Service configuration scheme generation method and device, computer equipment and storage medium

Abstract

The invention relates to a service configuration scheme generation method and device, computer equipment and a computer readable storage medium. The method comprises the following steps: in response to a service configuration scheme generation request triggered by a user, obtaining a service demand instruction matched with the service configuration scheme generation request; inputting the service demand instruction into a pre-constructed cloud network service agent, obtaining service demand information through the cloud network service agent, and generating an original service configuration scheme according to the service demand information and pre-stored service configuration specification information; inputting the original service configuration scheme into a 5GC core network, and obtaining a configuration scheme verification result obtained by verifying the original service configuration scheme by the 5GC core network; and under the condition that the configuration scheme verification result represents that verification is passed, taking the original service configuration scheme as a target service configuration scheme responding to the service configuration scheme generation request. By adopting the method, the efficiency of generating the accurate service configuration scheme can be improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for generating a business configuration solution. Background Art

[0002] With the development of computer technology, a method for generating business configuration plans through computers has emerged. This method can pre-configure a variety of business configuration models corresponding to different business types. When a business configuration plan needs to be generated, the user can select the corresponding business configuration model according to actual business needs and input the corresponding business parameters, so that the business configuration model generates the corresponding business configuration plan. After that, the user can manually verify the generated business configuration plan. After the verification is passed, the generation of the business configuration plan can be completed.

[0003] However, the generation of the above-mentioned business configuration plan usually requires the user to manually select a business configuration model and input business parameters, and the user is also required to perform manual verification after the business configuration plan is generated. Therefore, the generation cycle of the business configuration plan is too long, and the existing business configuration plan generation method is inefficient in generating accurate business configuration plans. Summary of the invention

[0004] Based on this, it is necessary to provide a business configuration solution generation method, apparatus, computer equipment, computer-readable storage medium and computer program product that can improve the efficiency of generating accurate business configuration solutions in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for generating a service configuration solution, comprising:

[0006] In response to a service configuration solution generation request triggered by a user, obtaining a service requirement instruction matching the service configuration solution generation request;

[0007] Input the business requirement instruction into a pre-built cloud network business intelligent body, obtain business requirement information matching the business requirement instruction through the cloud network business intelligent body, and generate an original business configuration plan matching the business configuration plan generation request based on the business requirement information and pre-stored business configuration specification information;

[0008] Inputting the original service configuration plan into the 5GC core network, and obtaining a configuration plan verification result obtained by the 5GC core network verifying the original service configuration plan;

[0009] When the configuration scheme verification result indicates that the verification is passed, the original service configuration scheme is used as a target service configuration scheme to respond to the service configuration scheme generation request.

[0010] In one of the embodiments, the cloud network business intelligent body is pre-set with a pre-trained large language model and a configuration solution generation model; the business requirement information matching the business requirement instruction is obtained through the cloud network business intelligent body, and an original business configuration solution matching the business configuration solution generation request is generated based on the business requirement information and the pre-stored business configuration specification information, including: inputting the business requirement instruction into the pre-trained large language model to obtain the business requirement information matching the business requirement instruction; inputting the business requirement information and the business configuration specification information into the business configuration solution generation model, and obtaining the original business configuration solution through the business configuration solution generation model.

[0011] In one embodiment, the business demand information is represented by a business processing flow chain; the business demand instruction is input into the pre-trained large language model to obtain business demand information matching the business demand instruction, including: inputting the business demand information into the cloud network business intelligent body, and obtaining a pre-built prompt word template through the cloud network business intelligent body; the prompt word template is constructed based on historical business demand survey information; obtaining business demand parameters from the business demand instruction, inputting the business demand parameters into the prompt word template, and obtaining a target prompt word matching the business demand instruction; the business demand parameters include: at least one of business type, activation area and manufacturer information; inputting the target prompt word into the large language model in the cloud network business intelligent body, and generating the business processing flow chain through the large language model.

[0012] In one of the embodiments, the business configuration specification information is stored in a business configuration specification learning library; the business configuration specification learning library includes: business level, instruction level and instruction parameter level; the business configuration specification information pre-stored by the cloud network business intelligent body, and the business demand information, before generating the original business configuration plan that matches the business configuration plan generation request, also includes: obtaining sample business configuration data corresponding to the sample communication business; from the sample business configuration data, obtaining business information, instruction information and instruction parameter information corresponding to the sample communication business; the business information includes: at least one of business name, business operation, manufacturer information and configuration object information, the instruction information includes: at least one of instruction name, instruction function and instruction sequence, and the instruction parameter information includes: at least one of parameter name, parameter value rule and parameter type; the business information is stored in the business level, the instruction information is stored in the instruction level, and the instruction parameter information is stored in the instruction parameter level, so as to store the sample business configuration data in the business configuration specification learning library.

