Medical data visual analysis system, method and equipment based on large model and medium

Abstract

The invention provides a medical data visual analysis system, method and device based on a large model and a medium, and belongs to the technical field of medical data analysis. The system comprises a data source management module which obtains and manages data source information registered by a user; the user interaction module responds to natural language input of a user, integrates the natural language input into a request message and sends the request message to the large model analysis module; the large model analysis module is used for identifying natural language input of a user from the received message, connecting a data source information query required table, and generating an SQL query statement according to the natural language input and the required table; the SQL execution module is connected with the data source information to execute an SQL query statement and perform related data query; and the data visualization module is used for carrying out visual graphic display on the data query result through an Echarts framework. Multi-source medical data can be effectively managed, the data analysis process is simplified through natural language processing, and the use threshold of medical staff is lowered.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical data analysis, and specifically relates to a medical data visualization analysis system, method, device and medium based on a large model. Background Art

[0002] With the generation of a large amount of medical data in the medical field, the analysis and processing of medical data has become increasingly important. However, although the existing medical data analysis system can perform data analysis to a certain extent, it still has some problems and shortcomings. First, the data sources are diverse and complex. For example, patient data may be scattered in different medical institutions or systems, and the database structure is diverse. For example, it may include relational databases, non-relational databases, electronic medical record systems, etc., which makes data cleaning and integration work extremely heavy. Secondly, the data analysis method is relatively traditional. Usually, statistical methods, machine learning methods, etc. are used for data analysis to perform complex preprocessing and cleaning, which requires high professional knowledge and programming skills from users, especially for most medical personnel. It is a major obstacle. Finally, the data visualization effect is not good, and it cannot fully display the analysis results intuitively and effectively based on the characteristics of medical data, which affects the user experience.

[0003] In summary, the current medical data analysis system is difficult to uniformly manage data from multiple sources. The data analysis and processing process relies on professional data and programming capabilities, and cannot intuitively display the analysis results. Therefore, there is an urgent need for a medical data analysis method that can simplify the data analysis process, lower the usage threshold and improve the visualization effect. Summary of the invention

[0004] In a first aspect, an embodiment of the present application provides a medical data visualization analysis system based on a large model, comprising: The data source management module obtains and manages the data source information registered by the user, and provides the data source information to the user for selection before data analysis; The user interaction module responds to the user's natural language input, integrates it into a request message and sends it to the large model analysis module; The large model analysis module identifies the user's natural language input from the received request message, connects to the data source information to query the required table, and generates SQL query statements based on the natural language input and the required table; SQL execution module, connects to data source information to execute SQL query statements, performs relevant data query, and provides data query results to data visualization module; The data visualization module uses the Echarts framework to visualize the data query results.

[0005] Furthermore, the data source management module includes: A data source registration unit, which obtains the data source information registered by the user, wherein the data source information includes the IP address, port number, account number and password of the disease-specific database; The data source management unit adds the data source information registered by the user to the data source record table, and can add, delete, modify and query the data source information according to the user's selection; The data source selection unit is responsive to the user's selection of required data source information before data analysis.

[0006] Furthermore, the user interaction module includes: A natural language input acquisition unit, responding to and acquiring a user's natural language input; The message integration unit extracts the natural language question, user identity information and operation type parameters from the user's natural language input and integrates them into a request message in JSON format; The query request sending unit sends the request message in JSON format to the large model analysis module in the backend server in the form of HTTP request.

[0007] Furthermore, the large model analysis module includes: The message parsing unit uses a large model to identify the user's natural language questions from the received JSON format request message; The data source connection unit connects to the disease-specific database corresponding to the pre-selected required data source information through the large model, and obtains the names of all tables; The required table selection unit analyzes the natural language question through a large model and selects the required table from the names of all tables in the disease-specific database; The field information acquisition unit connects the field information of the required table in the disease-specific database corresponding to the pre-selected required data source information again through the big model to obtain the structure of the required table; The SQL query statement generation unit generates the corresponding SQL query statement through the large model combined with the structure of the required table and the natural language question and provides it to the SQL execution module.

[0008] Furthermore, the SQL execution module includes: An SQL query statement checking unit performs syntax and semantics checking on received SQL query statements; The SQL query statement execution unit connects to the pre-selected data source information through JDBC, executes the SQL query statement that has passed the check, and queries the relevant data; The query result processing unit receives the query result in the form of a Result object returned from the data source information, processes the query result, and provides it to the data visualization module.

