RPA-based hospital intelligent management rating empirical material generation system and method

Abstract

The present application relates to the field of medical information technology, in particular to a hospital intelligent management rating empirical material generation system and method based on RPA, the system comprises: user operation data acquisition module, hospital intelligent management rating index setting module, screenshot automatic intercepting module, material collection module, file generation module and automatic closing toolbar and tray application module. The hospital intelligent management rating empirical material generation system and method based on RPA provided by the present application can realize the automatic operation of the hospital information system through the RPA technology, reduce manual intervention, improve the speed and accuracy of data processing, reduce the error rate, and have the advantages of high efficiency, low error, optimized resource allocation, high data quality and support for continuous improvement.

Description

Technical Field

[0001] This invention relates to the field of medical information technology, and in particular to a system and method for generating empirical materials for hospital smart management rating based on RPA. Background Technology

[0002] With the rapid development of information technology, hospital smart management is gradually transforming into intelligent management. The concept of hospital smart management has emerged, its core being to improve the quality of medical services and management efficiency through information technology and intelligent means. As an important component of smart hospital construction, hospital smart management aims to achieve optimized allocation of hospital resources and efficient operation of management processes through refined and intelligent management tools.

[0003] During this transformation process, hospitals need to collect and organize a large amount of empirical data to demonstrate the effectiveness and level of their smart hospital implementation. This data includes data and operation records from various medical information systems, such as medical and nursing management systems, human resource management systems, financial and asset management systems, equipment and facilities management systems, drug and consumable management systems, operations management systems, operational support management systems, teaching and research management systems, office management systems, and basic and security systems. This data is typically obtained manually, including manually logging into systems, querying data, exporting reports, and taking screenshots of user interfaces. This method is not only inefficient but also has a high error rate, making it difficult to meet the requirements for hospital smart management rating.

[0004] To this end, a system and method for generating empirical materials for hospital smart management rating based on RPA were proposed. Summary of the Invention

[0005] Therefore, it is necessary to provide a system and method for generating empirical materials for hospital smart management rating based on RPA to address the above-mentioned technical issues.

[0006] According to a first aspect of the present invention, a system for generating empirical materials for hospital smart management rating based on RPA is provided, comprising: a user operation data acquisition module, used to capture user operation step data related to hospital smart management rating in a medical information system based on RPA technology, AI technology, and multimodal data fusion technology, and identify system pages and key information contained in the system pages contained in the user operation step data; a hospital smart management rating indicator setting module, used to acquire rating indicators related to hospital smart management rating, and based on RPA technology, associate the rating indicators with user operation step data to generate a comparison table of rating indicators and system pages; an automatic screenshot capture module, used to identify and determine the target rating indicator to be captured according to the preset rating indicators of hospital smart management rating, perform location matching processing on the system page associated with the target rating indicator based on the comparison table of rating indicators and system pages, and perform screenshot processing on the key information contained in the associated system page based on intelligent screenshot optimization technology to obtain screenshot image data, and perform type labeling on the screenshot image data to obtain screenshot image labeling data including the target rating indicator; and a material collection module, used to acquire and capture data related to the user operation step data, and to identify system pages and key information contained in the system pages contained in the system pages based on intelligent screenshot optimization technology to obtain screenshot image data, and perform type labeling on the screenshot image data to obtain screenshot image labeling data including the target rating indicator; and a material collection module, used to acquire and capture data related to the user operation step data, and to identify system pages and key information contained in the system pages contained in the system pages. The system handles supporting documentation related to image annotations. Based on data type and target rating indicators, it categorizes the image annotation data and supporting documentation data into multiple categories. Data extraction is then performed on these categories to obtain extracted data. Based on target rating requirements, target rating indicators, and data type, the extracted data is archived, generating index and directory information. A file generation module creates various formatted file templates that meet the hospital's smart management rating requirements. Using template engine technology, the extracted data is matched with predefined placeholders in the file templates to obtain automatically filled text files. Formatting tools are used to style and format the text files, resulting in initial empirical material text files that meet the target rating requirements. The initial empirical material text files are then quality-verified to obtain the target empirical material text files. An automatic toolbar and tray application closing module identifies the system pages and operation sequence information that the user is currently or about to operate based on user operation step data. It then identifies active toolbars and / or tray applications and closes inactive toolbars and / or tray applications.

