Heuristic BI tool generation method, device, electronic device and storage medium

Abstract

The present invention relates to the field of business intelligence technology, and provides a method, device, electronic device and storage medium for generating a heuristic BI tool. The method comprises: first obtaining a target data set selected by a user from a target database; then using a preset business category recognition model to identify the target data set to obtain a recognition result; then using a preset business scenario generation model, based on the recognition result and the target data set, generating each business scenario and its data analysis idea; finally using a preset business scenario encoding model, based on each business scenario and its data analysis idea and the target database, generating a heuristic BI tool corresponding to the target data set; the heuristic BI tool is used to perform data analysis on a data set with the same data structure as the target data set. Users can use BI tools without having business background and data analysis knowledge, which lowers the threshold for using BI tools and improves the efficiency of data analysis and business decision-making.

Description

Technical Field

[0001] The present invention relates to the field of business intelligence technology, and in particular to a method, device, electronic device and storage medium for generating a heuristic BI tool. Background Art

[0002] BI (Business Intelligence) is a technology used to analyze and process business data to help enterprises make decisions based on data. Current conversational BI tools generate and display reports based on the data sets and data analysis requirements input by users. However, for conversational BI tools, users are usually required to accurately express their data analysis needs. Since most users lack relevant business background knowledge and have little knowledge of data analysis expertise, users are unable to accurately describe their needs, resulting in a high threshold for using conversational BI tools. In addition, conversational BI tools are obtained by fine-tuning large language models using specific business data, and can only perform data analysis on a single business. For industries with multiple businesses, such as the equipment manufacturing industry, conversational BI tools cannot be used for data analysis. Summary of the invention

[0003] In view of this, an object of the present invention is to provide a method, device, electronic device and storage medium for generating a heuristic BI tool.

[0004] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0005] In a first aspect, the present invention provides a method for generating a heuristic BI tool, the method comprising:

[0006] Obtain the target data set selected by the user from the target database;

[0007] Using a preset business category recognition model, the target data set is recognized to obtain a recognition result;

[0008] Using a preset business scenario generation model, based on the recognition result and the target data set, each business scenario and its data analysis ideas are generated;

[0009] Utilizing a preset business scenario coding model, based on each of the business scenarios and its data analysis ideas as well as the target database, a heuristic BI tool corresponding to the target data set is generated; wherein the heuristic BI tool is used to perform data analysis on a data set having the same data structure as the target data set.

[0010] In an optional implementation, the recognition result is a target business category to which the target data set belongs;

[0011] The step of using a preset business scenario generation model to generate each business scenario and its data analysis ideas based on the recognition result and the target data set includes:

[0012] According to a first preset template, generating a first prompt word according to the target data set and the target business category;

[0013] The first prompt word is input into the business scenario generation model, and the business scenario generation model is used to generate each business scenario corresponding to the target business category and its data analysis ideas.

[0014] In an optional implementation manner, the identification result is empty or a preset mark, and the preset mark indicates that the business category to which the target data set belongs is not identified;

[0015] The step of using a preset business scenario generation model to generate each business scenario and its data analysis ideas based on the recognition result and the target data set includes:

[0016] According to a second preset template, generating a second prompt word according to the target data set;

[0017] The second prompt word is input into the business scenario generation model, and the business scenario generation model is used to determine the new business category to which the target data set belongs, and to generate each business scenario corresponding to the new business category and its data analysis ideas.

[0018] In an optional implementation, the step of using a preset business scenario coding model to generate a heuristic BI tool corresponding to the target data set based on each of the business scenarios and its data analysis ideas and the target database includes:

[0019] Each of the business scenarios and its data analysis ideas as well as the target database are input into the business scenario coding model, and the target programming language is determined using the business scenario coding model, and the component set corresponding to each of the business scenarios is determined according to the preset component library, and execution code is generated based on each of the component sets according to the target programming language, and a file containing the execution code of all component sets is obtained, thereby obtaining a heuristic BI tool corresponding to the target data set.

[0020] In an optional implementation, the step of using a preset business scenario coding model to generate a heuristic BI tool corresponding to the target data set based on each of the business scenarios and its data analysis ideas and the target database includes:

[0021] Each of the business scenarios, its data analysis ideas, and the target database are input into the business scenario coding model, and the target programming language is determined using the business scenario coding model. The data analysis execution code corresponding to each of the business scenarios is generated according to the target programming language, a file containing all the data analysis execution codes is obtained, and a heuristic BI tool corresponding to the target data set is obtained.

