Data service publishing method, system and device of data middle platform and storage medium

Abstract

The application relates to the technical field of artificial intelligence, and specifically provides a data service publishing method, system and device of a data middle platform and a storage medium, which comprises the following steps: generating a service demand document based on logical relationships between business data of the data middle platform and user interaction data by using a large language model; generating a data service interface file based on a pre-constructed template according to the service demand document; and the service demand document comprising a data service type, a data service object and a data service target. The application can automatically generate a data service interface, improves the degree of automation, and shortens the development time of the service interface.

Description

Technical Field

[0001] This invention belongs to the field of artificial intelligence technology, specifically relating to a data service publishing method, system, device, and storage medium for a data platform. Background Technology

[0002] In today's data-driven era, enterprises rely on data platforms to integrate data from different sources to support business decisions. However, the data service delivery process often faces numerous challenges. Traditional methods primarily rely on manual requirements gathering, which is not only inefficient but also prone to misunderstandings, resulting in data services that fail to meet actual needs.

[0003] With the continuous advancement of artificial intelligence technology, especially the development of deep learning and natural language processing, many enterprises have begun to explore using AI to improve the efficiency and accuracy of demand analysis. Existing solutions typically focus on using AI for information extraction and pattern recognition, but they are still insufficient in how to systematically guide users to express their needs. Summary of the Invention

[0004] In view of the above-mentioned shortcomings of the prior art, the present invention provides a data service publishing method, system, device and storage medium for a data platform to solve the above-mentioned technical problems.

[0005] In a first aspect, the present invention provides a data service publishing method for a data platform, comprising: By leveraging the large language model to generate service requirement documents based on the logical relationships between business data and user interaction data from the data platform; Generate data service interface files based on pre-built templates according to the service requirements document; The service requirements document includes the data service type, the data service object, and the data service objective.

[0006] In one optional implementation, a service requirement document is generated using a large language model based on the logical relationships between business data from the data platform and user interaction data, including: Standardize the business data of the data platform to build a data dictionary containing the logical relationships between data tables; The generation of service requirement documents is broken down into multiple sub-tasks, and a chained Prompt is generated based on the multiple sub-tasks and user interaction data. The chained Prompt is input into a pre-trained large language model, which generates service requirement documents based on a data dictionary.

[0007] In one optional implementation, the business data of the data platform is standardized to construct a data dictionary containing logical relationships between data tables, including: The business data of the data platform is classified according to the preset data types. Establish data standards, assign identifiers to business data based on the data standards, and generate relationships between data tables based on the identifiers; A data dictionary is generated based on the data types and relationships between data tables. The data dictionary includes the meaning of each table's fields, data types, and relationships with other tables.

[0008] In one optional implementation, the generation of a service requirement document is decomposed into multiple subtasks, and a chained Prompt is generated based on the multiple subtasks and user interaction data, including: Set the initial prompt to an open-ended question, and the initial goal to obtain the type of data service the user needs; Obtain user feedback data on the initial prompt, extract key information from the feedback data, and generate subsequent prompts based on the key information; The algorithm uses reinforcement learning to analyze user input and feedback in real time and adjusts the prompt questioning method based on the analysis results. Based on the key information of the user feedback data corresponding to the prompt, the task of generating the service requirement document is broken down into multiple sub-tasks, each sub-task corresponding to a prompt. Arrange the Prompts according to the logical order of the subtasks to form an ordered chain; Set the instructions, background information, or constraint information for a single prompt to obtain a chain of prompts.

[0009] In an optional implementation, chained prompts are input into a pre-trained large language model, which generates service requirement documents based on a data dictionary, including: Extracting key entities from key information using named entity recognition technology; Relationship extraction techniques are used to determine the relationships between key entities based on a data dictionary; Extract the data source information corresponding to key entities; Based on the identified key entities and the relationships between them, generate business SQL statements. Using the business SQL statement, the target data is retrieved from the corresponding data source based on the data source information; The acquired target data is organized into a structured service requirement document.

