Power equipment data intelligent interaction method, system, equipment and medium

Abstract

A power equipment data intelligent interaction method, system, device and medium, comprising: retrieving database table information based on query information input by a user to obtain database table information; performing power equipment knowledge base retrieval based on the query information to obtain business knowledge calculation logic and a context learning example; creating prompts based on database table information, business knowledge calculation logic and context learning examples, and inputting the prompts into the large model to generate database statements; running the database statement and judging whether the statement succeeds or not, and if yes, outputting a query result; otherwise, error correction is carried out, and corrected database statements are obtained and run again; according to database table information retrieval, extraction of table field links, table main and foreign keys and table association relationships can be carried out on user query, the accuracy and performance of model generation database languages are improved, the data query threshold is lowered, and the data utilization efficiency is improved; the power equipment knowledge base can realize flexibility and expandability of business knowledge injection.

Description

Technical Field

[0001] The present application relates to the field of power equipment, and specifically to a method, system, equipment and medium for intelligent interaction of power equipment data. Background Art

[0002] In the field of power equipment, the following solutions are used to generate database query language SQL statements based on user natural language queries:

[0003] Solution 1: Template slot filling method. The SQL generation process is divided into multiple subtasks, each of which is responsible for predicting the columns in a grammatical phenomenon. This method works well for single tables without nesting, and the generated SQL can ensure grammatical correctness. The disadvantage is that it can only model a fixed SQL grammar template. For nested SQL situations, it cannot flexibly handle all nested phenomena.

[0004] Solution 2: Deep learning method. The main idea is to transform the SQL statement generation problem into a sequence generation or classification task. For example, the Seq2SQl algorithm divides the model into three components: an aggregation classifier, a pointer for selecting select columns, and a where condition decoder, and uses reinforcement learning to learn strategies to generate correct SQL query statements. The deep learning method can better capture the complex semantics of query statements, but it has high requirements for training data.

[0005] Solution 3: The method based on the big model. The main idea is to input the database structure as a prompt word into the big model to generate SQL statements. However, in actual business scenarios, the database structure is relatively complex and generally has multiple tables and columns. The token input to the model is long, while the input token length of the big model is limited, and the longer the invalid token is, the more obvious the model performance will be.

[0006] The real-time operation database table structure design in actual power equipment scenarios is relatively complex, often involving multiple tables, each table involving many fields, and it is difficult to input all table information as context into the model at the same time.

[0007] Therefore, there is an urgent need to solve the problems of high data query threshold and low data utilization efficiency in power equipment scenarios caused by lack of domain knowledge of databases, unfamiliarity with database structures, and unskilledness in SQL query statements. Summary of the invention

[0008] In order to solve the problems of high data query threshold and data utilization efficiency caused by lack of domain knowledge of database, unfamiliarity with database structure and unskilledness in SQL query statements in the prior art, this application proposes a method for intelligent interaction of power equipment data, including:

[0009] Retrieve database table information based on query information input by the user to obtain database table information;

[0010] Search the electric power equipment knowledge base based on the query information to obtain business knowledge calculation logic and context learning examples;

[0011] Creating prompts based on the database table information, business knowledge calculation logic, and contextual learning examples, and inputting the prompts into the big model to generate database statements;

[0012] The database statement is run and whether it is successful is determined. If the operation is successful, the query result corresponding to the query information is output; otherwise, error correction is performed according to the database statement, and the corrected database statement is obtained and re-run.

[0013] Preferably, the retrieving database table information based on the query information input by the user to obtain the database table information includes:

[0014] Encode the table name, column name and annotation information of the database table through an encoder to obtain a table vector library and a column vector library;

[0015] The user query code based on the query information is subjected to cosine similarity calculation with the table vector library and the column vector library respectively to obtain the table name and column name with the highest matching degree, and the primary and foreign keys and the connection relationship with other database tables are extracted.

