Artificial Intelligence Modeling Method, Device, Equipment and Medium Based on Report System

Abstract

The present application relates to an artificial intelligence modeling method, device, equipment and medium based on a report system. The method includes: converting data sets, controls and pages in the report system into a target formatted language description document; obtaining a data dictionary, performing data preprocessing based on the data dictionary and the target formatted language description document, and generating a metadata information catalog of all current data; obtaining a query request input by a target user and identifying query keywords in the query request; obtaining target controls and target data corresponding to the query keywords based on the metadata information catalog; constructing a user profile of the target user and determining recommended information for the target user according to the user profile; generating target report information according to the target controls, target data and recommended information, and displaying the target report information. The present application realizes artificial intelligence modeling within the report system, which is beneficial to improving the accuracy of generating control and recommended data information.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to an artificial intelligence modeling method, device, equipment and medium based on a reporting system. Background Art

[0002] In the reporting system (including embedded reports in the business system, independent BI reports, etc.), the reports prepared by the implementation personnel are usually difficult to meet the needs of all inquirers. Especially when performing overview queries or statistical queries, managers often put forward various unique reporting requirements. When the AI big model appeared, someone proposed to introduce the AI big model into the reporting system, and the user directly described the requirements to the AI. The AI is responsible for converting the requirements into query instructions, and after querying the data, the results are sorted, analyzed, and presented to the user. With the improvement and popularization of the capabilities of the AI big model, there are also many solutions built using this type of model, including open source solutions provided by large companies. However, due to various practical limitations, the application effect of the products made based on this solution is unsatisfactory, and there are few customer cases of successful actual deployment.

[0003] The existing AI big models need to understand the specific data meaning of the customer before they can provide query functions. In terms of databases and data warehouses, customers can usually get the corresponding data dictionary provided by the application provider or the data warehouse builder. The data dictionary can provide the definition and function of each table and each field, but lacks guidance for specific business scenarios. In addition, the AI big model lacks a global understanding of complete application functions or enterprise data, which is specifically manifested in: a. Lack of logical data relationships between businesses, such as lack of knowledge of the relationship between order data and inventory data, so it is impossible to provide relevant related information query and analysis; b. Lack of user scenario awareness, for example, when a financial staff member starts to search, the AI big model does not know which information the financial staff is concerned about, so it is impossible to provide data in a targeted manner. Therefore, it is difficult for the AI big model in the existing reporting system to improve accurate data. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose an artificial intelligence modeling method, device, equipment and medium based on a reporting system to realize artificial intelligence modeling within the reporting system and improve the accuracy of control and recommended data information generation.

[0005] In order to solve the above technical problems, the embodiment of the present application provides an artificial intelligence modeling method based on a reporting system, including:

[0006] Convert data sets, controls and pages in the report system into target formatting language description documents;

[0007] Obtain a data dictionary, and perform data preprocessing based on the data dictionary and the target formatted language description document to generate a metadata information catalog of all current data;

[0008] Obtain a query request input by a target user, and identify the query keywords in the query request;

[0009] Based on the metadata information catalog, obtain the target control corresponding to the query keyword;

[0010] Construct a user profile of the target user, and determine the recommended information of the target user according to the user profile;

[0011] Generate target report information according to the target control and the recommended information, and display the target report information.

[0012] To solve the above technical problems, an embodiment of the present application provides an artificial intelligence modeling device based on a report system, including:

[0013] A document conversion module, configured to convert datasets, controls, and pages in a report system into a target formatted language description document;

[0014] A preprocessing module, configured to obtain a data dictionary, and perform data preprocessing based on the data dictionary and the target formatted language description document to generate a metadata information catalog of all current data;

[0015] A request acquisition module, configured to obtain a query request input by a target user, and identify the query keywords in the query request;

[0016] A control acquisition module, configured to obtain the target control corresponding to the query keyword based on the metadata information catalog;

[0017] A user profile construction module, configured to construct a user profile of the target user, and determine the recommended information of the target user according to the user profile;

[0018] An information display module, configured to generate target report information according to the target control and the recommended information, and display the target report information.

[0019] To solve the above technical problems, a technical solution adopted by the present invention is: to provide a computer device, including one or more processors; a memory for storing one or more programs, so that one or more processors implement the artificial intelligence modeling method based on a report system described in any one of the above.

[0020] To solve the above technical problems, a technical solution adopted by the present invention is: a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the artificial intelligence modeling method based on the report system described in any one of the above is implemented.