[0022] In an optional implementation, the step of using a preset business scenario generation model to generate each business scenario and its data analysis ideas based on the recognition result and the target data set includes:

[0023] Using a preset business scenario generation model, based on the recognition result and the target data set, generate each business scenario and its data analysis ideas and a business analysis summary;

[0024] The step of using the preset business scenario coding model to generate a heuristic BI tool corresponding to the target data set based on each business scenario and its data analysis ideas and the target database includes:

[0025] Utilizing the preset business scenario coding model, based on each business scenario and its data analysis ideas, the target database and the business analysis overview, generate the heuristic BI tool and its effect description corresponding to the target data set; the effect description is used to represent the function of the heuristic BI tool.

[0026] In an optional implementation manner, the service category identification model is obtained in the following manner:

[0027] Obtain multiple training datasets from multiple databases;

[0028] Classifying each of the training data sets to obtain a business category to which each training data set belongs;

[0029] The basic recognition model is trained using the business category to which each training data set belongs to obtain the business category recognition model.

[0030] In a second aspect, the present invention provides a device for generating a heuristic BI tool, the device for generating a heuristic BI tool comprising:

[0031] A data acquisition module is used to acquire a target data set selected by a user from a target database;

[0032] A business identification module, used to identify the target data set using a preset business category identification model to obtain an identification result;

[0033] A scenario generation module, used to generate each business scenario and its data analysis ideas based on the recognition result and the target data set by using a preset business scenario generation model;

[0034] A tool generation module is used to generate a heuristic BI tool corresponding to the target data set based on each business scenario and its data analysis ideas and the target database by using a preset business scenario coding model; wherein the heuristic BI tool is used to perform data analysis on a data set with the same data structure as the target data set.

[0035] In a third aspect, the present invention provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and when the processor executes the computer program, the method for generating the heuristic BI tool described in any one of the aforementioned implementations is implemented.

[0036] In a fourth aspect, the present invention provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for generating a heuristic BI tool described in any one of the aforementioned embodiments.

[0037] The invention provides a method, device, electronic device and storage medium for generating a heuristic BI tool, the method comprising: first obtaining a target data set selected by a user from a target database; then using a preset business category recognition model to identify the target data set to obtain a recognition result; then using a preset business scenario generation model to generate each business scenario and its data analysis ideas based on the recognition result and the target data set; finally using a preset business scenario coding model to generate a heuristic BI tool corresponding to the target data set based on each business scenario and its data analysis ideas and the target database; wherein the heuristic BI tool is used to perform data analysis on a data set with the same data structure as the target data set. This enables users to use BI tools without having business background knowledge and data analysis knowledge, lowers the threshold for using BI tools, and improves the efficiency of data analysis and business decision-making.

[0038] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0040] Figure 1 A block diagram of an electronic device provided by an embodiment of the present invention is shown;

[0041] Figure 2 One of the flow charts of the method for generating a heuristic BI tool provided by an embodiment of the present invention is shown;

[0042] Figure 3 The second flowchart of the method for generating a heuristic BI tool provided by an embodiment of the present invention is shown;

[0043] Figure 4 A functional module diagram of a device for generating a heuristic BI tool provided by an embodiment of the present invention is shown.

[0044] Icons: 100 - electronic device; 110 - processor; 120 - memory; 130 - communication module; 300 - device for generating heuristic BI tool; 310 - data acquisition module; 330 - business identification module; 350 - scenario generation module; 370 - tool generation module. DETAILED DESCRIPTION

[0045] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0046] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present invention.

[0047] It should be noted that relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0048] BI (Business Intelligence) is a technology used to analyze and process business data to help enterprises make decisions based on data. Current conversational BI tools generate and display reports based on the data sets and data analysis requirements input by users. However, for conversational BI tools, users are usually required to accurately express their data analysis needs. Since most users lack relevant business background knowledge and have little knowledge of data analysis expertise, users cannot accurately describe their needs, resulting in a high threshold for using conversational BI tools. In addition, conversational BI tools are obtained by fine-tuning the language model using specific business data, and can only perform data analysis on a single business. For industries with complex businesses, such as equipment manufacturing industries such as vehicle manufacturing and general equipment manufacturing, which often involve multiple businesses such as procurement, production, and sales, conversational BI tools cannot be used for data analysis. Therefore, an embodiment of the present invention provides a method for generating a heuristic BI tool to solve the above problems.

[0049] See also Figure 1 , is a block diagram of an electronic device provided by an embodiment of the present invention. The electronic device 100 includes a processor 110, a memory 120, and a communication module 130, and each component is directly or indirectly electrically connected to each other to achieve data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines.

