Business configuration scheme generation method and device, computer device, and storage medium

Abstract

The application 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 intelligent agent, obtaining service demand information through the cloud network service intelligent 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, obtaining a configuration scheme verification result obtained by the 5GC core network verifying the original service configuration scheme; and in the case that the configuration scheme verification result represents that the verification is passed, taking the original service configuration scheme as a target service configuration scheme for generating the service configuration scheme. The method can improve the efficiency of generating an accurate service configuration scheme.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, computer device, computer-readable storage medium, and computer program product for generating business configuration schemes. Background Technology

[0002] With the development of computer technology, a method for generating business configuration schemes using computers has emerged. This method can pre-configure multiple business configuration models corresponding to different business types. When a business configuration scheme needs to be generated, the user can select the appropriate business configuration model according to actual business needs and input the corresponding business parameters, thereby generating the corresponding business configuration scheme from the business configuration model. Afterwards, the user can manually verify the generated business configuration scheme. Once the verification is passed, the generation of the business configuration scheme is complete.

[0003] However, the generation of the above-mentioned business configuration schemes usually requires users to manually select the business configuration model and input business parameters, and users also need to manually verify the business configuration schemes after they are generated. Therefore, the generation cycle of business configuration schemes is too long, and the existing business configuration scheme generation methods are inefficient in generating accurate business configuration schemes. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for generating business configuration schemes that can improve the efficiency of generating accurate business configuration schemes, in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a method for generating a business configuration scheme, including:

[0006] In response to a user-triggered request to generate a business configuration scheme, obtain a business requirement instruction that matches the request.

[0007] The business requirement instruction is input into a pre-built cloud network service intelligent agent. The cloud network service intelligent agent obtains the business requirement information that matches the business requirement instruction. Based on the business requirement information and the pre-stored business configuration specification information, an original business configuration scheme that matches the business configuration scheme generation request is generated.

[0008] The original service configuration scheme is input into the 5GC core network, and the configuration scheme verification result obtained by the 5GC core network in verifying the original service configuration scheme is obtained.

[0009] If the configuration scheme verification result indicates that the verification is successful, the original business configuration scheme will be used as the target business configuration scheme in response to the business configuration scheme generation request.

[0010] In one of the embodiments, the cloud network service intelligent agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service intelligent agent is configured to obtain service demand information matched with the service demand instruction, and generate an original service configuration scheme matched with the service configuration scheme generation request according to the service demand information and pre-stored service configuration specification information, including: inputting the service demand instruction into the pre-trained large language model to obtain the service demand information matched with the service demand instruction; and inputting the service demand information and the service configuration specification information into the service configuration scheme generation model to obtain the original service configuration scheme through the service configuration scheme generation model.

[0011] In one of the embodiments, the service demand information is represented by a service processing flow chain; the cloud network service intelligent agent is configured to input the service demand information into the cloud network service intelligent agent to obtain a pre-constructed prompt word template through the cloud network service intelligent agent; the prompt word template is constructed based on historical service demand research information; obtain service demand parameters from the service demand instruction, input the service demand parameters into the prompt word template to obtain a target prompt word matched with the service demand instruction; the service demand parameters include at least one of a service type, an opening area, and manufacturer information; and input the target prompt word into a large language model in the cloud network service intelligent agent to generate the service processing flow chain through the large language model.

[0012] In one of the embodiments, the service configuration specification information is stored in a service configuration specification learning library; the service configuration specification learning library includes a service level, an instruction level, and an instruction parameter level; before the cloud network service intelligent agent pre-stores the service configuration specification information and the service demand information to generate the original service configuration scheme matched with the service configuration scheme generation request, the cloud network service intelligent agent is further configured to obtain sample service configuration data corresponding to a sample communication service; obtain 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 a service name, a service operation, manufacturer information, and configuration object information, the instruction information includes at least one of an instruction name, an instruction function, and an instruction sequence, and the instruction parameter information includes at least one of a parameter name, a parameter value rule, and a parameter type; store the service information in the service level, the instruction information in the instruction level, and the instruction parameter information in the instruction parameter level to store the sample service configuration data in the service configuration specification learning library.

[0013] In one of the embodiments, the inputting the original service configuration scheme into the 5GC core network and obtaining a configuration scheme verification result obtained by the 5GC core network verifying the original service configuration scheme comprises: inputting the original service configuration scheme into the 5GC core network; performing parameter verification on the original service configuration scheme by 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 by the 5GC core network to obtain a service logic verification result of the original service configuration scheme; and taking the parameter verification result and the service logic verification result as the configuration scheme verification result.