[0010] In one optional implementation, a data service interface file is generated based on a pre-built template according to the service requirements document, including: Construct a data service interface template that conforms to the RESTful specification. The data service interface template includes an interface endpoint template, a request parameter template, and a response format template. Key parameters are extracted from the service requirement document using a natural language processing model; Fill the key parameters into the data service interface template; The populated data service interface template is integrated into an interface code file using a programming language, and an interface description file conforming to the OpenAPI specification is generated at the same time.

[0011] In an optional implementation, the method further includes: Once the interface description file has passed manual review and the interface code file has passed testing, the data service interface file is published to the data platform.

[0012] Secondly, the present invention provides a data service publishing system for a data platform, comprising: The requirements elicitation module is used to generate service requirement documents by leveraging the logical relationships between business data and user interaction data based on the data platform using a large language model. The file generation module is used to generate data service interface files based on pre-built templates according to the service requirement document; The service requirements document includes the data service type, the data service object, and the data service objective.

[0013] Thirdly, a device is provided, comprising: The storage device is used to store the data service publishing program of the data platform. The processor is configured to implement the steps of the data service publishing method for the data platform as provided in the first aspect when executing the data service publishing program of the data platform.

[0014] Fourthly, a computer-readable storage medium is provided, on which a data service publishing program for a data platform is stored, wherein when the data service publishing program for the data platform is executed by a processor, the steps of the data service publishing method for the data platform provided in the first aspect are implemented.

[0015] The beneficial effects of the present invention are that the data service publishing method, system, device and storage medium of the data platform provided by the present invention generate service requirement documents in the form of dialogue, and automatically generate data service interfaces based on the requirement documents and pre-built templates using artificial intelligence models, thereby improving the degree of automation and shortening the development time of service interfaces.

[0016] Furthermore, the design principle of this invention is reliable, the structure is simple, and it has a very wide range of application prospects. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic flowchart of a method according to an embodiment of the present invention.

[0019] Figure 2 This is a schematic diagram illustrating the principle of a method according to an embodiment of the present invention.

[0020] Figure 3 This is a schematic block diagram of a system according to an embodiment of the present invention.

[0021] Figure 4 This is a schematic diagram of the structure of a device provided in an embodiment of the present invention. Detailed Implementation

[0022] To enable those skilled in the art to better understand the technical solutions of this invention, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this invention.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0024] The key terms used in this invention will be explained below.

[0025] In large AI models, the primary function of a prompt is to provide the AI ​​model with contextual information about the input and the parameters it provides.

[0026] Large Language Models (LLMs) are deep learning models trained on massive amounts of text data, enabling them to generate natural language text or understand the meaning of language text. These models can provide in-depth knowledge and language production on a wide range of topics through training on large datasets. The core idea is to learn patterns and structures of natural language through large-scale unsupervised training, mimicking human language cognition and generation processes to some extent.

[0027] Natural Language Processing (NLP) is an important research direction in the field of artificial intelligence. It integrates knowledge from multiple disciplines such as linguistics, computer science, machine learning, mathematics, and cognitive psychology. It is an interdisciplinary field that combines computer science, artificial intelligence, and linguistics, encompassing two main aspects: natural language understanding and natural language generation. Its research content includes multiple levels such as characters, words, phrases, sentences, paragraphs, and texts, serving as a bridge between machine language and human language. Its aim is to enable machines to understand, interpret, and generate human language, achieving effective communication between humans and machines, and enabling computers to perform tasks such as language translation, sentiment analysis, and text summarization.

[0028] The data service publishing method of the data platform provided in this embodiment of the invention is executed by a computer device, and correspondingly, the data service publishing system of the data platform runs on the computer device.

[0029] Figure 1 This is a schematic flowchart illustrating a method according to an embodiment of the present invention. Wherein, Figure 1 The executing entity can be a data service publishing system of a data platform. Depending on different needs, the order of the steps in this flowchart can be changed, and some can be omitted.

[0030] like Figure 1 As shown, the method includes: S1. Using a large language model, based on the logical relationships between business data in the data middle platform and user interaction data, a service requirement document is generated. The service requirement document includes data service type, data service object, and data service objective.

[0031] The `generate_service_requirement_doc` function is used to send a Prompt containing business logic and user interaction data to the GPT-3.5-turbo model to obtain the generated service requirement document.

[0032] S2 generates data service interface files based on a pre-built template according to the service requirements document.