[0016] Preferably, searching the electric power equipment knowledge base based on the query information to obtain the business knowledge calculation logic and context learning examples includes:

[0017] Based on the domain knowledge dictionary, the query information is retrieved using a fuzzy matching algorithm to obtain the business knowledge calculation logic;

[0018] Based on the business knowledge question-answering database, the twin network encoding sentence vector is used to compare and learn with the query information to obtain contextual learning examples;

[0019] Among them, the power equipment knowledge base is composed of a domain knowledge dictionary constructed based on indicator calculation, enumeration conditions, entity aliases and fuzzy intentions in multiple dimensions, and a business knowledge question and answer library constructed based on high-frequency query intentions in power equipment scenarios.

[0020] Preferably, the execution determination based on the database statement and error correction if the execution fails include:

[0021] Based on the database statement, the thinking prompt chain technology is used to analyze the running error information, check whether the table name and column name exist, check whether the foreign key is correct, check whether there is missing or redundant ascending and descending or deduplication keywords, obtain the corrected database statement and re-run it.

[0022] Preferably, the database table information includes: one or more of: table name, column name, table primary and foreign keys, and association relationships.

[0023] Based on the same application concept, this application also proposes an intelligent interactive system for power equipment data, including:

[0024] A table information retrieval module is used to retrieve database table information based on query information input by a user to obtain database table information;

[0025] A domain knowledge retrieval module, used to search the power equipment knowledge base based on the query information to obtain business knowledge calculation logic and context learning examples;

[0026] A model reasoning module, used to create prompts based on the database table information, business knowledge calculation logic and context learning examples, and input the prompts into the big model to generate database statements;

[0027] The correction module is used to run the database statement and determine whether it is successful. If the operation is successful, the query result corresponding to the query information is output; otherwise, the error is corrected according to the database statement, the corrected database statement is obtained and re-run.

[0028] Preferably, the database table information retrieval module is specifically used for:

[0029] Encode the table name, column name and annotation information of the database table through an encoder to obtain a table vector library and a column vector library;

[0030] The user query code based on the query information is subjected to cosine similarity calculation with the table vector library and the column vector library respectively to obtain the table name and column name with the highest matching degree, and the primary and foreign keys and the connection relationship with other database tables are extracted.

[0031] Preferably, the domain knowledge retrieval module is specifically used for:

[0032] Based on the domain knowledge dictionary, the query information is retrieved using a fuzzy matching algorithm to obtain the business knowledge calculation logic;

[0033] Based on the business knowledge question-answering database, the query information is retrieved by using twin network encoding sentence vectors combined with contrastive learning to obtain contextual learning examples;

[0034] Among them, the power equipment knowledge base is composed of a domain knowledge dictionary constructed based on indicator calculation, enumeration conditions, entity aliases and fuzzy intentions in multiple dimensions, and a business knowledge question and answer library constructed based on high-frequency query intentions in power equipment scenarios.

[0035] Preferably, the correction module is specifically used for:

[0036] Based on the database statement, the thinking prompt chain technology is used to analyze the running error information, check whether the table name and column name exist, check whether the foreign key is correct, check whether there is missing or redundant ascending and descending or deduplication keywords, obtain the corrected database statement and re-run it.

[0037] Preferably, the database table information in the database table information retrieval module includes: one or more of: table name, column name, table primary and foreign keys, and association relationships.

[0038] On the other hand, the present application also proposes an electronic device, comprising: at least one processor and a memory; the memory and the processor are connected via a bus;

[0039] The memory is used to store one or more programs;

[0040] When the one or more programs are executed by the at least one processor, an intelligent interaction method for power equipment data as described above is implemented.

[0041] On the other hand, the present application also proposes a readable storage medium having an execution program stored thereon, and when the execution program is executed, an intelligent interaction method for power equipment data as described above is implemented.

