Strategy generation method and device, server and storage medium

Abstract

The invention discloses a strategy generation method and device, a server and a storage medium, and relates to the technical field of communication. The specific implementation scheme is as follows: receiving a computing power service request sent by a terminal, generating a computing power routing strategy for the terminal to access a computing power node and / or computing power service through a communication network based on computing power service demand information and computing network resource information, sending the computing power routing strategy to the terminal and / or a network element in the communication network, and sending the computing power routing strategy to the terminal and / or the network element in the communication network. Intelligent perception, intelligent arrangement and intelligent operation and maintenance management of the computing power network management module can be realized by using an artificial intelligence technology, the problems that the computing power network and artificial intelligence are not fused and the computing power network management is not intelligent are solved, the working efficiency and accuracy of the computing power network management are effectively improved, and the network operation and operation and maintenance efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a strategy generation method, device, server and storage medium. Background Art

[0002] The computing power network is "a new type of information infrastructure that allocates and flexibly schedules computing resources, storage resources, and network resources on demand between clouds, networks, and edges based on business needs."

[0003] In related technologies, computing power networks are still implemented in a traditional way, and the management functions of computing power networks have not integrated AI (Artificial Intelligence) algorithms, and the intelligent management of computing power networks has not been achieved. Summary of the invention

[0004] The present application provides a method, apparatus, device and storage medium for generating a routing strategy for a computing power network.

[0005] According to one aspect of the present application, a policy generation method is provided, the method comprising: receiving a computing power service request sent by a terminal, wherein the computing power service request is used to indicate the computing power service demand information of the terminal for the computing power network; based on the computing power service demand information and computing network resource information, generating a computing power routing strategy for the terminal to access computing power nodes and / or computing power services through a communication network, wherein the computing network resource information includes computing power resource information and network resource information; and sending the computing power routing strategy to the terminal and / or network elements in the communication network.

[0006] According to one embodiment of the present application, the computing power service request carries the voice collected by the terminal; the method also includes: performing natural language recognition on the voice based on an intelligent algorithm to obtain the computing power service demand information in text format.

[0007] According to an embodiment of the present application, the method further includes: acquiring the computing network resource information.

[0008] According to one embodiment of the present application, obtaining the computing network resource information includes: obtaining computing network resource status data collected by nodes in the access network and / or network elements in the communication network; extracting, analyzing and processing the computing network resource status data based on an intelligent algorithm to obtain the computing network resource information.

[0009] According to one embodiment of the present application, the computing network resource status data includes at least one of the following: the load of network elements in the communication network; the link information between network elements in the communication network; the load of nodes in the access network; the link information between nodes in the access network and network elements in the communication network; the load of computing nodes in the computing power network; the load of computing power services provided by the computing power network; and the resource utilization rate of computing power nodes in the computing power network.

[0010] According to one embodiment of the present application, the method also includes: receiving alarm events sent by nodes in an access network and / or network elements in a communication network; performing correlation analysis on the alarm events to obtain at least one associated alarm event associated with the alarm event; merging the alarm event with the at least one associated alarm event to obtain a merged alarm event; performing feature analysis on the at least one merged alarm event to obtain alarm feature information of the alarm event; matching the fault cause associated with the alarm feature information in a fault cause database based on the alarm feature information; and generating an alarm analysis result corresponding to the alarm event based on the fault cause.

[0011] According to one embodiment of the present application, the fault cause database includes alarm feature information, at least one fault cause corresponding to the alarm feature information, and probability information corresponding to each of the fault causes; the fault cause database is obtained by training based on training data in a training set, and the training data includes at least one of the following: historical alarm events; historical fault processing data; data of the computing power network; data of the access network and the communication network.

[0012] According to one embodiment of the present application, the method also includes: collecting network traffic data; inputting the network traffic data into a network traffic prediction model to obtain a network traffic prediction result; based on the network traffic prediction result, determining the computing power node accessed by the terminal, and generating a deployment strategy and / or migration strategy for the computing power service.

[0013] According to one embodiment of the present application, the computing power routing strategy for the terminal to access computing power nodes and / or computing power services through a communication network based on the computing power business demand information and the computing network resource information includes: inputting the computing power business demand information and the computing network resource information into an intelligent policy generation model to obtain the computing power routing strategy; wherein the intelligent policy generation model is obtained by performing association analysis training on training data with association relationships in a training set under multiple computing power application scenarios, and the training data with association relationships include at least one of the following: the association relationship between the computing power application scenario and the computing network resource type; the association relationship between the computing power application scenario and the computing network resource size; the optimal routing result of the computing power network; the degree of matching between the computing power routing strategy and the computing power business demand information.

[0014] According to an embodiment of the present application, the optimized intelligent strategy generation model is obtained by training based on the model execution status fed back by the intelligent strategy generation model and the model historical experience data.

[0015] According to another aspect of the present application, a policy generation device is provided, including a memory, a transceiver, and a processor: the memory is used to store computer programs; the transceiver is used to send and receive data under the control of the processor; the processor is used to read the computer program in the memory and perform the following operations: receiving a computing power service request sent by a terminal, wherein the computing power service request is used to indicate the computing power service demand information of the terminal for the computing power network; based on the computing power service demand information and computing network resource information, generating a computing power routing strategy for the terminal to access computing power nodes and / or computing power services through a communication network, wherein the computing network resource information includes computing power resource information and network resource information; and sending the computing power routing strategy to the terminal and / or network elements in the communication network.

[0016] According to another aspect of the present application, a policy generation device is provided, comprising: a receiving unit, used to receive a computing power service request sent by a terminal, wherein the computing power service request is used to indicate the computing power service demand information of the terminal for the computing power network; a generating unit, used to generate a computing power routing strategy for the terminal to access computing power nodes and / or computing power services through a communication network based on the computing power service demand information and computing network resource information; and a sending unit, used to send the computing power routing strategy to the terminal and / or network elements in the communication network.

[0017] According to another aspect of the present application, a processor-readable storage medium is provided, wherein the processor-readable storage medium stores a computer program, wherein the computer program is used to enable the processor to execute the method according to any one of claims 1 to 10.

[0018] According to another aspect of the present application, a computer program product is provided. When an instruction processor in the computer program product executes, the aforementioned policy generation method is executed.

[0019] According to the technology of this application, it is possible to use artificial intelligence technology to realize intelligent perception, intelligent orchestration, and intelligent operation and maintenance management of the computing power network management module, which solves the problem that the computing power network and artificial intelligence are not integrated and the computing power network management is not intelligent. It effectively improves the work efficiency and accuracy of computing power network management and improves the efficiency of network operation and maintenance.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present application.

[0022] Figure 1 It is a flowchart of a strategy generation method provided in an embodiment of the present application;

[0023] Figure 2 It is a flowchart of another strategy generation method provided in an embodiment of the present application;

[0024] Figure 3 It is a flowchart of another strategy generation method provided in an embodiment of the present application;

[0025] Figure 4 It is a flowchart of another strategy generation method provided in an embodiment of the present application;

[0026] Figure 5 It is a flowchart of another strategy generation method provided in an embodiment of the present application;

[0027] Figure 6 It is a flowchart of another strategy generation method provided in an embodiment of the present application;

[0028] Fig. 7A This is a schematic diagram of the computing power network intelligent management function architecture provided by the embodiment of the present application;

[0029] Figure 7B This is a schematic diagram of the intelligent management deployment architecture of the computing power network provided in the embodiment of the present application;

[0030] Figure 8 It is a structural diagram of a server provided in an embodiment of the present application;

[0031] Fig. 9It is a structural diagram of a strategy generation device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] In the embodiments of the present invention, the term "and / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent three situations: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0033] In the embodiments of the present application, the term "plurality" refers to two or more than two, and other quantifiers are similar.