[0033] The generate_data_service_interface_file function is used to read a pre-built template file and fill in the placeholders in the template according to the content of the service requirements document.

[0034] Finally, the populated content is written into the new data service interface file.

[0035] In one embodiment of the present invention, based on step S1, the following will provide a possible embodiment and describe its specific implementation in a non-limiting manner.

[0036] S101. Standardize the business data of the data platform to build a data dictionary containing the logical relationships of data tables.

[0037] (1) Classify the business data of the data platform according to the preset data types: First, clarify the preset data types, which can be divided into structured data (such as tabular data in relational databases), semi-structured data (such as JSON and XML format data), and unstructured data (such as text files, images, audio, etc.).

[0038] Structured data can be further subdivided according to business areas, such as customer data, product data, order data, and financial data.

[0039] For semi-structured and unstructured data, they are classified according to their source and purpose. For example, user feedback text is classified as customer-related data, and product images are classified as product-related data.

[0040] (2) Establish data standards, assign identifiers to business data based on the data standards, and generate relationships between data tables based on the identifiers: Establish data format standards, such as unifying the date format as "YYYY-MM-DD" and the telephone number format as "1 [3 - 9]\d {9}", etc.

[0041] Define data encoding rules, such as using UTF-8 encoding, and adopt a unified encoding system for specific business codes.

[0042] Establish data quality standards, including the accuracy, completeness, and consistency of the data. For example, stipulate that customer names cannot be empty and order amounts must be positive numbers.

[0043] Assign a unique identifier to each business data entity (such as customer, product, order, etc.). For example, for the customer table, use the prefix "CUST_" followed by an 8-digit serial number as the customer ID; for the product table, use the prefix "PROD_" followed by a 6-digit alphanumeric combination as the product ID.

[0044] Ensure the uniqueness and stability of identifiers throughout the entire data platform, avoiding duplication or conflicts.

[0045] Based on business logic and data sharing requirements, determine the relationship methods between data tables. For example, the order table and the customer table are linked by customer ID, and the order table and the product table are linked by product ID.

[0046] Use foreign key constraints to establish and maintain these relationships, ensuring data consistency and integrity. For example, add customer ID and product ID as foreign keys to the order table, referencing the corresponding primary keys in the customer and product tables, respectively.

[0047] (3) Generate a data dictionary based on the data types and relationships between data tables. The data dictionary includes the meaning of each table's fields, data types, and relationships with other tables. Create a data dictionary document and record detailed information for each table in tabular form.

[0048] For each table, record its basic information such as table name, brief description, and business domain.

[0049] For each field in the table, record information such as field name, field meaning, data type (e.g., integer, string, date), whether it is required, and default value.

[0050] Clearly define the relationships between each table and other tables, and record the related fields and relationship types (e.g., one-to-one, one-to-many, many-to-many). For example, the customer table and the order table have a one-to-many relationship, linked by customer ID; the order table and the product table also have a one-to-many relationship, linked by product ID.

[0051] S102. Decompose the generation of service requirement documents into multiple sub-tasks, and generate a chained Prompt based on the multiple sub-tasks and user interaction data; (1) Set the initial prompt to an open-ended question, and the initial goal is to obtain the type of data service the user needs: Design a clear, concise, and guiding initial prompt, such as: "What type of data services do you want to obtain from the data platform? For example, query, analysis, statistics, or other types of data services?" Ensure that the question stimulates user thinking and provides valuable feedback, while not limiting the scope of user responses.

[0052] (2) Obtain user feedback data on the initial prompt, extract key information from the feedback data, and generate subsequent prompts based on the key information: Obtain feedback data: Receive user responses to the initial prompt through a user interface (such as a web form, chat window, etc.).

[0053] Extracting key information: Using natural language processing techniques, such as lexical analysis and syntactic analysis, key information is extracted from user feedback. For example, if a user answers "I want to analyze sales data from the past year," key information such as "analyze," "past year," and "sales data" is extracted.