[0050] The processor 110 is used to read / write data or programs stored in the memory 120 and execute corresponding functions. It can be a general-purpose processor, including a CPU (Central Processing Unit), NP (Network Processor), etc.; it can also be a DSP digital signal processor, an ASIC application-specific integrated circuit, an FPGA off-the-shelf programmable gate array or other programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components.

[0051] The memory 120 is used to store programs or data, and may be RAM (Random Access Memory), ROM (Read Only Memory), PROM (Programmable Read-Only Memory), EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electric Erasable Programmable Read-Only Memory), etc.

[0052] The communication module 130 is used to perform signaling or data communications with other devices.

[0053] Understandably, Figure 1 The structure shown is only a schematic diagram of the structure of the electronic device 100. The electronic device 100 may also include Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown. Figure 1 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0054] The above-mentioned electronic device 100 will be used as an execution subject to execute each step in each method provided in the embodiment of the present invention and achieve corresponding technical effects.

[0055] See also Figure 2 , is a flow chart of a method for generating a heuristic BI tool provided in an embodiment of the present invention.

[0056] Step S202: obtaining a target data set selected by a user from a target database.

[0057] In this embodiment, the target database refers to the database from which the user selects a data set, and the target data set refers to the data set selected by the user. It should be noted that the data set includes multiple business fields and multiple values ​​corresponding to each business field. The business field can be understood as metadata used to describe the corresponding value. Based on the selection operation performed by the user, the identifier of the target database selected by the user and the selected target data set can be obtained.

[0058] Step S204: using a preset business category recognition model, the target data set is recognized to obtain a recognition result.

[0059] In this embodiment, a business category recognition model can be pre-trained to classify various business data. Then the obtained target data set can be input into the preset business category recognition model and recognized by the business category recognition model to obtain the recognition result.

[0060] It can be understood that the embodiment of the present invention uses a business category identification model to identify various business data in complex industries, so as to subsequently generate a heuristic BI tool adapted to the business to which the business data belongs, thereby improving the accuracy of data analysis by the heuristic BI tool.

[0061] Step S206, using the preset business scenario generation model, based on the recognition results and the target data set, generates each business scenario and its data analysis ideas.

[0062] In this embodiment, a language model can be used as a business scenario generation model, so the recognition results and the target data set can be input into the business scenario generation model, and the business scenario generation model can be used to understand and analyze the recognition results and the target data set, and generate business scenarios and the direction that can be analyzed based on the business fields in the target data set under the business scenario, that is, to obtain each business scenario and its data analysis ideas.

[0063] It can be understood that the embodiment of the present invention generates a model through business scenarios, generates specific business scenarios based on abstract business data, and provides corresponding data analysis ideas, so as to facilitate the subsequent generation of heuristic BI tools containing data analysis ideas. It enables users to use BI tools without having business background knowledge and data analysis knowledge, lowers the threshold for using BI tools, and provides strong technical support for business decision-making.

[0064] Step S208, using the preset business scenario coding model, based on each business scenario and its data analysis ideas and the target database, generate a heuristic BI tool corresponding to the target data set; wherein the heuristic BI tool is used to perform data analysis on a data set with the same data structure as the target data set.

[0065] In this embodiment, a large language model can be used as a business scenario encoding model, so each business scenario and its data analysis ideas, as well as the identifier of the target database can be input into the business scenario encoding model, and the business scenario encoding model can be used to generate code for implementing each data analysis idea, that is, to obtain the heuristic BI tool corresponding to the target data set.

[0066] It is understandable that the user can use this heuristic BI tool to directly perform data analysis on the target data set to generate a corresponding report; or use this heuristic BI tool to perform data analysis on a data set with the same business fields as the target data set.

[0067] It can be understood that the embodiment of the present invention generates a heuristic BI tool through a business scenario coding model, thereby providing users with targeted BI tools, and users can directly use the heuristic BI tool to perform data analysis on data sets with the same data structure, thereby improving the efficiency of data analysis and business decision-making.

[0068] It can be seen that based on the above steps, first obtain the target data set selected by the user from the target database; then use the preset business category recognition model to identify the target data set to obtain the recognition result; then use the preset business scenario generation model to generate each business scenario and its data analysis ideas based on the recognition result and the target data set; finally, use the preset business scenario encoding model to generate the heuristic BI tool corresponding to the target data set based on each business scenario and its data analysis ideas and the target database; the heuristic BI tool is used to perform data analysis on the data set with the same data structure as the target data set. This enables users to use BI tools without having business background knowledge and data analysis knowledge, lowers the threshold for using BI tools, and improves the efficiency of data analysis and business decision-making.

[0069] Optionally, for step S206, an embodiment of the present invention provides an implementation method.