[0021] An embodiment of the present invention provides an artificial intelligence modeling method, device, equipment and medium based on a report system. Among them, the method includes: converting the data set, controls and pages in the report system into a target formatted language description document; obtaining a data dictionary, and performing data preprocessing based on the data dictionary and the target formatted language description document to generate a metadata information catalog of all current data; obtaining a query request input by a target user, and identifying a query keyword in the query request; obtaining a target control corresponding to the query keyword based on the metadata information catalog; constructing a user portrait of the target user, and determining recommended information for the target user according to the user portrait; generating target report information according to the target control and the recommended information, and displaying the target report information. In the embodiment of the present invention, the data set, controls and pages in the report system are converted into a target formatted language description document, and a metadata information catalog of all current data is generated. At the same time, when the user makes a query, the corresponding control can be accurately queried according to the metadata information catalog, and the recommended information can be accurately identified according to the user portrait, so as to realize artificial intelligence modeling in the report system, which is beneficial to improving the accuracy of generating control and recommended data information. Description of the Drawings

[0022] In order to more clearly illustrate the solutions in the present application, the following will briefly introduce the drawings required for the description of the embodiments of the present application. Obviously, the following drawings are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings.

[0023] Figure 1 It is a flowchart of the implementation of the artificial intelligence modeling method based on the report system provided by the embodiment of the present application;

[0024] Figure 2 It is a flowchart of the implementation of the first sub-process in the artificial intelligence modeling method based on the report system provided by the embodiment of the present application;

[0025] Figure 3 It is a flowchart of the implementation of the second sub-process in the artificial intelligence modeling method based on the report system provided by the embodiment of the present application;

[0026] Figure 4 It is a flowchart of the implementation of the third sub-process in the artificial intelligence modeling method based on the report system provided by the embodiment of the present application;

[0027] Figure 5 It is the implementation flowchart of the fourth sub - process in the artificial intelligence modeling method based on a report system provided by an embodiment of the present application;

[0028] Figure 6 It is the implementation flowchart of the fifth sub - process in the artificial intelligence modeling method based on a report system provided by an embodiment of the present application;

[0029] Figure 7 It is the implementation flowchart of the sixth sub - process in the artificial intelligence modeling method based on a report system provided by an embodiment of the present application;

[0030] Figure 8 It is a schematic diagram of an artificial intelligence modeling device based on a report system provided by an embodiment of the present application;

[0031] Figure 9 It is a schematic diagram of a computer device provided by an embodiment of the present application. Detailed implementation manners

[0032] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs; the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above - mentioned drawings are intended to cover non - exclusive inclusion. The terms "first", "second", etc. in the specification and claims of this application or the above - mentioned drawings are used to distinguish different objects and not to describe a specific order.

[0033] Referring to "embodiments" herein means that specific features, structures, or characteristics described in connection with the embodiments can be included in at least one embodiment of this application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0034] In order to enable those skilled in the technical field to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0035] The present invention will be described in detail below with reference to the accompanying drawings and embodiments.

[0036] It should be noted that the artificial intelligence modeling method based on a report system provided by the embodiments of this application is generally executed by a server. Correspondingly, the artificial intelligence modeling device based on a report system is generally configured in the server.

[0037] Specifically, most current AI (Artificial Intelligence) solutions are independently built and can be connected to any software system. However, the AI solution in the embodiments of the present application is only an extended function of the report system and is integrated with the report system. Other applications (applications that need to embed the report system) should use the entire report system if they need to use it; the separately deployed report system (which can be applied to the intelligent cockpit for enterprise digital transformation, etc.) can be directly used. The present application is an independently deployed AI system, and the knowledge base it constructs requires the user to provide the data dictionary of the database to be connected. The embodiments of the present application can achieve artificial intelligence modeling within the report system, which is beneficial to improving the accuracy of generating control and recommended data information.

[0038] Please refer to Figure 1 , Figure 1 which shows a specific implementation manner of the artificial intelligence modeling method based on the report system.

[0039] It should be noted that if there are substantially the same results, the method of the present invention is not limited to Figure 1 the process sequence of the method shown, and the method includes the following steps:

[0040] S1: Convert the data set, control, and page in the report system into a target formatted language description document.

[0041] Specifically, the report system will first save a query as a data set, and the data set includes a name, a database link, and a query instruction. Each displayed data element in the report system is a control, and the control includes a name, a style (for example, if it is a pie chart, specific values and proportions need to be displayed; for example, if it is a form, which field is used for sorting, etc.), and an associated data set. The smallest unit presented at one time is a page, which includes a name and multiple controls. In the embodiments of the present application, the data set, control, and page in the report system are converted into a target formatted language description document. The data set, control, and page in the report system are all provided with their own permission controls. These permission control information will be associated with the data set, control, and page.

[0042] Please refer to Figure 2 , Figure 2 which shows a specific implementation manner of step S1, described in detail as follows:

[0043] S11: Generate a first formatted language description document based on the query instruction for the non-embedded query data set in the report system.

