Smart large-screen chart construction method and device, medium and product

Abstract

The invention discloses an intelligent large-screen chart construction method and device, a medium and a product, and relates to the field of intelligent large-screen chart construction. The core idea of the method is that a large language model is adopted as an intelligent engine for constructing an intelligent large-screen chart; the large language model is formed based on large-scale data training, has strong natural language processing and text generation capabilities, and can assist enterprises and public institutions in using a large screen to display statistical data more efficiently and flexibly; the method specifically comprises the following steps of: understanding the intention of a user by using a large language model, outputting a solution of a large-screen icon, calling a data source through different tools to obtain icon data, fusing the data by using a table related interface to form a final icon, and dynamically loading the final icon into a large screen to be displayed.

Description

Technical Field

[0001] The present invention relates to the field of intelligent large-screen chart construction, and specifically relates to a method, device, medium, and product for intelligent large-screen chart construction. By utilizing advanced natural language processing and machine learning technologies, the chart construction process becomes more efficient, accurate, and innovative. Background Art

[0002] The statements in this section only provide background information related to the present disclosure and may not constitute prior art.

[0003] With the rapid development of information technology, we have fully entered the big data era. Against this background, the application value of data analysis and data visualization technologies has become increasingly prominent, becoming a key means for various industries to explore data value and improve decision-making efficiency. The intelligent large screen, as a modern information display tool integrating data display, analysis, and interaction, has been widely used in many fields such as enterprise management, market analysis, public security, traffic scheduling, and decision-making support.

[0004] Traditional methods for constructing intelligent large-screen charts mainly rely on manual data processing, analysis, and design. This process not only consumes a large amount of time and human resources but also is prone to errors during data processing and conversion, affecting the accuracy and reliability of the charts. Specifically, the following problems are particularly prominent:

[0005] 1. Low data processing efficiency: During the process of manually constructing charts, a large amount of time is consumed in data cleaning, screening, conversion, etc., resulting in low overall data processing efficiency.

[0006] 2. Lack of innovation in chart design: Due to the limitations of manual design capabilities, the presentation forms and visual effects of intelligent large-screen charts are often relatively single, making it difficult to meet the diverse personalized needs of users.

[0007] 3. Difficult to maintain and update: With the development of business and the update of data, the charts displayed on the intelligent large screen need to be continuously adjusted and optimized. However, the traditional manual construction method makes the maintenance and update of charts complex and time-consuming.

[0008] 4. Insufficient interactivity: In traditional intelligent large-screen applications, the interaction methods between users and charts are relatively limited, making it difficult to achieve in-depth data exploration and analysis. Summary of the Invention

[0009] The purpose of the present invention is to provide a method, device, medium, and product for intelligent large-screen chart construction to solve the above problems. By utilizing advanced natural language processing and machine learning technologies, the chart construction process becomes more efficient, accurate, and innovative.

[0010] The technical solution of the present invention is as follows:

[0011] A method for constructing charts on an intelligent large screen, comprising:

[0012] Step S1: Data preprocessing; extracting the data to be presented from the original data and performing data preprocessing;

[0013] Step S2: Chart requirement input; the user inputs the requirements for chart construction through the intelligent large screen interface;

[0014] Step S3: Large language model processing; the large language model will understand the user's requirement intention according to the requirements input by the user, extract the key elements that meet the requirements, and generate the corresponding chart construction plan in combination with the understanding ability of the large language model;

[0015] Step S4: Chart generation; processing the original data according to the construction plan generated by the large language model, calling multiple modules, and generating the final chart according to the corresponding design specifications and style requirements.

[0016] Further, the data preprocessing includes: data cleaning, formatting, and classification.

[0017] Further, the requirements in step S2 include: chart type, data dimension, and metric; the requirements can be input in the form of natural language.

[0018] Further, if key elements are missing in step S3, the user is guided to complete the input through multiple rounds of dialogue.

[0019] Further, the chart construction plan includes: data processing, graphic design, and style selection.

[0020] Further, the multiple modules include: database, call interface, call system, call function.

[0021] The present invention also proposes a computing device, comprising:

[0022] At least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the above-mentioned method for constructing charts on an intelligent large screen.

[0023] The present invention also proposes a computer terminal storage medium storing computer terminal executable instructions for executing the above-mentioned method for constructing charts on an intelligent large screen.

[0024] The present invention also provides a computer program product, and when the computer program is executed by a processor, it implements the above-mentioned method for constructing intelligent large-screen charts.

[0025] Compared with the existing technologies, the beneficial effects of the present invention are as follows:

[0026] 1. The present invention introduces a large language model in the construction of intelligent large-screen charts, greatly improving the efficiency and accuracy of chart construction. Compared with the traditional manual construction method, the method of the present invention has the following advantages:

[0027] (1) Natural language input: Users can input construction requirements in the form of natural language without being familiar with professional chart design and data processing methods;

[0028] (2) High efficiency and accuracy: The large language model has the ability to automatically process and generate chart solutions, greatly saving the time and effort of manual processing and design.