[0007] Optionally, the user operation data acquisition module includes: a system initialization and configuration submodule, used by the user to input configuration information related to the hospital's smart management rating through a graphical user interface. The configuration information includes login credentials for the medical information system and a sequence of operation steps for monitoring the user's completion of the target task. The medical information system includes a medical and nursing management system, a human resources management system, a financial and asset management system, an equipment and facilities management system, a drug and consumables management system, an operations management system, an operations support management system, a teaching and research management system, an office management system, and a basic and security system. A user operation capture submodule is used to automatically log into the medical information system based on RPA technology and the login credentials for monitoring the user's completion of the target task. The system comprises several modules: an AI automatic recognition and recording submodule, and an intelligent learning and optimization submodule. The AI ​​automatic recognition and recording submodule uses multimodal data fusion technology to capture user operation step data related to hospital smart management rating and the corresponding contextual information of each operation step. The AI ​​automatic recognition and recording submodule, based on a trained user behavior recognition AI model and natural language processing technology, identifies system pages and key information contained within the user operation step data, and stores the system pages, key information, timestamps of the corresponding user operation steps, and contextual information of the corresponding user operation steps in a database. The intelligent learning and optimization submodule is used to build and train the user behavior recognition AI model, resulting in a trained user behavior recognition AI model.

[0008] Optionally, the user operation capture submodule further includes: a context-aware and multimodal data processing submodule, used to obtain the user's operation step sequence information in the medical information system through log analysis and behavior tracking technology; based on image processing technology, capture the system page and corresponding text information on the system page when the user performs the operation steps according to the operation step sequence information; parse and process the text information through natural language processing technology to obtain the user's operation step intent information and the corresponding user operation step context information; analyze the system page, the user's operation intent information, and the corresponding user operation step context information to obtain user operation step data related to the hospital's smart management rating.

[0009] Optionally, the hospital smart management rating indicator setting module includes: a rating indicator data integration submodule, used to obtain initial rating indicators related to hospital smart management rating from the website of the National Health Commission; a rating indicator parsing and mapping submodule, used to establish a mapping relationship between the initial rating indicators and key information based on preset mapping rules between indicators and key information; a user configuration and customization submodule, used to select preset rating indicators from the initial rating indicators according to the target rating requirements of hospital smart management rating, and assign corresponding weight values ​​to the preset rating indicators; a rating indicator dynamic adjustment submodule, used to dynamically adjust the preset rating indicators and corresponding weight values ​​according to the feedback information of hospital smart management rating and the latest rating indicators related to hospital smart management rating; an intelligent association and lookup table generation submodule, used to associate the preset rating indicators with user operation step data based on RPA technology to generate a lookup table between rating indicators and system pages; and a rating indicator review and release submodule, used to review the lookup table between rating indicators and system pages and the preset rating indicators, and release the preset rating indicators after the review is passed.

[0010] Optionally, the automatic screenshot capture module includes: a rating indicator identification and locking submodule, used to identify and determine the target rating indicator to be captured based on the preset rating indicators of the hospital's smart management rating; a system page lookup table matching submodule, used to perform location matching processing on the system pages associated with the target rating indicator based on the lookup table of rating indicators and system pages, and identify and determine the system pages to be captured; an automated login and navigation submodule, used to automatically log in to the medical information system based on the login credentials information of the medical information system using RPA technology, and navigate to the corresponding system page according to the lookup table of rating indicators and system pages; and an intelligent screenshot execution submodule, used to execute the screenshot within the specified time frame. Upon navigating to the corresponding system page, the system identifies its attribute information. Based on this attribute information, it analyzes the page elements to identify at least one area containing key information. Then, based on this area and the complexity of the system page's content, it automatically adjusts the screenshot resolution and timing, taking a screenshot of the area containing the key information to obtain at least one screenshot image. The screenshot data annotation and classification submodule is used to annotate the screenshot image data, obtaining screenshot image annotation data including target rating indicators, and classifying and storing the annotation data according to the target rating indicators.