[0044] Among them, the first formatted language description document includes data basic information, data result information, query information, permission control information, business rule information, and metadata version control information. The basic information includes the dataset name and unique identifier, associated database link information, creation time and last modification time, creator and maintainer information. The data structure information includes the involved tables and field definitions, the association relationships between fields (foreign keys, references, etc.), the business meanings and constraint conditions of fields, and the calculation logics of calculated fields. The query-related information includes the original query instructions, query conditions and filtering rules, sorting and grouping rules, aggregation functions and calculation formulas, and performance optimization tips (such as index usage suggestions). The permission control includes: field-level access permissions, data row-level filtering rules, permission rules for special roles, and sensitive data processing strategies. The business rules include: the business logic relationships between fields, data quality rules, business scenario tags, and common analysis dimensions. The metadata version control includes: version numbers and change records, dependency tracking, marked obsolete fields, and compatibility descriptions.

[0045] In the embodiments of the present application, for a dataset, since its main content is a query instruction, first, an AI model is used to analyze this query instruction to generate a document described in a formatted language (such as json). Since the query language is not a natural language, a specially tuned AI model or a general AI model supplemented with specific prompt words is used to decompose the query intention of the query language (including but not limited to SQL) to generate a formatted language. This is to avoid the differences, complexities, and irrelevancies of the query language. Differences: Relational databases use SQL, but data warehouses, object-oriented databases, streaming databases, big data processing services, third-party APIs, etc. usually have their own query language standards. It is necessary to organize them into a unified format for subsequent processing. Complexity: Due to differences in databases, for the same business data relationship, the data subordination relationships in different data sources may be different. And the present invention only needs to focus on the results presented by its datasets (flat data tables), and it is necessary to avoid the hierarchical interference of the data sources to subsequent model processing. Irrelevancy: In addition to fields, queries usually also include functions such as conditions, union queries, embedded subqueries, and function calls. Since the present invention uses these datasets as raw data and does not directly operate on the database, the AI does not need to understand these additional functions and only needs to focus on the fields.

[0046] Since the system of the present invention will not finally execute a query command in the data source to obtain the raw data by generating it, but through the reuse and integration of existing data sources, the system does not need to understand the calculations, built-in fixed conditions, fixed grouping, and summary formulas, etc. when obtaining the datasets, but needs to try to understand the business relationships between the datasets;

[0047] S12: Recursively analyze the embedded query datasets in the report system to generate multi-level relationship description information, and store the relationship description information in a vector database.

[0048] Specifically, for complex datasets with embedded queries, the system will recursively analyze and generate multi-level relationship descriptions for reuse in different query levels (such as explicit fact queries and implicit fact queries). This information will be stored in a vector database to support semantic retrieval and similarity matching.

[0049] In a specific embodiment, for datasets with embedded queries (such as embedded queries with SQL conditions), it is necessary to perform an independent analysis of the relationships of each subquery embedded in it. If there are still subqueries in the embedded query, the recursive execution is repeated. The process of this analysis is similar to the outer analysis, analyzing the tables and fields used in the query. The commands of the subqueries may be highly similar to the queries of some independent databases, and this information can determine the relationships between different data sources and be combined for use in subsequent queries;

[0050] S13: Convert the controls and pages in the report system into a second formatted language description document and a third formatted language description document respectively;

[0051] S14: Generate the target formatted language description document based on the first formatted language description document, the second formatted language description document, and the third formatted language description document;

[0052] Specifically, the controls in the report system are converted into a second formatted language description document through program code. In the second formatted language description document, information such as the name of this control, the name of the related dataset, the display style, filtering conditions, sorting and grouping, access permissions, etc. will be described. The pages in the report system are converted into a third formatted language description document through program code. In the third formatted language description document, information such as the name of this page, the name of the related controls, the hierarchical relationship (such as the control grouping under the page), the placement location, access permissions, etc. will be described;

[0053] S2: Obtain a data dictionary, and perform data preprocessing based on the data dictionary and the target formatted language description document to generate a catalog of metadata information for all current data.

[0054] Specifically, obtain the data dictionary provided by the original data provider (such as the system developer), and perform data preprocessing based on the data dictionary and the target formatted language description document, and integrate them into a unified catalog of metadata information for all current data.

[0055] Please refer to Figure 3 ,Figure 3 A specific implementation manner of step S2 is shown and described in detail as follows:

[0056] S21: Obtain the data dictionary provided by the original data provider;

[0057] S22: Perform data cleaning and standardization processing on the data dictionary and the target formatted language description document to generate target data information.

