart of a UPF registering AI detection capabilities in this exemplary embodiment is shown;

[0015] Figure 4 The interaction flowchart of a UPF updating AI detection capabilities in this exemplary embodiment is shown;

[0016] Figure 5 The system architecture diagram of a service data stream transmission in this exemplary embodiment is shown;

[0017] Figure 6 The structural block diagram of a service data detection device in this exemplary embodiment is shown;

[0018] Figure 7 An electronic device for implementing the above service data detection method in this exemplary embodiment is shown. Detailed implementation manners

[0019] The exemplary embodiments of the present disclosure will be described more comprehensively below in conjunction with the accompanying drawings.

[0020] The accompanying drawings are schematic diagrams of the present disclosure and are not necessarily drawn to scale. Some of the block diagrams shown in the accompanying drawings may be functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in hardware modules or integrated circuits, or implemented in networks, processors or microcontrollers. The embodiments can be implemented in multiple forms and should not be construed as limited to the examples described herein. The features, structures or characteristics described in the present disclosure can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to give a full explanation of the embodiments of the present disclosure. However, those skilled in the art should be aware that one or more specific details can be omitted when implementing the technical solutions of the present disclosure, or other methods, components, devices, steps, etc. can be used to replace one or more specific details.

[0021] In related technologies, when performing service flow detection, the header of a data packet is usually analyzed through deep packet inspection technology to identify service characteristics. With the continuous refinement of service detection at the granularity level, the increasing number of requirements, and the growing encryption capabilities of service flows, the difficulty of service flow detection has increased significantly. Traditional deep packet inspection technology can no longer meet the communication requirements of user services.

[0022] In view of the above problems, the exemplary embodiments of the present disclosure provide a service data detection method, a service data detection processing device, a computer program product, and an electronic device, which can be applied to the intelligent agent communication scenario of a mobile network, can increase the network AI detection capability, improve the detection capability of services, and meet the forwarding quality requirements of high-demand and encrypted services.

[0023] In an alternative embodiment, with reference to Figure 1 the following provides a service data detection method applied to a first network element, which may specifically include the following steps S110 to S120:

[0024] Step S110, in response to receiving a user service request with an artificial intelligence (AI) detection requirement, query the UPFs that support AI detection capabilities, and determine a target UPF that meets the user service request from the UPFs that support AI detection capabilities;

[0025] Step S120, send the access information corresponding to the user service request to the target UPF, so that the target UPF uses the AI detection capability to detect the user packet data that matches the access information.

[0026] Figure 1 In the method shown, by responding to receiving a user service request with an AI detection requirement and querying the UPFs that support AI detection capabilities, in order to select a target UPF from the UPFs that support AI detection capabilities for intelligent detection of user packet data, it can not only achieve differential service management and control, but also improve the packet detection capability of the communication network to a certain extent, making the packet data detection more intelligent, thereby meeting the more complex communication requirements of user services and improving the user's service experience. In addition, since the UPF is a network element in the core network that is mainly responsible for the routing and forwarding of user plane data packets, endowing the UPF with AI detection capabilities for intelligent packet detection is implemented based on the existing communication architecture, and the deployment is relatively convenient.

[0027] It should be noted that in the present disclosure, the first network element is a decision-making network element for selecting a UPF, and can provide UPF selection decision-making services. Taking the first network element as an SMF (Session Management Function) entity in the core network as an example, the SMF can, in response to receiving a user service request with an artificial intelligence (AI) detection requirement, query for UPFs that support AI detection capabilities, and determine a target UPF that meets the user service request from the UPFs that support AI detection capabilities; and send access information corresponding to the user service request to the target UPF, so that the target UPF can use the AI detection capabilities to detect user packet data based on the access information.

[0028] The following specifically describes Figure 1 each step in

[0029] In step S110, in response to receiving a user service request with an artificial intelligence (AI) detection requirement, query for UPFs that support AI detection capabilities, and determine a target UPF that meets the user service request from the UPFs that support AI detection capabilities.

[0030] Among them, the service request refers to a request initiated by a user device to implement a specific service, and may include, but is not limited to: user basic information, user device information, network location information, requested service type, service-specific requirements, etc. The present disclosure does not specifically limit this.

[0031] Among them, the AI detection requirement refers to a packet detection requirement that requires the use of AI detection capabilities, and the AI detection capabilities refer to the ability to perform intelligent analysis on packet data.