[0054] Generate follow-up prompts: Based on the extracted key information, generate more targeted follow-up prompts. For example, based on the above answer, it could generate "What aspects of sales data would you like analyzed? Sales revenue, sales volume, or sales trends, etc." (3) Use reinforcement learning algorithms to analyze user input and feedback in real time, and adjust the prompt questioning method based on the analysis results: Establish a reinforcement learning model whose input is user input and feedback, and whose output is suggestions for adjusting the way questions are asked.

[0055] Define a reward function that rewards users based on the quality of their feedback and its relevance to the goal. For example, a higher reward is given if the user provides more detailed and specific information about their needs; a lower reward is given if the user's feedback is vague or deviates from the goal.

[0056] Based on the output of the reinforcement learning model, the questioning style of subsequent prompts can be adjusted, such as changing the wording of questions or adding guiding information, in order to improve the quality and effectiveness of user feedback.

[0057] (4) Based on the key information of the user feedback data corresponding to the prompt, the task of generating the service requirement document is decomposed into multiple sub-tasks, each sub-task corresponding to a prompt: Further analysis of key information from user feedback is needed to determine the specific subtasks required to generate a service requirement document. For example, if the user requirement involves the analysis of sales data, the subtasks might include determining the time frame for the analysis, selecting the analytical metrics, and identifying the data sources.

[0058] Design a corresponding Prompt for each subtask, ensuring that each Prompt guides the user to provide the information needed to complete that subtask. For example, for a subtask that defines the analysis timeframe, the Prompt could be, "What timeframe do you want to analyze for the sales data? Is it the past month, a quarter, or a year?" (5) Arrange the Prompts according to the logical order of the subtasks to form an ordered chain: The Prompts are sorted according to the logical dependencies between subtasks. For example, first determine the time frame for the analysis, then select the metrics for analysis, and finally determine the data sources.

[0059] Ensure that each Prompt in the chain naturally leads to the next Prompt, forming a coherent and progressively deeper questioning process.

[0060] (6) Set the instructions, background information, or constraint information for a single Prompt to obtain a chained Prompt: For each prompt, clearly define its instructions so that the user knows exactly what they need to answer. For example, "Please specify the specific metrics of the sales data you wish to analyze, such as sales revenue, sales volume, profit margin, etc."

[0061] Add background or constraint information to each prompt as needed to help users better understand the problem and provide accurate answers. For example, "Due to storage limitations of the data platform, only sales data from the past three years can be provided at present. Please select the time range you wish to analyze within this range."

[0062] S103. Input the chained prompts into a pre-trained large language model, which generates service requirement documents based on a data dictionary.

[0063] (1) Extracting key entities from key information using named entity recognition technology: Input the user feedback data corresponding to the chained Prompts into the named entity recognition model. This model can be a pre-trained model based on deep learning, such as BERT or GPT.

[0064] The model identifies key entities in the text, such as data types (sales data, customer data, etc.), time (past year, last month, etc.), business objects (products, orders, etc.), and operations (analysis, queries, etc.).

[0065] The identified key entities are classified and labeled for subsequent processing.

[0066] (2) Using relation extraction techniques to determine the relationships between key entities based on the data dictionary: The extracted key entities are matched with the data dictionary, and relation extraction techniques are used to determine the relationships between the entities. For example, based on the association between the order table and the product table in the data dictionary, the association between the "order" and "product" entities is determined.

[0067] Analyze the semantic relationships between entities in the text. For example, "analyze sales data" indicates the interaction between the "analyze" operation and "sales data".

[0068] Create a relationship diagram of key entities to clearly show the connections between them.

[0069] (3) Extract the data source information corresponding to the key entities: Based on the information recorded in each table in the data dictionary, the data source corresponding to the key entity is determined. For example, if the key entity is "sales data", the data dictionary shows that it is stored in the sales order table, and the database containing that table is the data source.

[0070] Record detailed information about the data source, such as database type (MySQL, Oracle, etc.), server address, port number, database name, table name, etc.

[0071] (4) Based on the identified key entities and the relationships between them, generate business SQL statements: Based on key entities and their relationships, as well as data source information, construct SQL statements. For example, if a user needs to query sales data for the past year, involving key entities such as "Sales Orders Table" and "Time," the generated SQL statement would look like this: SELECT * FROM sales_order_table WHERE order_date>= '2023 - 01 - 01'AND order_date<= '2023 - 12 - 31'; Add necessary filtering conditions, aggregate functions, join operations, etc., according to specific needs to ensure that the SQL statement can accurately obtain the required data.