[0013] In one of the embodiments, the inputting the original business configuration plan into the 5GC core network and obtaining the configuration plan verification result obtained by the 5GC core network verifying the original business configuration plan include: inputting the original business configuration plan into the 5GC core network; performing parameter verification on the original business configuration plan through the 5GC core network to obtain the parameter verification result of the original business configuration plan, and performing business configuration logic verification and business configuration integrity verification on the original business configuration plan through the 5GC core network to obtain the business logic verification result of the original business configuration plan; and using the parameter verification result and the business logic verification result as the configuration plan verification result.

[0014] In one of the embodiments, the parameter verification of the original business configuration plan is performed through the 5GC core network to obtain the parameter verification result of the original business configuration plan, including: collecting network element configuration information associated with the original business configuration plan through the 5GC core network; performing parameter conflict verification on the network element configuration information to obtain the parameter verification result of the original business configuration plan.

[0015] In one of the embodiments, the business configuration logic verification and the business configuration integrity verification are performed on the original business configuration plan through the 5GC core network to obtain the business logic verification result of the original business configuration plan, including: sending the original business configuration plan to the cloud network digital twin environment through the 5GC core network, simulating the operation of the original business configuration plan using the cloud network digital twin environment to obtain the simulation operation result of the original business configuration plan; and verifying the operation logic accuracy and the operation logic integrity of the simulation operation result to obtain the business logic verification result.

[0016] In a second aspect, the present application also provides a service configuration scheme generating device, comprising:

[0017] A demand instruction acquisition module, used to respond to a business configuration solution generation request triggered by a user and acquire a business demand instruction matching the business configuration solution generation request;

[0018] The original solution generation module is used to input the business demand instruction into a pre-built cloud network business intelligent body, obtain business demand information matching the business demand instruction through the cloud network business intelligent body, and generate an original business configuration solution matching the business configuration solution generation request based on the business demand information and pre-stored business configuration specification information;

[0019] An original solution verification module is used to input the original service configuration solution into the 5GC core network, and obtain a configuration solution verification result obtained by the 5GC core network verifying the original service configuration solution;

[0020] The target solution generation module is used to use the original business configuration solution as a target business configuration solution in response to the business configuration solution generation request when the configuration solution verification result indicates that the verification is passed.

[0021] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method described in any one of the embodiments of the first aspect when executing the computer program.

[0022] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method described in any one of the embodiments of the first aspect.

[0023] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method described in any one of the embodiments of the first aspect.

[0024] The above-mentioned business configuration plan generation method, device, computer equipment, computer-readable storage medium and computer program product obtain business requirement instructions that match the business configuration plan generation request by responding to the business configuration plan generation request triggered by the user; input the business requirement instructions into a pre-built cloud network business intelligent body, obtain business requirement information that matches the business requirement instructions through the cloud network business intelligent body, and generate an original business configuration plan that matches the business configuration plan generation request based on the business requirement information and pre-stored business configuration specification information; input the original business configuration plan into the 5GC core network, and obtain the configuration plan verification result obtained by the 5GC core network to verify the original business configuration plan; when the configuration plan verification result indicates that the verification is passed, the original business configuration plan is used as the target business configuration plan for responding to the business configuration plan generation request. When receiving a business configuration plan generation request initiated by a user for generating a business configuration plan, the present application can also obtain the business requirement instructions that match the request, and then the instructions can be input into the cloud-network business intelligent body, and the cloud-network business intelligent body obtains the business requirement information that matches the business requirement instructions, thereby using the business requirement information and the business configuration specification information pre-stored by the cloud-network business intelligent body to generate an original business configuration plan, and then the original business configuration plan can be verified through the 5GC core network. After the verification, the original business configuration plan can be used as the target business configuration plan to respond to the business configuration plan generation request. In this way, the cloud-network business intelligent body can generate a business configuration plan, and the 5GC core network can be used to verify the business configuration plan without the need for users to manually generate and verify it, thereby improving the efficiency of generating accurate business configuration plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0026] Figure 1 A schematic diagram of a flow chart of a method for generating a service configuration solution in one embodiment;

[0027] Figure 2 A schematic diagram of a process for generating an original service configuration solution in an embodiment;

[0028] Figure 3 A schematic diagram of a process for obtaining business demand information in an embodiment;

[0029] Figure 4A schematic diagram of a process for obtaining a configuration scheme verification result in an embodiment;

[0030] Figure 5 A structural diagram of a system for generating a business configuration solution based on generative AI in one embodiment;

[0031] Figure 6 A flowchart of a business configuration solution generation system generating a configuration solution in one embodiment;

[0032] Figure 7 A schematic diagram of the workflow of a cloud network business agent in an embodiment;

[0033] Figure 8 It is a structural block diagram of a device for generating a service configuration solution in one embodiment;

[0034] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0036] In one embodiment, Figure 1 As shown, a method for generating a service configuration scheme is provided. This embodiment uses the method applied to a server as an example for illustration. It can be understood that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0037] Step S101 : in response to a service configuration solution generation request triggered by a user, obtaining a service requirement instruction matching the service configuration solution generation request.