[0032] Optionally, the AI detection requirement may include any one or more of the following: the requirement to distinguish critical packets, the requirement to analyze the correlation relationship of packets, the requirement to identify the quality of packets. It should be noted that in actual application processes, the AI detection requirement may also include other types of packet detection requirements that require the use of AI detection capabilities. The present disclosure does not specifically limit this.

[0033] Exemplarily, when a certain service requires that critical packets in it be given priority for transmission and requires lossless transmission, such a service can be configured as a service with a packet detection requirement.

[0034] Optionally, the AI detection capabilities may include any one or more of the following: the ability to intelligently identify critical packets, the ability to intelligently analyze the correlation relationship of packets, the ability to intelligently identify the quality of packets. It should be noted that in actual application processes, the AI detection capabilities may also include other types of capabilities that can perform intelligent analysis on packet data. The present disclosure does not specifically limit this.

[0035] Among them, there may be a corresponding relationship between the AI detection capabilities and the AI detection requirements, so that the AI detection capabilities can specifically meet various different AI detection requirements.

[0036] Among them, the UPF is the core network element for user plane data processing, responsible for the efficient forwarding of data packets, policy execution, and service awareness. The UPF supporting AI detection capabilities can be registered through the AI detection capabilities and discovered in the network, enabling the first network element to select an appropriate UPF to process the user packet data.

[0037] In an optional implementation manner, the above-mentioned steps of, in response to receiving a user service request with an artificial intelligence (AI) detection requirement, querying the user plane function (UPF) that supports AI detection capabilities and determining a target UPF that meets the user service request from the UPFs that support AI detection capabilities can be implemented through the following steps: In response to receiving a user service request with an AI detection requirement, determine the type to which the AI detection requirement corresponding to the user service request belongs, and query the UPFs that support AI detection capabilities matching the type to which the AI detection requirement belongs, so as to further determine the target UPF that meets the user service request from the UPFs that support AI detection capabilities matching the type to which the AI detection requirement belongs.

[0038] By querying the UPFs that support AI detection capabilities matching the corresponding type to which the AI detection requirement belongs for different AI detection requirements, it is possible to meet the different service processing requirements of users with relatively high accuracy.

[0039] In an optional implementation manner, the above-mentioned steps of, in response to receiving a user service request with an AI detection requirement, querying the UPF that supports AI detection capabilities and determining a target UPF that meets the user service request from the UPFs that support AI detection capabilities can be implemented through the following steps: In response to receiving a user service request with an AI detection requirement, query the UPFs that support AI detection capabilities from the second network element; the second network element provides the AI detection capabilities management service for each UPF in the network; determine the target UPF that meets the user service request from the UPFs that support AI detection capabilities.

[0040] Among them, the second network element may be a network element that provides the AI detection capabilities management service for each UPF in the network. Exemplarily, the second network element may be an NRF (Networking Routing Function) entity in the core network or a UDM (User Data Management) entity in the core network. The present disclosure does not make specific limitations thereto.

[0041] Among them, the NRF entity can provide the service registration and discovery functions of the UPF, store the identifiers of UPF instances and registered network functions, and support the SMF to filter available UPFs according to conditions.

[0042] Among them, the UDM entity can provide user subscription data to affect UPF selection.

[0043] In some embodiments, in response to receiving a user service request with artificial intelligence (AI) detection requirements, the first network element may also query the second network element for UPFs that support AI detection capabilities and meet other requirements of the user equipment, so as to further determine a target UPF from these UPFs.

[0044] Among them, other requirements of the user equipment refer to other requirement conditions except for AI detection requirements, such as network slice type, UPF location and other requirement conditions. Optionally, other requirements of the user equipment can be determined according to the user service request.

[0045] Exemplarily, taking the first network element as the SMF and the second network element as the NRF or UDM as an example, the SMF may query the NRF or UDM for a list of UPFs with AI detection capabilities and meeting other requirements of the user equipment, and the NRF or UDM may feedback the list of UPFs meeting these conditions to the SMF for the SMF to make a UPF selection decision.

[0046] By querying the second network element for UPFs that support AI detection capabilities, so that the determined target UPF can implement AI detection, the dimension of user plane path selection is enriched, and the intelligent ability of the mobile network is improved.

[0047] In some embodiments, the above determination of the target UPF that meets the user service request from the UPFs that support AI detection capabilities may be implemented through the following steps: determining the target UPF that meets the user service request from the UPFs that support AI detection capabilities according to the user service requirements determined by the user service request and / or the load corresponding to the UPFs that support AI detection capabilities.

[0048] Among them, the requirements of the user equipment may be some data transmission requirement information attached when the user equipment initiates a user service request, such as requirements for slice type, UPF location, etc., and the present disclosure does not specifically limit this.

