Automatic service orchestration method, system and device and storage medium

Abstract

The invention discloses an automatic service orchestration method, system and device and a storage medium, belongs to the technical field of computer science and information, and solves the technical problem that when an existing system processes complex queries and decisions, manual intervention is often needed, and the automation level is limited. The method comprises the steps that an intelligent agent obtains natural language query information input by a user and sends the natural language query information to the intelligent agent; preprocessing the natural language query information through the intelligent agent, wherein the preprocessing comprises word segmentation, part-of-speech tagging and syntactic analysis; the intent of the user is understood through the intelligent agent according to the preprocessing result, and a corresponding service process is planned in combination with a business rule and historical data; evaluating different service process options through the intelligent agent, making a decision, selecting an optimal scheme, and determining a specific execution path of the service process; starting to execute the service process through the intelligent agent according to the specific execution path; and confirming that all the steps of service orchestration are successfully executed through the intelligent agent.

Description

Technical Field

[0001] The present invention relates to the field of computer science and information technology, and more specifically, to a method, system, device and storage medium for automated service orchestration. Background Art

[0002] With the development of technology, automated service orchestration plays an increasingly important role in improving enterprise operational efficiency and reducing costs. Existing service orchestration systems usually rely on predefined rules and processes or implement service orchestration through hard coding, and developers must complete the corresponding orchestration work. They are inefficient, costly, lack sufficient flexibility and intelligence, and are difficult to adapt to rapidly changing business needs and environments. In addition, existing systems often require manual intervention when processing complex queries and decisions, which limits the level of automation. Summary of the invention

[0003] The technical problem to be solved by the present invention is to address the above-mentioned deficiencies in the prior art. One purpose of the present invention is to provide a method for automated service orchestration to improve the response speed and quality of services, reduce manual intervention, and enhance the adaptability and intelligence level of the system.

[0004] A second objective of the present invention is to provide a system for automated service orchestration.

[0005] A third object of the present invention is to provide a computer device.

[0006] A fourth objective of the present invention is to provide a computer storage medium.

[0007] In order to achieve the above-mentioned first objective, the present invention provides a method for automated service orchestration, including an agent, and the method comprises the following steps:

[0008] Step 1. Obtain natural language query information input by a user through a graphical user interface or an application programming interface, and send it to the agent;

[0009] Step 2. Preprocessing the natural language query information by the agent, the preprocessing including word segmentation, part-of-speech tagging and syntactic analysis;

[0010] Step 3. The agent understands the user's intention based on the preprocessing results, and plans the corresponding service process in combination with business rules and historical data;

[0011] Step 4. The agent evaluates different service process options and makes decisions, selects the best solution, and determines the specific execution path of the service process;

[0012] Step 5. The agent starts executing the service process according to the specific execution path;

[0013] Step 6. Confirm through the agent that all steps of the service orchestration have been successfully executed.

[0014] As a further improvement, the method further includes step 7, wherein the intelligent agent collects user feedback on the service orchestration results for system optimization and improvement of service orchestration.

[0015] Furthermore, step 3 includes:

[0016] Step 31. The agent analyzes the user's query intention using natural language processing technology based on the preprocessing results. If the analysis is successful, exit; otherwise, execute step 32;

[0017] Step 32. The agent constructs the input prompt words of the large model according to the preprocessing results, and submits the constructed prompt words and related data to the large model for processing;

[0018] Step 33. The intelligent agent receives the output results of the large model, and performs analysis, post-processing and verification to obtain the user's query intention.

[0019] Furthermore, in step 4, during the decision-making process, the agent considers multiple factors in combination with historical data, including user preferences, business priorities, resource availability, and cost-benefit analysis.

[0020] Furthermore, in step 5, the agent calls an internal or external API to start a service process, including calling a database service to retrieve information, calling a payment gateway to process transactions, and calling a logistics service to arrange delivery.

[0021] Further, in step 5, the agent identifies tasks that require support from external tools and calls the external tools through an API or service interface.

[0022] Furthermore, in step 5, during the entire service orchestration process, the agent monitors and handles abnormal situations. The agent sets up an exception capture and processing mechanism at each step, including exception detection, logging, and error notification. Once an exception is detected, the agent records the error information and takes recovery measures based on the error type. The recovery measures include retrying, rolling back, and notifying the user.