[0038] Among them, the service configuration scheme generation request can be a request triggered by the user for generating a service configuration scheme, and the service configuration scheme can be used to configure the communication service, and the service requirement instruction is an instruction that matches the service configuration scheme generation request, and the instruction can be a certain dialogue instruction. Specifically, when the user needs to generate a service configuration scheme, the service configuration scheme generation request can be initiated to the server. After receiving the service configuration scheme generation request, the server can initiate multiple rounds of dialogue interaction with the user. The user can input the corresponding service requirement instruction to the server through the above multiple rounds of dialogue interaction, and the server can use the service requirement instruction input by the user as the service requirement instruction that matches the service configuration scheme generation request.

[0039] Step S102, input the business demand instruction into the pre-built cloud network business intelligent body, obtain the business demand information matching the business demand instruction through the cloud network business intelligent body, and generate the original business configuration plan that matches the business configuration plan generation request based on the business demand information and the pre-stored business configuration specification information.

[0040] The cloud network business agent refers to a pre-created agent used to generate business configuration solutions. The agent can be built based on the LangChain framework and can be used to understand, analyze and respond to inputs, perform tasks, make decisions and interact with the environment. It is a system with complex reasoning capabilities, memory and means of executing tasks. Business demand information can refer to the business requirements of the business configuration solution that the user needs to generate. The business demand information can be identified based on the business demand instructions entered by the user. Business configuration specification information is the pre-stored business configuration specifications of different types of businesses, which can be pre-set in the cloud network business agent.

[0041] The original business configuration plan is the business configuration plan directly output by the cloud network business intelligent body. Specifically, after receiving the business demand instructions input by the user, the server can input the business demand instructions into the pre-built cloud network business intelligent body. The cloud network business intelligent body can then identify the user's business needs based on the input business demand instructions and obtain business demand information. After that, it can use the user's business demand information and pre-stored business configuration specification information to generate the original business configuration plan.

[0042] Step S103, inputting the original service configuration plan into the 5GC core network, and obtaining a configuration plan verification result obtained by the 5GC core network verifying the original service configuration plan;

[0043] Step S104: when the configuration scheme verification result indicates that the verification is passed, the original service configuration scheme is used as the target service configuration scheme for responding to the service configuration scheme generation request.

[0044] The target business configuration plan is the business configuration plan that is ultimately generated as a response to the business configuration plan generation request. The configuration plan verification result refers to the verification result obtained by verifying the original business configuration plan. The verification of the original business configuration plan can be achieved through the 5GC core network.

[0045] Specifically, after obtaining the original business configuration plan, the server can input the original business configuration plan into the 5GC core network, and the 5GC core network will verify the original business configuration plan to obtain the configuration plan verification result. If the configuration plan verification result indicates that the verification is passed, the server can use the generated original business configuration plan as the target business configuration plan generated in response to the business configuration plan generation request.

[0046] In the above-mentioned business configuration plan generation method, by responding to the business configuration plan generation request triggered by the user, a business requirement instruction matching the business configuration plan generation request is obtained; the business requirement instruction is input into a pre-built cloud network business intelligent body, and the business requirement information matching the business requirement instruction is obtained through the cloud network business intelligent body, and based on the business requirement information and the pre-stored business configuration specification information, an original business configuration plan matching the business configuration plan generation request is generated; the original business configuration plan is input into the 5GC core network, and a configuration plan verification result obtained by the 5GC core network for verifying the original business configuration plan is obtained; when the configuration plan verification result indicates that the verification is passed, the original business configuration plan is used as the target business configuration plan for responding to the business configuration plan generation request. When receiving a business configuration plan generation request initiated by a user for generating a business configuration plan, the present application can also obtain the business requirement instructions that match the request, and then the instructions can be input into the cloud-network business intelligent body, and the cloud-network business intelligent body obtains the business requirement information that matches the business requirement instructions, thereby using the business requirement information and the business configuration specification information pre-stored by the cloud-network business intelligent body to generate an original business configuration plan, and then the original business configuration plan can be verified through the 5GC core network. After the verification, the original business configuration plan can be used as the target business configuration plan to respond to the business configuration plan generation request. In this way, the cloud-network business intelligent body can generate a business configuration plan, and the 5GC core network can be used to verify the business configuration plan without the need for users to manually generate and verify it, thereby improving the efficiency of generating accurate business configuration plans.

[0047] In one embodiment, a pre-trained large language model and a configuration solution generation model are pre-set in the cloud network business agent; Figure 2 As shown, step S102 may further include:

[0048] Step S201 , input the business requirement instruction into a pre-trained large language model to obtain business requirement information matching the business requirement instruction.