[0049] By comprehensively considering factors such as user equipment requirements and UPF load and selecting the optimal UPF, personalized communication services can be further provided for the user equipment. It should be noted that other factors affecting UPF selection may also be comprehensively considered in actual application, and the present disclosure does not specifically limit this.

[0050] Among them, the target UPF refers to the key network element selected to undertake the routing and forwarding of user plane data packets corresponding to the target user equipment, and the target user equipment is the user equipment that initiates the corresponding user service request. By supporting the UPF path selection based on AI capabilities, AI capabilities are introduced into the mobile network, which can improve the service detection capabilities and refined management.

[0051] In step S120, the access information corresponding to the user service request is sent to the target UPF, so that the target UPF uses the AI detection capabilities to detect the user packet data matching the access information.

[0052] Among them, the access information refers to the relevant information used to establish a connection and conduct data transmission during network communication or system connection.

[0053] After determining the target UPF, the access information corresponding to the user service request can be sent to the corresponding target UPF, so as to establish and configure the data transmission path corresponding to the user service request.

[0054] In an alternative embodiment, after the first network element determines the target UPF, it can also send the UPF selection result, that is, the target UPF, to other network elements participating in the construction of the data communication connection, so that the service data can be correctly transmitted between the core network and the user equipment. Exemplarily, the UPF selection result can be sent to the AMF (Access and Mobility Management Function) entity, so that the AMF can interact with the target UPF according to the UPF selection result returned by the SMF to configure the user plane resources and prepare for the data transmission of the user equipment.

[0055] In an alternative embodiment, the above-mentioned sending the access information corresponding to the user service request to the target UPF, so that the target UPF uses the AI detection capabilities to detect the user packet data matching the access information, can be implemented through the following steps: sending the access information corresponding to the user service request to the target UPF, so that the target UPF establishes a PDN (Public Data Network) connection with the user equipment corresponding to the access information, where the PDN connection is used to transmit the user packet data corresponding to the access information, and the target UPF can use the AI detection capabilities to perform packet detection after receiving the user packet data corresponding to the access information.

[0056] After receiving the user packet data corresponding to the access information, the target UPF can complete the packet detection task by invoking the corresponding AI detection capabilities. Exemplarily, the key packet intelligent recognition capabilities can be invoked to detect the key packets in the user packet data.

[0057] By introducing the ability to detect complex services through AI technology in the mobile network, the differentiated forwarding requirements for services are improved.

[0058] Optionally, the AI detection ability can be built through the following steps: collect data and create models for services in various network environments, and perform model matching analysis on services through the AI model matching ability. Continuously iterate and update the corresponding models through the reinforcement learning algorithm to effectively improve the recognition accuracy of various services and achieve intelligent experience guarantee for different services and users.

[0059] Taking the first network element as the SMF and the second network element as the NRF or UDM as an example, as Figure 2 shown, an interaction flowchart for user boundary path selection is provided, which specifically may include the following steps:

[0060] Step S201, the UE sends a user service request with an AI detection requirement to the SMF;

[0061] Step S202, in response to receiving the user service request with an AI detection requirement, the SMF queries the NRF or UDM for a list of UPFs that support the AI detection ability and meet other UE requirements;

[0062] Step S203, the NRF or UDM returns to the SMF a list of UPFs that support the AI detection ability and meet other UE requirements;

[0063] Step S204, the SMF selects a target UPF from the list of UPFs that support the AI detection ability and meet other UE requirements by considering conditions such as UE requirements and UPF load;

[0064] Step S205, the SMF returns the UPF selection result to the AMF and notifies the target UPF of the access information so that a PDN connection is established between the target UPF and the UE;

[0065] Step S206, the target UPF calls the AI detection ability for intelligent detection after receiving the user packet data.

[0066] Among them, the UE is a user device, which can be a user terminal such as a computer, a mobile phone, a wearable device, etc. The present disclosure does not make specific limitations on this.

[0067] Figure 2 In the steps shown, by introducing the ability to detect complex services through AI technology in the mobile network, the detection ability of the mobile communication network for services can be improved, targeted differentiated strategies can be implemented, and thus the network can be optimized and the service experience can be improved.

[0068] In an alternative embodiment, the first UPF that has not registered its AI detection capability in the above network registers its AI detection capability by sending an AI detection capability registration request to a third network element, so that the third network element stores the AI detection capability registration information of the first UPF; the third network element provides a capability registration service.