[0029] (3) Innovation and diversity: Based on rich training data and patterns, the large language model can generate innovative and diverse chart construction solutions to meet the personalized needs of users.

[0030] (4) Scalability: The method of the present invention can adapt to different types and scales of data, as well as various chart requirements, and has good scalability and versatility.

[0031] 2. The present invention provides a method for intelligently constructing intelligent large-screen charts using a large language model. By introducing natural language processing and machine learning technologies, the construction of large-screen charts becomes more efficient, accurate, and innovative. This method has broad application prospects in the field of data visualization. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a schematic diagram of a method for constructing intelligent large-screen charts. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0033] It should be noted that relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variation thereof are intended to cover a non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising a..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0034] The features and performance of the present invention will be further described in detail below in conjunction with embodiments.

[0035] Embodiment 1

[0036] The core idea of the present invention is to use a large language model as the intelligent engine for constructing intelligent big screen charts; this large language model is trained based on large-scale data and has powerful natural language processing and text generation capabilities, enabling enterprises and institutions to use big screen display of statistical data more efficiently and flexibly; specifically, by using the large language model to understand the user's intention, output solutions for big screen icons, then obtain icon data by calling data sources through different tools, and then use table-related interfaces to fuse the data to form the final icon, and dynamically load it onto the big screen for display. This makes the display mode and content of the big screen no longer rigid and inflexible, and new big screen icon requirements can be responded to and completed in a timely manner. The steps of the present invention will be introduced in detail below.

[0037] Please refer to Figure 1 , a method for constructing intelligent big screen charts, specifically including the following steps:

[0038] Step S1: Data preprocessing; extract the data to be presented from the original data and perform data preprocessing; the data preprocessing includes data cleaning, formatting, and classification, etc., for subsequent chart construction;

[0039] Step S2: Chart requirement input; the user inputs the requirements for chart construction through the intelligent big screen interface; the requirements include chart type, data dimension, and metric indicators, etc.; these requirements can be input in the form of natural language, such as "construct a bar chart with different cities as the dimension and plot the indicator of sales amount";

[0040] Step S3: Large language model processing; the large language model will understand the user's requirement intention according to the requirements input by the user, extract the key elements that meet the requirements, and generate corresponding chart construction solutions in combination with the understanding ability of the large language model; it should be noted that if key elements are missing, the user will be guided to complete the input through multiple rounds of dialogue; the chart construction solutions include information such as data processing, graphic design, and style selection;

[0041] Step S4: Chart generation; according to the construction solutions generated by the large language model, process the original data, call multiple modules, and generate the final chart according to the corresponding design specifications and style requirements; the generated chart can be directly displayed on the intelligent big screen; the multiple modules include a database, call interfaces, call systems, and call functions.

[0042] In this embodiment, it should be noted that usually, large screens have data sources to support the display of their data content, generally including databases, unstructured data, API interfaces, etc. This embodiment mainly takes the MYSQL database as an example of the data source for illustration. (a) First, identify the database required by the large screen data source, and at the same time, represent all the description contents of the corresponding database, data tables, table field structures, and corresponding data in a structured manner; (b) For the above contents, add annotation explanations respectively according to different contents; the description of the database should be a definite description of the business scenario of the database, as well as an explanation of the content boundary included in the database, or an expression of the metadata attributes of the database; the data table also needs to annotate its specific business content, the basic function description of the data table, and the attribute fields included in the data table, etc.; the table field needs to clearly and uniquely describe the business of the field; (c) After the above two steps, a relatively complete basic description and context association relationship of a data source expressed in natural language in a structured manner are obtained; then, use a vectorization model, such as BGE (BAAI General Embedding), to vectorize the above data respectively to extract semantic vector representations and store them in a vector database.

[0043] In this embodiment, it should be noted that in the specific application process, proxy plugin definitions also need to be made. Each type of data source requires a standardized access tool and interface. Therefore, proxy plugins for accessing various data sources need to be defined. Taking the MYSQL database as an example in this embodiment, a proxy plugin for accessing the MYSQL database is required to connect to the data source and execute database commands, etc. For the large screen data requirements, only the basic function methods for connecting to and reading the database need to be defined. For operating the database, interface functions such as database connection, attribute query, database selection, and connection closing need to be defined; for operating data tables, interface functions such as querying data tables, querying table structures, data encoding, and data table union need to be defined;

[0044] According to the above definitions, each functional interface for operating the database should have corresponding inputs and outputs. Since the inputs to the large language model are all in natural language, the natural language needs to be escaped into a programming language that can be called by the interface. Therefore, first, enable the large language model to understand the function and input of each interface, and define the intent for each interface; secondly, define the large language model prompt words required for interface calls for the interfaces corresponding to the intent; finally, through process orchestration, associate the large language model with the proxy plugin so that it can call the plugin to execute database operation instructions and return the query results to the large language model in a structured form.

