Business query language generation method, system, equipment and medium
By receiving natural language query statements and optimizing the business entity compression structure, combining permission management, and generating business query languages, the problems of complex queries and permission management are solved, and efficient and secure natural language to business query language conversion is achieved. Improved conversion accuracy and efficiency.
Patent Information
- Application Number
- CN202411147500.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-20
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-08-20
AI Technical Summary
Existing natural language to structured query language (SQL) conversion technology is difficult to handle complex queries and permission management, resulting in inefficient data processing and security issues.
By receiving natural language query statements input by users, preprocessing and converting them into structured information, calling business entity compression structure services, optimizing and integrating them into large models, obtaining user permission information, generating query statements for business query languages, combining multiple Layer conversion and permission management realize efficient and secure natural language to business query language conversion.
It improves the semantic understanding and conversion accuracy of natural language problems, reduces the amount of data, improves the conversion efficiency and security, and can obtain accurate BQL query results through simple natural language problems, avoiding data leakage and security risks.
Smart Images

Figure CN118939679A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the fields of natural language processing and large-scale language models, and in particular to methods, systems, devices and media for generating business query languages. Background Art
[0002] With the prevalence of data-driven business decisions in modern enterprises, extracting data from databases quickly and accurately has become a critical requirement. However, existing natural language to structured query language (SQL) conversion technologies have the following shortcomings in dealing with complex queries and permission management: Insufficient complex query processing: Existing methods have difficulty processing complex natural language queries, especially queries involving multi-table associations and complex conditions. Lack of permission management: Direct conversion of SQL statements often lacks effective management of user permissions, which may lead to data leakage and security issues. Inefficiency: Existing methods often suffer from inefficiency when dealing with large-scale databases and complex queries.
[0003] With the rapid development of information technology, Business Query Language (BQL), a query tool for business users, has significantly lowered the barrier to entry for non-technical users to access databases through a visual interface and simplified query operations. Existing natural language conversion methods for BQL often rely on fixed templates or rules, making them difficult to handle complex and varied natural language queries, resulting in low conversion accuracy and efficiency. Summary of the Invention
[0004] In view of this, the present invention proposes a method, system, device and medium for generating business query language, which solves the accuracy and security problems of large models in generating business query language.
[0005] Based on the above objectives, the present invention proposes a method for generating a business query language, comprising: Receiving a natural language query statement input by a user, preprocessing the natural language query statement, and converting the query statement into structured information; Calling the business entity compression structure service, obtaining the compression structure of the corresponding business entity based on the structured information, optimizing the compression structure and integrating it into the large model; Obtaining user authority information, extracting authority restrictions from the user authority information and inputting them into the big model; Based on the optimized and integrated compression structure and the permission restriction, a query statement of a business query language is generated through a large model, and a query is performed and the query results are displayed according to the query statement of the business query language.
[0006] In some embodiments, the structured information includes a business entity ID and information.
[0007] In some embodiments, the step of obtaining a compressed structure of a corresponding business entity based on the structured information includes: Retrieve the corresponding table structure in the database according to the business entity ID and identify the key attributes in the table; Extracting the table structure and key attributes from the database as data of the business entity; The data of the business entities are converted and key attributes of each entity are extracted, and a compression structure of the business entities is constructed based on the key attributes.
[0008] In some embodiments, the step of optimizing the compressed structure and integrating it into the large model includes: The compression structure is subjected to data cleaning, feature dimension reduction and encoding, and standardization processing; Build an input pipeline to convert the standardized compressed structure into the required format of the large model and integrate it according to the input requirements of the large model; Use the integrated compressed structure as input to train or infer the large model.
[0009] In some embodiments, the step of receiving a natural language query statement input by a user, preprocessing the natural language query statement, and converting the query statement into structured information includes: Parsing natural language query statements entered by users; Based on the parsed natural language query statement, identify the user's query intent and map the user's query intent to a preset fixed content template; Identify and extract entities, attributes, and relationships between them in the query as structured information.