[0069] Among them, the third network element may be a network element that provides the service registration and discovery function of the UPF in the core network, such as the NRF. It should be noted that in the present disclosure, the third network element and the second network element may be the same network element or different network elements, and the present disclosure does not specifically limit this.

[0070] Among them, the AI detection capability registration request refers to the AI detection capability registration request initiated by the first UPF to the third network element, which may carry the AI detection capability registration information, such as a registration file containing the AI detection capability of the first UPF. The third network element may store the registration information of the first UPF, that is, the registration file of the first UPF, to support the detection based on the AI capability.

[0071] Taking the third network element as the NRF as an example, the first UPF may be a UPF that has not registered its AI detection capability in the network. It can register its AI detection capability by sending an AI detection capability registration request to the third network element. By supporting the UPF to register its own AI capability in the NRF, it can assist the AI capability selection of the SMF.

[0072] Taking the third network element as the NRF as an example, as Figure 3 shown, an interaction flow chart for a UPF to register its AI detection capability is provided, which may specifically include the following steps:

[0073] Step S301, the first UPF sends a registration request carrying AI detection capability information to the NRF to register its AI detection capability with the NRF;

[0074] Step S302, the NRF stores the registration information that the first UPF supports the AI detection capability;

[0075] Step S303, after the AI detection capability registration of the first UPF is successful, the NRF returns a registration response to the first UPF.

[0076] By registering the AI detection capability of the UPF in the NRF to support the selection of the user plane path based on the AI detection capability, the intelligence of the network can be increased.

[0077] Exemplarily, during the process of the first UPF registering with the NRF, the AI detection capability registration request may carry relevant AI detection capability information to register the AI detection capability, and the format of the AI detection capability information may be as shown in the cell format in Table 1 below.

[0078] Table 1

[0079]

[0080] Among them, "array(string)" indicates that the data type is an array of strings; P (position) is used to characterize whether the corresponding field is optional or mandatory. When P (position) is "O", it can indicate that the corresponding field is optional; "1..N" represents a range, with a lower limit of 1 and an upper limit of N, where N is an integer. A cardinality of 1..N means that the number of occurrences of the corresponding field can be any integer between 1 and N. It should be noted that in actual applications, the cells can be adaptively adjusted according to communication requirements, such as deleting, adding, or modifying elements in the fields. The present disclosure does not make specific limitations on this.

[0081] Optionally, based on the TS29.510 protocol, the AI detection capability identifier can be carried by extending the info cell of the UPF to indicate the UPF's support for AI. The info cell refers to a unit that contains specific information in relevant protocol messages.

[0082] In an alternative embodiment, the second UPF that has registered the AI detection capability in the above network updates the AI detection capability registration information of the second UPF by sending an AI detection capability update request to a third network element.

[0083] Among them, the AI detection capability update request refers to an AI detection capability update request initiated by the second UPF to the third network element, which can carry the updated AI detection capability, such as an updated registration file containing the AI detection capability of the second UPF. The third network element locally updates the stored registration information of the second UPF, that is, the registration file of the second UPF, to support the change of the AI detection capability.

[0084] Taking the third network element as the NRF as an example, the second UPF can be a UPF that has registered the AI detection capability in the network, and the AI detection capability can be changed by sending an AI detection capability update request to the third network element.

[0085] Taking the third network element as the NRF as an example, as Figure 4 shown, an interaction flowchart for the UPF to update the AI detection capability is provided, which specifically may include the following steps:

[0086] Step S401, the second UPF sends a registration update request for supporting the AI detection capability to the NRF to change the AI detection capability of the NRF;

[0087] Step S402, the NRF updates the registration information of the second UPF for supporting the AI detection capability;

[0088] Step S403: After the AI detection capability of the second UPF is successfully updated, the NRF returns an update response to the second UPF.

[0089] By updating the AI detection capabilities of the UPFs in the NRF, the flexible change of the AI detection capabilities of the UPFs in the network can be supported, which can increase the flexibility of the network.

[0090] Taking the user equipment as a wearable device as an example, as Figure 5 shown, a system architecture diagram for business data stream transmission is provided. The wearable device can perform relevant sensing and business processing. Its control data requires high-priority and deterministic transmission. When the wearable device accesses the network, if the SMF detects that the wearable device has an AI detection requirement for the service flow, it can request a list of UPFs that support AI detection capabilities from the NRF or UDM. The NRF or UDM returns a list of UPFs that support AI detection capabilities to the SMF, such as UPF1 and UPF2. The SMF can further select a UPF that supports AI detection capabilities as the forwarding node for the user corresponding to the wearable device based on the UPF location and other requirements of the user corresponding to the wearable device. For example, UPF1 that supports AI detection capabilities, so that data communication can be achieved between the wearable device and the business server, thereby realizing the detection of the user's business data stream and differential service guarantee during the data communication process.