[0070] Step S206 - 1 : Generate a first prompt word according to a first preset template, a target data set and a target business category.

[0071] Step S206-3: input the first prompt word into the business scenario generation model, and use the business scenario generation model to generate each business scenario corresponding to the target business category and its data analysis ideas.

[0072] In this embodiment, when the business category recognition model recognizes the category of the target data set, the recognition result outputted by it is the target business category to which the target data set belongs, that is, the business data indicating that the target data set belongs to the preset business category. Then, a template, namely the first preset template, can be pre-set to guide the business scenario generation model to understand the relationship between the business category and the business scenario (the business scenario is a process or link in the business category), and instruct it to output the business scenario and data analysis ideas according to the given data set and the given business category.

[0073] For ease of understanding, an example is provided in the embodiment of the present invention. Assume that the preset business categories include three categories: procurement business, production business, and sales business. For example, the target data set selected by the user is the customer satisfaction survey data of each product line in the past year selected from the customer feedback database, and the target data set includes three business fields: product line, survey time, and customer satisfaction, and multiple values ​​corresponding to each business field.

[0074] The target data set is input into the business category recognition model to be recognized by the business category recognition model, and the recognition result obtained is sales business, that is, the target data set belongs to the business data of the preset business category. Then the first preset template is used to splice the target data set and the target business category to obtain the first prompt word.

[0075] Then the first prompt word is input into the business scenario generation model, so as to generate each business scenario corresponding to the target business category and its data analysis ideas by using the business scenario generation model. For example, based on the target data set and the target business category being sales business, the business scenario generation model generates a business scenario such as "customer satisfaction tracking in sales business" and a data analysis idea of ​​"analyzing the trend of customer satisfaction of each product line over time".

[0076] It can be understood that when the business category identification model identifies the business category to which the data set belongs, the business scenario generation model can be directly used to generate various business scenarios of the business category and their data analysis ideas. This can help users to tap the potential value of the data, so that the generated heuristic BI tools containing data analysis ideas can inspire users to think about new business plans and make business decisions.

[0077] Optionally, for step S206, the embodiment of the present invention provides another implementation method.

[0078] Step S206-5: Generate a second prompt word according to the target data set according to the second preset template.

[0079] Step S206-7, input the second prompt word into the business scenario generation model, and use the business scenario generation model to determine the new business category to which the target data set belongs, and generate each business scenario corresponding to the new business category and its data analysis ideas.

[0080] In this embodiment, when the business identification model fails to identify the category of the target data set, the identification result outputted by it is empty or a preset mark, which indicates that the target data set does not belong to the business data of the preset business category. Then a template, namely the second preset template, can be preset to guide the business scenario generation model to understand the relationship between the business category and the business scenario (the business scenario is a process or link in the business category), and instruct it to identify the business category to which the given data set belongs, and output the business scenario and data analysis ideas according to the given data set and the identified business category.

[0081] For ease of understanding, the above-mentioned preset business categories including procurement business, production business and sales business are used as an example for explanation. For example, the target data set selected by the user is the inventory data of each current product selected from the inventory management database, and the target data set includes four business fields including product identification, product name, current inventory and historical average inventory, and multiple values ​​corresponding to each business field.

[0082] The target data set is input into the business category recognition model to be recognized by the business category recognition model, and the recognition result is a preset mark, that is, the target data set does not belong to the business data of the preset business category. Then the second preset template is used to generate a second prompt word based on the target data set.

[0083] Then the second prompt word is input into the business scenario generation model, so as to use the business scenario generation model to determine the new business category to which the target data set belongs, and generate each business scenario and its data analysis ideas corresponding to the new business category. For example, based on the target data set, the business scenario generation model determines that the new business category to which it belongs is inventory business, and generates a business scenario such as "horizontal analysis of product inventory in inventory business", and the data analysis idea is "analyzing out-of-stock products whose current inventory is lower than the historical average inventory and excess products whose current inventory is higher than the historical average inventory".

[0084] It can be understood that when the business category identification model fails to identify the business category to which the data set belongs, the business scenario generation model can be used to identify the new business category to which the data set belongs, and generate various business scenarios and data analysis ideas for the new business category. This can help users tap the potential value of the data, so that the generated heuristic BI tool containing data analysis ideas can inspire users to think about new business plans and make business decisions.

[0085] It is understandable that based on the new business categories identified by the business scenario generation model, some data sets belonging to the new business categories can also be constructed, and these data sets can be used to optimize the training of the business category recognition model to improve the recognition ability of the business category recognition model, thereby improving the versatility of the generated heuristic BI tool.