[0058] Please refer to Figure 4 , Figure 4 which shows a specific implementation manner of step S22 and is described in detail as follows:

[0059] S221: Perform unified field naming and data type on the data dictionary and the target formatted language description document to obtain basic data information;

[0060] S222: Remove outliers and missing values from the basic data information, and perform formula processing on business terms in the basic data information to obtain preprocessed data information;

[0061] S223: Build a field mapping relationship based on the preprocessed data information to generate the target data information.

[0062] Specifically, for data standardization, reducing data redundancy and data errors, it is necessary to perform unified field naming and data type on the data dictionary and the target formatted language description document to obtain basic data information, then remove outliers and missing values from the basic data information, and perform formula processing on business terms in the basic data information to obtain preprocessed data information, and then build a field mapping relationship based on the preprocessed data information to generate target data information;

[0063] S23: Use the RAGFlow engine to build a knowledge graph based on the target data information.

[0064] In the embodiment of the present application, the RAGFlow engine is used to construct a knowledge graph based on target data information. Among them, RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding. In the embodiment of the present application, entity intelligent recognition, relationship deep mining, multi-hop reasoning architecture, spatio-temporal causal modeling, and LLM collaborative construction can be realized. Among them, entity intelligent recognition combines the spaCy NER model and the BLINK entity linking technology to achieve accurate recognition and disambiguation of business entities. Relationship deep mining uses distant supervision plus pre-trained models to extract explicit / implicit business relationships (such as order-inventory association). The multi-hop reasoning architecture is based on graph neural networks to achieve reasoning capabilities across 3 levels of nodes (such as: order → product → supplier). Spatio-temporal causal modeling encodes time series and causal relationships in business rules (such as the impact of sales fluctuations on inventory). LLM collaborative construction is to establish a feedback optimization closed-loop through large model-assisted relationship discovery and pattern recognition. Since relationship mining is carried out in the embodiment of the present application, LLM collaborative relationship verification can be used, that is, the relationships mined by the algorithm are handed over to the LLM for business rationality verification (such as the causal relationship of "customer satisfaction → logistics timeliness"). At the same time, after the multi-hop reasoning is calculated, the LLM can also be used to judge the rationality and extend new multi-hop reasoning hypotheses, for example: path hypothesis (such as the link of "inventory backlog → capital turnover → financial expenses").

[0065] The knowledge graph in the embodiment of the present application includes a node structure and a relationship network. Among them, the node structure includes entity nodes, relationship edges, and community division. Entity nodes include name, description, type (such as organization / person / location). Relationship edges are explicit / implicit associations between entities. Community division is an entity community automatically clustered by graph algorithms. The entities therein are determined based on the actual business scenario. In one example, the business entity layer includes core business objects (orders / inventory / products), data elements (fields / tables / queries), and system components (data sets / controls / pages). The relationship network includes data logical relationships (order → inventory impact relationship), business rule relationships (calculation formula dependency chain), and permission inheritance relationships (permission transfer from page → control → field);

[0066] S24: Perform vectorization processing based on the topological structure of the knowledge graph to generate index information.

[0067] Please refer to Figure 5 , Figure 5 which shows a specific implementation manner of step S24, and is described in detail as follows:

[0068] S241: Encode the topological structure of the knowledge graph into a vector space to perform vectorization processing on the result information of the knowledge graph and generate the multi-dimensional vector index;

[0069] S242: Use a graph attention network to construct vector representation information of graph context based on the multi-dimensional vector index;

[0070] S243: Construct the progressive hierarchical index based on the vector representation information.

[0071] Specifically, encode the topological structure of the knowledge graph into the vector space to vectorize the result information of the knowledge graph, generate a multi-dimensional vector index, then use a graph attention network to construct vector representation information of graph context based on the multi-dimensional vector index, and then construct a progressive hierarchical index based on the vector representation information. This hierarchical index is a progressive index from the concept layer to the entity layer to the attribute layer. In the embodiments of the present application, the topological structure of the knowledge graph can also be used to optimize the vector retrieval performance and implement an incremental update mechanism;

[0072] S25: Construct a query module library and cache access information based on the target data information according to a preset cache policy.

[0073] Specifically, cache common query results according to a preset cache policy, pre-generate typical analysis scenarios, construct a query template library, and optimize hot data access. The pre-generated typical analysis scenarios can be weekly sales reports, inventory warnings, etc. By pre-generating analysis scenarios, users can directly call them when querying, reducing the time for real-time processing. Manually analyze historical query data or industry general templates to determine the analysis scenarios.