[0034] The technical solution provided in the embodiment of the present application can be applicable to a variety of systems, especially 5G systems. For example, the applicable system can be a global system of mobile communication (GSM) system, a code division multiple access (CDMA) system, a wideband code division multiple access (WCDMA) general packet radio service (GPRS) system, a long term evolution (LTE) system, a LTE frequency division duplex (FDD) system, a LTE time division duplex (TDD) system, an advanced long term evolution (LTE-A) system, a universal mobile telecommunication system (UMTS), a world-wide interoperability for microwave access (WiMAX) system, a 5G new air interface (NR) system, etc. These various systems include terminal equipment and network equipment. The system may also include a core network part, such as an evolved packet system (EPS), a 5G system (5GS), etc.

[0035] The terminal device involved in the embodiment of the present application may be a device that provides voice and / or data connectivity to a user, a handheld device with a wireless connection function, or other processing devices connected to a wireless modem. In different systems, the name of the terminal device may also be different. For example, in a 5G system, the terminal device may be called a user equipment (UE). A wireless terminal device can communicate with one or more core networks (CN) via a radio access network (RAN). The wireless terminal device may be a mobile terminal device, such as a mobile phone (or a "cellular" phone) and a computer with a mobile terminal device. For example, it may be a portable, pocket-sized, handheld, computer-built-in or vehicle-mounted mobile device that exchanges language and / or data with a wireless access network. For example, personal communication service (PCS) phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs) and other devices. The wireless terminal device may also be referred to as a system, a subscriber unit, a subscriber station, a mobile station, a mobile station, a remote station, an access point, a remote terminal device, an access terminal device, a user terminal device, a user agent, and a user device, but is not limited in the embodiments of the present application.

[0036] The network device involved in the embodiment of the present application may be a base station, which may include multiple cells providing services for the terminal. Depending on the specific application scenario, the base station may also be called an access point, or may be a device in the access network that communicates with the wireless terminal device through one or more sectors on the air interface, or other names. The network device may be used to interchange received air frames with Internet Protocol (IP) packets, and serve as a router between the wireless terminal device and the rest of the access network, wherein the rest of the access network may include an Internet Protocol (IP) communication network. The network device may also coordinate the attribute management of the air interface. For example, the network device involved in the embodiments of the present application may be a network device (Base Transceiver Station, BTS) in the Global System for Mobile communications (Global System for Mobile communications, GSM) or Code Division Multiple Access (Code Division Multiple Access, CDMA), or a network device (NodeB) in Wide-band Code Division Multiple Access (WCDMA), or an evolutionary network device (evolutional Node B, eNB or e-NodeB) in the long term evolution (long term evolution, LTE) system, a 5G base station (gNB) in the 5G network architecture (next generation system), or a home evolved Node B (Home evolved Node B, HeNB), a relay node, a home base station (femto), a pico base station (pico), etc., which is not limited in the embodiments of the present application. In some network structures, the network device may include a centralized unit (CU) node and a distributed unit (DU) node, and the centralized unit and the distributed unit may also be arranged geographically separately.

[0037] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. The following is a description of the exemplary embodiments of the present application in conjunction with the drawings, including various details of the embodiments of the present application to help understand, and they should be considered as merely exemplary. Therefore, ordinary technicians in this field should recognize that various changes and modifications can be made to the embodiments described here without departing from the scope and spirit of the present application. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0038] Figure 1 It is a flow chart of a policy generation method provided by an embodiment of the present application. It should be noted that the execution subject of the policy generation method of the embodiment of the present application is a policy generation device, which can be a hardware device or software in a hardware device. The hardware device is, for example, a server.

[0039] like Figure 1 As shown, the strategy generation method proposed in this embodiment includes the following steps:

[0040] Step 101, receiving a computing power service request sent by a terminal.

[0041] The computing power service request is used to indicate the computing power service demand information of the terminal for the computing power network.

[0042] In some embodiments, the policy generation device is capable of receiving a computing power service request sent by a user terminal through a communication network.

[0043] In some embodiments, the computing power service request may carry voice information, text information, etc. The computing power service request may have a variety of forms, which are not limited in the embodiments of the present application.

[0044] In some embodiments, the computing power service request may carry voice collected by the terminal. For example, the user may directly input the demand for computing power service in natural language. The terminal collects the voice input by the user, generates a computing power service request and sends it.

[0045] In some embodiments, when the computing power service request carries voice collected by the terminal, natural language recognition can be performed on the voice based on an intelligent algorithm to obtain computing power service demand information in text format.

[0046] Optionally, the above-mentioned intelligent algorithm used for natural language recognition of the speech may be, for example, a natural language processing algorithm, an intelligent speech algorithm, etc., which is not limited in this application.

[0047] In some embodiments, the terminal may also perform natural language recognition on the voice based on an intelligent algorithm. For example, a user may directly input the demand for computing power services in natural language. The terminal collects the voice input by the user and performs natural language recognition on the voice based on an intelligent algorithm to obtain computing power service demand information in text format, and sends a computing power service request to the policy generation device. The computing power service request is used to indicate the computing power service demand information.

[0048] In some embodiments, the nodes in the access network may also perform natural language recognition on the voice based on an intelligent algorithm. For example, a user may directly input the demand for computing power services in natural language. The terminal collects the voice input by the user and carries the voice in the computing power service request sent to the policy generation device through the access network. The nodes in the access network perform natural language recognition on the voice based on an intelligent algorithm to obtain the computing power service demand information in text format, and send the computing power service demand information to the policy generation device.

[0049] Optionally, the node in the access network may include at least one of the following: a base station, an access router, an access point (Access Point, AP), and the like.

[0050] Step 102: Based on the computing power business demand information and computing network resource information, generate a computing power routing strategy for the terminal to access the computing power node and / or computing power service through the communication network.

[0051] Among them, computing network resource information includes computing power resource information and network resource information.

[0052] In some embodiments, a computing power routing strategy corresponding to the terminal can be generated based on the computing power business demand information of the terminal and the acquired computing network resource information.

[0053] In some embodiments, the above-mentioned computing power routing strategy is the computing power routing strategy for the terminal to access the computing power node, or the computing power routing strategy for the terminal to access the computing power service, or the computing power routing strategy for the terminal to access the computing power node and the computing power service.

[0054] In some embodiments, the policy generation device can obtain the above-mentioned computing network resource information.

[0055] In some embodiments, the policy generation device can obtain computing network resource status data collected by nodes in the access network and / or network elements in the communication network, and extract, analyze and process the computing network resource status data based on an intelligent algorithm to obtain the above-mentioned computing network resource information.

[0056] Optionally, the intelligent algorithm used to extract, analyze and process the computing network resource status data may be, for example, a data mining algorithm, an association rule method, a neural network method, etc., which is not limited in this application. Based on the intelligent algorithm, the collected computing network resource status data can be extracted, converted, analyzed, modeled, etc. to obtain the computing network resource information.

[0057] In some embodiments, the computing network resource status data includes at least one of computing power resource status data and network resource status data.

[0058] In some embodiments, the network resource status data includes at least one of the following: the load of network elements in the communication network, link information between network elements in the communication network, the load of nodes in the access network, and link information between nodes in the access network and network elements in the communication network.

[0059] Optionally, when the communication network is a mobile communication core network, the network element in the communication network may be a user plane function (UPF), and the node in the access network may be an access node such as a base station. The load of the base station may refer to the load of the cell where the base station is located.

[0060] Optionally, when the communication network is a mobile communication core network, the link information between network elements in the communication network may include at least one of the following: link status between UPFs, link rate between UPFs, and link delay between UPFs.

[0061] Optionally, when the communication network is a mobile communication core network, the link information between the nodes in the access network and the network elements in the communication network may include at least one of the following: the link status between the access node (base station) and the user plane function UPF, the link rate between the access node (base station) and the UPF, and the link delay between the access node (base station) and the UPF.

[0062] Optionally, when the communication network is a bearer network, the network element in the communication network may be a computing power router, and the node in the access network may be an access node such as a base station.