[0072] (5) Using the business SQL statement, retrieve the target data from the corresponding data source based on the data source information: Use a database connection tool (such as Python's pymysql library for connecting to MySQL databases) to establish a connection to the database based on the data source information.

[0073] Execute the generated SQL statement to retrieve the target data from the database.

[0074] Handle potential exceptions, such as database connection failures and SQL statement execution errors, and provide corresponding error messages and solutions.

[0075] (6) Organize the acquired target data into a structured service requirement document: The retrieved target data is cleaned and preprocessed to ensure its accuracy and consistency.

[0076] Depending on the requirements, the data can be organized into a specific structure, such as tables or JSON format.

[0077] The service requirements document should describe in detail the source, processing, structure, and meaning of the data, as well as its correspondence with user needs.

[0078] In one embodiment of the present invention, based on step S2, the following will provide a possible embodiment and describe its specific implementation in a non-limiting manner.

[0079] S201. Construct a data service interface template that conforms to the RESTful specification. The data service interface template includes an interface endpoint template, a request parameter template, and a response format template.

[0080] Interface endpoint template: Defines the basic URL structure of the interface, for example, using ` / api / v1` as the version prefix followed by the specific resource path. Define different endpoints for each resource corresponding to different HTTP methods (GET, POST, PUT, DELETE, etc.). For example, for an interface to retrieve sales data, the endpoint for the GET method could be ` / api / v1 / sales_data`; for an interface to create a new order, the endpoint for the POST method could be ` / api / v1 / orders`. Define the basic description of the endpoint in the template, including functional descriptions, and the general format of requests and responses.

[0081] Request parameter templates: Define the type (e.g., string, integer, date), name, required status, and default value of request parameters based on different endpoints and business requirements. For complex request parameters, such as objects containing multiple fields, JSON format can be used for definition. For example, request parameters for creating an order might include order amount, order date, customer ID, etc., and the template can be defined as: { "order_amount": { "type": "number", "required": true, "description": "order amount"}, "order_date": { "type": "string", "format": "YYYY- MM - DD", "required": true, "description": "order date"}, "customer_id": { "type": "string", "required": true, "description": "customer ID"}}.

[0082] Response format template: Define the response status code, data structure, and format according to different endpoints and business requirements. For successful responses, define the returned data fields, their types, and meanings. For example, a successful response retrieving sales data might include fields such as total sales and sales details. A template example is as follows: { "status": { "type": "string", "description": "Response status, such as 'success' or 'error'"}, "total_sales": { "type": "number", "description": "Total sales"}, "sales_details": { "type": "array", "items": { "type": "object", "properties": { "product_id": { "type": "string", "description": "Product ID"},"quantity": { "type": "number", "description": "Sales quantity"}, "price": { "type": "number", "description": "Product unit price"}}}, "description": "Sales details"}}.

[0083] For error responses, define common error codes and error message formats. For example: { "status": "error", "error_code": { "type": "string", "description":"Error code, such as '400', indicates an error in the request parameters"}, "error_message": { "type": "string", "description": "Detailed error information"}}.

[0084] S202. Extract key parameters from the service requirement document using a natural language processing model.

[0085] Select a pre-trained BERT model and configure and optimize it appropriately based on the characteristics of the service requirement document and the task requirements. Fine-tune the model using labeled sample data to improve its ability to extract key parameters. The labeled sample data includes the text of the service requirement document and annotations on the location and type of key parameters within it.

[0086] The service requirement document is input into the BERT model. The model analyzes the text to identify key parameters, such as API endpoints, request parameters, and response formats. These extracted key parameters are then organized and categorized to ensure their accuracy and completeness.

[0087] S203. Fill the key parameters into the data service interface template.

[0088] (1) Interface endpoint population: Based on the extracted key parameters regarding the interface endpoint, such as resource path and HTTP method, populate the interface endpoint template.

[0089] Ensure that the populated interface endpoints conform to RESTful specifications and business requirements.

[0090] (2) Request parameter filling: The extracted request parameter information, including parameter name, type, whether it is required, and default value, is then filled into the request parameter template.