[0074] Establishing a query template library is to abstract common query patterns into reusable templates, such as filtering by time range, summarizing by department, etc. The establishment of the template library requires extracting patterns from existing reports and user queries, and natural language processing or pattern recognition technology such as LLM is needed to classify similar query requests. The hot data in optimizing hot data access refers to the data that is frequently accessed. The optimization strategies include cache policies, index optimization, or preloading mechanisms. Determine which data belongs to hot data according to the monitored access frequency, and at the same time use cache technologies such as Redis, or adjust the database index to speed up the query of data;

[0075] S26: Construct a catalog of metadata information for all current data based on the target data information, the knowledge graph, the index information, the query template library, and the cache access information.

[0076] Specifically, integrate the above preprocessed data (including target data information, knowledge graph, index information, query template library, and cache access information, etc.) into a unified catalog of metadata information.

[0077] Further, in another specific embodiment, for small-scale models running locally, the system will perform model tuning based on the preprocessed data, including tasks such as intent recognition, entity extraction, and relationship reasoning. For large-scale deployment scenarios, the preprocessed data will serve as a RAG knowledge base to support different levels of query requirements. Among them, the query requirements include: explicit fact query, implicit fact query, interpretability reasoning, and implicit reasoning query. An explicit fact query directly retrieves relevant information from the vector index. An implicit fact query performs multi-hop reasoning through a knowledge graph. Interpretability reasoning combines business rules for logical deduction. An implicit reasoning query uses historical data for pattern recognition;

[0078] S3: Obtain the query request input by the target user and identify the query keywords in the query request.

[0079] Specifically, the above steps have preprocessed the data in the report system to generate metadata information cataloging and knowledge base and other information. Therefore, after the target user enters a query request in the report system, it is necessary to identify the query keywords in the query request. The query keywords in the query request can be identified through a natural language model;

[0080] S4: Based on the metadata information cataloging, obtain the target control corresponding to the query keyword.

[0081] Specifically, in the metadata information cataloging, the corresponding control or control set can be matched according to the query keyword, and then the target control is determined from these controls or control sets.

[0082] Please refer to Figure 6 , Figure 6 which shows a specific implementation manner of step S4, described in detail as follows:

[0083] S41: Match the control or control set corresponding to the query keyword from the metadata information cataloging;

[0084] S42: Perform data query according to the style and associated data set of the control or the control set to determine the target control, and sort the target control by grouping;

[0085] S43: If the control or the control set is not matched, generate a supplementary recording prompt message and feedback it to the target user based on the supplementary recording prompt message.

[0086] Among them, the control or set of controls corresponding to the query keyword is matched from the metadata information catalog. Then, data query is performed according to the styles of the control or the set of controls and the associated data sets to determine the target control, and the target control is sorted according to the grouping. The control grouping can be performed according to the names in the page corresponding to the controls. The control sorting can be sorted according to the generation time or according to the similarity. If the control or the set of controls is not matched, a supplementary recording prompt message is generated and fed back to the target user based on the supplementary recording prompt message to remind the target user to perform the supplementary recording of the control;

[0087] S5: Construct the user portrait of the target user, and determine the recommended information of the target user according to the user portrait.

[0088] Please refer to Figure 7 , Figure 7 which shows a specific implementation manner of step S5, and is described in detail as follows:

[0089] S51: Obtain the historical data of the target user, and identify the user type, preference tags, display preference information, business field and permission information of the target user based on the historical data;

[0090] S52: Construct the user portrait of the target user according to the user type, the preference tags, the display preference information, the business field and the permission information;

[0091] S53: Determine the recommended information of the target user according to the user portrait.

[0092] Specifically, the user portraits of each user can be constructed in advance. When a user makes a query, the user portrait corresponding to the querying user can be determined, and the recommended information of the user can be determined according to the user portrait, so as to generate the recommended information that the user is interested in and improve the accuracy of data recommendation. In the embodiment of the present application, the historical data of the target user is obtained, and the user type, preference tags, display preference information, business field and permission information of the target user are identified based on the historical data. The user portrait of the target user is constructed according to the user type, preference tags, display preference information, business field and permission information, and finally the recommended information of the target user is determined according to the user portrait.

[0093] Among them, the user type is automatically identified by analyzing the keywords commonly used by the user (such as financial staff, sales manager). The preference label records the data types that the user often views (such as sales amount, inventory), forming preference labels. Displaying preference information means remembering the chart styles most recently used by the user (such as the pie chart / bar chart selected in the last 10 times). The business area is to count the business areas most frequently queried by the user (such as frequently querying order-related data). The permission information records the data range that the user can access to ensure no overstepping of authority.

[0094] In a specific embodiment, a "standard tool kit" is automatically recommended according to the position of the target user (such as a sales director defaulting to seeing a customer analysis dashboard). The route can be predicted based on the target user's navigation software, and automatically prepared in advance according to the sales weekly report that the user must check every Monday in the past 3 months;

[0095] S6: Generate target report information according to the target control and the recommendation information, and display the target report information.