[0014] In one of the embodiments, the performing parameter verification on the original service configuration scheme by the 5GC core network to obtain a parameter verification result of the original service configuration scheme comprises: collecting, by the 5GC core network, network element configuration information associated with the original service configuration scheme; and performing parameter conflict verification on the network element configuration information to obtain the parameter verification result of the original service configuration scheme.

[0015] In one of the embodiments, the performing service configuration logic verification and service configuration integrity verification on the original service configuration scheme by the 5GC core network to obtain a service logic verification result of the original service configuration scheme comprises: sending, by the 5GC core network, the original service configuration scheme to a cloud network digital twin environment, simulating running the original service configuration scheme by using the cloud network digital twin environment to obtain a simulation running result of the original service configuration scheme; and performing running logic accuracy verification and running logic integrity verification on the simulation running result to obtain the service logic verification result.

[0016] In a second aspect, the application further provides a service configuration scheme generation device, comprising:

[0017] A demand instruction acquisition module is configured to acquire a service demand instruction matched with the service configuration scheme generation request in response to a service configuration scheme generation request triggered by a user.

[0018] An original scheme generation module is configured to input the service demand instruction into a pre-constructed cloud network service intelligent agent, acquire service demand information matched with the service demand instruction by using the cloud network service intelligent agent, and generate an original service configuration scheme matched with the service configuration scheme generation request according to the service demand information and pre-stored service configuration specification information.

[0019] An original scheme verification module is configured to input the original service configuration scheme into a 5GC core network and obtain a configuration scheme verification result obtained by the 5GC core network in verification of the original service configuration scheme.

[0020] A target scheme generation module is configured to, in a case where the configuration scheme verification result represents a verification pass, generate the original service configuration scheme as a target service configuration scheme in response to the service configuration scheme generation request.

[0021] In a third aspect, the present application further provides a computer device, including a memory and a processor, the memory stores a computer program, and the processor implements the steps of the method 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, which stores a computer program, and the computer program implements the steps of the method in any one of the embodiments of the first aspect when executed by a processor.

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

[0024] The business configuration scheme generation method, apparatus, computer device, computer readable storage medium, and computer program product described above, in response to a user triggered business configuration scheme generation request, obtain a business demand instruction matched with the business configuration scheme generation request; input the business demand instruction into a pre-constructed cloud network business intelligent agent, obtain business demand information matched with the business demand instruction through the cloud network business intelligent agent, and generate an original business configuration scheme matched with the business configuration scheme generation request according to the business demand information and pre-stored business configuration specification information; input the original business configuration scheme into a 5GC core network, obtain a configuration scheme verification result obtained by the 5GC core network verifying the original business configuration scheme; and in the case that the configuration scheme verification result represents that the verification is passed, take the original business configuration scheme as a target business configuration scheme for responding to the business configuration scheme generation request. The present application can obtain a business demand instruction matched with the request when receiving a business configuration scheme generation request initiated by a user for generating a business configuration scheme, then input the instruction into a cloud network business intelligent agent, obtain business demand information matched with the business demand instruction through the cloud network business intelligent agent, and generate an original business configuration scheme by using the business demand information and pre-stored business configuration specification information of the cloud network business intelligent agent, and then verify the original business configuration scheme through the 5GC core network, and take the original business configuration scheme as a target business configuration scheme for responding to the business configuration scheme generation request after the verification is passed. In this way, the cloud network business intelligent agent can be used to generate a business configuration scheme, and the 5GC core network can be used to verify the business configuration scheme, without manual generation and verification by the user, so that the efficiency of generating an accurate business configuration scheme can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the description of the embodiments of the present application or the related art will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other related drawings can be obtained by those skilled in the art without creative labor.