[0091] Check whether the populated request parameters are complete, reasonable, and match the functionality of the interface endpoint.

[0092] (3) Response format filling: Based on the extracted key parameters regarding the response format, such as status code, data fields and their types, the response format template is populated.

[0093] Ensure that the format of the filled response accurately reflects the requirements for the response in the service requirements document.

[0094] S204. Use a programming language to integrate the populated data service interface template into an interface code file, and at the same time generate an interface description file that conforms to the OpenAPI specification.

[0095] Based on project requirements and the team's technology stack, select appropriate programming languages ​​and frameworks to implement the data service interface. For example, use Python and the FastAPI framework, or Java and the Spring Boot framework.

[0096] Write the interface code using the selected programming language and framework, based on the populated interface endpoint template, request parameter template, and response format template.

[0097] Implement the API logic in the code, including receiving requests, validating request parameters, calling business logic processing functions, and returning responses. Ensure the API code is readable, maintainable, and secure.

[0098] Use the tools or libraries provided by the framework to generate an interface description file (usually in YAML or JSON format) that conforms to the OpenAPI specification based on the interface code.

[0099] The description file defines the interface's path, methods, request parameters, response format, and other information in detail so that other developers can understand and use the interface.

[0100] Verify the generated interface description file to ensure it complies with the OpenAPI specification.

[0101] Please refer to Figure 2 The intelligent data service publishing method includes the following steps: The first step is to establish a data service model: Because the data in the data platform is complex and interwoven, standardized business data differentiation and logical relationships between tables require a data service standard management mechanism. This standardized data service, combined with user requirements based on a prompt chain, allows for the creation of a requirement model. This module systematically standardizes and categorizes business data tables and mapping relationships by directory and theme, facilitating subsequent calls to larger models.

[0102] The second step is the requirement establishment and real-time feedback mechanism: This invention employs a pre-trained large language model, leveraging its powerful language understanding and generation capabilities to design a chained Prompt mechanism. This mechanism guides users to progressively describe their data service needs through a series of questions. The initial questions are designed as open-ended questions, with subsequent questions becoming increasingly detailed based on the user's responses. For example: Initial question: What type of data service do you hope to provide? Another question: For which specific business modules do you want data services to be provided? In-depth question: What kind of data results do you hope to obtain for this business module? … During user interaction, reinforcement learning algorithms are used to analyze user input and feedback in real time, continuously improving the accuracy of data requirements.

[0103] The third step, requirement confirmation and generation: After user input is complete, information extraction techniques are used to analyze the input and extract key information, such as data sources, functional requirements, user roles, and the final business SQL. This process involves various NLP techniques, including named entity recognition and relation extraction, to ensure that the information obtained is comprehensive and accurate. The generated structured requirements document will be presented to the user in a clear format for confirmation, ensuring that the final requirements are fully understood.

[0104] Step 4: Integrating the AI ​​Agent with standard data service products: Once the requirements are confirmed, the structured requirements document will be automatically generated into a RESTful data service API using the AI ​​Agent. The system employs a template-based approach, combining existing standard service product API design patterns to generate API documentation that includes necessary call parameters and formatting specifications.

[0105] Step 5, Review and Release: The generated data service API will be officially released after review by the development team. The review includes interface connectivity testing, security testing, and performance evaluation to ensure the generated service meets enterprise standards. Once approved, the API will be automatically published to the data platform for subsequent use and invocation.

[0106] This invention provides a flexible and efficient data service publishing solution by combining a prompt chain (Prompt), an AI Agent, and a data platform. Its main advantages include: Enhanced user experience: Publishing data service APIs via dialogue within the data platform greatly improves the user experience.

[0107] Reduced error rate: Real-time feedback and dynamic adjustment mechanisms enhance the accuracy of requirement confirmation and significantly reduce the error rate after release.

[0108] Automation and Efficiency Improvement: By automating the generation and review of APIs based on demand and standard template information, service release time is shortened, availability is improved, and enterprises can respond quickly to market changes.

[0109] Decision support: This approach not only improves the efficiency of data service delivery, but also provides a reliable data service foundation for enterprise decision support, thus facilitating digital transformation.