[0096] Specifically, in the report system, generate target report information based on the target control and the recommendation information, and display the target report information to the target user.

[0097] Furthermore, the embodiment of the present application can record the actual usage of the recommended content by the user, automatically update the user feature information regularly, and compare the effects of different recommendation strategies regularly. At the same time, it can also clean up the display templates that have not been used for a long time, discover new business rules and update the rules. Each time a query request is generated and the location of the original data is displayed in the report system, a button will be added to allow the user to save this query as a data set and a control for direct use in subsequent report design. For the same or highly similar content queried by multiple users multiple times, AI will give a reminder and recommend saving it.

[0098] In the embodiments of the present application, the data sets, controls, and pages in the report system are converted into a target formatted language description document; a data dictionary is obtained, and data preprocessing is performed based on the data dictionary and the target formatted language description document to generate a metadata information catalog of all current data; a query request input by a target user is obtained, and the query keywords in the query request are identified; a target control corresponding to the query keywords is obtained based on the metadata information catalog; a user portrait of the target user is constructed, and recommended information for the target user is determined according to the user portrait; target report information is generated according to the target control and the recommended information, and the target report information is displayed. In the report system of the embodiments of the present invention, the data sets, controls, and pages are converted into a target formatted language description document, and a metadata information catalog of all current data is generated. At the same time, when the user makes a query, the corresponding control and data can be accurately queried according to the metadata information catalog, and the recommended information can be accurately identified according to the user portrait, so as to realize artificial intelligence modeling in the report system, which is beneficial to improving the accuracy of the generation of control and recommended data information.

[0099] Please refer to Figure 8 , as an implementation of the above Figure 1 method shown, an embodiment of an artificial intelligence modeling device based on a report system is provided in the present application. This device embodiment corresponds to the Figure 1 method embodiment shown, and this device can be specifically applied to various electronic devices.

[0100] As Figure 8 shown, the artificial intelligence modeling device based on the report system in this embodiment includes: a document conversion module 71, a preprocessing module 72, a request acquisition module 73, a control acquisition module 74, a user portrait construction module 75, and an information display module 76, where:

[0101] The document conversion module 71 is used to convert the data sets, controls, and pages in the report system into a target formatted language description document;

[0102] The preprocessing module 72 is used to obtain a data dictionary, perform data preprocessing based on the data dictionary and the target formatted language description document, and generate a metadata information catalog of all current data;

[0103] The request acquisition module 73 is used to obtain a query request input by a target user and identify the query keywords in the query request;

[0104] The control acquisition module 74 is used to obtain a target control corresponding to the query keywords based on the metadata information catalog;

[0105] The user profile construction module 75 is used to construct the user profile of the target user and determine the recommended information of the target user according to the user profile;

[0106] The information display module 76 is used to generate target report information according to the target control and the recommended information and display the target report information.

[0107] Furthermore, the document conversion module 71 includes:

[0108] The first conversion unit is used to generate a first formatted language description document based on the non-embedded query data set in the report system according to a query instruction, where the first formatted language description document includes data basic information, data result information, query information, permission control information, business rule information, and metadata version control information;

[0109] The recursive analysis unit is used to perform recursive analysis on the embedded query data set in the report system, generate multi-level relationship description information, and store the relationship description information in a vector database;

[0110] The second conversion unit is used to convert the controls and pages in the report system into a second formatted language description document and a third formatted language description document respectively;

[0111] The description document generation unit is used to generate the target formatted language description document based on the first formatted language description document, the second formatted language description document, and the third formatted language description document.

[0112] Furthermore, the preprocessing module 72 includes:

[0113] The data dictionary acquisition unit is used to acquire the data dictionary provided by the original data provider;

[0114] The target data information generation unit is used to perform data cleaning and standardization processing on the data dictionary and the target formatted language description document to generate target data information;

[0115] The knowledge graph construction unit is used to construct a knowledge graph based on the target data information by using the RAGFlow engine;

[0116] The index information generation unit is used to perform vectorization processing based on the topological structure of the knowledge graph to generate index information;

[0117] The query module library construction unit is used to construct a query module library and cache access information based on the target data information according to a preset cache policy;

[0118] A catalog generation unit, configured to construct a catalog of the metadata information of all current data according to the target data information, the knowledge graph, the index information, the query template library, and the cache access information.

[0119] Further, the target data information generation unit includes:

[0120] A basic data information generation unit, configured to perform unified field naming and data type on the data dictionary and the target formatted language description document to obtain basic data information;

[0121] A preprocessed data information generation unit, configured to remove outliers and missing values from the basic data information, and perform formula processing on business terms and calculation formulas in the basic data information to obtain preprocessed data information;

[0122] A mapping relationship construction unit, configured to construct a field mapping relationship based on the preprocessed data information to generate the target data information.