[0091] An exemplary embodiment of the present disclosure further provides a business data detection device, which is applied to a first network element, and the first network element provides a decision-making service for UPF selection of the user plane function. Refer to Figure 6 shown, the business data detection device 600 may include the following program modules:

[0092] The UPF screening module 610 is configured to, in response to receiving a user service request with an artificial intelligence (AI) detection requirement, query UPFs that support AI detection capabilities, and determine a target UPF that meets the user service request from the UPFs that support AI detection capabilities;

[0093] The access control module 620 is configured to send access information corresponding to the user service request to the target UPF, so that the target UPF uses the AI detection capability to detect user packet data that matches the access information.

[0094] In an optional embodiment, based on the foregoing solution, the UPF screening module 610 may be configured to: in response to receiving a user service request with an artificial intelligence (AI) detection requirement, query UPFs that support AI detection capabilities from a second network element; the second network element provides an AI detection capability management service for each UPF in the network; and determine a target UPF that meets the user service request from the UPFs that support AI detection capabilities.

[0095] In an alternative embodiment, based on the foregoing solution, the UPF screening module 610 may include a target UPF determination module configured to determine a target UPF that meets the user service request from the UPFs supporting AI detection capabilities. The target UPF determination module may be configured to: determine a target UPF that meets the user service request from the UPFs supporting AI detection capabilities according to the user equipment requirements determined by the user service request and / or the load corresponding to the UPFs supporting AI detection capabilities.

[0096] In an alternative embodiment, based on the foregoing solution, the access control module 620 may be configured to: send the access information corresponding to the user service request to the target UPF, so that the target UPF establishes a public data network (PDN) connection with the user equipment corresponding to the access information, where the PDN connection is used to transmit the user packet data corresponding to the access information, and the target UPF performs packet detection using the AI detection capabilities after receiving the user packet data corresponding to the access information.

[0097] In an alternative embodiment, based on the foregoing solution, the AI detection requirements include any one or more of the following: critical packet discrimination requirements, packet correlation analysis requirements, packet quality authentication requirements; the AI detection capabilities include any one or more of the following: critical packet intelligent recognition capabilities, packet correlation intelligent analysis capabilities, packet quality intelligent authentication capabilities.

[0098] In an alternative embodiment, based on the foregoing solution, the first UPF that has not registered its AI detection capabilities in the network sends an AI detection capabilities registration request to a third network element to register its AI detection capabilities, so that the third network element stores the AI detection capabilities registration information of the first UPF; the third network element provides a capabilities registration service.

[0099] In an alternative embodiment, based on the foregoing solution, the second UPF that has already registered its AI detection capabilities in the network sends an AI detection capabilities update request to the third network element to update the AI detection capabilities registration information of the second UPF.

[0100] The specific details of each part of the foregoing service data detection device 600 have been described in detail in the embodiments of the method part. The details not disclosed can be referred to the embodiments of the method part, and thus will not be elaborated here.

[0101] It should be noted that although several modules or units of devices for action execution are mentioned in the foregoing detailed description, this division is not mandatory. In fact, according to the exemplary embodiments of the present disclosure, the features and functions of two or more modules or units described above may be embodied in one module or unit. Conversely, the features and functions of one module or unit described above may be further divided and embodied by multiple modules or units.

[0102] Exemplary embodiments of the present disclosure also provide a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the above-described business data detection method is implemented.

[0103] In one embodiment, the computer program product may be a tangible product containing the computer program, such as a computer-readable storage medium storing the computer program. The readable storage medium may be a storage medium based on signals such as electricity, magnetism, light, electromagnetic, infrared, etc., including but not limited to: random access memory (RAM), read-only memory (ROM), magnetic tape, floppy disk, flash memory (Flash), hard disk drive (HDD), solid state drive (SSD), and so on. Exemplarily, the computer program product may be implemented as a non-volatile storage medium storing the computer program, such as read-only memory, NAND flash memory, etc.

[0104] In one embodiment, the computer program product may be an intangible product containing the computer program. Exemplarily, the computer program product may be implemented as a virtual digital product, such as an executable file storing the computer program, a digital file such as an installation package.

[0105] The code of the computer program can be written in one or more programming languages. Programming languages such as C language, Java, C++, etc. The program code can be executed entirely on the user computing device, or partially on the user computing device, or executed as an independent software package, or partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, such as a local area network (LAN), a wide area network (WAN), etc., or can be connected to an external computing device (for example, through an Internet connection provided by an operator).