[0009] Furthermore, the data visualization module includes: The query result analysis unit analyzes the query results through the Echarts chart engine to determine the graphical display method and the default fields to be displayed; A visual graphic display unit is used to visually output the fields that need to be displayed by default in the query results according to a determined graphic display method; The visual graphics adjustment unit responds to the user's adjustment of the default fields to be displayed, and then adjusts the visual output according to the adjusted fields and the determined image display method.

[0010] In a second aspect, the present application also provides a medical data visualization analysis method based on a large model, comprising the following steps: S1. The front-end interactive interface obtains the query question entered by the user in the form of natural language input and integrates it into a request message and sends it to the back-end server; S2. The backend server uses the big model to identify the user's natural language input from the received request message, connects to the data source information to query the required table, and generates an SQL query statement based on the natural language input and the required table; S3. The backend server connects to the data source information through the big model and executes SQL query statements to query relevant data and obtain data query results; S4. The front-end graphical interface uses the Echarts framework to visualize the data query results.

[0011] Furthermore, step S1 includes the following steps: S11. Respond to and obtain the user's natural language input through the front-end interactive interface of the Vue.js framework, extract the natural language question, user identity information and operation type parameters from the user's natural language input, and integrate them into a request message in JSON format; S12. Send the request message in JSON format to the large model analysis module on the backend server in the form of HTTP request through the front-end interactive interface of the Vue.js framework; The specific steps of step S2 are as follows: S21. The data source information registered by the user is obtained in advance through the Spring Boot framework, and the data source information is added to the data source record table; the data source information includes the IP address, port number, account number and password of the disease database, and the data source information can be added, deleted, modified and queried according to the user's choice; S22. Using the Spring Boot framework, respond to the user's selection of the required data source information before data analysis; S23. Identify the user's natural language questions from the received request message in JSON format through a large model based on QWen2.5; S24. Connect the disease-specific database corresponding to the pre-selected required data source information through the large model based on QWen2.5, obtain the names of all tables, analyze the natural language question, and select the required table from the names of all tables in the disease-specific database; S25. Connect the field information of the required table in the disease-specific database corresponding to the pre-selected required data source information again through the large model based on QWen2.5 to obtain the structure of the required table, and generate the corresponding SQL query statement in combination with the structure of the required table and the natural language question; The specific steps of step S3 are as follows: S31. After checking the syntax and semantics of the received SQL query statement, the pre-selected data source information is connected through JDBC to perform a query on the relevant data; S32. Receive the query result in the form of a Result object returned from the data source information, and process the query result; The specific steps of step S4 are as follows: S41. Analyze the query results through the Echarts chart framework to determine the graphic display method and the default fields to be displayed; S42. Visually output the fields that need to be displayed by default in the query results according to the determined graphic display method through the Echarts chart framework; S43. Determine whether a user request to adjust the display field is received; If yes, go to step S44; If not, end; S44. Obtain the fields adjusted by the user, and adjust the visual output according to the fields adjusted by the user and the determined image display method.

[0012] In a third aspect, an embodiment of the present application further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the medical data visualization analysis method based on a large model as described in the second aspect are implemented.

[0013] In a fourth aspect, an embodiment of the present application further provides a storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the medical data visualization analysis method based on a large model as described in the second aspect are implemented.

[0014] It can be seen from the above technical solutions that the present invention has the following advantages: The medical data visualization analysis system, method, device and medium based on the big model provided by this application provide an efficient and reliable solution for medical data analysis by integrating medical data from multiple sources, simplifying the data analysis process, lowering the usage threshold and improving the visualization effect. This application can not only improve the efficiency and accuracy of medical data analysis, but also provide auxiliary basis for medical decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solution of the present invention, the accompanying drawings required for use in the description will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0016] Figure 1 It is a schematic diagram of the medical data visualization analysis system based on a large model of the present invention.

[0017] Figure 2 It is a flowchart of the medical data visualization analysis method based on a large model of the present invention. DETAILED DESCRIPTION

[0018] In the following, a medical data visualization analysis system based on a large model will be described in detail, and various embodiments of the present disclosure will be described more comprehensively. The present disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of the present disclosure to the specific embodiments disclosed herein, but the present disclosure should be understood to cover all adjustments, equivalents and / or alternatives that fall within the spirit and scope of the various embodiments of the present disclosure.