[0049] In this embodiment, the cloud network business intelligent body can be pre-set with a pre-trained large language model and a configuration plan generation model, where the large language model can be an LLM, which is used to understand the user's business needs, and the configuration plan generation model can be implemented through a long short-term memory model, namely an LSTM model, which is mainly used to generate business configuration plans.

[0050] Specifically, the server can first input the business demand instructions into a pre-trained large language model, which can include two types, namely a general large language model and a special large language model dedicated to the communications industry, so that the large language model can output corresponding business demand information based on the business demand instructions.

[0051] Step S202: inputting the business requirement information and the business configuration specification information into the business configuration solution generation model, and obtaining the original business configuration solution through the business configuration solution generation model.

[0052] The business configuration plan generation model can be a long short-term memory model, that is, an LSTM model. The server can input business demand information and business configuration specification information into the business configuration plan generation model, and the business configuration plan generation model obtains the original business configuration plan. For example, the business demand information can be input as short-term memory, and the business configuration specification information can be input as stored long-term memory into the business configuration plan generation model, and the business configuration plan generation model generates the corresponding original business configuration plan.

[0053] In this embodiment, a pre-trained large language model and a configuration plan generation model can also be set in the cloud network business intelligence body, so that the business demand information can be identified by the large language model, and the original business configuration plan can be generated by the business configuration plan generation model. In this way, the accuracy of the generation of the original business configuration plan can be improved.

[0054] Furthermore, business demand information is represented by a business process chain; e.g. Figure 3 As shown, step S201 may further include:

[0055] Step S301, inputting the business demand information into the cloud network business intelligent body, and obtaining the pre-built prompt word template through the cloud network business intelligent body; the prompt word template is constructed based on the historical business demand survey information.

[0056] In this embodiment, the business demand information can be represented by a business process chain, which refers to a complete process from identifying customer needs to ultimately delivering products or services through a series of interrelated steps and activities, which can be used to optimize and improve business operation efficiency. The prompt word template refers to a prompt template, which is used to guide the large language model to output structured prompts or questions for specific content. They usually include preset formats or keywords to help the large language model understand the type and style of content that needs to be generated.

[0057] Specifically, the cloud network business intelligent body can convert the historical business demand survey form into a prompt template in advance as a prompt word template, and input the collected business demand information into the cloud network business intelligent body on the server. The cloud network business intelligent body can then obtain the above-mentioned pre-built prompt word template.

[0058] Step S302, obtaining a business requirement parameter from the business requirement instruction, inputting the business requirement parameter into a prompt word template, and obtaining a target prompt word that matches the business requirement instruction; the business requirement parameter includes: at least one of: a business type, an opening area, and manufacturer information;

[0059] Step S303: input the target prompt word into the large language model in the cloud network business agent, and generate a business processing flow chain through the large language model.

[0060] The business requirement parameters refer to the parameter information carried in the business requirement instructions, which may include the type of service, the service activation area information, the service manufacturer information, etc. For example, if the business requirement instructions limit the type of service, then the type can be used as a business requirement parameter. Similarly, the business requirement instructions can also limit the service activation area, then the activation area can also be used as a business requirement parameter.

[0061] Specifically, after receiving the business demand instruction, the cloud network business intelligent agent can identify the business demand parameters carried by the business demand instruction, such as the service type, activation area, and manufacturer information, etc., and write the business demand parameters into the prompt word template to generate a prompt word that matches the business demand instruction, namely the target prompt word. The target prompt word can then be input into the large language model in the cloud network business intelligent agent to generate a business processing flow chain.

[0062] In this embodiment, the server can also obtain a prompt word template that is pre-constructed based on historical business demand survey information, identify business demand parameters, and then construct a target prompt word in combination with the prompt word template. The target prompt word can then be input into the large language model in the cloud network business intelligence body to generate a business processing flow chain as business demand information. In this way, the recognition accuracy of business demand information can be improved.

[0063] In one embodiment, the business configuration specification information is stored in a business configuration specification learning library; the business configuration specification learning library includes: a business level, an instruction level, and an instruction parameter level; before step S102, it may also include: obtaining sample business configuration data corresponding to the sample communication business; obtaining business information, instruction information, and instruction parameter information corresponding to the sample communication business from the sample business configuration data; the business information includes: at least one of the business name, business operation, manufacturer information, and configuration object information, the instruction information includes: at least one of the instruction name, instruction function, and instruction sequence, and the instruction parameter information includes: at least one of the parameter name, parameter value rule, and parameter type; the business information is stored in the business level, the instruction information is stored in the instruction level, and the instruction parameter information is stored in the instruction parameter level, so as to store the sample business configuration data in the business configuration specification learning library.