[0010] In some embodiments, the step of generating a query statement in a business query language through a large model based on the optimized and integrated compression structure and the permission restriction includes: Retrieve business entities and attributes from the optimized and consolidated compressed structure; Determine the user's permission scope based on the permission restriction and use it as a constraint when generating a query statement, and filter inaccessible fields based on the constraint; A complete query statement in the business query language is formed based on the filtered fields and constraints.
[0011] In some embodiments, the method further includes: when generating a query statement of a business query language through the big model, providing context information for the big model through a preset fixed content template.
[0012] The present invention proposes a system for generating a business query language, comprising: an acquisition unit configured to receive a natural language query statement input by a user, preprocess the natural language query statement, and convert the query statement into structured information; a compression unit configured to call a business entity compression structure service, obtain a compression structure of a corresponding business entity based on the structured information, optimize the compression structure, and integrate the compression structure into the large model; a permission unit configured to obtain user permission information, extract permission restrictions from the user permission information, and input the restrictions into the large model; The query unit is configured to generate a query statement in a business query language through a large model based on the optimized and integrated compression structure and the permission restriction, perform a query according to the query statement in the business query language, and display the query results.
[0013] The present invention provides a computer device, comprising: At least one processor; and a memory storing a computer program executable on the processor, wherein the processor executes the steps of the method for generating a business query language when executing the program.
[0014] The present invention provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the computer program executes the steps of the method for generating a business query language.
[0015] The present invention has at least the following beneficial technical effects: The present invention proposes a method, system, device and medium for generating a business query language. The method includes: receiving a natural language query statement input by a user, preprocessing the natural language query statement and converting it into structured information; calling a business entity compression structure service, obtaining a compression structure of a corresponding business entity based on the structured information, optimizing the compression structure and integrating it into a large model; obtaining user authority information, extracting authority restrictions from the user authority information and inputting them into the large model; generating a query statement in a business query language through the large model based on the optimized and integrated compression structure and the authority restrictions, performing a query according to the query statement in the business query language and displaying the query results.
[0016] This invention achieves efficient and secure conversion from natural language to business query language through multi-layer conversion and compression structure optimization, combined with permission management. It can more accurately understand the semantics and context of natural language questions, thereby improving conversion accuracy. The construction of a compression structure reduces the amount of data to be processed later, making the conversion process more efficient. Simple natural language questions can generate accurate BQL query results without having to master complex query syntax. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other embodiments can be obtained based on these drawings without paying any creative work.
[0018] Figure 1 A flow chart of the method for generating a business query language provided by the present invention; Figure 2 A system module diagram generated by the business query language provided by the present invention; Figure 3 A flowchart of an embodiment of a method for generating a business query language provided by the present invention; Figure 4 An embodiment of the method for generating a business query language provided by the present invention generates a BQL flow chart according to a compression structure; Figure 5 A schematic structural diagram of an embodiment of a computer device provided by the present invention; Figure 6 This is a schematic structural diagram of an embodiment of a computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION
[0019] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the embodiments of the present invention are further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.
[0020] It should be noted that all expressions using "first" and "second" in the embodiments of the present invention are for distinguishing two non-identical entities with the same name or non-identical parameters. It can be seen that "first" and "second" are only for the convenience of expression and should not be understood as limitations on the embodiments of the present invention. Subsequent embodiments will not explain this one by one.
[0021] This invention proposes a method for generating a business query language. Figure 1 、 Figure 3 and Figure 4 ,include: S1: receiving a natural language query statement input by a user, preprocessing the natural language query statement, and converting it into structured information; S2: calling the business entity compression structure service, obtaining the compression structure of the corresponding business entity based on the structured information, optimizing the compression structure and integrating it into the large model; S3: Obtain user authority information, extract authority restrictions from the user authority information, and input them into the large model; S4: Based on the optimized and integrated compression structure and the permission restriction, a query statement of a business query language is generated through a large model, and a query is performed according to the query statement of the business query language and the query results are displayed.