[0019] For example, in the medical field, with the large amount of data generated during diagnosis and treatment, the in-depth analysis and processing of medical data has become increasingly critical. However, although the current medical data analysis system can process data to some extent, it still faces several challenges and shortcomings. The first problem is that the source of data is wide and complex. Various types of patient information may be scattered in different medical institutions or systems. In addition, the database architecture is diverse, covering relational and non-relational databases and electronic medical record systems, which makes data cleaning and integration extremely difficult. Secondly, data analysis methods are relatively traditional, mainly relying on statistical methods and machine learning techniques, which require complex preprocessing and cleaning steps, and require a considerable degree of professional knowledge and programming skills, which poses a considerable challenge for most medical workers. Furthermore, the effect of data visualization is not satisfactory, and it fails to fully combine the uniqueness of medical data for intuitive and effective display, thus affecting the user experience.

[0020] In summary, the current medical data analysis system is difficult to achieve unified management of multiple data sources, the data analysis process is highly dependent on professional data processing and programming skills, and lacks the ability to intuitively display analysis results. Therefore, there is an urgent need for a new medical data analysis method that can simplify the data analysis process, reduce the difficulty of operation, and enhance the visualization effect.

[0021] In response to the above problems, this embodiment provides a medical data visualization analysis system based on a large model, which can effectively manage medical data from multiple sources, simplify the data analysis process through natural language processing, lower the usage threshold for medical personnel, and improve the display effect of analysis results through advanced data visualization technology.

[0022] The following will be combined with the 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. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] See also Figure 1 FIG. 1 is a schematic diagram of a medical data visualization analysis system based on a large model in a specific embodiment, and the system includes: The data source management module obtains and manages the data source information registered by the user, and provides the data source information to the user for selection before data analysis; It should be noted that by uniformly managing medical data from multiple sources, the problem of data dispersion and diverse structures is solved, providing a reliable data foundation for data analysis; The user interaction module responds to the user's natural language input, integrates it into a request message and sends it to the large model analysis module; It should be noted that natural language input simplifies the interaction process between users and the system, lowers the usage threshold, and improves the system's ease of use and user experience; The large model analysis module identifies the user's natural language input from the received request message, connects to the data source information to query the required table, and generates SQL query statements based on the natural language input and the required table; It should be noted that the large model analysis module can intelligently identify the user's natural language input and generate corresponding SQL query statements, which improves the intelligence level and accuracy of data analysis; SQL execution module, connects to data source information to execute SQL query statements, performs relevant data query, and provides data query results to data visualization module; It should be noted that the SQL execution module enables efficient execution of SQL query statements, ensuring the real-time and accuracy of data queries and providing strong support for data analysis; Data visualization module, which uses the Echarts framework to visualize the data query results; It should be noted that the Echarts framework enables intuitive display of query results, helping users to better understand and analyze data and improving user experience.

[0024] This embodiment lowers the threshold for using medical data analysis through the data source management module, user interaction module, large model analysis module, SQL execution module, and data visualization module, allowing non-professionals to easily perform data analysis, avoiding the problem that users need to have complex data analysis knowledge and programming skills to use existing data analysis systems, and the problem that existing data analysis systems have poor visualization effects and cannot effectively display data analysis results.