[0011] Optionally, the material collection module includes: a material identification and classification submodule, used to acquire supporting material data related to the screenshot image annotation data, wherein the supporting material data is business data related to the screenshot image annotation data; classifying the screenshot image annotation data and supporting material data according to the target rating index to obtain first category data under the target rating index classification; classifying the first category data according to data type to obtain second category data corresponding to each data type under each target rating index; a data extraction and organization submodule, used to extract data from the second category data to obtain extracted data, wherein the extracted data includes key information extracted from the screenshot image annotation data in the second category data and supporting information related to the key information extracted from the supporting material data in the second category data, wherein the extracted data is structured format data; and a material archiving and indexing submodule, used to archive the extracted data according to the target rating requirements, target rating indexes and data types, and generate index information and catalog information.

[0012] Optionally, the document generation module includes: a template preparation and customization submodule, used to create various format document templates that meet the requirements of hospital smart management rating; a data binding and autofill submodule, used to match extracted data with predefined placeholders in the document template based on template engine technology, according to the target rating requirements, target rating indicators, and data types, to obtain an autofilled text file, wherein the target rating requirements, target rating indicators, and data types correspond to different types of placeholders; a formatting and layout submodule, used to perform style and layout processing on the text file based on a formatting tool, to obtain an initial empirical material text file that meets the target rating requirements; a data verification and quality control submodule, used to obtain detailed information related to hospital smart management rating, and to perform quality verification on the initial empirical material text file based on the detailed information, to obtain a target empirical material text file; and a file saving and version management submodule, used to store and manage the version of the target empirical material text file.

[0013] According to a second aspect of the present invention, a method for generating empirical materials for hospital smart management rating based on RPA is provided, comprising: capturing user operation step data related to hospital smart management rating in a medical information system through a user operation data acquisition module using RPA technology, AI technology, and multimodal data fusion technology, and identifying system pages and key information contained in the system pages contained in the user operation step data; acquiring rating indicators related to hospital smart management rating through a hospital smart management rating indicator setting module, and associating the rating indicators with the user operation step data based on RPA technology to generate a comparison table of rating indicators and system pages; identifying and determining the target rating indicator to be screenshotted according to the preset rating indicators of hospital smart management rating through a screenshot automatic capture module, performing location matching processing on the system page associated with the target rating indicator based on the comparison table of rating indicators and system pages, and performing screenshot processing on the key information contained in the associated system page based on intelligent screenshot optimization technology to obtain screenshot image data, and performing type labeling on the screenshot image data to obtain screenshot image labeling data including the target rating indicator; and acquiring supporting materials related to the screenshot image labeling data through a material collection module. The data, specifically the supporting documentation data, consists of business data related to the screenshot image annotation data. Based on data type and target rating indicators, the screenshot image annotation data and supporting documentation data are categorized to obtain multiple categories. Data extraction is performed on these categories to obtain extracted data. Based on target rating requirements, target rating indicators, and data type, the extracted data is archived, generating index and directory information. A file generation module creates various formatted file templates that meet the hospital's smart management rating requirements. Using template engine technology, the extracted data is matched with predefined placeholders in the file templates to obtain automatically filled text files. Based on a formatting tool, the text files are styled and formatted to obtain initial supporting documentation text files that meet the target rating requirements. The initial supporting documentation text files are then quality-verified to obtain the target supporting documentation text files. Finally, an automatic toolbar and tray application closing module identifies the system pages and operation sequence information that the user is currently or about to operate based on user operation step data. Based on this information, it identifies active toolbars and / or tray applications and closes inactive toolbars and / or tray applications.

[0014] According to a third aspect of the present invention, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method.

[0015] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method.