[0022] Furthermore, the present invention comprises the following steps: Multi-layer natural language processing: By calling external REST APIs, natural language queries entered by users are converted into structured information, including business entity IDs and information; Business entity compression structure acquisition: Acquire and process the compressed structure information of business entities. This information is optimized to help improve query performance and efficiency. Process and manage user permission information to ensure that generated query statements meet permission control requirements and ensure data security; Provide contextual information for large models through fixed content templates, ensuring consistency and flexibility in transformation.
[0023] The big model generates BQL (Business Query Language) queries: Leveraging the powerful natural language processing capabilities of the big model, structured information and user queries are converted into BQL query statements.
[0024] Query result processing and presentation: Query results are processed and presented through various methods, including converting the results into string format for user understanding and use.
[0025] This invention achieves efficient and secure conversion from natural language to business query language through multi-layer conversion and compression structure optimization, combined with permission management. It can more accurately understand the semantics and context of natural language questions, thereby improving conversion accuracy. The construction of a compression structure reduces the amount of data to be processed later, making the conversion process more efficient. Simple natural language questions can generate accurate BQL query results without having to master complex query syntax.
[0026] The large model selects large language models (LLMs) with powerful natural language processing (NLP) capabilities, such as GPT and BERT. The query statements of the business query language are queried through the BQL engine and the visual interface. When the query statement is entered on the visual interface, the BQL engine will automatically convert the query conditions into SQL statements and execute them in the database.
[0027] In some embodiments, see Figure 1 、 Figure 3 and Figure 4 , the structured information includes business entity ID and information.
[0028] In the process of generating a business query language, structured information includes business entity IDs and information, which is crucial for precisely locating and querying business data. Business entity IDs typically serve as the primary key or unique identifier of a data table, while the information may include multiple attributes or fields related to that business entity.
[0029] In some embodiments, refer to Figure 1 、 Figure 3 and Figure 4 , the step of obtaining the compressed structure of the corresponding business entity based on the structured information includes: Retrieve the corresponding table structure in the database according to the business entity ID and identify the key attributes in the table; Extract the table structure and key attributes from the database as the data of the business entity; Convert the data of the business entity and extract the key attributes of each entity, and form the compressed structure of the business entity based on the key attributes.
[0030] In a business query language, a large amount of data storage and retrieval are involved. Using a compressed structure can significantly reduce storage costs. The compressed structure obtained based on structured information usually contains rich business logic and data relationships, helping to generate more accurate and efficient query statements to meet complex query requirements. Features such as multi-level conversion and index optimization in the compressed structure can enhance the flexibility of queries, enabling the system to quickly adjust query strategies according to different query conditions and requirements, improving the accuracy and efficiency of queries.
[0031] The compressed structure has a unified data format and storage specification, which helps to simplify the workflow of data management and maintenance. As the business develops and changes, more data types and query logics need to be supported. The compressed structure obtained based on structured information has good scalability and upgradability, and can easily adapt to these changes.
[0032] In some embodiments, refer to Figure 1 、 Figure 3 and Figure 4 , the step of optimizing the compressed structure and integrating it into a large model includes: Perform data cleaning, feature dimensionality reduction and encoding on the compressed structure, and standardize it; Build an input pipeline, convert the standardized compressed structure into the required format of the large model and integrate it according to the input requirements of the large model; Use the integrated compressed structure as input to train or infer the large model.
[0033] One of the innovations of this invention is structured information processing, which is based on obtaining the compressed structure information of business entities and using it to optimize the process of converting natural language into business query language. This is achieved through the following steps: Receive structured information: Structured information obtained from the NLP conversion module, including business entity IDs and information.
[0034] Call the compression structure service: Use the business entity compression structure service (such as BECompressEntity service) to obtain the compression structure information of the corresponding business entity.
[0035] Optimize compression structure: Optimize the obtained compression structure information to improve query performance and efficiency.
[0036] Integrate compressed structure information: Integrate the optimized compressed structure information into the input of the large model to generate BQL queries.