[0123] Further, the index information includes a multi-dimensional vector index and a hierarchical index, and the index information generation unit includes:

[0124] A vectorization processing unit, configured to encode the topological structure of the knowledge graph into a vector space to perform vectorization processing on the result information of the knowledge graph and generate the multi-dimensional vector index;

[0125] A vector representation information construction unit, configured to construct vector representation information of graph context based on the multi-dimensional vector index using a graph attention network;

[0126] A hierarchical index construction unit, configured to construct the progressive hierarchical index based on the vector representation information.

[0127] Further, the control acquisition module 74 includes:

[0128] A module space construction unit, configured to match a control or a set of controls corresponding to the query keyword from the catalog of the metadata information;

[0129] A control sorting unit, configured to perform data query according to the style of the control or the set of controls and the associated data set to determine the target control, and sort the target control according to groups;

[0130] A supplementary recording prompt information generation unit, configured to generate supplementary recording prompt information if the control or the set of controls is not matched, and feedback the supplementary recording prompt information to the target user.

[0131] Further, the user portrait construction module 75 includes:

[0132] A historical data acquisition unit, configured to acquire historical data of the target user, and identify a user type, preference tags, display preference information, business field, and permission information of the target user based on the historical data;

[0133] A user profile generation unit, configured to construct a user profile of the target user according to the user type, the preference tags, the display preference information, the business field, and the permission information;

[0134] A recommended information generation unit, configured to determine recommended information for the target user according to the user profile.

[0135] To solve the above technical problems, an embodiment of the present application further provides a computer device. For details, please refer to Figure 9 , Figure 9 which is a basic structural block diagram of the computer device in this embodiment.

[0136] The computer device 8 includes a memory 81, a processor 82, and a network interface 83 that communicate with each other through a system bus. It should be noted that Figure 9 only a computer device 8 with three components, namely a memory 81, a processor 82, and a network interface 83, is shown in

[0137] However, it should be understood that it is not required to implement all the shown components, and more or fewer components can be alternatively implemented. Among them, those skilled in the art of the present technology can understand that a computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), an embedded device, etc.

[0138] The memory 81 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disc, etc. In some embodiments, the memory 81 may be an internal storage unit of the computer device 8, such as the hard disk or memory of the computer device 8. In other embodiments, the memory 81 may also be an external storage device of the computer device 8, such as a plug-in hard disk, SmartMedia Card (SMC), Secure Digital (SD) card, Flash Card, etc. equipped on the computer device 8. Of course, the memory 81 may also include both the internal storage unit and the external storage device of the computer device 8. In this embodiment, the memory 81 is generally used to store the operating system and various application software installed on the computer device 8, such as the program code of the artificial intelligence modeling method based on the report system. In addition, the memory 81 may also be used to temporarily store various data that have been output or will be output.

[0139] In some embodiments, the processor 82 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. The processor 82 is generally used to control the overall operation of the computer device 8. In this embodiment, the processor 82 is used to run the program code stored in the memory 81 or process data, such as running the program code of the above artificial intelligence modeling method based on the report system to implement various embodiments of the artificial intelligence modeling method based on the report system.

[0140] The network interface 83 may include a wireless network interface or a wired network interface, and the network interface 83 is generally used to establish a communication connection between the computer device 8 and other electronic devices.

[0141] The present application also provides another implementation manner, that is, to provide a computer-readable storage medium storing a computer program, and the computer program can be executed by at least one processor so that at least one processor executes the steps of an artificial intelligence modeling method based on a report system as described above.

[0142] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described example methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present application, in essence or the part that contributes 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 ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods of the various embodiments of the present application.

[0143] Obviously, the above-described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The accompanying drawings show preferred embodiments of the present application, but do not limit the scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosed content of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments or equivalently replace some of the technical features. Any equivalent structure directly or indirectly using the content of the specification and drawings of the present application in other related technical fields is similarly within the protection scope of the present application.

Claims

1. An artificial intelligence modeling method based on a report system, characterized in that, Including: Converting datasets, controls, and pages in the report system into a target formatted language description document; Obtaining a data dictionary, performing data preprocessing based on the data dictionary and the target formatted language description document, and generating a metadata information catalog of all current data; Obtaining a query request input by a target user and identifying query keywords in the query request; Obtaining a target control corresponding to the query keyword based on the metadata information catalog; Constructing a user profile of the target user and determining recommended information for the target user according to the user profile; Generating target report information according to the target control and the recommended information, and displaying the target report information; The obtaining a data dictionary, performing data preprocessing based on the data dictionary and the target formatted language description document, and generating a metadata information catalog of all current data includes: Obtaining the data dictionary provided by the original data provider; Performing data cleaning and standardization processing on the data dictionary and the target formatted language description document to generate target data information; Using the RAGFlow engine to construct a knowledge graph based on the target data information; Performing vectorization processing based on the topological structure of the knowledge graph to generate index information; Constructing a query template library and cache access information based on the target data information according to a preset cache policy; Constructing the metadata information catalog of all current data according to the target data information, the knowledge graph, the index information, the query template library, and the cache access information.