[0086] Optionally, for step S208, an embodiment of the present invention provides an implementation method, namely: each business scenario and its data analysis ideas and the target database are input into the business scenario coding model, and the target programming language is determined using the business scenario coding model, and the component set corresponding to each business scenario is determined according to the preset component library, and the execution code is generated based on each component set according to the target programming language, and a file containing the execution code of all component sets is obtained, and the heuristic BI tool corresponding to the target data set is obtained.

[0087] In this embodiment, a component library can be pre-built, which includes a variety of components commonly used to display reports, such as graphic components, page element components, etc. In addition, a variety of programming languages ​​can be set, such as SQL (Structured Query Language), HTML (Hyper Text Markup Language), JavaScript, Python, and R.

[0088] Then the business scenario coding model can determine the programming language to be used, that is, the target programming language, based on the input data analysis ideas, and select matching components from the component library based on the data analysis ideas of each business scenario and combine them to obtain the component set corresponding to each business scenario; then generate execution code based on each component set according to the target programming language, and obtain a file containing the execution code of the entire component set, that is, the corresponding heuristic BI tool.

[0089] For ease of understanding, the following is an example in which the business scenario is "customer satisfaction tracking in sales business", the data analysis idea is "analyzing the trend of customer satisfaction of each product line over time", and the target database is the customer feedback database.

[0090] For example, the business scenario and its data analysis ideas, as well as the identifier of the customer feedback database, are input into the business scenario coding model, so as to use the business scenario coding model to determine the corresponding programming language based on the data analysis ideas, that is, to obtain the target programming language such as Python, and obtain the graphics component, namely the dcc.Graph component, and the timing component, namely the dcc.Interval component, from the dash library and combine them, that is, to obtain the component set of the business scenario; then, according to the Python programming language, based on the component set and the identifier of the customer feedback database, namely customer_feedback, a file containing the execution code of the component set, namely customer_satisfaction_dashboard.py, is generated. And the execution code contained in the file is as follows:

[0091] import dash

[0092] import pandas as pd

[0093] from dash import html, dcc

[0094] from dash.dependencies import Input, Output

[0095] app = dash.Dash(__name__)

[0096] df = pd.read_sql('SELECT product_line, satisfaction_score, timestampFROM customer_feedback', con)

[0097] app.layout = html.Div([

[0098] dcc.Graph(

[0099] id='satisfaction-trend',

[0100] figure={}

[0101] ),

[0102] dcc.Interval(

[0103] id='interval-component',

[0104] interval=1*60000,

[0105] n_intervals=0 ) ])

[0108] @app.callback(

[0109] Output('satisfaction-trend', 'figure'),

[0110] [Input('interval-component', 'n_intervals')] )

[0112] def update_graph(n):

[0113] figure = {

[0114] 'data': [{

[0115] 'x': df['timestamp'],

[0116] 'y': df['satisfaction_score'],

[0117] 'type': 'line',

[0118] 'name': df['product_line'].astype(str)

[0119] }],

[0120] 'layout': {

[0121] 'title': 'Customer Satisfaction Trend'

[0122] }

[0123] }

[0124] return figure

[0125] if __name__ == '__main__':

[0126] app.run_server(debug=True)

[0127] Obtaining the file containing the above execution code means obtaining the heuristic BI tool corresponding to the target data set. Then the user can use the heuristic BI tool to analyze the data set containing the three business fields of product line, survey time, and customer satisfaction and multiple values ​​corresponding to each business field to obtain the trend of customer satisfaction of each product line over time.

[0128] Optionally, for step S208, an embodiment of the present invention provides another implementation method, namely: input each business scenario, its data analysis ideas, and the target database into the business scenario coding model, and use the business scenario coding model to determine the target programming language, and generate the data analysis execution code corresponding to each business scenario according to the target programming language, obtain a file containing all the data analysis execution codes, and obtain the heuristic BI tool corresponding to the target data set.

[0129] In this embodiment, based on the pre-setting of multiple programming languages, the business scenario coding model can also determine the programming language used according to the input data analysis ideas, that is, obtain the target programming language, and directly generate the corresponding data analysis execution code according to the target programming language and the data analysis ideas of each business scenario, and obtain a file containing all the data analysis execution codes, that is, obtain the corresponding heuristic BI tool.

[0130] For ease of understanding, the following is an example in which the business scenario is "horizontal analysis of product inventory in inventory business", the data analysis idea is "analyzing out-of-stock products whose current inventory is lower than the average inventory and excess products whose current inventory is higher than the average inventory", and the target database is the inventory management database.