[0026] Figure 1 A flowchart of a business configuration scheme generation method in an embodiment;

[0027] Figure 2 A flowchart of generating an original business configuration scheme in an embodiment;

[0028] Figure 3 A flowchart of obtaining business demand information in an embodiment;

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

[0030] Figure 5 A structural diagram of a service configuration scheme generation system based on generative AI in an embodiment;

[0031] Figure 6 A flowchart of a process for generating a configuration scheme by a service configuration scheme generation system in an embodiment;

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

[0033] Figure 8 A structural block diagram of a service configuration scheme generation apparatus in an embodiment;

[0034] Figure 9 An internal structural diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0035] In order to make the purposes, technical solutions and advantages of the present application clearer, further detailed description will be made to the present application in combination 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 an embodiment, as shown in Figure 1 , a service configuration scheme generation method is provided, and the present embodiment takes the method applied to a server as an example for illustration. It should 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 can be realized through the interaction of the terminal and the server. In the present embodiment, the method includes the following steps:

[0037] Step S101, 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.

[0038] The service configuration scheme generation request can be a request triggered by a user for generating a service configuration scheme, the service configuration scheme can be used for configuring a communication service, and the service demand instruction is an instruction matched with the service configuration scheme generation request. The instruction can be a certain dialogue instruction. Specifically, when the user needs to generate a service configuration scheme, the user can initiate a service configuration scheme generation request to a server. After the server receives the service configuration scheme generation request, the server can initiate a multi-round dialogue interaction with the user. The user can input a corresponding service demand instruction to the server through the multi-round dialogue interaction, and the server can take the service demand instruction input by the user as the service demand instruction matched with the service configuration scheme generation request.

[0039] Step S102: Input the business requirement instruction into the pre-built cloud network service intelligent agent, obtain the business requirement information matching the business requirement instruction through the cloud network service intelligent agent, and generate the original business configuration scheme matching the business configuration scheme generation request based on the business requirement information and the pre-stored business configuration specification information.

[0040] A cloud-network service intelligent agent refers to a pre-created intelligent agent used to generate service configuration schemes. This agent, built on the LangChain framework, can understand, analyze, and respond to input, execute tasks, make decisions, and interact with the environment. It is a system with complex reasoning capabilities, memory, and task execution methods. Service requirement information refers to the service requirements that the user needs to generate for the service configuration scheme. This information can be identified based on the user's input service requirement commands. Service configuration specification information consists of pre-stored service configuration specifications for different types of services, which can be pre-set within the cloud-network service intelligent agent.

[0041] The original service configuration scheme is the service configuration scheme directly output by the cloud network service intelligent agent. Specifically, after the server receives the service requirement instruction input by the user, it can input the service requirement instruction into the pre-built cloud network service intelligent agent. The cloud network service intelligent agent can then identify the user's service requirements based on the input service requirement instruction, obtain the service requirement information, and then use the user's service requirement information and the pre-stored service configuration specification information to generate the original service configuration scheme.

[0042] Step S103: Input the original service configuration scheme into the 5GC core network and obtain the configuration scheme verification result obtained by the 5GC core network in verifying the original service configuration scheme.

[0043] Step S104: If the configuration scheme verification result indicates that the verification is successful, the original business configuration scheme is used as the target business configuration scheme in response to the business configuration scheme generation request.

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

[0045] Specifically, after obtaining the original service configuration scheme, the server can input the original service configuration scheme to the 5GC core network, and the 5GC core network verifies the original service configuration scheme to obtain a configuration scheme verification result. If the configuration scheme verification result indicates that the verification is passed, the server can generate the original service configuration scheme as the target service configuration scheme generated in response to the service configuration scheme generation request.

[0046] In the above service configuration scheme generation method, the service demand instruction matched with the service configuration scheme generation request is obtained in response to the service configuration scheme generation request triggered by the user; the service demand instruction is input into the cloud network service agent, and the service demand information matched with the service demand instruction is obtained through the cloud network service agent, and the original service configuration scheme matched with the service configuration scheme generation request is generated according to the service demand information and the pre-stored service configuration specification information; the original service configuration scheme is input into the 5GC core network, and the configuration scheme verification result obtained by the 5GC core network verifying the original service configuration scheme is obtained; and in the case that the configuration scheme verification result indicates that the verification is passed, the original service configuration scheme is taken as the target service configuration scheme responding to the service configuration scheme generation request. Through the above method, when the service configuration scheme generation request for generating the service configuration scheme initiated by the user is received, the service demand instruction matched with the request can also be obtained, and then the instruction can be input into the cloud network service agent, and the service demand information matched with the service demand instruction can be obtained through the cloud network service agent, so that the original service configuration scheme can be generated by using the service demand information and the pre-stored service configuration specification information of the cloud network service agent. After that, the original service configuration scheme can also be verified through the 5GC core network, and after the verification is passed, the original service configuration scheme can be taken as the target service configuration scheme responding to the service configuration scheme generation request. Through the above method, the cloud network service agent can be used to generate the service configuration scheme, and the 5GC core network can be used to verify the service configuration scheme, so that the user does not need to manually generate and manually verify, and the efficiency of generating the accurate service configuration scheme can be improved.