[0064] The business configuration specification learning library is a pre-built learning library for storing business configuration specification information, and the learning library may include three different levels, namely, the business level, the instruction level, and the instruction parameter level. The sample communication service refers to the communication service that has been initiated, and the sample service configuration data refers to the service configuration data corresponding to the sample communication service. In this embodiment, when constructing the business configuration specification learning library, the sample communication service may be collected first, for example, the communication service that has completed the service configuration may be used as the sample communication service, and the service configuration data of the sample communication service may be collected as the sample service configuration data.

[0065] Afterwards, the business information, instruction information and instruction parameter information related to the sample communication service can be identified from the sample business configuration data, where the business information may refer to the service name, business operation, manufacturer information and configuration object information, etc., the instruction information may include the instruction name, instruction function and instruction sequence, etc., and the instruction parameter information may include the parameter name, parameter value rules and parameter type, etc.

[0066] Specifically, the server can identify the service name, service operation, manufacturer information and configuration object information of the sample communication service from the sample service configuration data as the service information of the sample communication service, and can also identify the instruction name, instruction function and instruction sequence of the sample communication service from the sample service configuration data as the instruction information of the sample communication service, and can also identify the parameter name, parameter value rule and parameter type of the sample communication service from the sample service configuration data as the instruction parameter information. After that, the service information can be stored in the service level, the instruction information can be stored in the instruction level and the instruction parameter information can be stored in the instruction parameter level, so as to realize the storage of the sample service configuration data in the service configuration specification learning library.

[0067] In this embodiment, sample business configuration data corresponding to the sample communication business can also be collected, and the business information, instruction information and instruction parameter information corresponding to the sample communication business can be identified from the sample business configuration data, so that the business information, instruction information and instruction parameter information can be stored at the business level, instruction level and instruction parameter level respectively. In this way, the construction of a business configuration specification learning library can be realized, and the integrity of the storage of business configuration specification information can be improved.

[0068] In one embodiment, Figure 4 As shown, step S103 may further include:

[0069] Step S401: input the original service configuration plan into the 5GC core network.

[0070] 5GC core network refers to the core network of the fifth-generation mobile communication system and is an important part of the 5G network. In this embodiment, after the server generates the original service configuration plan, it also needs to audit and verify the service configuration plan, and the verification is implemented through the 5GC core network. Therefore, the server can first input the original service configuration plan into the 5GC core network to verify the original service configuration plan.

[0071] Step S402: Perform parameter verification on the original business configuration plan through the 5GC core network to obtain the parameter verification result of the original business configuration plan, and perform business configuration logic verification and business configuration integrity verification on the original business configuration plan through the 5GC core network to obtain the business logic verification result of the original business configuration plan.

[0072] The parameter verification result refers to the verification result obtained by performing parameter verification on the original business configuration plan, while the business logic verification result refers to the verification result obtained by performing business configuration logic verification and business configuration integrity verification on the original business configuration plan.

[0073] Specifically, the 5GC core network can be used to perform parameter verification on the original business configuration plan to obtain parameter verification results, or the 5GC core network can be used to perform business configuration logic verification and business configuration integrity verification on the original business configuration plan to obtain business logic verification results.

[0074] Step S403: taking the parameter verification result and the business logic verification result as the configuration solution verification result.

[0075] Finally, the server can use the parameter verification results and the business logic verification results as the configuration scheme verification results. In this way, the parameter verification and business logic verification for the business configuration scheme can be completed, thereby improving the integrity of the business configuration scheme verification.

[0076] In this embodiment, the original service configuration plan can also be verified by parameters, service configuration logic and service configuration integrity through the 5GC core network. In this way, the integrity of the service configuration plan verification can be improved.

[0077] Furthermore, step S402 may further include: collecting network element configuration information associated with the original service configuration plan through the 5GC core network; performing parameter conflict verification on the network element configuration information to obtain a parameter verification result of the original service configuration plan.

[0078] In this embodiment, parameter verification can be achieved by performing parameter conflict verification on the network element configuration information associated with the original business configuration plan. Specifically, the network element configuration information can be collected through 5GC, for example, by collecting the configuration information of the network elements in the 5GC core network interface through an automated script or tool, and then parameter conflict verification can be performed based on the configuration information to obtain the parameter verification result of the original business configuration plan.

[0079] In this embodiment, the server can also collect network element configuration information associated with the original service configuration plan through the 5GC core network, and then use the network element configuration information to perform parameter conflict verification to obtain parameter verification results. In this way, parameter conflicts in the service configuration plan can be avoided.

[0080] In addition, step S402 may further include: sending the original business configuration plan to the cloud network digital twin environment through the 5GC core network, using the cloud network digital twin environment to simulate the operation of the original business configuration plan, and obtaining the simulation operation results of the original business configuration plan; verifying the accuracy of the operation logic and the integrity of the operation logic of the simulation operation results to obtain the business logic verification results.