[0110] In some embodiments, the data service publishing system of the data platform may include multiple functional modules composed of computer program segments. The computer programs of each program segment in the data service publishing system of the data platform may be stored in the memory of a computer device and executed by at least one processor to perform (see details). Figure 1 (Description) The function of publishing data services in the data platform.

[0111] In this embodiment, the data service publishing system of the data platform can be divided into multiple functional modules according to the functions it performs, such as... Figure 3 As shown. The system's functional modules may include: a requirements acquisition module and a file generation module. The module referred to in this invention is a series of computer program segments that can be executed by at least one processor and perform a fixed function, stored in memory. In this embodiment, the functions of each module will be detailed in subsequent embodiments.

[0112] The requirements elicitation module is used to generate service requirement documents by leveraging the logical relationships between business data and user interaction data based on the data platform using a large language model. The file generation module is used to generate data service interface files based on pre-built templates according to the service requirement document; The service requirements document includes the data service type, the data service object, and the data service objective.

[0113] Figure 4 The data service publishing method for the data platform provided in this application embodiment can be applied to devices. Those skilled in the art will understand that the device structure involved in the embodiments of this invention does not constitute a limitation on the device. A device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. In the embodiments of this invention, the device includes, but is not limited to, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of this application described and / or claimed herein.

[0114] The device 400 may include a processor 410, a memory 420, and a communication unit 430. These components communicate via one or more buses. Those skilled in the art will understand that the server structure shown in the figure does not constitute a limitation of the present invention. It may be a bus topology or a star topology, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0115] The memory 420 can be used to store execution instructions of the processor 410. The memory 420 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. When the execution instructions in the memory 420 are executed by the processor 410, the device 400 is able to perform some or all of the steps in the above method embodiments.

[0116] The processor 410 serves as the control center of the storage device, connecting various parts of the electronic device via various interfaces and lines. It executes software programs and / or modules stored in the memory 420, and calls data stored in the memory to perform various functions of the electronic device and / or process data. The processor can be composed of integrated circuits (ICs), such as a single packaged IC or multiple packaged ICs with the same or different functions connected together. For example, the processor 410 may consist only of a central processing unit (CPU). In this embodiment of the invention, the CPU may have a single processing core or include multiple processing cores.

[0117] The communication unit 430 is used to establish a communication channel, enabling the storage device to communicate with other devices. It can receive user data sent by other devices or send user data to other devices.

[0118] The present invention also provides a computer storage medium, wherein the computer storage medium may store a program, which, when executed, may include some or all of the steps provided in the embodiments of the present invention. The storage medium may be a magnetic disk, an optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0119] Those skilled in the art will clearly understand that the techniques in the embodiments of the present invention can be implemented using software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solutions in the embodiments of the present invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or any other medium capable of storing program code. It includes several instructions to cause a computer device (which may be a personal computer, a server, or a second device, network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0120] The same or similar parts between the various embodiments in this specification can be referred to mutually. In particular, the device embodiments are basically similar to the method embodiments, so the description is relatively simple, and the relevant parts can be referred to the description in the method embodiments.

[0121] In the embodiments provided by this invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between systems or modules may be electrical, mechanical, or other forms.

[0122] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0123] In addition, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0124] Although the present invention has been described in detail with reference to the accompanying drawings and preferred embodiments, the present invention is not limited thereto. Various equivalent modifications or substitutions can be made to the embodiments of the present invention by those skilled in the art without departing from the spirit and essence of the invention, and such modifications or substitutions should all be within the scope of the present invention. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should also be covered within the protection scope of the present invention.

Claims

1. A method for publishing data services on a data platform, characterized in that, include: By leveraging the large language model to generate service requirement documents based on the logical relationships between business data and user interaction data from the data platform; Generate data service interface files based on pre-built templates according to the service requirements document; The service requirements document includes the data service type, the data service object, and the data service objective; Specifically, by utilizing a large language model based on the logical relationships between business data from the data platform and user interaction data, service requirement documents are generated, including: Standardize the business data of the data platform to build a data dictionary containing the logical relationships between data tables; The generation of service requirement documents is broken down into multiple sub-tasks, and a chained Prompt is generated based on the multiple sub-tasks and user interaction data. The chained prompts are input into a pre-trained large language model, which generates service requirement documents based on a data dictionary. The chained prompts are input into a pre-trained large language model, which generates service requirement documents based on a data dictionary, including: Extracting key entities from key information using named entity recognition technology; Relationship extraction techniques are used to determine the relationships between key entities based on a data dictionary; Extract the data source information corresponding to key entities; Based on the identified key entities and the relationships between them, generate business SQL statements. Using the business SQL statement, the target data is retrieved from the corresponding data source based on the data source information; The acquired target data is organized into a structured service requirement document.