[0063] Optionally, when the communication network is a bearer network, the link information between network elements in the communication network may include at least one of the following: link status between computing power routers, link rate between computing power routers, and link delay between computing power routers.

[0064] Optionally, when the communication network is a bearer network, the link information between the nodes in the access network and the network elements in the communication network may include at least one of the following: the link status between the access node and the computing power router, the link rate between the access node and the computing power router, and the link delay between the access node and the computing power router.

[0065] In some embodiments, nodes in the access network (eg, base stations) may serve as both network resources and computing resources.

[0066] In some embodiments, the computing resource status data includes at least one of the following: the load of the computing nodes in the computing network, the load of the computing services provided by the computing network, and the resource utilization of the computing nodes in the computing network.

[0067] Among them, the computing power node is a node that accesses the computing power network through a computing power router.

[0068] In some embodiments, the policy generation device may input the computing power business demand information and the computing network resource information into the intelligent policy generation model to obtain a computing power routing strategy.

[0069] Among them, the intelligent strategy generation model is obtained by performing association analysis training on the training data with association relationships in the training set under various computing power application scenarios.

[0070] The above-mentioned training data with correlation relationships include at least one of the following: the correlation relationship between computing power application scenarios and computing network resource types, the correlation relationship between computing power application scenarios and computing network resource sizes, the optimal routing results of the computing power network, and the degree of matching between computing power routing strategies and computing power business demand information.

[0071] Optionally, the intelligent algorithm used in the above-mentioned association analysis training may be, for example, reinforcement learning, artificial intelligence association learning, etc., which is not limited in this application.

[0072] Optionally, the above-mentioned intelligent strategy generation model can also feedback the model execution status and the model's historical experience data to achieve self-optimization of the model.

[0073] Optionally, the optimized intelligent strategy generation model is obtained by training based on the model execution status fed back by the intelligent strategy generation model and the model historical experience data.

[0074] Step 103: Send the computing power routing strategy to the terminal and / or network elements in the communication network.

[0075] In an embodiment of the present application, the policy generating device can send the generated computing power routing policy to the terminal and / or network elements in the communication network.

[0076] In some embodiments, the policy generating device can send the generated computing power routing policy to the terminal.

[0077] In some embodiments, the policy generation device can send the generated computing power routing policy to the network elements in the communication network.

[0078] In some embodiments, the policy generation device can send the generated computing power routing policy to the terminal and the network elements in the communication network.

[0079] Optionally, the network element in the communication network may be, for example, a policy control function (PCF) and a session management function (SMF) of a mobile communication core network, a network controller of a bearer network, and the like.

[0080] In some embodiments, the policy generation device is also capable of receiving alarm events sent by nodes in the access network and / or network elements in the communication network, and is capable of performing correlation analysis on the alarm events to obtain at least one associated alarm event associated with the alarm event, merging the alarm event with at least one associated alarm event to obtain a merged alarm event, performing feature analysis on at least one merged alarm event to obtain alarm feature information of the alarm event, matching the fault cause associated with the alarm feature information in the fault cause database based on the alarm feature information; and generating an alarm analysis result corresponding to the alarm event based on the fault cause.

[0081] Optionally, the above-mentioned fault cause database includes: alarm characteristic information, at least one fault cause corresponding to the alarm characteristic information, and probability information corresponding to each fault cause.

[0082] Optionally, the above-mentioned fault cause database includes: a matching relationship between alarm feature information, a fault cause, and the probability of the fault cause.

[0083] Optionally, the above-mentioned fault cause database is obtained by training based on training data in a training set, and the training data includes at least one of the following: historical alarm events, historical fault processing data, computing power network data, access network and communication network data.

[0084] Optionally, the data of the computing power network may be, for example, computing power nodes, computing power services, etc., and the data of the access network and the communication network may be, for example, network topology, network performance, etc.

[0085] Optionally, the intelligent algorithm used to train the above-mentioned fault cause database may be, for example, deep learning, reinforcement learning, association rule algorithm, etc., which is not limited in this application.

[0086] In some embodiments, the policy generation device can also collect network traffic data, input the network traffic data into a network traffic prediction model, obtain a network traffic prediction result, determine the computing power node accessed by the terminal based on the network traffic prediction result, and generate a deployment strategy and / or migration strategy for the computing power service.

[0087] The policy generation method of the embodiment of the present application generates a computing power routing strategy for the terminal to access the computing power node and / or computing power service through the communication network based on the computing power service demand information and computing network resource information by receiving the computing power service request sent by the terminal, and sends the computing power routing strategy to the terminal and / or the network element in the communication network. It can use artificial intelligence technology to realize intelligent perception, intelligent orchestration and intelligent operation and maintenance management of the computing power network management module, solve the problem that the computing power network and artificial intelligence are not integrated and the computing power network management is not intelligent, effectively improve the work efficiency and accuracy of the computing power network management, and improve the network operation and maintenance efficiency.

[0088] Figure 2 It is a flowchart of another strategy generation method provided in an embodiment of the present application.

[0089] like Figure 2 As shown, the strategy generation method proposed in this embodiment includes the following steps:

[0090] Step 201, receiving a computing power service request sent by a terminal.

[0091] The computing power service request is used to indicate the computing power service demand information of the terminal for the computing power network.

[0092] In some embodiments, the policy generation device is capable of receiving a computing power service request sent by a user terminal through a communication network.

[0093] In some embodiments, the computing power service request may carry voice information, text information, etc. The computing power service request may have a variety of forms, which are not limited in the embodiments of the present application.

[0094] In some embodiments, the computing power service request may carry voice collected by the terminal. For example, the user may directly input the demand for computing power service in natural language. The terminal collects the voice input by the user, generates a computing power service request and sends it.

[0095] In some embodiments, when the computing power service request carries voice collected by the terminal, natural language recognition can be performed on the voice based on an intelligent algorithm to obtain computing power service demand information in text format.

[0096] Optionally, the above-mentioned intelligent algorithm used for natural language recognition of the speech may be, for example, a natural language processing algorithm, an intelligent speech algorithm, etc., which is not limited in this application.

[0097] In some embodiments, the terminal may also perform natural language recognition on the voice based on an intelligent algorithm. For example, a user may directly input the demand for computing power services in natural language. The terminal collects the voice input by the user and performs natural language recognition on the voice based on an intelligent algorithm to obtain computing power service demand information in text format, and sends a computing power service request to the policy generation device. The computing power service request is used to indicate the computing power service demand information.

[0098] In some embodiments, the nodes in the access network may also perform natural language recognition on the voice based on an intelligent algorithm. For example, a user may directly input the demand for computing power services in natural language. The terminal collects the voice input by the user and carries the voice in the computing power service request sent to the policy generation device through the access network. The nodes in the access network perform natural language recognition on the voice based on an intelligent algorithm to obtain the computing power service demand information in text format, and send the computing power service demand information to the policy generation device.

[0099] Optionally, the node in the access network may include at least one of the following: a base station, an access router, an access point AP, and the like.

[0100] Step 202: Input computing power business demand information and computing network resource information into the intelligent policy generation model to obtain the computing power routing policy.

[0101] Among them, computing network resource information includes computing power resource information and network resource information.

[0102] In some embodiments, a computing power routing strategy corresponding to the terminal can be generated based on the computing power business demand information of the terminal and the acquired computing network resource information.

[0103] In some embodiments, the above-mentioned computing power routing strategy is the computing power routing strategy for the terminal to access the computing power node, or the computing power routing strategy for the terminal to access the computing power service, or the computing power routing strategy for the terminal to access the computing power node and the computing power service.

[0104] In some embodiments, the policy generation device can obtain the above-mentioned computing network resource information.

[0105] In some embodiments, the policy generation device can obtain computing network resource status data collected by nodes in the access network and / or network elements in the communication network, and extract, analyze and process the computing network resource status data based on an intelligent algorithm to obtain the above-mentioned computing network resource information.