[0037] Optimizing compression structure information is a key step in ensuring efficient queries. By analyzing and optimizing the compression structure, query performance can be significantly improved. Integrating this optimized compression structure information into the input of the large model ensures that the generated BQL queries are accurate and efficient.
[0038] In some embodiments, see Figure 1 、 Figure 3 and Figure 4 The steps of receiving a natural language query statement input by a user, preprocessing the natural language query statement, and converting the query statement into structured information include: Parsing natural language query statements entered by users; Based on the parsed natural language query statement, identify the user's query intent and map the user's query intent to a preset fixed content template; Identify and extract entities, attributes, and relationships between them in the query as structured information.
[0039] Through preprocessing steps such as word segmentation, part-of-speech tagging, and syntactic analysis, the intent and context of user queries can be understood more accurately, helping the system to parse user questions more precisely and reduce misunderstandings and ambiguities.
[0040] Converting natural language queries into structured information makes query requests clearer and more specific, helping the system accurately locate the required data or resources and improving query accuracy.
[0041] In some embodiments, see Figure 1 、 Figure 3 and Figure 4The step of generating a query statement in a business query language through a large model based on the optimized and integrated compression structure and the permission restriction includes: Retrieve business entities and attributes from the optimized and consolidated compressed structure; Determine the user's permission scope based on the permission restriction and use it as a constraint when generating a query statement, and filter inaccessible fields based on the constraint; A complete query statement in the business query language is formed based on the filtered fields and constraints.
[0042] The optimized and integrated compression structure reduces data redundancy and improves data processing efficiency. This enables large models to access and process relevant data more quickly when generating query statements, thereby improving query efficiency.
[0043] Permission restrictions ensure that only query requests that comply with security regulations and data privacy policies are processed. This helps reduce invalid queries and potential security risks, and improves query accuracy and security.
[0044] The large model possesses powerful natural language processing and knowledge reasoning capabilities, enabling it to accurately understand user intent and generate appropriate query statements. Combined with a compressed structure and permission restrictions, the large model generates more precise and efficient queries. By generating queries using the large model, the system can adapt to diverse query scenarios and needs. Whether for simple data retrieval or complex business analysis, the system generates appropriate queries based on user input and permission restrictions.
[0045] In some embodiments, see Figure 1 、 Figure 3 and Figure 4 The method further includes: when generating a query statement of a business query language through the big model, providing context information for the big model through a preset fixed content template.
[0046] Pre-set fixed content templates help the model more accurately understand the user's query intent. The keywords, sentence structure, and logical relationships within the templates guide the model in generating responses that better meet the user's expectations. After receiving user input, the model can quickly match it with the preset template. This matching process is typically much faster than parsing and understanding natural language from scratch, significantly improving processing efficiency and response speed. Pre-set fixed content templates can be flexibly expanded and modified based on business needs. When business scenarios change, simply update the template without requiring large-scale model retraining. This enhances the model's adaptability and flexibility.
[0047] The present invention proposes a system for generating business query language, please refer to Figure 2 ,include: The acquisition unit 100 is configured to receive a natural language query statement input by a user, pre-process the natural language query statement, and convert it into structured information; The compression unit 200 is configured to call a business entity compression structure service, obtain a compression structure of a corresponding business entity based on the structured information, optimize the compression structure, and integrate it into the large model; The permission unit 300 is configured to obtain user permission information, extract permission restrictions in the user permission information, and input the restrictions into the macro model; The query unit 400 is configured to generate a query statement in a business query language through a large model based on the optimized and integrated compression structure and the permission restriction, perform a query according to the query statement in the business query language, and display the query results.
[0048] The system architecture of the present invention further includes: User input module: used for users to input queries through natural language.
[0049] NLP conversion module: used to convert natural language into structured information.
[0050] Structured information processing module: used to process structured information and obtain the compressed structure of business entities.
[0051] Permission management module: used to process and manage user permission information.
[0052] Large model generation module: used to generate BQL query statements using large models.
[0053] Query execution module: used to execute the generated BQL query statements.