2. The artificial intelligence modeling method based on a report system according to claim 1, wherein The converting datasets, controls, and pages in the report system into a target formatted language description document includes: Generating a first formatted language description document for non-embedded query datasets in the report system based on a query instruction, where the first formatted language description document includes data basic information, data result information, query information, permission control information, business rule information, and metadata version control information; Performing recursive analysis on the embedded query datasets in the report system to generate multi-level relationship description information, and storing the relationship description information in a vector database; Respectively converting controls and pages in the report system into a second formatted language description document and a third formatted language description document; Generating the target formatted language description document based on the first formatted language description document, the second formatted language description document, and the third formatted language description document.

3. The artificial intelligence modeling method based on the report system according to claim 1, wherein The performing data cleaning and standardization processing on the data dictionary and the target formatted language description document to generate target data information includes: Performing unified field naming and unified data type on the data dictionary and the target formatted language description document to obtain basic data information; Removing outliers and missing values from the basic data information and performing standardization processing on business terms in the basic data information to obtain preprocessed data information; Constructing a field mapping relationship based on the preprocessed data information to generate the target data information.

4. The artificial intelligence modeling method based on a report system according to claim 1, characterized in that, The index information includes a multi-dimensional vector index and a hierarchical index. The vectorization process based on the topological structure of the knowledge graph to generate index information includes: Encoding the topological structure of the knowledge graph into a vector space to vectorize the result information of the knowledge graph and generate the multi-dimensional vector index; Using a graph attention network to construct vector representation information of the graph context based on the multi-dimensional vector index; Constructing the progressive hierarchical index based on the vector representation information.

5. The artificial intelligence modeling method based on a report system according to any one of claims 1 to 4, characterized in that The obtaining of the target control corresponding to the query keyword based on the cataloging of the metadata information includes: Matching the control or control set corresponding to the query keyword from the cataloging of the metadata information; Performing data query according to the style and associated data set of the control or the control set to determine the target control, and sorting the target control by grouping; If the control or the control set is not matched, generating a supplementary cataloging prompt information and feeding it back to the target user based on the supplementary cataloging prompt information.

6. The artificial intelligence modeling method based on a report system according to any one of claims 1 to 4, characterized in that The constructing of the user profile of the target user and determining the recommended information of the target user according to the user profile includes: Obtaining the historical data of the target user, and identifying the user type, preference tags, display preference information, business domain and permission information of the target user based on the historical data; Constructing the user profile of the target user according to the user type, the preference tags, the display preference information, the business domain and the permission information; Determining the recommended information of the target user according to the user profile.

7. An artificial intelligence modeling device based on a report system, characterized in that, It includes: A document conversion module for converting data sets, controls and pages in a report system into a target formatted language description document; A preprocessing module for obtaining a data dictionary, performing data preprocessing based on the data dictionary and the target formatted language description document, and generating a cataloging of metadata information of all current data; A request acquisition module for acquiring a query request input by a target user and identifying a query keyword in the query request; A control acquisition module for obtaining a target control corresponding to the query keyword based on the cataloging of the metadata information; A user profile construction module for constructing the user profile of the target user and determining the recommended information of the target user according to the user profile; An information display module for generating target report information according to the target control and the recommended information, and displaying the target report information; The preprocessing module includes: A data dictionary acquisition unit for acquiring the data dictionary provided by the original data provider; A target data information generation unit for performing data cleaning and standardization processing on the data dictionary and the target formatted language description document to generate target data information; A knowledge graph construction unit for constructing a knowledge graph based on the target data information by using the RAGFlow engine; An index information generation unit for performing vectorization processing based on the topological structure of the knowledge graph to generate index information; A query module library construction unit for constructing a query template library and cache access information based on the target data information according to a preset cache policy; A catalog generation unit, configured to construct a catalog of metadata information of all current data according to the target data information, the knowledge graph, the index information, the query template library, and the cache access information.

8. A computer device, characterized in that, It includes a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the artificial intelligence modeling method based on the report system according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium. When the computer program is executed by the processor, the artificial intelligence modeling method based on the report system according to any one of claims 1 to 6 is implemented.

Images