[0106] Optionally, the intelligent algorithm used to extract, analyze and process the computing network resource status data may be, for example, a data mining algorithm, an association rule method, a neural network method, etc., which is not limited in this application. Based on the intelligent algorithm, the collected computing network resource status data can be extracted, converted, analyzed, modeled, etc. to obtain the computing network resource information.

[0107] In some embodiments, the computing network resource status data includes at least one of computing power resource status data and network resource status data.

[0108] In some embodiments, the network resource status data includes at least one of the following: the load of network elements in the communication network, link information between network elements in the communication network, the load of nodes in the access network, and link information between nodes in the access network and network elements in the communication network.

[0109] Optionally, when the communication network is a mobile communication core network, the network element in the communication network may be a user plane function UPF, and the node in the access network may be an access node such as a base station. The load of the base station may refer to the load of the cell where the base station is located.

[0110] Optionally, when the communication network is a mobile communication core network, the link information between network elements in the communication network may include at least one of the following: link status between UPFs, link rate between UPFs, and link delay between UPFs.

[0111] Optionally, when the communication network is a mobile communication core network, the link information between the nodes in the access network and the network elements in the communication network may include at least one of the following: the link status between the access node (base station) and the user plane function UPF, the link rate between the access node (base station) and the UPF, and the link delay between the access node (base station) and the UPF.

[0112] Optionally, when the communication network is a bearer network, the network element in the communication network may be a computing power router, and the node in the access network may be an access node such as a base station.

[0113] Optionally, when the communication network is a bearer network, the link information between network elements in the communication network may include at least one of the following: link status between computing power routers, link rate between computing power routers, and link delay between computing power routers.

[0114] Optionally, when the communication network is a bearer network, the link information between the nodes in the access network and the network elements in the communication network may include at least one of the following: the link status between the access node and the computing power router, the link rate between the access node and the computing power router, and the link delay between the access node and the computing power router.

[0115] In some embodiments, nodes in the access network (eg, base stations) may serve as both network resources and computing resources.

[0116] In some embodiments, the computing resource status data includes at least one of the following: the load of the computing nodes in the computing network, the load of the computing services provided by the computing network, and the resource utilization of the computing nodes in the computing network.

[0117] Among them, the computing power node is a node that accesses the computing power network through a computing power router.

[0118] Among them, the intelligent strategy generation model is obtained by performing association analysis training on the training data with association relationships in the training set under various computing power application scenarios.

[0119] The above-mentioned training data with correlation relationships include at least one of the following: the correlation relationship between computing power application scenarios and computing network resource types, the correlation relationship between computing power application scenarios and computing network resource sizes, the optimal routing results of the computing power network, and the degree of matching between computing power routing strategies and computing power business demand information.

[0120] Optionally, the intelligent algorithm used in the above-mentioned association analysis training may be, for example, reinforcement learning, artificial intelligence association learning, etc., which is not limited in this application.

[0121] Optionally, the above-mentioned intelligent strategy generation model can also feedback the model execution status and the model's historical experience data to achieve self-optimization of the model.

[0122] Optionally, the optimized intelligent strategy generation model is obtained by training based on the model execution status fed back by the intelligent strategy generation model and the model historical experience data.

[0123] Step 203: Send the computing power routing strategy to the terminal and / or network elements in the communication network.

[0124] In an embodiment of the present application, the policy generating device can send the generated computing power routing policy to the terminal and / or network elements in the communication network.

[0125] In some embodiments, the policy generating device can send the generated computing power routing policy to the terminal.

[0126] In some embodiments, the policy generation device can send the generated computing power routing policy to the network elements in the communication network.

[0127] In some embodiments, the policy generation device can send the generated computing power routing policy to the terminal and the network elements in the communication network.

[0128] Optionally, the network element in the communication network may be, for example, a policy control function PCF, a session management function SMF of a mobile communication core network, a network controller of a bearer network, and the like.

[0129] The policy generation method of the embodiment of the present application receives the computing power service request sent by the terminal, inputs the computing power service demand information and the computing network resource information into the intelligent policy generation model, obtains the computing power routing strategy, and sends the computing power routing strategy to the terminal and / or the network element in the communication network. It can use artificial intelligence technology to realize the intelligent perception, intelligent orchestration and intelligent operation and maintenance management of the computing power network management module, solves the problem that the computing power network and artificial intelligence are not integrated, and the computing power network management is not intelligent, effectively improves the work efficiency and accuracy of the computing power network management, and improves the network operation and maintenance efficiency.

[0130] Figure 3 It is a flowchart of another strategy generation method provided in an embodiment of the present application.

[0131] like Figure 3 As shown, the strategy generation method proposed in this embodiment includes the following steps:

[0132] Step 301: Receive a computing power service request sent by a terminal, where the computing power service request carries voice collected by the terminal.

[0133] In an embodiment of the present application, the computing power service request may carry voice collected by the terminal. For example, the user may directly input the demand for computing power service in natural language, and the terminal collects the voice input by the user, generates a computing power service request and sends it.

[0134] Step 302: Perform natural language recognition on the speech based on an intelligent algorithm to obtain computing power business demand information in text format.

[0135] In some embodiments, when the computing power service request carries voice collected by the terminal, natural language recognition can be performed on the voice based on an intelligent algorithm to obtain computing power service demand information in text format.

[0136] Optionally, the above-mentioned intelligent algorithm used for natural language recognition of the speech may be, for example, a natural language processing algorithm, an intelligent speech algorithm, etc., which is not limited in this application.

[0137] Step 303: input the computing power business demand information and computing network resource information into the intelligent policy generation model to obtain the computing power routing policy.

[0138] Step 304: Send the computing power routing strategy to the terminal and / or network elements in the communication network.

[0139] It should be noted that the explanations of steps 303-304 in the various embodiments of the present application are also applicable to this embodiment and will not be repeated here.

[0140] The policy generation method of the embodiment of the present application receives a computing power service request sent by a terminal, where the computing power service request carries voice collected by the terminal, performs natural language recognition on the voice based on an intelligent algorithm to obtain computing power service demand information in text format, inputs the computing power service demand information and computing network resource information into an intelligent policy generation model, obtains the computing power routing policy, and sends the computing power routing policy to the terminal and / or network elements in the communication network. It can use artificial intelligence technology to realize intelligent perception, intelligent orchestration, and intelligent operation and maintenance management of the computing power network management module, solves the problem that computing power network and artificial intelligence are not integrated and computing power network management is not intelligent, effectively improves the work efficiency and accuracy of computing power network management, and improves network operation and maintenance efficiency.

[0141] Figure 4 It is a flowchart of another strategy generation method provided in an embodiment of the present application.

[0142] like Figure 4 As shown, the strategy generation method proposed in this embodiment includes the following steps:

[0143] Step 401, receiving a computing power service request sent by a terminal.

[0144] Step 402: Acquire computing network resource status data collected through nodes in the access network and / or network elements in the communication network.

[0145] In an embodiment of the present application, the policy generation device can obtain the above-mentioned computing network resource information.

[0146] In an embodiment of the present application, the policy generation device can obtain computing network resource status data collected by nodes in the access network and / or network elements in the communication network.

[0147] Optionally, when the communication network is a mobile communication core network, the policy generation device can subscribe to the above-mentioned network resource status data to the intelligent network function of the core network (such as network data analysis (Network Data Analytics Function, NWDAF) etc.), and the intelligent network function can collect and process data according to the subscription events, and can automatically and periodically feedback the status data to the policy generation device.

[0148] Optionally, in the case where the communication network is a mobile communication core network, the intelligent network function may collect network resource status data related to access nodes (base stations) from the access network.

[0149] Optionally, when the communication network is a mobile communication core network, the policy generation device may also directly subscribe to the computing network resource status data from the access node, and the access node automatically and periodically feeds back the computing network resource status data to the policy generation device based on the subscription.