[0106] The computer program can be carried or transmitted by signals such as electricity, magnetism, light, electromagnetic, infrared, etc. The electronic device can convert the signal carrying the computer program into a digital signal, and then run the computer program. When the computer program runs on the electronic device, its code is used to cause the electronic device to execute (more specifically, to cause the processor of the electronic device to execute) the method steps of various exemplary embodiments of the present disclosure. For example, the above method can be executed, which includes the following steps:

[0107] In response to receiving a user service request with an artificial intelligence (AI) detection requirement, query the user plane function (UPF) supporting AI detection capabilities, and determine a target UPF that meets the user service request from the UPFs supporting AI detection capabilities;

[0108] Send the access information corresponding to the user service request to the target UPF, so that the target UPF uses the AI detection capability to detect the user packet data matching the access information.

[0109] In an optional implementation manner, based on the foregoing solution, in response to receiving a user service request with an artificial intelligence (AI) detection requirement, query the user plane function (UPF) that supports the AI detection capability, and determine the target UPF that meets the user service request from the UPFs that support the AI detection capability. This can be achieved through the following steps: In response to receiving a user service request with an AI detection requirement, query the UPF that supports the AI detection capability from the second network element; the second network element provides the AI detection capability management service for each UPF in the network; determine the target UPF that meets the user service request from the UPFs that support the AI detection capability.

[0110] In an optional implementation manner, based on the foregoing solution, to determine the target UPF that meets the user service request from the UPFs that support the AI detection capability, this can be achieved through the following steps: Determine the target UPF that meets the user service request from the UPFs that support the AI detection capability according to the user equipment requirements determined by the user service request and / or the load corresponding to the UPF that supports the AI detection capability.

[0111] In an optional implementation manner, based on the foregoing solution, to send the access information corresponding to the user service request to the target UPF, so that the target UPF uses the AI detection capability to detect the user packet data matching the access information, this can be achieved through the following steps: Send the access information corresponding to the user service request to the target UPF, so that the target UPF establishes a public data network (PDN) connection with the user equipment corresponding to the access information, where the PDN connection is used to transmit the user packet data corresponding to the access information, and the target UPF performs packet detection using the AI detection capability after receiving the user packet data corresponding to the access information.

[0112] In an optional implementation manner, based on the foregoing solution, the AI detection requirement includes any one or more of the following: the requirement to distinguish critical packets, the requirement to analyze the packet correlation relationship, the requirement to identify the packet quality; the AI detection capability includes any one or more of the following: the intelligent identification capability of critical packets, the intelligent analysis capability of packet correlation relationships, the intelligent identification capability of packet quality.

[0113] In an optional implementation manner, based on the foregoing solution, the first UPF that has not registered the AI detection capability in the network registers the AI detection capability by sending an AI detection capability registration request to the third network element, so that the third network element stores the AI detection capability registration information of the first UPF; the third network element provides the capability registration service.

[0114] In an alternative embodiment, based on the foregoing solution, the second UPF that has registered its AI detection capability in the network updates the AI detection capability registration information of the second UPF by sending an AI detection capability update request to a third network element.

[0115] During the above service data detection process, by responding to a user service request with an artificial intelligence (AI) detection requirement, querying the UPFs that support the AI detection capability, and selecting a target UPF from the UPFs that support the AI detection capability to perform intelligent detection of user packet data, not only can differential service management and control be achieved, but also the packet detection capability of the communication network can be improved to a certain extent, making the packet data detection more intelligent, thereby meeting the more complex communication requirements of user services and improving the user's service experience. In addition, since the UPF is a network element in the core network that is mainly responsible for the routing and forwarding of user plane data packets, endowing the UPF with the AI detection capability to perform intelligent packet detection is implemented based on the existing communication architecture and is relatively convenient to deploy.

[0116] An exemplary embodiment of the present disclosure further provides an electronic device capable of implementing the above service data detection method. The electronic device may include a processor and a memory. The memory stores executable instructions of the processor, which may be program code. The processor executes the executable instructions to execute the method in this exemplary embodiment. In addition, the electronic device may further include a display for displaying a graphical user interface.

[0117] Next, with reference to Figure 7 , an electronic device will be described by way of example in the form of a general computing device. It should be understood that Figure 7 the electronic device 700 shown is merely an example and should not impose limitations on the functions and usage scope of the embodiments of the present disclosure.