[0025] Further, as a refinement and extension of the specific implementation of the above embodiment, in order to fully illustrate the specific implementation process in this embodiment, another medical data visualization analysis system based on a large model is provided, which includes: The data source management module obtains and manages the data source information registered by the user, and provides the data source information to the user for selection before data analysis; the data source management module includes: A data source registration unit, which obtains the data source information registered by the user, wherein the data source information includes the IP address, port number, account number and password of the disease-specific database; The data source management unit adds the data source information registered by the user to the data source record table, and can add, delete, modify and query the data source information according to the user's selection; A data source selection unit, responding to a user selecting required data source information before data analysis; The user interaction module responds to the user's natural language input, integrates it into a request message and sends it to the large model analysis module; the user interaction module includes: A natural language input acquisition unit, responding to and acquiring a user's natural language input; The message integration unit extracts the natural language question, user identity information and operation type parameters from the user's natural language input and integrates them into a request message in JSON format; The query request sending unit sends the request message in JSON format to the large model analysis module in the backend server in the form of HTTP request; The large model analysis module identifies the user's natural language input from the received request message, connects the data source information to query the required table, and generates SQL query statements based on the natural language input and the required table; the large model analysis module includes: The message parsing unit uses a large model to identify the user's natural language questions from the received JSON format request message; The data source connection unit connects to the disease-specific database corresponding to the pre-selected required data source information through the large model, and obtains the names of all tables; The required table selection unit analyzes the natural language question through a large model and selects the required table from the names of all tables in the disease-specific database; The field information acquisition unit connects the field information of the required table in the disease-specific database corresponding to the pre-selected required data source information again through the big model to obtain the structure of the required table; The SQL query statement generation unit generates the corresponding SQL query statement through the large model combined with the structure of the required table and the natural language question and provides it to the SQL execution module; The SQL execution module connects to the data source information to execute SQL query statements, perform relevant data queries, and provide the data query results to the data visualization module; the SQL execution module includes: An SQL query statement checking unit performs syntax and semantics checking on received SQL query statements; The SQL query statement execution unit connects to the pre-selected data source information through JDBC, executes the SQL query statement that has passed the check, and queries the relevant data; A query result processing unit receives the query result in the form of a Result object returned from the data source information, processes the query result, and provides it to the data visualization module; The data visualization module uses the Echarts framework to visualize the data query results; the data visualization module includes: The query result analysis unit analyzes the query results through the Echarts chart engine to determine the graphical display method and the default fields to be displayed; A visual graphic display unit is used to visually output the fields that need to be displayed by default in the query results according to a determined graphic display method; The visual graphics adjustment unit responds to the user's adjustment of the default fields to be displayed, and then adjusts the visual output according to the adjusted fields and the determined image display method.

[0026] like Figure 2As shown, the following is an embodiment of the medical data visualization analysis method based on a big model provided by the embodiment of the present disclosure. This method has the same inventive concept as the medical data visualization analysis system based on a big model in the above-mentioned embodiments. For details not described in detail in the embodiment of the medical data visualization analysis method based on a big model, please refer to the above-mentioned embodiment of the medical data visualization analysis system based on a big model.

[0027] Methods include: S1. The front-end interactive interface obtains the query question entered by the user in the form of natural language input and integrates it into a request message and sends it to the back-end server; It should be noted that obtaining the user's natural language input through the front-end interactive interface and integrating it into a request message to be sent to the back-end server simplifies the interaction process between the user and the system and improves the usability of the system; S2. The backend server uses the big model to identify the user's natural language input from the received request message, connects to the data source information to query the required table, and generates an SQL query statement based on the natural language input and the required table; It should be noted that the backend server recognizes the user's natural language input through a large model and generates corresponding SQL query statements, which improves the intelligence level and accuracy of data analysis; S3. The backend server connects to the data source information through the big model and executes SQL query statements to query relevant data and obtain data query results; It should be noted that SQL query statements are executed on the back-end server to query relevant data and obtain data query results, thus ensuring the real-time and accuracy of data query; S4. The front-end graphical interface uses the Echarts framework to visualize the data query results; It should be noted that the Echarts framework is used to visualize the data query results in the front-end graphical interface, helping users to better understand and analyze the data and improving the user experience.

[0028] This embodiment achieves fast, accurate and intuitive analysis of medical data through natural language processing, SQL query and data visualization, thereby improving the efficiency and accuracy of medical data analysis.