[0150] Optionally, when the communication network is a bearer network, the policy generation device can subscribe to the above-mentioned computing network resource status data to the communication network and / or access network, and the communication network (such as a network controller, a router, a software module with management and control functions, etc.) can collect data from the access node (such as an access router and / or an access point AP) according to the subscription event.

[0151] Optionally, an access node (eg, an access router and / or an access point AP) may deploy an intelligent algorithm, and the access node may perform intelligent data collection based on the intelligent algorithm.

[0152] Optionally, the intelligent algorithm for performing intelligent data collection may be, for example, a traffic monitoring algorithm, which can collect network traffic between computing power routers and between computing power nodes and computing power routers.

[0153] In some embodiments, the computing network resource status data includes at least one of computing power resource status data and network resource status data.

[0154] In some embodiments, the network resource status data includes at least one of the following: the load of network elements in the communication network, link information between network elements in the communication network, the load of nodes in the access network, and link information between nodes in the access network and network elements in the communication network.

[0155] Optionally, when the communication network is a mobile communication core network, the network element in the communication network may be a user plane function UPF, and the node in the access network may be an access node such as a base station. The load of the base station may refer to the load of the cell where the base station is located.

[0156] Optionally, when the communication network is a mobile communication core network, the link information between network elements in the communication network may include at least one of the following: link status between UPFs, link rate between UPFs, and link delay between UPFs.

[0157] Optionally, when the communication network is a mobile communication core network, the link information between the nodes in the access network and the network elements in the communication network may include at least one of the following: the link status between the access node (base station) and the user plane function UPF, the link rate between the access node (base station) and the UPF, and the link delay between the access node (base station) and the UPF.

[0158] Optionally, when the communication network is a bearer network, the network element in the communication network may be a computing power router, and the node in the access network may be an access node such as a base station.

[0159] Optionally, when the communication network is a bearer network, the link information between network elements in the communication network may include at least one of the following: link status between computing power routers, link rate between computing power routers, and link delay between computing power routers.

[0160] Optionally, when the communication network is a bearer network, the link information between the nodes in the access network and the network elements in the communication network may include at least one of the following: the link status between the access node and the computing power router, the link rate between the access node and the computing power router, and the link delay between the access node and the computing power router.

[0161] In some embodiments, nodes in the access network (eg, base stations) may serve as both network resources and computing resources.

[0162] In some embodiments, the computing resource status data includes at least one of the following: the load of the computing nodes in the computing network, the load of the computing services provided by the computing network, and the resource utilization of the computing nodes in the computing network.

[0163] Among them, the computing power node is a node that accesses the computing power network through a computing power router.

[0164] Step 403: extract, analyze and process the computing network resource status data based on an intelligent algorithm to obtain computing network resource information.

[0165] In an embodiment of the present application, the policy generation device can extract, analyze and process the computing network resource status data based on an intelligent algorithm to obtain the above-mentioned computing network resource information.

[0166] Optionally, the intelligent algorithm used to extract, analyze and process the computing network resource status data may be, for example, a data mining algorithm, an association rule method, a neural network method, etc., which is not limited in this application. Based on the intelligent algorithm, the collected computing network resource status data can be extracted, converted, analyzed, modeled, etc. to obtain the computing network resource information.

[0167] Step 404: input the computing power business demand information and computing network resource information into the intelligent policy generation model to obtain the computing power routing policy.

[0168] Step 405: Send the computing power routing strategy to the terminal and / or network elements in the communication network.

[0169] It should be noted that the explanations of steps 401, 404-405 in the various embodiments of the present application are also applicable to this embodiment and will not be repeated here.

[0170] The policy generation method of the embodiment of the present application receives a computing power service request sent by a terminal, obtains computing network resource status data collected by nodes in the access network and / or network elements in the communication network, extracts and analyzes the computing network resource status data based on an intelligent algorithm to obtain computing network resource information, inputs the computing power service demand information and the computing network resource information into an intelligent policy generation model to obtain the computing power routing policy, and sends the computing power routing policy to the terminal and / or network elements in the communication network. It can use artificial intelligence technology to realize intelligent perception, intelligent orchestration and intelligent operation and maintenance management of the computing power network management module, solves the problem that the computing power network and artificial intelligence are not integrated and the computing power network management is not intelligent, effectively improves the work efficiency and accuracy of computing power network management, and improves network operation and maintenance efficiency.

[0171] Figure 5 It is a flowchart of another strategy generation method provided in an embodiment of the present application.

[0172] like Figure 5 As shown, the strategy generation method proposed in this embodiment includes the following steps:

[0173] Step 501, receiving a computing power service request sent by a terminal.

[0174] Step 502: Input computing power business demand information and computing network resource information into the intelligent policy generation model to obtain the computing power routing strategy.

[0175] Step 503: Send the computing power routing strategy to the terminal and / or network elements in the communication network.

[0176] It should be noted that the explanations of steps 501-503 in the various embodiments of the present application are also applicable to this embodiment and will not be repeated here.

[0177] Step 504: Receive an alarm event sent by a node in the access network and / or a network element in the communication network.

[0178] In the embodiment of the present application, the policy generating device may also receive alarm events sent by nodes in the access network and / or network elements in the communication network.

[0179] In some embodiments, the policy generating device may also receive an alarm event sent by a node in the access network.

[0180] In some embodiments, the policy generating device may also receive an alarm event sent by a network element in the communication network.

[0181] In some embodiments, the policy generating device may also receive alarm events sent by nodes in the access network and network elements in the communication network.

[0182] Step 505: perform correlation analysis on the alarm event to obtain at least one associated alarm event associated with the alarm event.

[0183] In some embodiments, the policy generation device can pre-process the received alarm events, and can perform correlation analysis on multiple identical or similar alarm events based on an intelligent algorithm to obtain multiple correlated associated alarm events.

[0184] Step 506: merge the alarm event with the at least one associated alarm event to obtain a merged alarm event.

[0185] In some embodiments, the policy generating device can merge the alarm event and one or more associated alarm events associated with the alarm event into one alarm to obtain a merged alarm event.

[0186] Optionally, the policy generating device may receive multiple alarm events, and after performing correlation analysis and merging processing, may still obtain at least one merged alarm event.

[0187] Step 507: Perform feature analysis on the at least one merged alarm event to obtain alarm feature information of the alarm event.

[0188] In some embodiments, the strategy generating device can perform feature analysis on the merged alarm events to obtain alarm feature information corresponding to the alarm events.

[0189] Step 508: Based on the alarm characteristic information, a fault cause associated with the alarm characteristic information is matched in a fault cause database.

[0190] The fault cause database includes alarm characteristic information, at least one fault cause corresponding to the alarm characteristic information, and probability information corresponding to each fault cause.

[0191] Optionally, the above fault cause database is obtained by training based on training data in the training set, wherein the training data includes at least one of the following: historical alarm events, historical fault processing data, computing network data, access network and communication network data.

[0192] Optionally, the data of the computing power network may be, for example, computing power nodes, computing power services, etc., and the data of the access network and the communication network may be, for example, network topology, network performance, etc.

[0193] Optionally, the intelligent algorithm used to train the above-mentioned fault cause database may be, for example, deep learning, reinforcement learning, association rule algorithm, etc., which is not limited in this application.

[0194] In some embodiments, the strategy generation device can match the fault cause associated with the alarm characteristic information in the fault cause database based on the alarm characteristic information.

[0195] In the embodiment of the present application, the strategy generation device can match and identify the possible fault cause corresponding to the alarm event based on the above-mentioned alarm feature information and the above-mentioned fault cause database.

[0196] Step 509: Generate an alarm analysis result corresponding to the alarm event based on the fault cause.

[0197] In the embodiment of the present application, based on the fault cause obtained by matching, an alarm analysis result corresponding to the alarm event can be generated.

[0198] Optionally, the alarm analysis result may include at least one of the following: diagnostic information of the alarm event, the location of the fault (for example, a faulty computing node, a faulty link, a faulty port, a faulty computing service, etc.).