[0118] As Figure 7 shown, the electronic device 700 may include: a processor 710, a memory 720, a bus 730, an I / O (input / output) interface 740, a network adapter 750, and a display 760.

[0119] The memory 720 may include volatile memory, such as RAM 721 and a cache unit 722, and may also include non-volatile memory, such as ROM 723. The memory 720 may further include one or more program modules 724, and such program modules 724 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment. For example, the program module 724 may include each module in the above device.

[0120] The processor 710 may include one or more processing units. For example, the processor 710 may include an AP (Application Processor), a modem processor, a GPU (Graphics Processing Unit), an ISP (Image Signal Processor), a controller, an encoder, a decoder, a DSP (Digital Signal Processor), a baseband processor, and / or an NPU (Neural-Network Processing Unit), etc.

[0121] The processor 710 can be used to execute the executable instructions stored in the memory 720, such as executing any one or more of the method steps in this exemplary embodiment.

[0122] Exemplarily, the processor 710 can execute the following steps:

[0123] In response to receiving a user service request with an artificial intelligence (AI) detection requirement, query the user plane function (UPF) that supports AI detection capabilities, and determine a target UPF that meets the user service request from the UPFs that support AI detection capabilities;

[0124] Send the access information corresponding to the user service request to the target UPF, so that the target UPF uses the AI detection capabilities to detect the user packet data that matches the access information.

[0125] In an alternative embodiment, based on the foregoing solution, the above-mentioned step of, in response to receiving a user service request with an artificial intelligence (AI) detection requirement, querying the user plane function (UPF) that supports AI detection capabilities and determining a target UPF that meets the user service request from the UPFs that support AI detection capabilities can be implemented by the following steps: in response to receiving a user service request with an artificial intelligence (AI) detection requirement, query the UPF that supports AI detection capabilities from a second network element; the second network element provides an AI detection capability management service for each UPF in the network; determine a target UPF that meets the user service request from the UPFs that support AI detection capabilities.

[0126] In an alternative embodiment, based on the foregoing solution, the above-mentioned step of determining a target UPF that meets the user service request from the UPFs that support AI detection capabilities can be implemented by the following steps: determine a target UPF that meets the user service request from the UPFs that support AI detection capabilities according to the user equipment requirements determined by the user service request and / or the load corresponding to the UPF that supports AI detection capabilities.

[0127] In an alternative embodiment, based on the foregoing solution, the access information corresponding to the user service request is sent to the target UPF, so that the target UPF uses the AI detection capability to detect the user packet data matching the access information, which can be implemented through the following steps: sending the access information corresponding to the user service request to the target UPF, so that the target UPF establishes a public data network (PDN) connection with the user equipment corresponding to the access information, where the PDN connection is used to transmit the user packet data corresponding to the access information, and the target UPF performs packet detection using the AI detection capability after receiving the user packet data corresponding to the access information.

[0128] In an alternative embodiment, based on the foregoing solution, the AI detection requirements include any one or more of the following: the requirement to distinguish critical packets, the requirement to analyze the packet correlation relationship, the requirement to identify the packet quality; the AI detection capabilities include any one or more of the following: the intelligent identification capability of critical packets, the intelligent analysis capability of packet correlation relationships, the intelligent identification capability of packet quality.

[0129] In an alternative embodiment, based on the foregoing solution, the first UPF that has not registered the AI detection capability in the network registers the AI detection capability by sending an AI detection capability registration request to the third network element, so that the third network element stores the AI detection capability registration information of the first UPF; the third network element provides the capability registration service.

[0130] In an alternative embodiment, based on the foregoing solution, the second UPF that has already registered the AI detection capability in the network updates the AI detection capability registration information of the second UPF by sending an AI detection capability update request to the third network element.

[0131] During the above service data detection process, by responding to the received user service request with an artificial intelligence (AI) detection requirement, querying the UPFs that support the AI detection capability, so as to select a target UPF from the UPFs that support the AI detection capability for intelligent detection of user packet data, it can not only achieve differential service management and control, but also improve the packet detection capability of the communication network to a certain extent, make the packet data detection more intelligent, and thus meet the more complex communication requirements of user services, and further improve the user's service experience. In addition, since the UPF is a network element in the core network that is mainly responsible for the routing and forwarding of user plane data packets, endowing the UPF with the AI detection capability for intelligent packet detection is implemented based on the existing communication architecture, and the deployment is relatively convenient.

[0132] The electronic device 700 can communicate with one or more external devices 800 (such as a keyboard, a mouse, an external controller, etc.) through the I / O interface 740.