[0047] In one embodiment, the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model. Figure 2 As shown in FIG. 10, step S102 can further include:

[0048] In step S201, the service demand instruction is input into the pre-trained large language model to obtain the service demand information matched with the service demand instruction.

[0049] In this embodiment, the cloud network service agent can be pre-configured with a pre-trained large language model and a configuration scheme generation model, wherein the large language model can be an LLM, which is used to understand the service demand of the user, and the configuration scheme generation model can be implemented through a long short-term memory model, i.e., an LSTM model, which is mainly used to generate a service configuration scheme.

[0050] Specifically, the server can first input the service demand instruction into the pre-trained large language model, which can include two types, namely a general-purpose general large language model and a communication industry-specific special large language model, so as to output the corresponding service demand information based on the service demand instruction by the large language model.

[0051] In step S202, the service demand information and the service configuration specification information are input into the service configuration scheme generation model, and the original service configuration scheme is obtained through the service configuration scheme generation model.

[0052] The service configuration scheme generation model can be a long short-term memory model, i.e., an LSTM model. The server can input the service demand information and the service configuration specification information into the service configuration scheme generation model, and obtain the original service configuration scheme from the service configuration scheme generation model. For example, the service demand information can be input as short-term memory, and the service configuration specification information can be input as stored long-term memory into the service configuration scheme generation model, so as to generate the corresponding original service configuration scheme by the service configuration scheme generation model.

[0053] In this embodiment, the pre-trained large language model and the configuration scheme generation model can also be set in the cloud network service agent, so as to identify the service demand information by the large language model, and generate the original service configuration scheme through the service configuration scheme generation model. In this way, the accuracy of generating the original service configuration scheme can be improved.

[0054] Further, the service demand information is represented through a service processing flow chain; as shown in FIG. 2, step S201 can further include: Figure 3

[0055] In step S301, the service demand information is input into the cloud network service agent, and a pre-constructed prompt word template is obtained through the cloud network service agent; the prompt word template is constructed based on historical service demand research information.

[0056] ​In this embodiment, business requirement information can be represented by a business process chain, which refers to a complete process from identifying customer needs to finally delivering a product or service through a series of interrelated steps and activities. This chain can be used to optimize and improve business operational efficiency. The prompt template refers to a structured prompt or question used to guide the large language model in outputting specific content. These templates typically include preset formats or keywords to help the large language model understand the type and style of content to be generated.

[0057] Specifically, the cloud network business intelligence agent can convert historical business demand survey forms into prompt templates in advance, which can then be used as prompt word templates. The collected business demand information is input into the cloud network business intelligence agent on the server, and the cloud network business intelligence agent can then obtain the aforementioned pre-built prompt word templates.

[0058] Step S302: Obtain business requirement parameters from the business requirement instruction, input the business requirement parameters into the prompt word template, and obtain the target prompt word that matches the business requirement instruction; the business requirement parameters include at least one of the following: business type, service area, and manufacturer information;

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

[0060] Business requirement parameters refer to the parameter information carried in the business requirement instruction. These can include the type of business, the service coverage area, and the manufacturer information. For example, if the business requirement instruction specifies the type of business, then that type can be used as a business requirement parameter. Similarly, the business requirement instruction can also specify the service coverage area, so the coverage area can also be used as a business requirement parameter.

[0061] Specifically, after receiving a business requirement instruction, the cloud network business intelligent agent can identify the business requirement parameters carried in the instruction, such as the business type, coverage area, and manufacturer information. These parameters are then written into a prompt word template to generate a prompt word that matches the business requirement instruction, i.e., a 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 pre-built 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 intelligent agent to generate a business processing flow chain as business demand information. This method can improve the accuracy of business demand information identification.