[0023] In order to achieve the above-mentioned second objective, the present invention provides a system for automated service orchestration, comprising:

[0024] An acquisition module, used for acquiring natural language query information input by a user through a graphical user interface or an application programming interface, and sending the information to the agent;

[0025] A preprocessing module, used to preprocess the natural language query information through the agent, the preprocessing including word segmentation, part-of-speech tagging and syntactic analysis;

[0026] A planning module, used to understand the user's intention according to the preprocessing results through the agent, and plan the corresponding service process in combination with business rules and historical data;

[0027] A decision-making module, used to evaluate different service process options and make decisions through the agent, select the best solution, and determine the specific execution path of the service process;

[0028] An execution module, used to start executing the service process according to the specific execution path through the agent;

[0029] A confirmation module is used to confirm through the agent that all steps of the service orchestration have been successfully executed.

[0030] In order to achieve the third objective above, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned method of automated service orchestration when executing the computer program.

[0031] In order to achieve the fourth objective above, the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for automated service orchestration is implemented.

[0032] Beneficial Effects

[0033] Compared with the prior art, the present invention has the following advantages:

[0034] 1. The present invention can improve user experience and enhance user satisfaction.

[0035] 2. The present invention can reduce the configuration of predefined rules and processes, reduce the amount of hard-coded code, improve quality, reduce costs, and increase efficiency.

[0036] 3. The present invention can improve service response speed and quality, reduce waiting time, reduce manual intervention, improve operational efficiency, and reduce service operating costs.

[0037] 4. The present invention can enhance the adaptability and intelligence level of the system, better meet user needs, increase the strength of enterprise capability opening, and make it possible to realize enterprise data assets. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0039] The present invention will be further described below with reference to the specific embodiments in the accompanying drawings.

[0040] See also Figure 1 , a method for automated service orchestration, including an intelligent agent (i.e., an AI Agent), the method comprising the following steps 1 to 6:

[0041] Step 1. Obtain natural language query information input by the user through the graphical user interface GUI or application programming interface API, and send it to the intelligent agent.

[0042] That is, users send natural language queries or requests through a graphical user interface GUI or an application programming interface API. The GUI can be a web page, mobile application or desktop software that provides a text box for user input. The API allows other software systems to interact with the system through HTTP requests. Speech recognition function can also be provided as an optional function to convert the user's voice input into text format to enhance the user experience. The speech recognition module needs to be trained in advance to recognize the voice characteristics and dialects of different users, so as to achieve multi-language support capabilities and be able to receive and process input in different languages ​​according to user preferences or system settings.

[0043] Step 2: Preprocess the natural language query information through the intelligent agent, where the preprocessing includes word segmentation, part-of-speech tagging and syntactic analysis.

[0044] The agent can also listen to user input through a preset interface. For a GUI, this usually involves an event listener, which is triggered when the user submits a form. For an API, the agent receives HTTP requests through server-side logic. The received text is first preprocessed, including removing noise characters, standardizing text formats, identifying languages, etc. The preprocessing step is critical to improving the accuracy of subsequent processing. The agent uses natural language processing (NLP) technology to perform word segmentation, part-of-speech tagging, and syntactic analysis on the input. Word segmentation is the decomposition of continuous text into meaningful units (such as words and phrases). Part-of-speech tagging determines the grammatical category of each word (such as noun, verb). Syntactic analysis constructs the grammatical structure of a sentence, such as identifying the subject, predicate, and object.

[0045] Step 3. The intelligent agent understands the user's intention based on the preprocessing results, and plans the corresponding service process in combination with business rules and historical data.

[0046] In step 3 include:

[0047] Step 31. The agent further analyzes the user's query intention using natural language processing (NLP) technology based on the preprocessing results. If the analysis is successful, exit; otherwise, execute step 32;

[0048] Step 32. The agent constructs the input prompt words of the large model LLM according to the preprocessing results, and submits the constructed prompt words and related data to the large model LLM for processing;

[0049] Step 33. The intelligent agent receives the output results of the large model LLM, and performs analysis, post-processing and verification to obtain the user's query intention.

[0050] Analyzing the user's query intent involves intent recognition and entity extraction. Intent recognition determines the type of operation the user wants to perform, such as product query, reservation, payment, or comment. Entity extraction identifies specific information related to the user's intent, such as date, location, or product name. The agent plans the steps of the service process based on the identified intent and entities, combined with business rules and historical data. Business rules define the basic logic of the service process, such as the user's identity must be verified before payment can be processed. Historical data provides a reference for user preferences and behavior patterns, helping the agent make more personalized plans.