[0054] Result processing module: used to process and display query results.
[0055] In the present invention, when LLM is not accurate enough when converting natural language to BQL, a multi-layer conversion and optimization process is used to efficiently and securely convert natural language queries into business query language, especially when processing complex queries and managing permissions. This falls in the direction of large-scale intelligent models and solves the accuracy and security issues of large models in generating business query languages. The system can automatically generate business query languages based on user input or preset conditions, eliminating the need for manual writing of complex query statements. This greatly saves time and improves the efficiency of business processing. Through natural language processing technology and machine learning algorithms, the system can deeply understand the user's query intent and needs and generate accurate query statements. This helps reduce query errors and misunderstandings and improves the accuracy of query results.
[0056] Based on the same inventive concept, according to another aspect of the present invention, Figure 5 As shown, an embodiment of the present invention further provides a computer device 30, which includes a processor 310 and a memory 320. The memory 320 stores a computer program 321 that can be run on the processor. When the processor 310 executes the program, the steps of the above method are performed.
[0057] Based on the same inventive concept, according to another aspect of the present invention, Figure 6 As shown, an embodiment of the present invention further provides a computer-readable storage medium 40 , which stores a computer program 410 for executing the above method when executed by a processor.
[0058] The embodiment of the present invention may further include a corresponding computer device, which includes a memory, at least one processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes any one of the above methods when executing the program.
[0059] The memory, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules in the embodiments of the present application. The processor executes the non-volatile software programs, instructions, and modules stored in the memory to execute various functional applications and data processing of the device, thereby implementing the above-mentioned method.
[0060] The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the device, etc. In addition, the memory may include a high-speed random access memory and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In an embodiment, the memory may optionally include a memory remotely located relative to the processor, and these remote memories may be connected to the local module via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0061] Finally, it should be noted that those skilled in the art will understand that all or part of the processes in the above-described method embodiments can be implemented using a computer program to instruct the relevant hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes in the above-described method embodiments. The program storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM). The above-described computer program embodiments can achieve the same or similar effects as any of the corresponding aforementioned method embodiments.
[0062] It will also be appreciated by those skilled in the art that the various exemplary logic blocks, modules, circuits and algorithmic steps described in conjunction with the disclosure herein can be implemented as electronic hardware, computer software or a combination of the two. In order to clearly illustrate this interchangeability of hardware and software, a general description has been given of the functions of various schematic components, blocks, modules, circuits and steps. Whether this function is implemented as software or hardware depends on specific applications and the design constraints imposed on the entire system. Those skilled in the art can implement the function in various ways for each specific application, but this implementation decision should not be interpreted as causing a departure from the disclosed scope of the embodiments of the present invention.
[0063] The above are exemplary embodiments disclosed in the present invention, but it should be noted that various changes and modifications can be made without departing from the scope of the disclosure of the embodiments of the present invention as defined in the claims. The functions, steps and / or actions of the method claims according to the disclosed embodiments described herein do not need to be performed in any particular order. The serial numbers of the embodiments disclosed in the above embodiments of the present invention are for description only and do not represent the advantages and disadvantages of the embodiments. In addition, although the elements disclosed in the embodiments of the present invention can be described or required in individual form, they can also be understood as multiple unless expressly limited to the singular.
[0064] It should be understood that, as used herein, the singular forms "a" and "an" are intended to include the plural forms as well, unless the context clearly supports an exception. It should also be understood that, as used herein, "and / or" is intended to include any and all possible combinations of one or more of the associated listed items.
[0065] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to limit the scope of the disclosure of the present invention (including the claims) to these examples. Within the spirit of the present invention, the technical features of the above embodiments or different embodiments may be combined, and many other variations exist in different aspects of the above embodiments, which are not provided in detail for the sake of clarity. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
Claims
1. Method of generating business query language, It is characterized in that include: Receiving a natural language query statement input by a user, preprocessing the natural language query statement, and converting the natural language query statement into structured information; Calling the business entity compression structure service, obtaining the compression structure of the corresponding business entity based on the structured information, optimizing the compression structure and integrating it into the large model; Obtaining user authority information, extracting authority restrictions in the user authority information and inputting them into the big model; Based on the optimized and integrated compression structure and the permission restriction, a query statement of a business query language is generated through a large model, and a query is performed and the query result is displayed according to the query statement of the business query language.