[0199] In an embodiment of the present application, the alarm analysis result can also be presented and output to the operation and maintenance personnel to support the operation and maintenance personnel in performing subsequent troubleshooting.

[0200] The policy generation method of the embodiment of the present application receives a computing power service request sent by a terminal, inputs computing power service demand information and computing network resource information into an intelligent policy generation model, obtains the computing power routing policy, sends the computing power routing policy to the terminal and / or the network element in the communication network, receives an alarm event sent by a node in the access network and / or the network element in the communication network, performs a correlation analysis on the alarm event, obtains at least one associated alarm event associated with the alarm event, merges the alarm event with the at least one associated alarm event to obtain a merged alarm event, performs a feature analysis on the at least one merged alarm event to obtain alarm feature information of the alarm event, matches the fault cause associated with the alarm feature information in a fault cause database based on the alarm feature information, generates an alarm analysis result corresponding to the alarm event based on the fault cause, and can use artificial intelligence technology to realize intelligent perception, intelligent orchestration and intelligent operation and maintenance management of the computing power network management module, solves the problem that the computing power network and artificial intelligence are not integrated and the computing power network management is not intelligent, effectively improves the work efficiency and accuracy of the computing power network management, and improves the network operation and maintenance efficiency.

[0201] Figure 6It is a flowchart of another strategy generation method provided in an embodiment of the present application.

[0202] like Figure 6 As shown, the strategy generation method proposed in this embodiment includes the following steps:

[0203] Step 601, receiving a computing power service request sent by a terminal.

[0204] Step 602: Input computing power business demand information and computing network resource information into the intelligent policy generation model to obtain the computing power routing strategy.

[0205] Step 603: Send the computing power routing strategy to the terminal and / or network elements in the communication network.

[0206] It should be noted that the explanations of steps 601-603 in various embodiments of the present application are also applicable to this embodiment and will not be repeated here.

[0207] Step 604, collecting network traffic data.

[0208] In some embodiments, the policy generating device may also collect network traffic data.

[0209] Optionally, network traffic data may be collected based on intelligent algorithms.

[0210] Optionally, the collected network traffic data may include at least one of the following: network traffic data corresponding to each category of application, network traffic data corresponding to each geographical area, and network traffic peak data within a preset time length.

[0211] Step 605: input the network traffic data into a network traffic prediction model to obtain a network traffic prediction result.

[0212] In some embodiments, the policy generation device can input the collected network traffic data into a network traffic prediction model to obtain a network traffic prediction result.

[0213] Optionally, the above network traffic prediction model can be obtained based on deep learning technology.

[0214] Optionally, the network traffic prediction results may include at least one of the following: network traffic change trends (such as growth or decrease, etc.) corresponding to each category of application, network traffic change trends corresponding to each geographical area, and network traffic peak assessment prediction within a preset time length.

[0215] Step 606: Based on the network traffic prediction result, determine the computing power node accessed by the terminal, and generate a deployment strategy and / or migration strategy for the computing power service.

[0216] In some embodiments, the policy generation device can determine the appropriate computing node for terminal access based on the above-mentioned network traffic prediction results, and can pre-deploy, deploy or dynamically migrate computing services.

[0217] The policy generation method of the embodiment of the present application receives a computing power service request sent by a terminal, inputs the computing power service demand information and the computing network resource information into an intelligent policy generation model, obtains the computing power routing policy, sends the computing power routing policy to the terminal and / or the network element in the communication network, collects network traffic data, inputs the network traffic data into a network traffic prediction model, obtains a network traffic prediction result, determines the computing power node accessed by the terminal based on the network traffic prediction result, and generates a deployment strategy and / or migration strategy for the computing power service. It can use artificial intelligence technology to realize intelligent perception, intelligent orchestration, and intelligent operation and maintenance management of the computing power network management module, solves the problem that the computing power network and artificial intelligence are not integrated, and the computing power network management is not intelligent, effectively improves the work efficiency and accuracy of the computing power network management, and improves the network operation and maintenance efficiency.

[0218] In the above embodiments of the present application, an intelligent management module integrating intelligent algorithms is designed for the computing network management function in the computing network. In the computing network architecture, AI algorithms are used to realize computing network management functions such as intelligent perception of computing network resources and services, intelligent routing orchestration, and intelligent operation and maintenance, thereby realizing intelligent computing network management. The policy generation device of the above embodiments of the present application can be deployed in the intelligent management module.

[0219] Among them, the computing power network intelligent management function architecture is as follows Fig. 7A As shown in the figure, the intelligent management deployment architecture of computing power network is as follows Figure 7B shown.

[0220] In some embodiments, the intelligent management module may include at least one of the following functional modules:

[0221] Intelligent perception: Collaborate with the end side (user domain) and edge side (access domain, communication domain) to realize intelligent perception of computing network resources and services;

[0222] Intelligent orchestration: Use AI algorithms to automatically generate computing power routing strategies and intelligently orchestrate computing power services;

[0223] Intelligent Operations, Administration and Maintenance (OAM): Use AI algorithms to achieve intelligent operation and maintenance management of computing power networks.

[0224] In some embodiments, the user domain may include various types of terminals, and the terminals may support the deployment of intelligent algorithms (such as natural language processing algorithms, intelligent voice algorithms, etc.), realize intelligent perception of user business needs from the terminal side, and further realize the intelligence of business demand perception in computing power management;

[0225] In some embodiments, in the case of a mobile communication network, the access domain mainly includes base stations where AI algorithms are deployed; in the case of a bearer network, the access domain mainly includes computing network access routers where AI algorithms are deployed; in the case of a wireless access network such as WLAN and Bluetooth, the access domain mainly includes various access points (APs) where AI algorithms are deployed.

[0226] Optionally, the access nodes of the access domain (including base stations, access routers, various access points, etc. that deploy AI algorithms) can receive service requests from terminals and use AI algorithms (such as natural language processing algorithms, intelligent voice algorithms, etc.) to realize intelligent perception of computing power requirements from the access domain, or real-time intelligent perception of computing network resource status, to further realize intelligent resource perception in computing power management.

[0227] In some embodiments, in the case of mobile communication networks, the communication domain mainly refers to the core network with intelligent network functions (such as NWDAF, etc.) (such as NWDAF to realize data collection and analysis, such as load analysis, location analysis, etc.); in the case of bearer networks, the communication domain mainly refers to computing network routers that deploy AI algorithms, bearer network routers or switches that deploy AI algorithms, etc. (such as AI algorithms to realize traffic monitoring).

[0228] In order to implement the above embodiments, the present application also provides a server.

[0229] Figure 8 It is a structural diagram of a server provided according to an embodiment of the present application.

[0230] like Figure 8 As shown, the server may include a memory 810, a transceiver 820, and a processor 830, wherein:

[0231] The transceiver 820 is used to receive and send data under the control of the processor 830 .

[0232] Among them, Figure 8In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 830 and various circuits of memory represented by memory 810 are linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 820 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium, which transmission medium may include a wireless channel, a wired channel, an optical cable, and other transmission media. The processor 830 is responsible for managing the bus architecture and general processing, and the memory 810 may store data used by the processor 830 when performing operations.

[0233] The processor 830 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or a complex programmable logic device (CPLD). The processor may also adopt a multi-core architecture.

[0234] The processor 830 calls a computer program stored in the memory and performs the following operations: receiving a computing power service request sent by a terminal, wherein the computing power service request is used to indicate the computing power service demand information of the terminal for the computing power network; based on the computing power service demand information and the computing network resource information, generating a computing power routing strategy for the terminal to access the computing power node and / or computing power service through the communication network, wherein the computing network resource information includes computing power resource information and network resource information; and sending the computing power routing strategy to the terminal and / or the network element in the communication network.

[0235] Optionally, the computing power service request carries voice collected by the terminal; the processor 830 is also used to execute: performing natural language recognition on the voice based on an intelligent algorithm to obtain the computing power service demand information in text format.