[0042] Compared with the prior art, the beneficial effects of this application are:

[0043] A method, system, device and medium for intelligent interaction of power equipment data, comprising: retrieving database table information based on query information input by a user to obtain database table information; retrieving a knowledge base of power equipment based on the query information to obtain business knowledge calculation logic and context learning examples; creating prompts based on the database table information, business knowledge calculation logic and context learning examples, and inputting the prompts into a large model to generate database statements; running the database statements and determining whether they are successful, and if successful, outputting query results corresponding to the query information; otherwise, performing error correction according to the database statements, obtaining the corrected database statements and re-running them; the application performs database table information retrieval to realize the extraction of table field links, table primary and foreign keys, and table association relationships for user queries, effectively improving the accuracy and performance of the model generation database language, lowering the data query threshold, and improving data utilization efficiency; the power equipment knowledge base of the application can realize the flexibility and scalability of business knowledge injection; the application performs error correction on database statements with running errors, which can improve the accuracy of model generation;

[0044] This application uses domain knowledge dictionaries and knowledge question-and-answer bases for retrieval, which can solve the problem of fuzzy intent queries in actual business and improve the scalability and interpretability of business knowledge. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is a flow chart of a method for intelligent interaction of power equipment data in this application;

[0046] Figure 2 This is a flow chart of the large model knowledge enhancement method of this application;

[0047] Figure 3 This is a flow chart of intelligent interaction of power equipment data for this application;

[0048] Figure 4 This is a structural diagram of an intelligent interactive system for power equipment data in this application;

[0049] Figure 5 This is a structural diagram of an electronic device of the present application. DETAILED DESCRIPTION

[0050] In order to solve the problem of high threshold for power equipment data query and low data utilization rate caused by lack of business knowledge, unfamiliarity with database structure and unskilled use of structured query statements in the field of power equipment, this application proposes a method for intelligent interaction of power equipment data. In order to better understand this application, the content of this application is further explained below in conjunction with the drawings and embodiments of the specification.

[0051] Embodiment 1:

[0052] A method for intelligent interaction of power equipment data, the specific process is as follows Figure 1 As shown, including:

[0053] Step 1: retrieve database table information based on query information input by the user to obtain database table information;

[0054] Step 2: searching the electric power equipment knowledge base based on the query information to obtain business knowledge calculation logic and context learning examples;

[0055] Step 3, creating prompts based on the database table information, business knowledge calculation logic and context learning examples, and inputting the prompts into the big model to generate database statements;

[0056] Step 4, run the database statement and determine whether it is successful. If the operation is successful, the query result corresponding to the query information is output; otherwise, error correction is performed according to the database statement, and the corrected database statement is obtained and re-run.

[0057] In step 1, database table information is retrieved based on the query information input by the user to obtain database table information, which specifically includes:

[0058] Since the database information in the power equipment scenario is not standardized, it is necessary to manage the database table to improve the model generation effect. Standardize the table name and column name, ensure that the table comment and column comment information description are clear, concise and different, and the table primary and foreign keys and association relationships are complete. Based on the large model knowledge enhancement method, such as Figure 2 shown.

[0059] Based on the query information entered by the user, the database table information is retrieved to identify the table name, column name, and cell value related to the user query. The table name and comment, column name and comment are encoded by Bert encoder and stored in table vector library and column vector library, and then the user query is encoded and the cosine similarity is calculated with the table vector library and the corresponding column vector library respectively to obtain the most matching table name and column name, and extract the related primary and foreign keys and the connection relationship with other database tables.

[0060] In step 2, based on the query information, a power equipment knowledge base is searched to obtain business knowledge calculation logic and context learning examples, specifically including:

[0061] Build a domain knowledge dictionary based on indicator calculation, enumeration conditions, entity aliases and fuzzy intents in multiple dimensions; build a business knowledge question-and-answer database based on high-frequency query intents in power equipment scenarios;

[0062] The power equipment knowledge base is composed of the domain knowledge dictionary and the business knowledge question and answer base.

[0063] When querying based on the domain knowledge dictionary, a fuzzy matching algorithm is used to retrieve the business calculation logic related to the user query.

[0064] When querying based on the business knowledge question and answer database, the twin network encoding sentence vector is used to retrieve the question and answer database to obtain a set number of question and answer pairs ranked at the top, and context learning examples are obtained through context learning. In this embodiment, the number is set to 5.