[0029] Further, as a refinement and extension of the specific implementation of the above embodiment, in order to fully illustrate the specific implementation process in this embodiment, another medical data visualization analysis method based on a large model is provided, and the method has the following steps: S1. The front-end interactive interface obtains the query question input by the user in the form of natural language input and integrates it into a request message and sends it to the back-end server; step S1 includes the following steps: S11. Respond to and obtain the user's natural language input through the front-end interactive interface of the Vue.js framework, extract the natural language question, user identity information and operation type parameters from the user's natural language input, and integrate them into a request message in JSON format; S12. Send the request message in JSON format to the large model analysis module on the backend server in the form of HTTP request through the front-end interactive interface of the Vue.js framework; S2. The backend server identifies the user's natural language input from the received request message through the large model, connects to the data source information to query the required table, and generates an SQL query statement based on the natural language input and the required table; the specific steps of step S2 are as follows: S21. The data source information registered by the user is obtained in advance through the Spring Boot framework, and the data source information is added to the data source record table; the data source information includes the IP address, port number, account number and password of the disease database, and the data source information can be added, deleted, modified and queried according to the user's choice; S22. Using the Spring Boot framework, respond to the user's selection of the required data source information before data analysis; S23. Identify the user's natural language questions from the received request message in JSON format through a large model based on QWen2.5; S24. Connect the disease-specific database corresponding to the pre-selected required data source information through the large model based on QWen2.5, obtain the names of all tables, analyze the natural language question, and select the required table from the names of all tables in the disease-specific database; S25. Connect the field information of the required table in the disease-specific database corresponding to the pre-selected required data source information again through the large model based on QWen2.5 to obtain the structure of the required table, and generate the corresponding SQL query statement in combination with the structure of the required table and the natural language question; S3. The back-end server connects to the data source information through the large model and executes SQL query statements to query relevant data and obtain data query results; the specific steps of step S3 are as follows: S31. After checking the syntax and semantics of the received SQL query statement, the pre-selected data source information is connected through JDBC to perform a query on the relevant data; S32. Receive the query result in the form of a Result object returned from the data source information, and process the query result; S4. The front-end graphical interface uses the Echarts framework to visualize the data query results; the specific steps of step S4 are as follows: S41. Analyze the query results through the Echarts chart framework to determine the graphic display method and the default fields to be displayed; S42. Visually output the fields that need to be displayed by default in the query results according to the determined graphic display method through the Echarts chart framework; S43. Determine whether a user request to adjust the display field is received; If yes, go to step S44; If not, end; S44. Obtain the fields adjusted by the user, and adjust the visual output according to the fields adjusted by the user and the determined image display method.

[0030] For example, a user enters a query question in natural language: "I want to know the average cost of treatment for patients aged 40-50 who suffer from a specific disease (e.g., diabetes)." 1. Front-end interaction module The user inputs the above natural language query question through the front-end interactive interface based on the Vue.js framework; the system responds and obtains the user's input, and extracts the query question, user identity information and operation type (such as query type, time range); and integrates this information into a request message in JSON format; The front-end interactive interface sends a request message in JSON format to the large model analysis module on the back-end server through HTTP request; 2. Backend server processing After receiving the request message, the big model analysis module parses the user's natural language question through the big model based on QWen2.5; according to the user's choice, it connects to pre-exclusive data sources (such as a hospital's disease database) and obtains the names of all tables; analyzes the natural language question and selects the query-related table (such as patient information table, treatment cost table, etc.) from the names of all tables; connects to the relevant tables in the selected data source again, obtains the table's field information, and determines the required fields (such as disease name, age, treatment cost, etc.); combines the structure of the required table and the natural language question, and generates the corresponding SQL query statement; The SQL execution module performs syntax and semantic checks on the generated SQL query statements; connects to the pre-selected data source information through JDBC and executes the SQL query statements that pass the check; receives the query results in the form of Result objects returned from the data source and processes the query results (such as calculating the average value, etc.).

[0031] 3. Data Visualization The data visualization module receives the processed query results, analyzes the query results through the Echarts chart engine, determines the graphical display method (such as bar chart, line chart, etc.) and the fields that need to be displayed by default (such as average treatment cost); visualizes the fields that need to be displayed by default in the query results according to the determined graphical display method; users can see a visualized chart of the average treatment cost of patients with a specific disease (diabetes) and aged between 40 and 50 years old on the front-end interface; Users can adjust the fields or graphic display methods displayed in the visualization chart as needed; the system responds to the user's adjustment request and regenerates the visualization output based on the user's selection.

[0032] The user finally sees a clear chart on the front-end graphical interface, showing the average treatment costs for patients with diabetes aged 40-50 years old. The chart includes titles, axis labels, data points, etc., allowing users to intuitively understand the query results.

[0033] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0034] The medical data visualization analysis method based on the large model provided in the embodiment of the present application can be applied to electronic devices. It can be understood by those skilled in the art that the electronic device structure involved in the embodiment of the present invention does not constitute a limitation on the electronic device, and the electronic device may include more or less components than shown, or combine certain components, or arrange different components. In an embodiment of the present invention, the electronic device includes but is not limited to a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples, and are not intended to limit the implementation of the embodiments of the present application described and / or required herein.