[0063] In an embodiment, the service configuration specification information is stored in a service configuration specification learning library; the service configuration specification learning library comprises a service level, an instruction level, and an instruction parameter level; before step S102, the method can further comprise: obtaining sample service configuration data corresponding to a sample communication service; obtaining service information, instruction information, and instruction parameter information corresponding to the sample communication service from the sample service configuration data; the service information comprises at least one of a service name, a service operation, vendor information, and configuration object information; the instruction information comprises at least one of an instruction name, an instruction function, and an instruction sequence; the instruction parameter information comprises at least one of a parameter name, a parameter value rule, and a parameter type; storing the service information in the service level, storing the instruction information in the instruction level, and storing the instruction parameter information in the instruction parameter level, so as to store the sample service configuration data in the service configuration specification learning library.

[0064] The service configuration specification learning library is a learning library pre-constructed for storing service configuration specification information, and the learning library can comprise three different levels, namely a service level, an instruction level, and an instruction parameter level. The sample communication service refers to a communication service that has been initiated, and the sample service configuration data refers to service configuration data corresponding to the sample communication service. In the embodiment, when the service configuration specification learning library is constructed, a sample communication service can be collected first, for example, a communication service that has completed service configuration can be taken as a sample communication service, and service configuration data of the sample communication service can be collected as sample service configuration data.

[0065] Then, service information, instruction information, and instruction parameter information related to the sample communication service can be identified from the sample service configuration data, wherein the service information can refer to a service name, a service operation, vendor information, and configuration object information, etc., the instruction information can refer to an instruction name, an instruction function, and an instruction sequence, etc., and the instruction parameter information can refer to a parameter name, a parameter value rule, and a parameter type, etc.

[0066] Specifically, the server can identify a service name, a service operation, vendor information, and configuration object information of the sample communication service from the sample service configuration data as service information of the sample communication service, identify an instruction name, an instruction function, and an instruction sequence of the sample communication service from the sample service configuration data as instruction information of the sample communication service, and identify a parameter name, a parameter value rule, and a parameter type of the sample communication service from the sample service configuration data as instruction parameter information. Then, 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 store the sample service configuration data in the service configuration specification learning library.

[0067] In this embodiment, sample service configuration data corresponding to the sample communication service can also be collected, and service information, instruction information, and instruction parameter information corresponding to the sample communication service can be identified from the sample service configuration data, so as to store the service information, the instruction information, and the instruction parameter information in the service level, the instruction level, and the instruction parameter level respectively. In this way, the construction of the service configuration specification learning library can be implemented, and the completeness of the service configuration specification information storage can be improved.

[0068] In one embodiment, as shown in FIG. 10, step S103 can further include: Figure 4

[0069] Step S401 inputs the original service configuration scheme into the 5GC core network.

[0070] The 5GC core network refers to the core network of the fifth generation mobile communication system, which is an important component of the 5G network. In this embodiment, after generating the original service configuration scheme, the server needs to audit and verify the service configuration scheme, and the verification is implemented through the 5GC core network. Therefore, the server can first input the original service configuration scheme into the 5GC core network to implement the verification of the original service configuration scheme.

[0071] Step S402 performs 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 performs 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.

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

[0073] Specifically, the parameter verification result can be obtained by performing parameter verification on the original service configuration scheme through the 5GC core network, and the service logic verification result can be obtained by performing service configuration logic verification and service configuration integrity verification on the original service configuration scheme through the 5GC core network.

[0074] Step S403 takes the parameter verification result and the service logic verification result as the configuration scheme verification result.

[0075] Finally, the server can take the parameter verification result and the service logic verification result as the configuration scheme verification result. In this way, the parameter verification and the service logic verification on the service configuration scheme can be completed, thereby improving the completeness of the service configuration scheme verification.

[0076] ​In this embodiment, the 5GC core network can also perform parameter verification, service configuration logic verification, and service configuration integrity verification on the original service configuration scheme, so as to improve the completeness of service configuration scheme verification.

[0077] Further, step S402 can further include: collecting, by the 5GC core network, network element configuration information associated with the original service configuration scheme; and performing parameter conflict verification on the network element configuration information to obtain a parameter verification result of the original service configuration scheme.

[0078] In this embodiment, the parameter verification can be achieved by performing parameter conflict verification on the network element configuration information associated with the original service configuration scheme. Specifically, the 5GC can collect the network element configuration information, for example, by using an automatic script or tool to collect the configuration information of the network element in the 5GC core network interface. Then, parameter conflict verification can be performed according to the configuration information, so as to obtain the parameter verification result of the original service configuration scheme.