2. The method for generating a business query language according to claim 1, It is characterized in that The structured information includes business entity ID and information.
3. The method for generating a business query language according to claim 2, It is characterized in that The step of acquiring the compression structure of the corresponding business entity based on the structured information comprises: Retrieve the corresponding table structure in the database according to the business entity ID and identify the key attributes in the table; Extract the table structure and key attributes from the database as data of the business entity; The data of the business entity is converted and key attributes of each entity are extracted, and a compression structure of the business entity is constructed based on the key attributes.
4. The method for generating a business query language according to claim 1, It is characterized in that The step of optimizing the compression structure and integrating it into the large model comprises: The compressed structure is subjected to data cleaning, feature dimension reduction and encoding, and standardization processing; Build an input pipeline to convert the standardized compression structure into the required format of the large model and integrate it according to the input requirements of the large model; Use the integrated compressed structure as input to train or infer large models.
5. The method for generating a business query language according to claim 1, It is characterized in that The step of receiving a natural language query statement input by a user, preprocessing the natural language query statement, and converting the query statement into structured information includes: Parse natural language query statements entered by users; According to the parsed natural language query statement, the user's query intention is identified, and the user's query intention is mapped to a preset fixed content template; Identify and extract entities, attributes, and relationships between them in the query as structured information.
6. The method for generating a business query language according to claim 5, It is characterized in that The step of generating a query statement of a business query language through a large model based on the optimized and integrated compression structure and the authority restriction includes: Retrieve business entities and attributes from the optimized and consolidated compressed structure; Determine the user's permission scope according to the permission restriction and use it as a constraint when generating a query statement, and filter inaccessible fields according to the constraint; A complete query statement of the business query language is formed based on the filtered fields and constraints.
7. The method for generating a business query language according to claim 6, It is characterized in that Also includes: When a query statement of a business query language is generated through a big model, context information is provided to the big model through a preset fixed content template.
8. Business query language generated system, It is characterized in that include: An acquisition unit configured to receive a natural language query statement input by a user, pre-process the natural language query statement, and convert it into structured information; A compression unit, configured to call a business entity compression structure service, obtain a compression structure of a corresponding business entity based on the structured information, optimize the compression structure and integrate it into a large model; A permission unit, configured to obtain user permission information, extract permission restrictions in the user permission information, and input the restrictions into the large model; The query unit is configured to generate a query statement in a business query language through a large model based on the optimized and integrated compression structure and the permission restriction, perform a query according to the query statement in the business query language, and display the query result.
9. A computer device, include: at least one processor; and a memory storing a computer program executable on the processor, wherein the processor executes the steps of the method for generating a business query language according to any one of claims 1 to 7 when executing the program.
10. A computer-readable storage medium storing a computer program. It is characterized in that When the computer program is executed by a processor, the steps of the method for generating a business query language according to any one of claims 1 to 7 are performed.
Citation Information
Patent Citations
SQL (Structured Query Language) statement acquisition method and device, report generation method and device, computer equipment and storage medium device
CN116541411A
SQL (Structured Query Language) statement generation method and system, medium and equipment
CN117251469A
Method for converting natural language into SQL (Structured Query Language) in vector database
CN118394778A
Database query statement generation method, system and equipment and medium
CN118467682A
Entity-relationship model extensions using annotations
US20150074081A1
Cited By
Information extraction method and field selection method
CN119226498A
Search optimization method, device and medium based on large model
CN119782494A
Enterprise data processing method and device, electronic equipment and storage medium
CN120763194A
SQL statement generation method and device based on multiple libraries
CN120804132A
A method and apparatus for generating SQL statements based on multiple databases
CN120804132B