[0065] In step 3, creating prompts based on the database table information, business knowledge calculation logic and context learning examples, and inputting the prompts into the big model to generate database statements, specifically includes:

[0066] Automatically build prompts based on user queries, retrieved table information, business knowledge calculation logic, and contextual learning examples, and input them into the big model to generate the final SQL statement.

[0067] In step 4, the database statement is run and whether it is successful is determined. If the run is successful, the query result corresponding to the query information is output; otherwise, error correction is performed according to the database statement, and the corrected database statement is obtained and re-run, which specifically includes:

[0068] The error prompts for failed operations are input into the large model, and self-correction is performed based on the thought prompt chain. The prompt model checks and corrects step by step according to the following thought process:

[0069] Analyze the causes of SQL execution error information;

[0070] Check whether the table name and column name in SQL exist;

[0071] Check whether the foreign key used for the Join is correct;

[0072] Check whether there are missing or redundant ascending, descending or duplicate keywords;

[0073] Get the corrected database statement and re-execute it.

[0074] The intelligent interaction process of power equipment data is as follows: Figure 3 As shown, including:

[0075] First, the database table information is retrieved for the query information input by the user, and the relevant database table names, column names, primary and foreign keys, association relationships and enumeration values ​​are retrieved.

[0076] Then, the query input by the user is searched in the power equipment knowledge base, which includes business knowledge dictionary matching and business question and answer base search to obtain business knowledge calculation logic.

[0077] Based on the above-obtained database table information, business knowledge calculation logic, and contextual learning examples, prompts are automatically constructed and input into the large model to generate the final SQL statement.

[0078] Execute the generated SQL and get the query results if it succeeds.

[0079] If the operation fails, the error self-correction will be carried out. The error prompts of the operation failure will be input into the large model, and self-correction will be carried out based on the thinking prompt chain.

[0080] This application focuses on complex database query scenarios in power equipment, and specifically proposes a method based on a knowledge-enhanced large language model. By building multi-table information retrieval, domain knowledge dictionary, and business knowledge question-and-answer library, it solves the query of complex database structures and fuzzy intent queries in actual scenarios. In addition, the model accuracy is improved by introducing an error correction method based on the thinking chain. Ultimately, the SQL query threshold is lowered, the query efficiency of the power equipment database is improved, and the resources required by enterprises in related business development and dimensions are reduced.

[0081] The real-time operation database table structure design in the actual power equipment scenario is relatively complex, often involving multiple tables, each table involving many fields, and it is difficult to input all table information as context into the model at the same time. The present invention first designs a database table management method, and then designs a multivariate table information retrieval strategy based on semantic vector encoding, which can realize table field linking for user queries, table primary and foreign keys, and table association relationship extraction, effectively improving the accuracy and performance of model-generated SQL.

[0082] This application solves fuzzy intent queries in actual business and improves the scalability and interpretability of business knowledge by constructing a domain knowledge dictionary and a knowledge question-and-answer database, retrieving domain knowledge related to user queries, and injecting business calculation logic into a large model to generate SQL statements. This solves the problem that existing methods rely heavily on the display of database table names and field names, and that the accuracy of fuzzy intent queries is poor due to lack of business knowledge. If business knowledge is trained directly into the model, the scalability is poor and it is not conducive to the addition or modification of business knowledge.

[0083] This application combines SQL running error information and builds an error correction module based on the thinking chain prompt method to improve the accuracy of model generation and solve the problem of hallucinations in large model generation results in power equipment scenarios.

[0084] Embodiment 2:

[0085] An intelligent interactive system for power equipment data, the structure of which is as follows Figure 4 As shown, including:

[0086] A table information retrieval module is used to retrieve database table information based on query information input by a user to obtain database table information;

[0087] A domain knowledge retrieval module, used to search the power equipment knowledge base based on the query information to obtain business knowledge calculation logic and context learning examples;

[0088] A model reasoning module, used to create prompts based on the database table information, business knowledge calculation logic and context learning examples, and input the prompts into the big model to generate database statements;

[0089] The correction module is used to run the database statement and determine whether it is successful. If the operation is successful, the query result corresponding to the query information is output; otherwise, the error is corrected according to the database statement, the corrected database statement is obtained and re-run.