[0079] In this embodiment, the server can also collect, by the 5GC core network, network element configuration information associated with the original service configuration scheme, so as to perform parameter conflict verification using the network element configuration information to obtain a parameter verification result. In this way, parameter conflict in the service configuration scheme can be avoided.

[0080] In addition, step S402 can further include: sending, by the 5GC core network, the original service configuration scheme to a cloud network digital twin environment, simulating running of the original service configuration scheme using the cloud network digital twin environment to obtain a simulation running result of the original service configuration scheme; and performing running logic accuracy verification and running logic integrity verification on the simulation running result to obtain a service logic verification result.

[0081] The cloud network digital twin environment is a virtual space. By creating a digital model corresponding to the real world network and service, real-time monitoring, analysis, and optimization of network performance, state, and behavior can be achieved. Specifically, when performing running logic accuracy verification and running logic integrity verification on the 5GC core network, the original service configuration scheme can be sent to the cloud network digital twin environment. The cloud network digital twin environment simulates running of the original service configuration scheme to obtain a simulation running result. Then, running logic accuracy verification and running logic integrity verification are performed on the simulation running result to obtain a service logic verification result.

[0082] In this embodiment, the 5GC core network can also send the original service configuration scheme to the cloud network digital twin environment, and simulate running of the original service configuration scheme using the cloud network digital twin environment, so as to perform running logic accuracy verification and running logic integrity verification on the simulation running result. In this way, the running logic accuracy and integrity of the original service configuration scheme can be ensured.

[0083] In one embodiment, a generative AI-based business configuration scheme generation system and method are also provided, which can realize the characteristics of autonomous perception, planning and decision-making, and execution of complex tasks of the application agent, intelligent learning of configuration specification content, flexible and autonomous query of network parameter values, intelligent injection of business opening process, reduction of manual auditing workload, and improvement of auditing accuracy.

[0084] The embodiment can realize business configuration scheme generation through a generative AI-based business configuration scheme generation system as shown in Figure 5 The system includes a dialogue interaction module, a specification input and scheme analysis module, and a cloud network business agent, and the functions of each module are as follows:

[0085] Specification input and scheme analysis module: 1. Analysis: based on natural language processing algorithm to analyze configuration specification related information, mainly including business level, instruction level, and instruction parameter level label information; 2. Storage: store business tag information as long-term memory;

[0086] Dialogue interaction module: understand and confirm business requirements, and store interaction information as short-term memory;

[0087] Cloud network business agent: the components of the agent are memory + planning + perception + action, and the LangChain framework is used to create the agent, corresponding to the following modules;

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

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

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

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

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

[0093] As shown in Figure 6 The process of the above system to realize configuration scheme generation can include the following steps:

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

[0095] Analyze the business configuration specification learning library of the device telecommunication, and the learning library mainly includes three levels, business level, instruction level, and instruction parameter level.

[0096] The business level includes the "business name" tag, the "business operation" tag, the "manufacturer" tag, the "configuration object" tag, and the like information;

[0097] The instruction level includes an instruction name, an instruction function tag, an instruction tag, and an instruction sequence tag. The instruction function tag mainly marks the function of the instruction, and the instruction sequence tag mainly marks the execution dependency sequence under a certain configuration business;

[0098] The instruction parameter level indicates the meaning of the instruction parameter, including a parameter name, a parameter value rule, and a parameter type.

[0099] And store as long-term memory in the memory storage module.

[0100] Step two: based on the generated cloud network business agent, call the large model for planning, generate guiding words through multiple rounds of interactive dialogue, understand and confirm the business requirements such as business type, opening area, manufacturer information, etc., and store the confirmed content as short-term memory in the memory storage module.

[0101] Here, the prompt template can be converted in advance according to the historical business demand research, and based on the LangChain framework, the template and the instance information are used as the training data of the intelligent agent core planning module--the large model, to generate the business processing flow chain.

[0102] Step three: use the long short-term memory network (LSTM) to understand and confirm the business requirements and library information according to the context information, and generate the first configuration scheme by the cloud network business agent.

[0103] According to the active understanding of the configuration scheme, the tool is called for verification. For example, through 5GC to collect network element configuration information, verify whether the parameters conflict, through 5GC control to issue to the twin environment, verify whether the business configuration logic is correct and the business configuration integrity is complete.

[0104] Step four: after the verification, the information gets the final configuration scheme.