[0131] For example, the business scenario and its data analysis ideas, as well as the identification of the inventory management database, are input into the business scenario coding model, so as to use the business scenario coding model to determine the corresponding programming language based on the data analysis ideas, that is, to obtain the target programming language such as SQL language, and according to the SQL language, based on the data analysis ideas of the business scenario, to generate the corresponding data analysis execution code, and obtain the file containing the data analysis execution code, namely inventory_analysis_query.sql. And the data analysis execution code contained in the file is as follows:

[0132] SELECT product_id, product_name, current_stock, avg_stock

[0133] FROM (

[0134] SELECT product_id, product_name, current_stock, AVG(stock) OVER(PARTITION BY product_id) AS avg_stock

[0135] FROM inventory_records

[0136] ) AS subquery

[0137] WHERE current_stock<avg_stock*0.8 OR current_stock> avg_stock*1.2

[0138] Obtaining the file containing the above data analysis execution code means obtaining the heuristic BI tool corresponding to the target data set. Then the user can use the heuristic BI tool to analyze the data set containing the four business fields of product ID, product name, current inventory and historical average inventory and multiple values ​​corresponding to each business field, so as to obtain out-of-stock products whose current inventory is lower than the historical average inventory and surplus products whose current inventory is higher than the historical average inventory.

[0139] Optionally, for step S206, an embodiment of the present invention further provides an implementation method: step S206A, using a preset business scenario generation model, based on the recognition results and the target data set, generates each business scenario and its data analysis ideas and a business analysis overview.

[0140] Based on step S206A, an embodiment of the present invention provides a corresponding implementation method for step S208: step S208A, using a preset business scenario coding model, based on each business scenario and its data analysis ideas, the target database and the business analysis overview, generates a heuristic BI tool and its effect description corresponding to the target data set; the effect description is used to represent the function of the heuristic BI tool.

[0141] It is understandable that in order to facilitate users to understand the functional effects of the generated heuristic BI tool, the business scenario generation model can also be used to generate each business scenario and its data analysis ideas and business analysis overview based on the recognition results and the target data set. Among them, the business analysis overview can be understood as an overview of the generated data analysis ideas. Then, each business scenario and its data analysis ideas, the target database and the business analysis overview are input into the business scenario coding model to generate the corresponding heuristic BI tool and its effect description. The effect description is used to represent the function of the BI tool.

[0142] For ease of understanding, the following example uses the target dataset as customer satisfaction survey data for each product in the past year, and the recognition result as sales business. For example, using the business scenario generation model, based on the recognition result and the target dataset, a business scenario such as "customer satisfaction tracking in sales business" is generated, and its data analysis idea is "analyzing the trend of customer satisfaction of each product line over time", and the business analysis summary is "displaying customer satisfaction of each product line".

[0143] Then, using the business scenario coding model, based on the business scenario and its data analysis ideas, the target database, and the business analysis overview, the corresponding heuristic BI tool is generated, as well as the effect description of the heuristic BI tool, such as "A dynamic dashboard is created using Python to show the trend of customer satisfaction of each product line over time in real time." Then, based on this effect description, the user can know the functional effect of the heuristic BI tool. Therefore, the user can select the corresponding heuristic BI tool for data analysis based on the effect description of each heuristic BI tool.

[0144] Optionally, based on the above-mentioned service category identification model, the embodiment of the present invention further provides an implementation method for obtaining the service category identification model, please refer to Figure 3 .

[0145] Step S212, obtaining multiple training data sets from multiple databases.

[0146] Step S214, classify each training data set to obtain the business category to which each training data set belongs.

[0147] Step S216, using the business category to which each training data set belongs, the basic recognition model is trained to obtain a business category recognition model.

[0148] In this embodiment, multiple initial data sets can be obtained from various databases of ERP (Enterprise Resource Planning), SCM (Supply Chain Management) and CRM (Customer Relationship Management) systems. Each initial data set includes multiple business fields and multiple values ​​corresponding to each business field. After each initial data set is preprocessed such as data cleaning, data formatting, deleting duplicate values ​​and filling missing values, each training data set is obtained.

[0149] Then, a preset classification algorithm such as a hierarchical clustering algorithm or a K-means clustering algorithm is used to classify each training data set to determine the business category to which each training data set belongs. Then, the basic recognition model is trained using the business category to which each training data set belongs to obtain a trained basic recognition model, that is, a business category recognition model. Optionally, the basic recognition model can use an SVM (Support Vector Machine), a random forest model, or a deep learning model.

[0150] Furthermore, each training data set and the business category to which it belongs can be stored in a relational database such as a MySQL database, a PostgreSQL database, or a NoSQL database to construct a training data sample library, so as to provide data support for iterative optimization of the business category recognition model.