[0090] Database table information retrieval module, specifically used for:

[0091] Encode the table name, column name and annotation information of the database table through an encoder to obtain a table vector library and a column vector library;

[0092] The user query code based on the query information is subjected to cosine similarity calculation with the table vector library and the column vector library respectively to obtain the table name and column name with the highest matching degree, and the primary and foreign keys and the connection relationship with other database tables are extracted.

[0093] Domain knowledge retrieval module, specifically used for:

[0094] Based on the domain knowledge dictionary, the query information is retrieved using a fuzzy matching algorithm to obtain the business knowledge calculation logic;

[0095] Based on the business knowledge question-answering database, the query information is retrieved by using twin network encoding sentence vectors combined with contrastive learning to obtain contextual learning examples;

[0096] Among them, the power equipment knowledge base is composed of a domain knowledge dictionary constructed based on indicator calculation, enumeration conditions, entity aliases and fuzzy intentions in multiple dimensions, and a business knowledge question and answer library constructed based on high-frequency query intentions in power equipment scenarios.

[0097] The correction module is specifically used for:

[0098] Based on the database statement, the thinking prompt chain technology is used to analyze the running error information, check whether the table name and column name exist, check whether the foreign key is correct, check whether there is missing or redundant ascending and descending or deduplication keywords, obtain the corrected database statement and re-run it.

[0099] The database table information in the database table information retrieval module includes: one or more of: table name, column name, table primary and foreign keys, and association relationships.

[0100] Embodiment 3:

[0101] like Figure 5 As shown, the present invention also provides an electronic device, which may be a computer device, a single-chip device, an intelligent mobile device, etc. The electronic device in this embodiment may include a processor, a memory, a transceiver component, etc. The memory, the processor, and the transceiver component are connected via a bus; the memory may be used to store an execution program, and an exemplary execution program may include instructions; the processor is used to execute the instructions stored in the memory. The memory may also be used to store data, which may be called and / or modified when the instructions are executed.

[0102] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in a storage medium to implement the corresponding method flow or corresponding functions, so as to realize the steps of an intelligent data interaction method for power equipment in the above-mentioned embodiment.

[0103] Example 4

[0104] Based on the same inventive concept, the present invention also provides a readable storage medium, specifically an electronic device readable storage medium (Memory), which is a memory device in an electronic device for storing programs and data. It can be understood that the storage medium here can include both built-in storage media in electronic devices and, of course, extended storage media supported by electronic devices. The storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by a processor are also stored in the storage space, and these instructions can be one or more execution programs (including program codes). It should be noted that the storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk storage. The processor loads and executes one or more instructions stored in the storage medium, which can implement the steps of a method for intelligent interaction of power equipment data in the above embodiment.

[0105] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0106] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0107] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0108] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0109] The above are merely embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application are included in the scope of the claims of the present application to be approved.

Claims

1. A method for intelligent interaction of power equipment data, characterized in that: include: Retrieve database table information based on query information input by the user to obtain database table information; Search the electric power equipment knowledge base based on the query information to obtain business knowledge calculation logic and context learning examples; Creating prompts based on the database table information, business knowledge calculation logic, and contextual learning examples, and inputting the prompts into the big model to generate database statements; Run the database statement and determine whether it is successful, and if successful, output the query result corresponding to the query information; Otherwise, error correction is performed according to the database statement, and the corrected database statement is obtained and re-run.

2. The method according to claim 1, characterized in that: The database table information is retrieved based on the query information input by the user to obtain the database table information, including: Encode the table name, column name and annotation information of the database table through an encoder to obtain a table vector library and a column vector library; The user query code based on the query information is subjected to cosine similarity calculation with the table vector library and the column vector library respectively to obtain the table name and column name with the highest matching degree, and the primary and foreign keys and the connection relationship with other database tables are extracted.