[0105] The cloud network business agent workflow can be as shown in Figure 7 .

[0106] In this embodiment, combined with the general large model and the telecom industry large model, the LangChain framework is used to have better reasoning and action ability, to form an industry vertical application intelligent agent, and to land in actual production business scenarios. Combined with natural language processing technology, the label data in the configuration scheme is automatically parsed to obtain matching information and generate an audit report, which can improve data effectiveness and optimize the process, reduce the verification cost of manual scheme issuance, and speed up the business opening online.

[0107] It should be understood that although each step in the flowchart involved in each embodiment as described above is shown in sequence according to the direction of the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless explicitly stated herein, there is no strict order limitation for the execution of these steps, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or multiple stages, which 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 sequential, but can be alternately or alternately executed with at least part of other steps or steps or stages in other steps.

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

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

[0110] The demand instruction acquisition module 801 is configured to acquire the service demand instruction matched with the service configuration scheme generation request in response to the service configuration scheme generation request triggered by the user;

[0111] The original scheme generation module 802 is configured to input the service demand instruction into the cloud network service agent constructed in advance, acquire the service demand information matched with the service demand instruction through the cloud network service agent, and generate the original service configuration scheme matched with the service configuration scheme generation request according to the service demand information and the pre-stored service configuration specification information;

[0112] The original scheme verification module 803 is configured to input the original service configuration scheme into the 5GC core network, and acquire the configuration scheme verification result obtained by the 5GC core network verifying the original service configuration scheme;

[0113] The target scheme generation module 804 is configured to take the original service configuration scheme as the target service configuration scheme for responding to the service configuration scheme generation request in the case that the configuration scheme verification result represents that the verification is passed.

[0114] In an embodiment, the cloud network service intelligent agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the original scheme generation module 802 is further configured to input the service demand instruction into the pre-trained large language model to obtain service demand information matched with the service demand instruction; and input the service demand information and the service configuration specification information into the service configuration scheme generation model to obtain an original service configuration scheme through the service configuration scheme generation model.

[0115] In an embodiment, the service demand information is represented by a service processing flow chain; the original scheme generation module 802 is further configured to input the service demand information into the cloud network service intelligent agent to obtain a pre-constructed prompt word template through the cloud network service intelligent agent; the prompt word template is constructed based on historical service demand research information; obtain a service demand parameter from the service demand instruction, input the service demand parameter into the prompt word template to obtain a target prompt word matched with the service demand instruction; the service demand parameter includes at least one of a service type, an opening area, and manufacturer information; and input the target prompt word into a large language model in the cloud network service intelligent agent to generate a service processing flow chain through the large language model.

[0116] In an embodiment, the service configuration specification information is stored in a service configuration specification learning library; the service configuration specification learning library includes a service level, an instruction level, and an instruction parameter level; the original scheme generation module 802 is further configured to obtain sample service configuration data corresponding to a sample communication service; obtain 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 a service name, a service operation, manufacturer information, and configuration object information, the instruction information includes at least one of an instruction name, an instruction function, and an instruction sequence, and the instruction parameter information includes at least one of a parameter name, a parameter value rule, and a parameter type; store the service information in the service level, store the instruction information in the instruction level, and store the instruction parameter information in the instruction parameter level to store the sample service configuration data in the service configuration specification learning library.

[0117] In an embodiment, the original scheme verification module 803 is further configured to input the original service configuration scheme into a 5GC core network; perform 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 perform 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; and take the parameter verification result and the service logic verification result as a configuration scheme verification result.

[0118] In an embodiment, the original scheme verification module 803 is further configured to collect, by the 5GC core network, network element configuration information associated with the original service configuration scheme; and perform parameter conflict verification on the network element configuration information to obtain a parameter verification result of the original service configuration scheme.

[0119] In an embodiment, the original scheme verification module 803 is further configured to send, by the 5GC core network, the original service configuration scheme to a cloud-network digital twin environment, simulate running of the original service configuration scheme by using the cloud-network digital twin environment, and obtain a simulation running result of the original service configuration scheme; and perform running logic accuracy verification and running logic integrity verification on the simulation running result to obtain a service logic verification result.

[0120] The modules in the service configuration scheme generation apparatus described above can be implemented in whole or in part by software, hardware, and combinations thereof. The modules described above can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a memory in a computer device in software form, so as to be called and executed by a processor to perform operations corresponding to the modules described above.