[0236] Optionally, the processor 830 is further configured to execute: obtaining the computing network resource information.

[0237] Optionally, obtaining the computing network resource information includes: obtaining computing network resource status data collected by nodes in the access network and / or network elements in the communication network; extracting, analyzing and processing the computing network resource status data based on an intelligent algorithm to obtain the computing network resource information.

[0238] Optionally, the computing network resource status data includes at least one of the following: the load of network elements in the communication network; link information between network elements in the communication network; the load of nodes in the access network; link information between nodes in the access network and network elements in the communication network; the load of computing nodes in the computing power network; the load of computing power services provided by the computing power network; and resource utilization of computing power nodes in the computing power network.

[0239] Optionally, the processor 830 is also used to execute: receiving alarm events sent by nodes in an access network and / or network elements in a communication network; performing correlation analysis on the alarm event to obtain at least one associated alarm event associated with the alarm event; merging the alarm event with the at least one associated alarm event to obtain a merged alarm event; performing feature analysis on the at least one merged alarm event to obtain alarm feature information of the alarm event; matching the fault cause associated with the alarm feature information in a fault cause database based on the alarm feature information; and generating an alarm analysis result corresponding to the alarm event based on the fault cause.

[0240] Optionally, the fault cause database includes alarm characteristic information, at least one fault cause corresponding to the alarm characteristic information, and probability information corresponding to each fault cause; the fault cause database is trained based on training data in a training set, and the training data includes at least one of the following: historical alarm events; historical fault processing data; computing power network data; data of the access network and the communication network.

[0241] Optionally, the processor 830 is also used to execute: collecting network traffic data; inputting the network traffic data into a network traffic prediction model to obtain a network traffic prediction result; based on the network traffic prediction result, determining the computing power node accessed by the terminal, and generating a deployment strategy and / or migration strategy for the computing power service.

[0242] Optionally, based on the computing power business demand information and the computing network resource information, a computing power routing strategy for the terminal to access the computing power node and / or computing power service through the communication network is generated, including: inputting the computing power business demand information and the network resource information into an intelligent policy generation model to obtain the computing power routing strategy; wherein the intelligent policy generation model is obtained by performing association analysis training on training data with association relationships in a training set under multiple computing power application scenarios, and the training data with association relationships include at least one of the following: the association relationship between the computing power application scenario and the computing network resource type; the association relationship between the computing power application scenario and the computing network resource size; the optimal routing result of the computing power network; the degree of matching between the computing power routing strategy and the computing power business demand information.

[0243] Optionally, the optimized intelligent strategy generation model is obtained by training based on the model execution status fed back by the intelligent strategy generation model and the model historical experience data.

[0244] It should be noted that the server provided in the embodiment of the present application can achieve the above Figures 1 to 6 All the method steps implemented in the method embodiment can achieve the same technical effect, and the parts and beneficial effects of this embodiment that are the same as those in the method embodiment will not be described in detail here.

[0245] With the above Figures 1 to 6 Corresponding to the strategy generation method provided in the embodiment, the present application also provides a strategy generation device. Figures 1 to 6 The policy generation method provided in the embodiment corresponds to the above, so the implementation of the policy generation method is also applicable to the policy generation device provided in the embodiment of the present application, and will not be described in detail in the embodiment of the present application.

[0246] Fig. 9 It is a structural diagram of a strategy generation device provided in an embodiment of the present application.

[0247] like Fig. 9 As shown, the strategy generating device 900 includes: a receiving unit 910 , a generating unit 920 , and a sending unit 930 .

[0248] The receiving unit 910 is used to receive a computing power service request sent by a terminal, wherein the computing power service request is used to indicate computing power service demand information of the terminal for the computing power network;

[0249] A generating unit 920 is used to generate a computing power routing strategy for the terminal to access the computing power node and / or computing power service through the communication network based on the computing power business demand information and the computing network resource information;

[0250] The sending unit 930 is used to send the computing power routing strategy to the terminal and / or the network element in the communication network.

[0251] Optionally, the computing power service request carries voice collected by the terminal; the policy generation device 900 also includes a natural language recognition unit (not shown in the figure), which is used to perform natural language recognition on the voice based on an intelligent algorithm to obtain the computing power service demand information in text format.

[0252] Optionally, the strategy generating device 900 further includes a computing network resource acquiring unit (not shown in the figure) for acquiring the computing network resource information.

[0253] Optionally, the computing network resource acquisition unit is specifically used to: acquire computing network resource status data collected by nodes in the access network and / or network elements in the communication network; extract, analyze and process the computing network resource status data based on an intelligent algorithm to obtain the computing network resource information.

[0254] Optionally, the computing network resource status data includes at least one of the following: the load of network elements in the communication network; link information between network elements in the communication network; the load of nodes in the access network; link information between nodes in the access network and network elements in the communication network; the load of computing nodes in the computing power network; the load of computing power services provided by the computing power network; and resource utilization of computing power nodes in the computing power network.

[0255] Optionally, the policy generating device 900 also includes an alarm unit (not shown in the figure), which is specifically used to: receive alarm events sent by nodes in the access network and / or network elements in the communication network; perform correlation analysis on the alarm event to obtain at least one associated alarm event associated with the alarm event; merge the alarm event with the at least one associated alarm event to obtain a merged alarm event; perform feature analysis on the at least one merged alarm event to obtain alarm feature information of the alarm event; match the fault cause associated with the alarm feature information in the fault cause database based on the alarm feature information; and generate an alarm analysis result corresponding to the alarm event based on the fault cause.

[0256] Optionally, the fault cause database includes alarm characteristic information, at least one fault cause corresponding to the alarm characteristic information, and probability information corresponding to each fault cause; the fault cause database is trained based on training data in a training set, and the training data includes at least one of the following: historical alarm events; historical fault processing data; computing power network data; data of the access network and the communication network.

[0257] Optionally, the strategy generating device 900 also includes a traffic prediction unit (not shown in the figure), which is used to: collect network traffic data; input the network traffic data into a network traffic prediction model to obtain a network traffic prediction result; based on the network traffic prediction result, determine the computing power node accessed by the terminal, and generate a deployment strategy and / or migration strategy for the computing power service.

[0258] Optionally, the generation unit 920 is specifically used to: input the computing power business demand information and the network resource information into an intelligent policy generation model to obtain the computing power routing strategy; wherein the intelligent policy generation model is obtained by performing association analysis training on the training data with association relationships in a training set under multiple computing power application scenarios, and the training data with association relationships include at least one of the following: the association relationship between the computing power application scenario and the computing network resource type; the association relationship between the computing power application scenario and the computing network resource size; the optimal routing result of the computing power network; the degree of matching between the computing power routing strategy and the computing power business demand information.

[0259] Optionally, the optimized intelligent strategy generation model is obtained by training based on the model execution status fed back by the intelligent strategy generation model and the model historical experience data.

[0260] It should be noted that the time domain measurement device provided in the embodiment of the present application can achieve the above Figures 1 to 4 All the method steps implemented in the method embodiment can achieve the same technical effect, and the parts and beneficial effects of this embodiment that are the same as those in the method embodiment will not be described in detail here.

[0261] It should be noted that the division of units in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional unit in each embodiment of the present application may be integrated into a processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0262] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network side device, etc.) or a processor (processor) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store program codes.

[0263] It should be noted here that the above-mentioned device provided in the embodiment of the present application can implement all the method steps implemented in the above-mentioned method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as those in the method embodiment will not be described in detail here.

[0264] According to an embodiment of the present application, the present application also provides a processor-readable storage medium.

[0265] The processor-readable storage medium stores a computer program, which is used to enable the processor to execute the above-mentioned Figures 1 to 6 The strategy generation method described in the embodiment.

[0266] Among them, the processor-readable storage medium can be any available medium or data storage device that can be accessed by the processor, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid-state drive (SSD)), etc.