[0151] In order to execute the corresponding steps in the above embodiments and various possible methods, a method for implementing a device for generating a heuristic BI tool is provided below. Figure 4 , is a functional module diagram of the heuristic BI tool generation device provided in an embodiment of the present invention. It should be noted that the basic principle and technical effects of the heuristic BI tool generation device 300 provided in this embodiment are the same as those of the above embodiment. For the sake of brief description, for matters not mentioned in this embodiment, reference can be made to the corresponding contents in the above embodiment. The heuristic BI tool generation device 300 includes:

[0152] The data acquisition module 310 is used to acquire the target data set selected by the user from the target database.

[0153] The business identification module 330 is used to identify the target data set using a preset business category identification model to obtain an identification result.

[0154] The scenario generation module 350 is used to generate each business scenario and its data analysis ideas based on the recognition results and the target data set using the preset business scenario generation model.

[0155] The tool generation module 370 is used to generate a heuristic BI tool corresponding to the target data set based on each business scenario and its data analysis ideas and the target database using a preset business scenario coding model; wherein the heuristic BI tool is used to perform data analysis on a data set with the same data structure as the target data set.

[0156] Optionally, the recognition result is the target business category to which the target data set belongs, and the scenario generation module 350 is also used to: generate a first prompt word according to the target data set and the target business category according to a first preset template; input the first prompt word into the business scenario generation model, and use the business scenario generation model to generate each business scenario corresponding to the target business category and its data analysis ideas.

[0157] Optionally, the recognition result is empty or a preset mark, and the preset mark indicates that the business category to which the target data set belongs is not identified. The scenario generation module 350 is also used to: generate a second prompt word according to the target data set according to a second preset template; input the second prompt word into the business scenario generation model, and use the business scenario generation model to determine the new business category to which the target data set belongs, and generate each business scenario corresponding to the new business category and its data analysis ideas.

[0158] Optionally, the tool generation module 370 is also used to: input each business scenario and its data analysis ideas and target database into the business scenario coding model, and use the business scenario coding model to determine the target programming language, and determine the component set corresponding to each business scenario according to the preset component library, and generate execution code based on each component set according to the target programming language, obtain a file containing the execution code of all component sets, and obtain the heuristic BI tool corresponding to the target data set.

[0159] Optionally, the tool generation module 370 is also used to: input each business scenario, its data analysis ideas, and the target database into the business scenario coding model, and use the business scenario coding model to determine the target programming language, and generate the data analysis execution code corresponding to each business scenario according to the target programming language, obtain a file containing all the data analysis execution codes, and obtain the heuristic BI tool corresponding to the target data set.

[0160] Optionally, the scenario generation module 350 is also used to: utilize a preset business scenario generation model to generate each business scenario and its data analysis ideas and a business analysis overview based on the recognition results and the target data set; the tool generation module 370 is also used to: utilize a preset business scenario encoding model to generate a heuristic BI tool and its effect description corresponding to the target data set based on each business scenario and its data analysis ideas, the target database and the business analysis overview; the effect description is used to represent the function of the heuristic BI tool.

[0161] Optionally, the business category identification model is obtained in the following manner: obtain multiple training data sets from multiple databases; classify each training data set to obtain the business category to which each training data set belongs; use the business category to which each training data set belongs to train the basic identification model to obtain the business category identification model.

[0162] The embodiment of the present invention further provides an electronic device 100, including a processor 110 and a memory 120, wherein the memory 120 stores a computer program, and when the processor 110 executes the computer program, the method for generating a heuristic BI tool disclosed in the embodiment of the present invention is implemented.

[0163] An embodiment of the present invention further provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for generating a heuristic BI tool disclosed in an embodiment of the present invention is implemented.