[0035] The electronic device may include a processor, an external memory interface, an internal memory, a universal serial bus (USB) interface, a charging management module, a power management module, a battery, a wireless communication module, an audio module, a speaker, a microphone, a sensor module, buttons, a camera, a display, and a SIM card interface, etc.

[0036] It is to be understood that the structure illustrated in the embodiments of the present application does not constitute a specific limitation on the electronic device. In other embodiments of the present application, the electronic device may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0037] The processor may include one or more processing units, for example, the processor may include a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Among them, different processing units may be independent devices or integrated into one or more processors.

[0038] The processor can be the nerve center and command center of the electronic device. The controller can generate an operation control signal according to the instruction operation code and timing signal to complete the control of fetching and executing instructions.

[0039] A memory may also be provided in the processor for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. The memory may store instructions or data that the processor has just used or is cyclically used. If the processor needs to use the instruction or data again, it may be directly called from the memory. This avoids repeated access, reduces the waiting time of the processor, and thus improves system efficiency.

[0040] The above-mentioned electronic device implements the request message of the medical data visualization analysis method based on the big model of the present application to be sent to the back-end server; the back-end server recognizes the user's natural language input from the received request message through the big model, connects the data source information to query the required table, and generates an SQL query statement based on the natural language input and the required table; the back-end server connects the data source information through the big model to execute the SQL query statement, performs relevant data query, and obtains the data query result; the front-end graphical interface uses the Echarts framework to visualize the data query result. The technical solution achieves the beneficial effect of being able to effectively manage medical data from multiple sources, simplify the data analysis process through natural language processing, lower the threshold for medical personnel to use, and improve the display effect of the analysis results through advanced data visualization technology.

[0041] The storage medium provided in the present application stores a program product that can implement a large model-based medical data visualization analysis method.

[0042] The medical data visualization analysis method based on the big model includes: the front-end interactive interface obtains the query questions input by the user in the form of natural language input and integrates them into a request message and sends them to the back-end server; the back-end server recognizes the user's natural language input from the received request message through the big model, connects the data source information to query the required table, and generates an SQL query statement based on the natural language input and the required table; the back-end server connects the data source information through the big model to execute the SQL query statement, perform relevant data query, and obtain the data query result; the front-end graphical interface visualizes the data query result through the Echarts framework.

[0043] In some possible implementations, the big model-based medical data visualization analysis method disclosed herein can be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps described in the above “Exemplary Method” section of this specification according to various exemplary implementations of the present disclosure.

[0044] The storage medium of the present disclosure can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0045] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A medical data visualization analysis system based on a large model, characterized in that: include: The data source management module obtains and manages the data source information registered by the user, and provides the data source information to the user for selection before data analysis; The user interaction module responds to the user's natural language input, integrates it into a request message and sends it to the large model analysis module; The large model analysis module identifies the user's natural language input from the received request message, connects to the data source information to query the required table, and generates SQL query statements based on the natural language input and the required table; SQL execution module, connects to data source information to execute SQL query statements, performs relevant data query, and provides data query results to data visualization module; The data visualization module uses the Echarts framework to visualize the data query results.

2. The medical data visualization analysis system based on a large model according to claim 1 is characterized in that: The data source management module includes: A data source registration unit, which obtains the data source information registered by the user, wherein the data source information includes the IP address, port number, account number and password of the disease-specific database; The data source management unit adds the data source information registered by the user to the data source record table, and can add, delete, modify and query the data source information according to the user's selection; The data source selection unit is responsive to the user's selection of required data source information before data analysis.

3. The medical data visualization analysis system based on a large model according to claim 2 is characterized in that: The user interaction module includes: A natural language input acquisition unit, responding to and acquiring a user's natural language input; The message integration unit extracts the natural language question, user identity information and operation type parameters from the user's natural language input and integrates them into a request message in JSON format; The query request sending unit sends the request message in JSON format to the large model analysis module in the backend server in the form of HTTP request.