[0267] These computer programs (also referred to as programs, software, software applications, or code) include machine instructions for programmable processors and can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or means (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0268] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0269] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0270] A computer system may include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship to each other.

[0271] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution disclosed in this application can be achieved, and this document is not limited here.

[0272] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A strategy generation method, characterized in that: The method comprises: Receiving a computing power service request sent by a terminal, wherein the computing power service request is used to indicate computing power service demand information of the terminal for the computing power network; Based on the computing power service demand information and computing network resource information, generating a computing power routing strategy for the terminal to access the computing power node and / or computing power service through the communication network, wherein the computing network resource information includes computing power resource information and network resource information; Send the computing power routing strategy to the terminal and / or a network element in the communication network.

2. The method according to claim 1, characterized in that The computing power service request carries the voice collected by the terminal; and the method further includes: The speech is subjected to natural language recognition based on an intelligent algorithm to obtain the computing power business demand information in a text format.

3. The method according to claim 1, characterized in that The method further comprises: Obtain the computing network resource information.

4. The method according to claim 3, characterized in that The obtaining of the computing network resource information includes: Acquire computing network resource status data collected by nodes in the access network and / or network elements in the communication network; The computing network resource status data is extracted, analyzed and processed based on an intelligent algorithm to obtain the computing network resource information.

5. The method according to claim 4, characterized in that The computing network resource status data includes at least one of the following: The load of the network element in the communication network; Link information between network elements in the communication network; The load of the nodes in the access network; Link information between a node in the access network and a network element in the communication network; The load of the computing nodes in the computing network; The load of the computing services provided by the computing network; Resource utilization of computing nodes in the computing network.

6. The method according to claim 1, characterized in that The method further comprises: Receiving alarm events sent by nodes in the access network and / or network elements in the communication network; Performing correlation analysis on the alarm event to obtain at least one associated alarm event associated with the alarm event; Merging the alarm event with the at least one associated alarm event to obtain a merged alarm event; Performing feature analysis on the at least one merged alarm event to obtain alarm feature information of the alarm event; Obtaining a fault cause associated with the alarm characteristic information by matching the alarm characteristic information in a fault cause database; An alarm analysis result corresponding to the alarm event is generated based on the fault cause.

7. The method according to claim 6, characterized in that The fault cause database includes alarm characteristic information, at least one fault cause corresponding to the alarm characteristic information, and probability information corresponding to each of the fault causes; The fault cause database is obtained by training based on training data in a training set, and the training data includes at least one of the following: Historical alarm events; Historical fault handling data; Data of the computing power network; data of the access network and the communication network.

8. The method according to claim 1, characterized in that The method further comprises: Collect network traffic data; Inputting the network traffic data into a network traffic prediction model to obtain a network traffic prediction result; Based on the network traffic prediction result, the computing power node accessed by the terminal is determined, and a deployment strategy and / or migration strategy for the computing power service is generated.

9. The method according to any one of claims 1 to 8, characterized in that: The generating, based on the computing power service demand information and the computing network resource information, a computing power routing strategy for the terminal to access the computing power node and / or computing power service through the communication network includes: Inputting the computing power service demand information and the computing network resource information into an intelligent strategy generation model to obtain the computing power routing strategy; The intelligent strategy generation model is obtained by performing association analysis training on training data with association relationships in a training set in a variety of computing power application scenarios, and the training data with association relationships includes at least one of the following: The association between the computing power application scenario and the computing network resource type; The relationship between the computing power application scenario and the size of the computing network resources; The optimal routing results of the computing power network; The degree of matching between the computing power routing strategy and the computing power business demand information.

10. The method according to claim 9, characterized in that The optimized intelligent strategy generation model is obtained by training based on the model execution status fed back by the intelligent strategy generation model and the model historical experience data.

11. A strategy generating device, characterized in that: Including memory, transceiver, processor: A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations: Receiving a computing power service request sent by a terminal, wherein the computing power service request is used to indicate computing power service demand information of the terminal for the computing power network; Based on the computing power service demand information and computing network resource information, generate a computing power routing strategy for the terminal to access the computing power node and / or computing power service through the communication network, wherein the computing network resource information includes computing power resource information and network resource information; Send the computing power routing strategy to the terminal and / or a network element in the communication network.

12. The device according to claim 11, characterized in that The computing power service request carries the voice collected by the terminal; and the processor is further configured to execute: The speech is subjected to natural language recognition based on an intelligent algorithm to obtain the computing power business demand information in a text format.

13. The device according to claim 11, characterized in that The processor is further configured to execute: Obtain the computing network resource information.

14. The device according to claim 13, characterized in that The obtaining of the computing network resource information includes: Acquire computing network resource status data collected by nodes in the access network and / or network elements in the communication network; The computing network resource status data is extracted, analyzed and processed based on an intelligent algorithm to obtain the computing network resource information.

15. The device according to claim 14, characterized in that The computing network resource status data includes at least one of the following: The load of the network element in the communication network; Link information between network elements in the communication network; The load of the nodes in the access network; Link information between a node in the access network and a network element in the communication network; The load of the computing nodes in the computing network; The load of the computing services provided by the computing network; Resource utilization of computing nodes in the computing network.

16. The device according to claim 11, characterized in that The processor is further configured to execute: Receiving alarm events sent by nodes in the access network and / or network elements in the communication network; Performing correlation analysis on the alarm event to obtain at least one associated alarm event associated with the alarm event; Merging the alarm event with the at least one associated alarm event to obtain a merged alarm event; Performing feature analysis on the at least one merged alarm event to obtain alarm feature information of the alarm event; Obtaining a fault cause associated with the alarm characteristic information by matching the alarm characteristic information in a fault cause database; An alarm analysis result corresponding to the alarm event is generated based on the fault cause.

17. The device according to claim 16, characterized in that The fault cause database includes alarm characteristic information, at least one fault cause corresponding to the alarm characteristic information, and probability information corresponding to each of the fault causes; The fault cause database is obtained by training based on training data in a training set, and the training data includes at least one of the following: Historical alarm events; Historical fault handling data; Data of the computing power network; data of the access network and the communication network.

18. The device according to claim 11, characterized in that The processor is further configured to execute: Collect network traffic data; Inputting the network traffic data into a network traffic prediction model to obtain a network traffic prediction result; Based on the network traffic prediction result, the computing power node accessed by the terminal is determined, and a deployment strategy and / or migration strategy for the computing power service is generated.

19. The device according to any one of claims 11 to 18, characterized in that: The generating, based on the computing power service demand information and the computing network resource information, a computing power routing strategy for the terminal to access the computing power node and / or computing power service through the communication network includes: Inputting the computing power service demand information and the network resource information into an intelligent strategy generation model to obtain the computing power routing strategy; The intelligent strategy generation model is obtained by performing association analysis training on training data with association relationships in a training set in a variety of computing power application scenarios, and the training data with association relationships includes at least one of the following: The association between the computing power application scenario and the computing network resource type; The relationship between the computing power application scenario and the size of the computing network resources; The optimal routing results of the computing power network; The degree of matching between the computing power routing strategy and the computing power business demand information.

20. The device according to claim 19, characterized in that The optimized intelligent strategy generation model is obtained by training based on the model execution status fed back by the intelligent strategy generation model and the model historical experience data.

21. A strategy generating device, characterized in that: include: A receiving unit, configured to receive a computing power service request sent by a terminal, wherein the computing power service request is used to indicate computing power service demand information of the terminal for the computing power network; A generating unit, configured to generate a computing power routing strategy for the terminal to access computing power nodes and / or computing power services through a communication network based on the computing power business demand information and computing network resource information; A sending unit is used to send the computing power routing strategy to the terminal and / or the network element in the communication network.

22. A processor-readable storage medium, characterized in that: The processor-readable storage medium stores a computer program, and the computer program is used to enable the processor to execute the method according to any one of claims 1 to 10.

Images