3. The method according to claim 1, characterized in that The searching of the electric power equipment knowledge base based on the query information to obtain the business knowledge calculation logic and context learning example includes: Based on the domain knowledge dictionary, the query information is retrieved using a fuzzy matching algorithm to obtain the business knowledge calculation logic; Based on the business knowledge question-answering database, the twin network encoding sentence vector is used to compare and learn with the query information to obtain contextual learning examples; Among them, the power equipment knowledge base is composed of a domain knowledge dictionary constructed based on indicator calculation, enumeration conditions, entity aliases and fuzzy intentions in multiple dimensions, and a business knowledge question and answer library constructed based on high-frequency query intentions in power equipment scenarios.

4. The method according to claim 1, characterized in that: The step of performing error correction according to the database statement, obtaining the corrected database statement and re-running the statement comprises: Based on the database statement, the thinking prompt chain technology is used to analyze the running error information, check whether the table name and column name exist, check whether the foreign key is correct, check whether there is missing or redundant ascending and descending or deduplication keywords, obtain the corrected database statement and re-run it.

5. The method according to claim 3, characterized in that: The database table information includes: one or more of: table name, column name, table primary and foreign keys, and association relationships.

6. An intelligent interactive system for power equipment data, characterized in that: include: A table information retrieval module is used to retrieve database table information based on query information input by a user to obtain database table information; A domain knowledge retrieval module, used to search the power equipment knowledge base based on the query information to obtain business knowledge calculation logic and context learning examples; A model reasoning module, used to create prompts based on the database table information, business knowledge calculation logic and context learning examples, and input the prompts into the big model to generate database statements; A correction module, used to run the database statement and determine whether it is successful, and if the operation is successful, output the query result corresponding to the query information; Otherwise, error correction is performed according to the database statement, and the corrected database statement is obtained and re-run.

7. The system according to claim 6, characterized in that The database table information retrieval module is specifically used for: Encode the table name, column name and annotation information of the database table through an encoder to obtain a table vector library and a column vector library; The user query code based on the query information is subjected to cosine similarity calculation with the table vector library and the column vector library respectively to obtain the table name and column name with the highest matching degree, and the primary and foreign keys and the connection relationship with other database tables are extracted.

8. The system according to claim 6, characterized in that The domain knowledge retrieval module is specifically used for: Based on the domain knowledge dictionary, the query information is retrieved using a fuzzy matching algorithm to obtain the business knowledge calculation logic; Based on the business knowledge question-answering database, the query information is retrieved by using a twin network encoding sentence vector combined with contrastive learning to obtain a context learning example; Among them, the power equipment knowledge base is composed of a domain knowledge dictionary constructed based on indicator calculation, enumeration conditions, entity aliases and fuzzy intentions in multiple dimensions, and a business knowledge question and answer library constructed based on high-frequency query intentions in power equipment scenarios.

9. The system according to claim 6, characterized in that The correction module is specifically used for: Based on the database statement, the thinking prompt chain technology is used to analyze the running error information, check whether the table name and column name exist, check whether the foreign key is correct, check whether there is missing or redundant ascending and descending or deduplication keywords, obtain the corrected database statement and re-run it.

10. The system according to claim 8, characterized in that The database table information in the database table information retrieval submodule includes: one or more of: table name, column name, table primary and foreign keys, and association relationships.

11. An electronic device, characterized in that: include: at least one processor and memory; The memory and the processor are connected via a bus; The memory is used to store one or more programs; When the one or more programs are executed by the at least one processor, an intelligent interaction method for power equipment data as described in any one of claims 1 to 5 is implemented.

12. A readable storage medium, characterized in that: An execution program is stored thereon, and when the execution program is executed, an intelligent interaction method for power equipment data as described in any one of claims 1 to 5 is implemented.

Images