[0081] The cloud-network digital twin environment is a virtualized space that creates a digital model corresponding to the real-world network and services to achieve real-time monitoring, analysis and optimization of network performance, status and behavior. Specifically, when the 5GC core network verifies the accuracy and integrity of the operation logic, the original business configuration plan can be sent to the cloud-network digital twin environment, and the cloud-network digital twin environment simulates the operation of the original business configuration plan to obtain the simulation operation results. After that, the simulation operation results are verified for accuracy and integrity of the operation logic to obtain the business logic verification results.

[0082] In this embodiment, the 5GC core network can also send the original business configuration plan to the cloud network digital twin environment, and simulate the operation of the original business configuration plan through the cloud network digital twin environment, so as to verify the operation logic accuracy and operation logic integrity of the simulation operation results. In this way, the operation logic accuracy and integrity of the original business configuration plan can be ensured.

[0083] In one embodiment, a system and method for generating a business configuration solution based on generative AI is also provided, which can achieve: applying the characteristics of intelligent body autonomous perception, planning and decision-making, and execution of complex tasks, intelligently learning configuration specification content, flexibly and autonomously querying the values ​​of existing network parameters, adding intelligence to the business activation process, reducing the workload of manual auditing, and improving auditing accuracy.

[0084] This embodiment can be implemented by Figure 5 The business configuration solution generation system based on generative AI shown in the figure realizes the business configuration solution generation. The system includes: a dialogue interaction module, a specification input and solution analysis module, and a cloud network business intelligent body. The functions of each module are as follows:

[0085] Specification entry and solution analysis module: 1. Analysis: Based on the natural language processing algorithm, the configuration specification related information is analyzed, mainly including the label information of the business level, instruction level, and instruction parameter level; 2. Storage: The obtained business label information is stored as long-term memory;

[0086] Dialogue interaction module: understands and confirms business requirements and stores interaction information as short-term memory;

[0087] Cloud network business agent: The components of the agent are memory + planning + perception + action. The agent is created using the LangChain framework, corresponding to the following modules;

[0088] Memory storage module: vectorize and store long and short-term memory;

[0089] Cloud network big model + general big model: the core brain of the intelligent agent, providing decision-making planning and interaction;

[0090] 5GC collection: collects configuration, alarm, log and other information of 5GC network elements and establishes active perception function;

[0091] 5GC control: Send instructions to network elements through API;

[0092] Cloud network digital twin: stores the topological relationship and real-time configuration data of 5GC network elements.

[0093] like Figure 6 As shown, the process of generating a configuration scheme in the above system may include the following steps:

[0094] Step 1: Build a business specification configuration learning library.

[0095] The business configuration specification learning library of the parsing equipment telecommunications mainly includes three levels: business level, instruction level, and instruction parameter level.

[0096] The business level includes information such as "business name" label, "business operation" label, "manufacturer" label, and "configuration object" label;

[0097] The instruction level includes: instruction name, instruction function label, instruction label, and instruction sequence label. Among them, the instruction function label mainly marks the function of the instruction, and the instruction sequence label mainly marks the execution dependency order under a certain configuration business;

[0098] Instruction parameter level Instruction parameter meaning, including: parameter name, parameter value rule, parameter type, etc.;

[0099] And it will be stored in the memory storage module as long-term memory.

[0100] Step 2: Based on the generated cloud network business agent, call the large model used for planning, conduct multiple rounds of interactive dialogues by generating guide words, understand and confirm business requirements, such as business type, activation area, manufacturer information, etc., and store the confirmed content as short-term memory in the memory storage module.

[0101] It is explained here that the historical business demand survey form can be converted into a prompt template in advance, and based on the LangChain framework, the template and instance information can be used as training data for the big model, the core planning module of the intelligent agent, to generate a business processing flow chain.

[0102] Step 3: Use the long short-term memory network (LSTM) to understand the confirmed business needs and learning library information based on the context information, and the cloud network business agent generates the first configuration plan.

[0103] Based on the active understanding of the configuration plan, the tool is called for verification. For example, 5GC is used to collect network element configuration information to verify whether the parameters conflict, and 5GC is used to control and send it to the twin environment to verify whether the business configuration logic is correct and whether the business configuration integrity is available.

[0104] Step 4: After verification, the information is obtained to obtain the final configuration plan.

[0105] Among them, the cloud network business intelligent body workflow can be as follows Figure 7 shown.

[0106] In this embodiment, the general large model and the telecommunications industry large model are combined, and the LangChain framework is used to have better reasoning and action capabilities, to form an industry vertical application intelligent body, and to land in actual production business scenarios. It also combines natural language processing technology to automatically parse the label data in the configuration plan, obtain matching information, and generate an audit report, which can improve data validity and optimize processes, while reducing the manual verification cost of the plan and speeding up the launch of services.