[0045] In this embodiment, it should be noted that the large language model can be deployed as a standard REST API in the form of a WEB service, and the input and output of the interface comply with the Open AI specification, which is convenient for other software or third-party dependent packages to dock. At the same time, the speech-to-text model Whisper Tiny is deployed as a standard REST API in the form of a WEB service. Finally, the large screen integrates the speech module and the large language model module;

[0046] After the above integration, the user inputs the natural language speech for querying data according to actual needs. The speech conversion model realizes speech-to-text conversion, and then inputs the text into the large language model. The large language model first understands the user's intention. If it is to query the large screen data, and if it is a query semantics, it calls the data source proxy plugin to connect to the database, and then extracts the query data parameters according to the semantic content, such as key information like entities, time, location, etc., and realizes the mapping and correction between the natural language fields and the actual extracted fields through the vector library. Finally, the parameters are assembled into a query SQL statement, and the query statement is executed through the data source proxy plugin to return the query result;

[0047] The large language model completes the conversion of natural speech into the result data of the database query through the above steps. Finally, the query result data is input into the large language model again, and the corresponding chart of the large screen is generated using the Prompt prompt, such as "display the query result data in the form of a line chart". The large language model then generates the JS code for rendering the line chart-related chart, and sends the JS code to the front end of the large screen for execution, thus completing the ability to convert natural speech into large screen charts.

[0048] In addition, in some embodiments, a computing device is also proposed, including:

[0049] At least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a method for constructing a smart large screen chart as described above; examples of the computing device include a PC, a tablet computer, a smart phone, or a PDA, etc.

[0050] In addition, in some embodiments, a computer terminal storage medium is also proposed, storing computer terminal executable instructions, and the computer terminal executable instructions are used to execute a method for constructing a smart large screen chart as described above; examples of the computer storage medium include magnetic storage media (such as floppy disks, hard disks, etc.), optical recording media (such as CD-ROMs, DVDs, etc.), or memories such as memory cards, ROMs, or RAMs, etc. The computer storage medium can also be distributed on a computer system connected by a network, such as an application store.

[0051] In addition, in some embodiments, a computer program product is also provided. When the computer program is executed by a processor, it implements the above-mentioned method for constructing intelligent large-screen charts.

[0052] The above-described embodiments merely represent specific implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the protection scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the technical solution of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application.

[0053] This background art section is provided to generally present the context of the present invention. The work of the currently named inventors, to the extent described in this background art section, and aspects of the work that are not prior art as of the time of filing this application are neither expressly nor impliedly admitted to be prior art to the present invention.

Claims

1. A method for constructing a smart large-screen chart, characterized in that: include: Step S1: data preprocessing: extracting the data to be presented from the original data and performing data preprocessing; Step S2: diagram requirement input; Users input chart construction requirements through the smart large screen interface; Step S3: large language model processing; The big language model will understand the user's demand intention based on the user's input needs, extract the key elements that meet the needs, and generate the corresponding chart construction plan based on the understanding ability of the big language model; Step S4: Chart generation: According to the construction plan generated by the large language model, the original data is processed, multiple modules are called, and the final chart is generated according to the corresponding design specifications and style requirements.

2. A method for constructing a smart large-screen chart according to claim 1, characterized in that: The data preprocessing includes: data cleaning, formatting and classification.

3. A method for constructing a smart large-screen chart according to claim 1, characterized in that: The requirements in step S2 include: chart type, data dimension and metric; the requirements can be input in natural language.

4. A method for constructing a smart large-screen chart according to claim 1, characterized in that: If a key element is missing in step S3, the user is guided to complete the input through multiple rounds of dialogue.

5. The method for constructing a smart large-screen chart according to claim 1, characterized in that: The chart construction scheme includes: data processing, graphic design and style selection.

6. A method for constructing a smart large-screen chart according to claim 1, characterized in that: The multiple modules include: database, calling interface, calling system, and calling function.

7. A computing device, characterized in that: include: at least one processor; And a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a smart large-screen chart construction method as described in any one of claims 1-6.

8. A computer terminal storage medium storing computer terminal executable instructions, characterized in that: The computer terminal executable instructions are used to execute a smart large-screen chart construction method as described in any one of claims 1-6.

9. A computer program product, characterized in that When the computer program is executed by a processor, it implements a method for constructing a smart large-screen chart as described in any one of claims 1 to 6.

Images