[0164] In several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0165] In addition, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0166] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0167] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for generating a heuristic BI tool, characterized in that: The method for generating the heuristic BI tool includes: Acquire a target data set selected by a user from a target database; the target data set includes a plurality of business fields and a plurality of values ​​corresponding to each business field; Using a preset business category recognition model, the target data set is recognized to obtain a recognition result; Using a preset business scenario generation model, based on the recognition result and the target data set, each business scenario and its data analysis ideas are generated; Using a preset business scenario coding model, based on each of the business scenarios and its data analysis ideas and the target database, a heuristic BI tool corresponding to the target data set is generated; wherein the heuristic BI tool is used to perform data analysis on a data set having the same data structure as the target data set; The recognition result is empty or a preset mark, and the preset mark indicates that the business category to which the target data set belongs is not recognized; the step of using a preset business scenario generation model to generate each business scenario and its data analysis idea based on the recognition result and the target data set includes: According to a second preset template, generating a second prompt word according to the target data set; Inputting the second prompt word into the business scenario generation model, and using the business scenario generation model to determine the new business category to which the target data set belongs, and generating each business scenario corresponding to the new business category and its data analysis ideas; The step of using the preset business scenario coding model to generate a heuristic BI tool corresponding to the target data set based on each business scenario and its data analysis ideas and the target database includes: Each of the business scenarios, its data analysis ideas, and the target database are input into the business scenario coding model, and the target programming language is determined using the business scenario coding model. The data analysis execution code corresponding to each of the business scenarios is generated according to the target programming language, a file containing all the data analysis execution codes is obtained, and a heuristic BI tool corresponding to the target data set is obtained.

2. The method for generating a heuristic BI tool according to claim 1, characterized in that: The recognition result is the target business category to which the target data set belongs; The step of using a preset business scenario generation model to generate each business scenario and its data analysis ideas based on the recognition result and the target data set includes: According to a first preset template, generating a first prompt word according to the target data set and the target business category; The first prompt word is input into the business scenario generation model, and the business scenario generation model is used to generate each business scenario corresponding to the target business category and its data analysis ideas.

3. The method for generating a heuristic BI tool according to claim 1, characterized in that: The step of using the preset business scenario coding model to generate a heuristic BI tool corresponding to the target data set based on each business scenario and its data analysis ideas and the target database includes: Each of the business scenarios and its data analysis ideas as well as the target database are input into the business scenario coding model, and the target programming language is determined using the business scenario coding model, and the component set corresponding to each of the business scenarios is determined according to the preset component library, and execution code is generated based on each of the component sets according to the target programming language, and a file containing the execution code of all component sets is obtained, thereby obtaining a heuristic BI tool corresponding to the target data set.

4. The method for generating a heuristic BI tool according to claim 1, characterized in that: The step of using a preset business scenario generation model to generate each business scenario and its data analysis ideas based on the recognition result and the target data set includes: Using a preset business scenario generation model, based on the recognition result and the target data set, generate each business scenario and its data analysis ideas and a business analysis summary; The step of using the preset business scenario coding model to generate a heuristic BI tool corresponding to the target data set based on each business scenario and its data analysis ideas and the target database includes: Utilizing the preset business scenario coding model, based on each business scenario and its data analysis ideas, the target database and the business analysis overview, generate the heuristic BI tool and its effect description corresponding to the target data set; the effect description is used to represent the function of the heuristic BI tool.

5. The method for generating a heuristic BI tool according to claim 1, characterized in that: The business category identification model is obtained in the following manner: Obtain multiple training data sets from multiple databases; Classifying each of the training data sets to obtain a business category to which each training data set belongs; The basic recognition model is trained using the business category to which each training data set belongs to obtain the business category recognition model.

6. A device for generating a heuristic BI tool, characterized in that: The generating device of the heuristic BI tool comprises: A data acquisition module, used to acquire a target data set selected by a user from a target database; the target data set includes multiple business fields and multiple values ​​corresponding to each business field; A business identification module, used to identify the target data set using a preset business category identification model to obtain an identification result; A scenario generation module, used to generate each business scenario and its data analysis ideas based on the recognition result and the target data set by using a preset business scenario generation model; A tool generation module, used to generate a heuristic BI tool corresponding to the target data set based on each of the business scenarios and its data analysis ideas and the target database using a preset business scenario coding model; wherein the heuristic BI tool is used to perform data analysis on a data set having the same data structure as the target data set; The recognition result is empty or a preset mark, and the preset mark indicates that the business category to which the target data set belongs is not recognized; the scenario generation module is further used to: generate a second prompt word according to the target data set according to a second preset template; input the second prompt word into the business scenario generation model, and use the business scenario generation model to determine the new business category to which the target data set belongs, and generate each business scenario corresponding to the new business category and its data analysis ideas; The tool generation module is also used to: input each of the business scenarios, its data analysis ideas and the target database into the business scenario coding model, and use the business scenario coding model to determine the target programming language, and generate the data analysis execution code corresponding to each of the business scenarios according to the target programming language, obtain a file containing all the data analysis execution codes, and obtain the heuristic BI tool corresponding to the target data set.

7. An electronic device, characterized in that: It comprises a processor and a memory, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the method for generating the heuristic BI tool as claimed in any one of claims 1 to 5.

8. A storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, implements the method for generating a heuristic BI tool according to any one of claims 1 to 5.

Images