4. The medical data visualization analysis system based on a large model according to claim 3 is characterized in that: Large model analysis modules include: The message parsing unit uses a large model to identify the user's natural language questions from the received JSON format request message; The data source connection unit connects to the disease-specific database corresponding to the pre-selected required data source information through the large model, and obtains the names of all tables; The required table selection unit analyzes the natural language question through a large model and selects the required table from the names of all tables in the disease-specific database; The field information acquisition unit connects the field information of the required table in the disease-specific database corresponding to the pre-selected required data source information again through the big model to obtain the structure of the required table; The SQL query statement generation unit generates the corresponding SQL query statement through the large model combined with the structure of the required table and the natural language question and provides it to the SQL execution module.

5. The medical data visualization analysis system based on a large model according to claim 4 is characterized in that: The SQL execution module includes: An SQL query statement checking unit performs syntax and semantics checking on received SQL query statements; The SQL query statement execution unit connects to the pre-selected data source information through JDBC, executes the SQL query statement that has passed the check, and queries the relevant data; The query result processing unit receives the query result in the form of a Result object returned from the data source information, processes the query result, and provides it to the data visualization module.

6. The medical data visualization analysis system based on a large model according to claim 5 is characterized in that: The data visualization module includes: The query result analysis unit analyzes the query results through the Echarts chart engine to determine the graphical display method and the default fields to be displayed; A visual graphic display unit is used to visually output the fields that need to be displayed by default in the query results according to a determined graphic display method; The visual graphics adjustment unit responds to the user's adjustment of the default fields to be displayed, and then adjusts the visual output according to the adjusted fields and the determined image display method.

7. A medical data visualization analysis method based on a large model, characterized in that: The steps include: S1. The front-end interactive interface obtains the query question entered by the user in the form of natural language input and integrates it into a request message and sends it to the back-end server; S2. The backend server uses the big model to identify the user's natural language input from the received request message, connects to the data source information to query the required table, and generates an SQL query statement based on the natural language input and the required table; S3. The backend server connects to the data source information through the big model and executes SQL query statements to query relevant data and obtain data query results; S4. The front-end graphical interface uses the Echarts framework to visualize the data query results.

8. The method for visualizing and analyzing medical data based on a large model as claimed in claim 7, characterized in that: Step S1 includes the following steps: S11. Respond to and obtain the user's natural language input through the front-end interactive interface of the Vue.js framework, extract the natural language question, user identity information and operation type parameters from the user's natural language input, and integrate them into a request message in JSON format; S12. Send the request message in JSON format to the large model analysis module on the backend server in the form of HTTP request through the front-end interactive interface of the Vue.js framework; The specific steps of step S2 are as follows: S21. The data source information registered by the user is obtained in advance through the Spring Boot framework, and the data source information is added to the data source record table; the data source information includes the IP address, port number, account number and password of the disease database, and the data source information can be added, deleted, modified and queried according to the user's choice; S22. Using the Spring Boot framework, respond to the user's selection of the required data source information before data analysis; S23. Identify the user's natural language questions from the received request message in JSON format through a large model based on QWen2.5; S24. Connect the disease-specific database corresponding to the pre-selected required data source information through the large model based on QWen2.5, obtain the names of all tables, analyze the natural language question, and select the required table from the names of all tables in the disease-specific database; S25. Connect the field information of the required table in the disease-specific database corresponding to the pre-selected required data source information again through the large model based on QWen2.5 to obtain the structure of the required table, and generate the corresponding SQL query statement in combination with the structure of the required table and the natural language question; The specific steps of step S3 are as follows: S31. After checking the syntax and semantics of the received SQL query statement, the pre-selected data source information is connected through JDBC to perform a query on the relevant data; S32. Receive the query result in the form of a Result object returned from the data source information, and process the query result; The specific steps of step S4 are as follows: S41. Analyze the query results through the Echarts chart framework to determine the graphic display method and the default fields to be displayed; S42. Visually output the fields that need to be displayed by default in the query results according to the determined graphic display method through the Echarts chart framework; S43. Determine whether a user request to adjust the display field is received; If yes, go to step S44; If not, end; S44. Obtain the fields adjusted by the user, and adjust the visual output according to the fields adjusted by the user and the determined image display method.

9. An electronic device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the large model-based medical data visualization analysis method as described in any one of claims 7 to 8 are implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the large model-based medical data visualization analysis method as described in any one of claims 7 to 8 are implemented.

Images