[0133] The electronic device 700 can communicate with one or more networks through the network adapter 750. For example, the network adapter 750 can provide mobile communication solutions such as 3G / 4G / 5G, or wireless communication solutions such as wireless local area network, Bluetooth, and near field communication. The network adapter 750 can communicate with other modules of the electronic device 700 through the bus 730.

[0134] The electronic device 700 can display a graphical user interface and the like through the display 760.

[0135] Although Figure 7 not shown in the figure, other hardware and / or software modules can also be provided in the electronic device 700, including but not limited to: a display, microcode, device drivers, redundant processors, external disk drive arrays, RAID (Redundant Arrays of Independent Disks) systems, tape drives, and data backup storage systems, etc.

[0136] It should be noted that although several modules or units of the devices for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the exemplary embodiments of the present disclosure, the features and functions of the two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0137] Those skilled in the art can understand that various aspects of the present disclosure can be implemented as a system, a method, or a program product. Therefore, various aspects of the present disclosure can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, which can be collectively referred to as "circuits", "modules", or "systems" here. Those skilled in the art will easily think of other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application aims to cover any variations, uses, or adaptive changes of the present disclosure, which follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not disclosed in the present disclosure. The specification and embodiments are only regarded as exemplary, and the true scope and spirit of the present disclosure are pointed out by the claims.

[0138] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only defined by the appended claims.

Claims

1. A method for detecting service data, characterized in that, Applied to a first network element, the first network element provides a user plane function UPF selection decision service, and the method includes: In response to receiving a user service request with an artificial intelligence AI detection requirement, query UPFs supporting AI detection capabilities, and determine a target UPF that meets the user service request from the UPFs supporting AI detection capabilities; Send the access information corresponding to the user service request to the target UPF, so that the target UPF uses the AI detection capabilities to detect user packet data matching the access information.

2. The method according to claim 1, wherein The step of, in response to receiving a user service request with an artificial intelligence AI detection requirement, querying UPFs supporting AI detection capabilities and determining a target UPF that meets the user service request from the UPFs supporting AI detection capabilities includes: In response to receiving a user service request with an artificial intelligence AI detection requirement, query a second network element for UPFs supporting AI detection capabilities; the second network element provides an AI detection capability management service for each UPF in the network; Determine a target UPF that meets the user service request from the UPFs supporting AI detection capabilities.

3. The method according to claim 1 or 2, characterized in that, The step of determining a target UPF that meets the user service request from the UPFs supporting AI detection capabilities includes: Determine a target UPF that meets the user service request from the UPFs supporting AI detection capabilities according to the user equipment requirements determined by the user service request and / or the load corresponding to the UPFs supporting AI detection capabilities.

4. The method according to claim 1, characterized in that The step of sending the access information corresponding to the user service request to the target UPF, so that the target UPF uses the AI detection capabilities to detect user packet data matching the access information includes: Send the access information corresponding to the user service request to the target UPF, so that the target UPF establishes a public data network PDN connection with the user equipment corresponding to the access information, where the PDN connection is used to transmit the user packet data corresponding to the access information, and the target UPF uses the AI detection capabilities to perform packet detection after receiving the user packet data corresponding to the access information.

5. The method according to claim 1, characterized in that, The AI detection requirement includes any one or more of the following: critical packet discrimination requirement, packet correlation analysis requirement, packet quality identification requirement; The AI detection capabilities include any one or more of the following: critical packet intelligent identification capability, packet correlation intelligent analysis capability, packet quality intelligent identification capability.

6. The method according to claim 1, characterized in that, A first UPF that has not registered its AI detection capabilities in the network registers its AI detection capabilities by sending an AI detection capability registration request to a third network element, so that the third network element stores the AI detection capability registration information of the first UPF; The third network element provides a capability registration service.

7. The method according to claim 6, wherein A second UPF that has already registered its AI detection capabilities in the network updates its AI detection capability registration information by sending an AI detection capability update request to the third network element.

8. A service data detection device, characterized in that Applied to a first network element, the first network element provides a user plane function UPF selection decision service, and the apparatus includes: A UPF screening module, configured to query UPFs supporting AI detection capabilities in response to receiving a user service request with an AI detection requirement, and determine a target UPF that meets the user service request from the UPFs supporting AI detection capabilities; An access control module, configured to send access information corresponding to the user service request to the target UPF, so that the target UPF uses the AI detection capabilities to detect user packet data matching the access information.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that, Comprising: A processor; And A memory, configured to store executable instructions of the processor; Wherein, the processor is configured to execute the method according to any one of claims 1 to 7 by executing the executable instructions.

Images