[0121] In an exemplary embodiment, a computer device, which can be a server, is provided, and an internal structure diagram of the computer device can be as shown in Figure 9 The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. 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. The processor of the computer device is configured 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 running of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is configured to store service demand instruction data. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to communicate with external terminals through a network connection. The computer program is executed by the processor to implement a service configuration scheme generation method.

[0122] Those skilled in the art can understand that Figure 9 the structure shown in the above

[0123] In an embodiment, a computer device is also provided, comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps in the above method embodiments when executing the computer program.

[0124] In an embodiment, a computer readable storage medium is provided, storing a computer program, and the computer program implementing the steps in the above method embodiments when executed by a processor.

[0125] In an embodiment, a computer program product is provided, comprising a computer program, and the computer program implementing 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 for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0127] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to 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. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0128] The technical features of the above embodiments can be combined in any manner. To make the description concise, all possible combinations of the technical features in the above embodiments are not described, but as long as the combinations of the technical features do not exist contradictions, they should be considered as the scope of the present application.

[0129] The above-described embodiments are merely illustrative of several embodiments of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the scope of the patent. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. A service configuration scheme generation method characterized by, The method comprises: obtaining a service demand instruction matched with the service configuration scheme generation request in response to a user-triggered service configuration scheme generation request; inputting the service demand instruction into a pre-constructed cloud network service agent, obtaining service demand information matched with the service demand instruction through the cloud network service agent, and generating an original service configuration scheme matched with the service configuration scheme generation request 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 the 5GC core network verifying the original service configuration scheme; in the case that the configuration scheme verification result represents that the verification is passed, taking the original service configuration scheme as a target service configuration scheme responding to the service configuration scheme generation request.

2. The method of claim 1, wherein, The cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; 3. The method of claim 2, wherein, the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; 4. The method of claim 1, wherein, the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model and a configuration scheme generation model; the cloud network service agent is pre-provided with a pre-trained large language model From the sample service configuration data, obtain service information, instruction information and instruction parameter information corresponding to the sample communication service; 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, and 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 that the sample service configuration data is stored in the service configuration specification learning library.

5. The method according to any one of claims 1 to 4, characterized in that, The original service configuration scheme is input into the 5GC core network, and a configuration scheme verification result obtained by the 5GC core network verifying the original service configuration scheme is obtained, including: The original service configuration scheme is input into the 5GC core network; The 5GC core network performs parameter verification on the original service configuration scheme to obtain a parameter verification result of the original service configuration scheme, and performs 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 service logic verification result are used as the configuration scheme verification result.

6. The method of claim 5, wherein, The 5GC core network performs parameter verification on the original service configuration scheme to obtain a parameter verification result of the original service configuration scheme, including: The 5GC core network collects network element configuration information associated with the original service configuration scheme; The network element configuration information is subjected to parameter conflict verification to obtain a parameter verification result of the original service configuration scheme.

7. The method of claim 5, wherein, The 5GC core network performs service configuration logic verification and service configuration integrity verification on the original service configuration scheme to obtain a service logic verification result of the original service configuration scheme, including: The 5GC core network sends the original service configuration scheme to a cloud network digital twin environment, simulates running of the original service configuration scheme by using the cloud network digital twin environment, and obtains a simulation running result of the original service configuration scheme; The simulation running result is subjected to running logic accuracy verification and running logic integrity verification to obtain the service logic verification result.

8. A service configuration scheme generating apparatus characterized by comprising: The device includes: A demand instruction acquisition module configured to, in response to a service configuration scheme generation request triggered by a user, acquire a service demand instruction matched with the service configuration scheme generation request; An original scheme generation module configured to input the service demand instruction into a pre-constructed cloud network service intelligent agent, acquire service demand information matched with the service demand instruction by using the cloud network service intelligent agent, and generate an original service configuration scheme matched with the service configuration scheme generation request according to the service demand information and pre-stored service configuration specification information. An original scheme verification module is configured to input the original service configuration scheme into a 5GC core network, and obtain a configuration scheme verification result obtained by the 5GC core network verifying the original service configuration scheme. A target scheme generation module is configured to, in a case where the configuration scheme verification result represents that the verification is passed, generate the original service configuration scheme as a target service configuration scheme in response to the service configuration scheme generation request. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The processor executes the computer program to implement the steps of the method in any one of claims 1 to 7.

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

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

Images