[0107] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0108] Based on the same inventive concept, the embodiment of the present application also provides a service configuration solution generation device for implementing the service configuration solution generation method involved above. The implementation solution for solving the problem provided by the device is similar to the implementation solution recorded in the above method, so the specific limitations in the one or more service configuration solution generation device embodiments provided below can refer to the limitations of the service configuration solution generation method above, and will not be repeated here.

[0109] In one embodiment, Figure 8 As shown, a service configuration scheme generating device is provided, comprising: a demand instruction acquisition module 801, an original scheme generating module 802, an original scheme verification module 803 and a target scheme generating module 804, wherein:

[0110] The demand instruction acquisition module 801 is used to respond to the business configuration solution generation request triggered by the user and acquire the business demand instruction matching the business configuration solution generation request;

[0111] The original solution generation module 802 is used to input the business demand instruction into the pre-built cloud network business intelligent body, obtain the business demand information matching the business demand instruction through the cloud network business intelligent body, and generate the original business configuration solution matching the business configuration solution generation request according to the business demand information and the pre-stored business configuration specification information;

[0112] The original solution verification module 803 is used to input the original service configuration solution into the 5GC core network and obtain the configuration solution verification result obtained by the 5GC core network verifying the original service configuration solution;

[0113] The target solution generation module 804 is configured to use the original business configuration solution as a target business configuration solution for responding to the business configuration solution generation request when the configuration solution verification result indicates that the verification is passed.

[0114] In one embodiment, a pre-trained large language model and a configuration plan generation model are pre-set in the cloud network business intelligent body; the original plan generation module 802 is further used to input the business requirement instructions into the pre-trained large language model to obtain business requirement information that matches the business requirement instructions; the business requirement information and business configuration specification information are input into the business configuration plan generation model, and the original business configuration plan is obtained through the business configuration plan generation model.

[0115] In one embodiment, business demand information is represented by a business processing flow chain; the original solution generation module 802 is further used to input the business demand information into the cloud network business intelligent body, and obtain a pre-built prompt word template through the cloud network business intelligent body; the prompt word template is constructed based on historical business demand survey information; business demand parameters are obtained from the business demand instructions, and the business demand parameters are input into the prompt word template to obtain target prompt words that match the business demand instructions; the business demand parameters include: business type, activation area and at least one of manufacturer information; the target prompt words are input into the large language model in the cloud network business intelligent body, and the business processing flow chain is generated through the large language model.

[0116] In one embodiment, the business configuration specification information is stored in a business configuration specification learning library; the business configuration specification learning library includes: business level, instruction level and instruction parameter level; the original solution generation module 802 is also used to obtain sample business configuration data corresponding to the sample communication business; from the sample business configuration data, obtain the business information, instruction information and instruction parameter information corresponding to the sample communication business; the business information includes: at least one of the business name, business operation, manufacturer information and configuration object information, the instruction information includes: at least one of the instruction name, instruction function and instruction sequence, and the instruction parameter information includes: at least one of the parameter name, parameter value rule and parameter type; store the business information in the business level, store the instruction information in the instruction level, and store the instruction parameter information in the instruction parameter level, so as to store the sample business configuration data in the business configuration specification learning library.

[0117] In one embodiment, the original solution verification module 803 is further used to input the original business configuration solution into the 5GC core network; perform parameter verification on the original business configuration solution through the 5GC core network to obtain the parameter verification result of the original business configuration solution, and perform business configuration logic verification and business configuration integrity verification on the original business configuration solution through the 5GC core network to obtain the business logic verification result of the original business configuration solution; and use the parameter verification result and the business logic verification result as the configuration solution verification result.

[0118] In one embodiment, the original solution verification module 803 is further used to collect network element configuration information associated with the original service configuration solution through the 5GC core network; perform parameter conflict verification on the network element configuration information to obtain the parameter verification result of the original service configuration solution.

[0119] In one embodiment, the original plan verification module 803 is further used to send the original business configuration plan to the cloud network digital twin environment through the 5GC core network, and use the cloud network digital twin environment to simulate the operation of the original business configuration plan to obtain the simulation operation result of the original business configuration plan; the simulation operation result is verified for the accuracy of the operation logic and the integrity of the operation logic to obtain the business logic verification result.

[0120] Each module in the above-mentioned service configuration scheme generating device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module above.

[0121] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig. 9 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store business demand instruction data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for generating a business configuration solution is implemented.

[0122] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0123] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0124] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0125] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0126] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0127] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0128] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0129] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for generating a business configuration scheme, characterized in that: The method comprises: In response to a service configuration solution generation request triggered by a user, obtaining a service requirement instruction matching the service configuration solution generation request; Input the business requirement instruction into a pre-built cloud network business intelligent body, obtain business requirement information matching the business requirement instruction through the cloud network business intelligent body, and generate an original business configuration plan matching the business configuration plan generation request based on the business requirement information and pre-stored business configuration specification information; Inputting the original service configuration plan into the 5GC core network, and obtaining a configuration plan verification result obtained by the 5GC core network verifying the original service configuration plan; When the configuration scheme verification result indicates that the verification is passed, the original service configuration scheme is used as a target service configuration scheme to respond to the service configuration scheme generation request.