2. The method according to claim 1, characterized in that, The business data of the data platform is standardized to construct a data dictionary containing the logical relationships between data tables, including: The business data of the data platform is classified according to the preset data types. Establish data standards, assign identifiers to business data based on the data standards, and generate relationships between data tables based on the identifiers; A data dictionary is generated based on the data types and relationships between data tables. The data dictionary includes the meaning of each table's fields, data types, and relationships with other tables.

3. The method according to claim 1, characterized in that, The generation of service requirement documents is broken down into multiple sub-tasks, and a chained Prompt is generated based on these sub-tasks and user interaction data, including: Set the initial prompt to an open-ended question, and the initial goal to obtain the type of data service the user needs; Obtain user feedback data on the initial prompt, extract key information from the feedback data, and generate subsequent prompts based on the key information; The algorithm uses reinforcement learning to analyze user input and feedback in real time and adjusts the prompt questioning method based on the analysis results. Based on the key information of the user feedback data corresponding to the prompt, the task of generating the service requirement document is broken down into multiple sub-tasks, each sub-task corresponding to a prompt. Arrange the Prompts according to the logical order of the subtasks to form an ordered chain; Set the instructions, background information, or constraint information for a single prompt to obtain a chain of prompts.

4. The method according to claim 1, characterized in that, Generate data service interface files based on pre-built templates from the service requirements document, including: Construct a data service interface template that conforms to the RESTful specification. The data service interface template includes an interface endpoint template, a request parameter template, and a response format template. Key parameters are extracted from the service requirement document using a natural language processing model; Fill the key parameters into the data service interface template; The populated data service interface template is integrated into an interface code file using a programming language, and an interface description file conforming to the OpenAPI specification is generated at the same time.

5. The method according to claim 4, characterized in that, The method further includes: Once the interface description file has passed manual review and the interface code file has passed testing, the data service interface file is published to the data platform.

6. A data service publishing system for a data platform, characterized in that, include: The requirements elicitation module is used to generate service requirement documents by leveraging the logical relationships between business data and user interaction data based on the data platform using a large language model. The file generation module is used to generate data service interface files based on pre-built templates according to the service requirement document; The service requirements document includes the data service type, the data service object, and the data service objective; Specifically, by utilizing a large language model based on the logical relationships between business data from the data platform and user interaction data, service requirement documents are generated, including: Standardize the business data of the data platform to build a data dictionary containing the logical relationships between data tables; The generation of service requirement documents is broken down into multiple sub-tasks, and a chained Prompt is generated based on the multiple sub-tasks and user interaction data. The chained prompts are input into a pre-trained large language model, which generates service requirement documents based on a data dictionary. The chained prompts are input into a pre-trained large language model, which generates service requirement documents based on a data dictionary, including: Extracting key entities from key information using named entity recognition technology; Relationship extraction techniques are used to determine the relationships between key entities based on a data dictionary; Extract the data source information corresponding to key entities; Based on the identified key entities and the relationships between them, generate business SQL statements. Using the business SQL statement, the target data is retrieved from the corresponding data source based on the data source information; The acquired target data is organized into a structured service requirement document.

7. A data service publishing device for a data platform, characterized in that, include: The storage device is used to store the data service publishing program of the data platform. A processor is configured to implement the steps of the data service publishing method for the data platform as described in any one of claims 1-5 when executing the data service publishing program of the data platform.

8. A computer-readable storage medium storing a computer program, characterized in that, The readable storage medium stores a data service publishing program for the data platform, which, when executed by a processor, implements the steps of the data service publishing method for the data platform as described in any one of claims 1-5.

Images