[0051] In the process of the agent calling the large model LLM to handle complex natural language tasks, the agent constructing the input prompt words of the LLM is a key step because it directly affects the output quality of the LLM. The prompt words need to be carefully designed to guide the LLM to generate the most relevant answers. This involves providing contextual information, a clear description of the problem, and any necessary constraints. The agent submits the constructed prompt words and data to the LLM for processing. This process involves communication with a remote server, so network latency and reliability issues also need to be considered. The agent needs to process the output of the LLM, which includes parsing, post-processing, and verification. Parsing is the process of converting the text generated by the LLM into structured data. Post-processing involves eliminating ambiguity, enhancing readability, or formatting the output. Verification ensures that the output of the LLM meets the expected standards and quality.

[0052] The process of the large model processing the tasks submitted by the agent and generating responses is as follows: LLM receives the input of the agent and uses deep learning technology for semantic understanding and information retrieval. This involves complex algorithms such as attention mechanisms, memory networks, or reinforcement learning. LLM generates natural language responses to meet user needs. This process needs to consider the user's query intent, contextual information, and business rules. LLM also needs to consider the coherence, relevance, and accuracy of the generated text. The output of LLM needs to be further optimized and adjusted according to business needs to adapt to specific application scenarios. For example, when generating product recommendations, LLM needs to consider the user's purchase history and preferences.

[0053] The agent parses the output of the LLM and extracts the necessary information and instructions. This may involve text analysis, information extraction, and instruction recognition. The agent performs service operations, such as calling business processes, updating databases, sending notifications, etc. This requires the agent to have the ability to interact with various services and systems, including calling APIs, operating databases, and processing files. The agent also needs to handle problems that may arise during execution, such as service unavailability, inconsistent data, or failed operations. This involves error handling and exception management, such as retry mechanisms, rollback operations, and error logging.

[0054] Step 4. The agent evaluates different service process options and makes decisions, selects the best solution, and determines the specific execution path of the service process.

[0055] The decision-making process involves complex algorithms such as decision trees, rule engines, or machine learning models. In the decision-making process, the agent considers multiple factors, including user preferences, business priorities, resource availability, cost-benefit analysis, etc. For example, if the user prefers fast service, the agent may choose a more expensive but faster processing path. The agent also needs to consider abnormal situations and risk management. For example, when processing payments, the agent needs to evaluate the security of the transaction and prevent fraud.

[0056] Step 5. Start executing the service process through the agent according to the specific execution path.

[0057] The agent calls an internal or external API to start the service process. This includes calling a database service to retrieve information, calling a payment gateway to process a transaction, and calling a logistics service to arrange delivery. During the execution process, the agent needs to monitor the status of the service process in real time to ensure that each step is carried out as planned. This involves process management technologies such as workflow engines or task queue systems. The agent also needs to deal with concurrency and transaction management issues. For example, when processing requests from multiple users, the agent needs to ensure the consistency and integrity of the data. In scenarios involving monetary transactions, the agent needs to ensure the atomicity of the transaction, that is, all operations are either all successful or all failed.

[0058] In certain situations, the agent calls external tools or services to complete specific tasks. The agent identifies tasks that require external tool support, such as payment processing, logistics tracking, or data analysis. This involves a deep understanding of business needs and an assessment of external service capabilities. The agent calls external tools through an API or service interface. The agent needs to have the ability to communicate with external systems, including handling authentication, authorization, and data exchange. The agent needs to process the responses and results of the external tools. This series of processes involves data parsing, parameter verification, result verification, and triggering of subsequent operations.

[0059] Throughout the service orchestration process, the agent monitors and handles exceptions. The agent sets up exception capture and handling mechanisms at each step. This involves exception detection, logging, and error notification. Once an exception is detected, the agent records the error information and takes recovery measures based on the error type, such as retrying, rolling back, or notifying the user. This requires the agent to have flexible error handling strategies and strong self-recovery capabilities. For unrecoverable errors, the agent needs to notify the user and provide further support, so it is necessary to provide users with friendly prompts in the user interface, the generation of error reports, and guidance for user support.

[0060] Step 6. Confirm through the agent that all steps of the service orchestration have been successfully executed.

[0061] The agent verifies the service results to ensure that they meet user needs. The agent needs to verify the results, evaluate the quality, and collect user feedback. The agent also needs to record the logs of service orchestration for subsequent analysis and optimization. This requires the agent to have log management and data analysis capabilities.

[0062] As a further improvement, the method further includes step 7, collecting user feedback on the service orchestration results through the intelligent agent for system optimization and improvement of service orchestration.

[0063] Users can provide feedback through the interface, and the agent collects and records user satisfaction and suggestions. This involves the design of the user interface, the implementation of the feedback mechanism, and the strategy of data collection. The agent has the ability of data analysis, pattern recognition, and decision support. The agent analyzes user feedback for system optimization and improvement of service orchestration.