2. The method according to claim 1, characterized in that The cloud network business intelligent agent is pre-set with a pre-trained large language model and a configuration solution generation model; The step of obtaining the business requirement information matching the business requirement instruction through the cloud network business intelligent agent, and generating an original business configuration scheme matching the business configuration scheme generation request according to the business requirement information and pre-stored business configuration specification information, includes: Inputting the business requirement instruction into the pre-trained large language model to obtain business requirement information matching the business requirement instruction; The business requirement information and the business configuration specification information are input into the business configuration solution generation model, and the original business configuration solution is obtained through the business configuration solution generation model.

3. The method according to claim 2, characterized in that The business requirement information is represented by a business process flow chain; the business requirement instruction is input into the pre-trained large language model to obtain business requirement information matching the business requirement instruction, including: Inputting the business demand information into the cloud network business agent, and obtaining a pre-built prompt word template through the cloud network business agent; the prompt word template is constructed based on historical business demand survey information; Acquire a business requirement parameter from the business requirement instruction, input the business requirement parameter into the prompt word template, and obtain a target prompt word that matches the business requirement instruction; the business requirement parameter includes: at least one of a business type, an opening area, and manufacturer information; The target prompt word is input into the large language model in the cloud network business agent, and the business processing flow chain is generated through the large language model.

4. The method according to claim 1, characterized in that: The business configuration specification information is stored in a business configuration specification learning library; the business configuration specification learning library includes: a business level, an instruction level, and an instruction parameter level; the business configuration specification information pre-stored by the cloud network business intelligent body, and the business demand information, before generating the original business configuration scheme that matches the business configuration scheme generation request, also includes: Obtaining sample service configuration data corresponding to the sample communication service; Acquire service information, instruction information, and instruction parameter information corresponding to the sample communication service from the sample service configuration data; the service information includes: at least one of service name, service operation, vendor information, and configuration object information; the instruction information includes: at least one of instruction name, instruction function, and instruction sequence; the instruction parameter information includes: at least one of parameter name, parameter value rule, and parameter type; The service information is stored in the service level, the instruction information is stored in the instruction level, and the instruction parameter information is stored in the instruction parameter level, so as to store the sample service configuration data in the service configuration specification learning library.

5. The method according to any one of claims 1 to 4, characterized in that: The inputting the original service configuration scheme into the 5GC core network and obtaining the configuration scheme verification result obtained by the 5GC core network verifying the original service configuration scheme includes: Input the original service configuration plan into the 5GC core network; Performing parameter verification on the original service configuration scheme through the 5GC core network to obtain a parameter verification result of the original service configuration scheme, and performing service configuration logic verification and service configuration integrity verification on the original service configuration scheme through the 5GC core network to obtain a service logic verification result of the original service configuration scheme; The parameter verification result and the business logic verification result are used as the configuration solution verification result.

6. The method according to claim 5, characterized in that The performing parameter verification on the original service configuration scheme through the 5GC core network to obtain a parameter verification result of the original service configuration scheme includes: Collecting network element configuration information associated with the original service configuration solution through the 5GC core network; Perform parameter conflict verification on the network element configuration information to obtain a parameter verification result of the original service configuration solution.

7. The method according to claim 5, characterized in that The performing service configuration logic verification and service configuration integrity verification on the original service configuration scheme through the 5GC core network to obtain a service logic verification result of the original service configuration scheme includes: The original service configuration scheme is sent to the cloud network digital twin environment through the 5GC core network, and the cloud network digital twin environment is used to simulate and run the original service configuration scheme to obtain a simulation operation result of the original service configuration scheme; The simulation operation result is verified for operation logic accuracy and operation logic integrity to obtain the business logic verification result.

8. A device for generating a business configuration scheme, characterized in that: The device comprises: A demand instruction acquisition module, used to respond to a business configuration solution generation request triggered by a user and acquire a business demand instruction matching the business configuration solution generation request; The original solution generation module is used to input the business demand instruction into a pre-built cloud network business intelligent body, obtain business demand information matching the business demand instruction through the cloud network business intelligent body, and generate an original business configuration solution matching the business configuration solution generation request based on the business demand information and pre-stored business configuration specification information; An original solution verification module is used to input the original service configuration solution into the 5GC core network, and obtain a configuration solution verification result obtained by the 5GC core network verifying the original service configuration solution; The target solution generation module is used to use the original business configuration solution as a target business configuration solution in response to the business configuration solution generation request when the configuration solution verification result indicates that the verification is passed.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images