[0064] A system for automated service orchestration, comprising:

[0065] An acquisition module, used for acquiring natural language query information input by a user through a graphical user interface GUI or an application programming interface API, and sending the information to the intelligent agent;

[0066] A preprocessing module, used to preprocess the natural language query information through the agent, the preprocessing including word segmentation, part-of-speech tagging and syntactic analysis;

[0067] A planning module, used to understand the user's intention according to the preprocessing results through the agent, and plan the corresponding service process in combination with business rules and historical data;

[0068] A decision-making module, used to evaluate different service process options and make decisions through the agent, select the best solution, and determine the specific execution path of the service process;

[0069] An execution module, used to start executing the service process according to the specific execution path through the agent;

[0070] A confirmation module is used to confirm through the agent that all steps of the service orchestration have been successfully executed.

[0071] A computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the above-mentioned method of automatic service orchestration is implemented.

[0072] A computer-readable storage medium stores a computer program, which implements the above-mentioned method of automatic service orchestration when executed by a processor.

[0073] The above are only preferred embodiments of the present invention. It should be pointed out that for those skilled in the art, several modifications and improvements can be made without departing from the structure of the present invention, which will not affect the effect of the implementation of the present invention and the practicality of the patent.

Claims

1. A method for automated service orchestration, comprising an agent, characterized in that: The method comprises the following steps: Step 1. Obtain natural language query information input by a user through a graphical user interface (GUI) or an application programming interface (API), and send it to the intelligent agent; Step 2. Preprocessing the natural language query information by the agent, the preprocessing including word segmentation, part-of-speech tagging and syntactic analysis; Step 3. The agent understands the user's intention based on the preprocessing results, and plans the corresponding service process in combination with business rules and historical data; Step 4. The agent evaluates different service process options and makes decisions, selects the best solution, and determines the specific execution path of the service process; Step 5. The agent starts executing the service process according to the specific execution path; Step 6. Confirm through the agent that all steps of the service orchestration have been successfully executed.

2. The method for automated service orchestration according to claim 1, characterized in that: The method also includes step 7, collecting user feedback on the service orchestration results through the intelligent agent for system optimization and improvement of service orchestration.

3. The method for automated service orchestration according to claim 1, characterized in that: In step 3 include: Step 31. The agent analyzes the user's query intention using natural language processing (NLP) technology based on the preprocessing results. If the analysis is successful, exit; otherwise, execute step 32; Step 32. The agent constructs the input prompt words of the large model (LLM) according to the preprocessing results, and submits the constructed prompt words and related data to the large model (LLM) for processing; Step 33. The intelligent agent receives the output result of the large model (LLM), and performs analysis, post-processing and verification to obtain the user's query intention.

4. The method for automated service orchestration according to claim 1, characterized in that: In step 4, during the decision-making process, the agent considers multiple factors in combination with historical data, including user preferences, business priorities, resource availability, and cost-benefit analysis.

5. The method for automated service orchestration according to claim 1, characterized in that: In step 5, the agent calls an internal or external API to start the service process, including calling a database service to retrieve information, calling a payment gateway to process transactions, and calling a logistics service to arrange delivery.

6. The method for automated service orchestration according to claim 1, characterized in that: In step 5, the agent identifies tasks that require support from external tools and calls the external tools through an API or service interface.

7. The method for automated service orchestration according to claim 1, characterized in that: In step 5, during the entire service orchestration process, the agent monitors and handles abnormal situations. The agent sets up an exception capture and processing mechanism at each step, including exception detection, logging, and error notification. Once an exception is detected, the agent records the error information and takes recovery measures based on the error type. The recovery measures include retrying, rolling back, and notifying the user.

8. A system for automated service orchestration, characterized in that: include: An acquisition module, used for acquiring natural language query information input by a user through a graphical user interface (GUI) or an application programming interface (API), and sending the natural language query information to the agent; A preprocessing module, used to preprocess the natural language query information through the agent, the preprocessing including word segmentation, part-of-speech tagging and syntactic analysis; A planning module, used to understand the user's intention according to the preprocessing results through the agent, and plan the corresponding service process in combination with business rules and historical data; A decision-making module, used to evaluate different service process options and make decisions through the agent, select the best solution, and determine the specific execution path of the service process; An execution module, used to start executing the service process according to the specific execution path through the agent; A confirmation module is used to confirm through the agent that all steps of the service orchestration have been successfully executed.

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 method for automated service orchestration described in any one of claims 1 to 7 is 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 method for automated service orchestration described in any one of claims 1 to 7 is implemented.

Images