[0016] The RPA-based system and method for generating empirical materials for hospital smart management rating provided in this application have the following beneficial effects: 1. High efficiency: Compared with the traditional method of manually acquiring materials, the RPA technology can significantly improve the speed and accuracy of data processing, and can also continuously execute predefined tasks, reducing manual intervention and greatly improving the efficiency of generating empirical materials for hospital smart management rating; 2. Low error rate: By combining RPA technology with intelligent screenshot optimization technology, key information on system pages can be accurately captured to reduce errors and omissions caused by manual operation, thereby improving the quality of screenshots and the efficiency of the automated rating process. Furthermore, in conjunction with the document generation module, the empirical materials can be verified and quality controlled during the material generation process to ensure the accuracy of the final output text file; 3. Optimized resource allocation: By adopting RPA technology, the operation of medical information systems can be automated, reducing reliance on external consultation and support services, thereby reducing hospital operating costs. It can also allocate manpower to tasks currently being performed or about to be performed by users. The system liberates system page resources from tedious data processing, reducing the workload of medical staff. Furthermore, by automatically closing toolbars and tray application modules, based on an intelligent resource management mechanism, it can automatically recognize and process operation sequence information, ensuring that business processing and screenshot work are only performed in active toolbars and / or tray applications. This optimizes the working environment of the medical information system, thereby improving the efficiency and accuracy of hospital smart management rating. 4. High data quality: Utilizing a combination of RPA, AI, and multimodal data fusion technologies, it can automatically collect and integrate scattered data from the medical information system, ensuring data consistency and accuracy, thereby improving the data quality of generated empirical material text files. 5. Support for continuous improvement: By setting a dynamic adjustment submodule for rating indicators, it can dynamically adjust preset rating indicators and corresponding weight values ​​based on feedback information from hospital smart management rating and the latest rating indicators related to hospital smart management rating. This allows for dynamic adjustment of the content of empirical material text files, supporting continuous improvement of hospital smart management rating work. Attached Figure Description

[0017] Figure 1 This is a system principle block diagram of the present invention.

[0018] Figure 2 This is a system principle block diagram of the user operation data acquisition module of the present invention.

[0019] Figure 3This is a system principle block diagram of the hospital smart management rating index setting module of the present invention.

[0020] Figure 4 This is a system principle block diagram of the automatic screenshot capture module of the present invention.

[0021] Figure 5 This is a system principle block diagram of the material collection module of the present invention.

[0022] Figure 6 This is a system principle block diagram of the document generation module of the present invention.

[0023] Figure 7 This is the overall flowchart of the present invention.

[0024] Figure 8 This is a schematic diagram of the electronic device of the present invention. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments and accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0026] Example 1

[0027] Reference Appendix Figure 1-6 The system 100 is a hospital smart management rating empirical material generation system based on RPA. The system includes a user operation data acquisition module 110, a hospital smart management rating indicator setting module 120, an automatic screenshot capture module 130, a material collection module 140, a file generation module 150, and an automatic toolbar and tray application closing module 160.

[0028] In some embodiments, refer to the appendix Figure 2 The user operation data acquisition module 110 is used to capture user operation step data related to the hospital's smart management rating in the medical information system based on RPA technology, AI technology, and multimodal data fusion technology, and to identify the system pages contained in the user operation step data and the key information contained in the system pages.

[0029] Furthermore, the user operation data acquisition module 110 includes a system initialization and configuration submodule 1110, used by the user to input configuration information related to the hospital's smart management rating through a graphical user interface. The configuration information includes login credentials for the medical information system and the sequence of operation steps for monitoring the user to complete the target task. The user operation capture submodule 1120 is used to automatically log in to the medical information system based on RPA technology and the login credentials for the medical information system, and to monitor the user's operation steps for completing the target task. Based on multimodal data fusion technology, it captures user operation step data related to the hospital's smart management rating and the contextual information of the corresponding user operation steps. The AI ​​automatic recognition and recording submodule 1130 is used to identify the system pages and key information contained in the user operation step data based on the trained user behavior recognition AI model and natural language processing technology, and to store the system pages, the key information contained in the system pages, the timestamps of the corresponding user operation steps, and the contextual information of the corresponding user operation steps in the database. The intelligent learning and optimization submodule 1140 is used to build and train the user behavior recognition AI model to obtain the trained user behavior recognition AI model.

[0030] Furthermore, after the system is started, the user inputs the necessary configuration information through the graphical user interface of the system initialization and configuration submodule 1110. This configuration information includes the login credentials of the medical information system and the sequence of operation steps for monitoring the user to complete the target task, such as: logging into the financial asset management system, navigating to a target module of the financial asset management system, querying a target data, etc. The input of these operation step sequence information enables the system to accurately identify and monitor key operation processes, thereby automatically capturing user operation step data closely related to the hospital's smart management rating.

[0031] Furthermore, by setting up a user operation capture submodule 1120 and employing RPA technology, this system can automatically log into the medical information system based on the login credentials information and monitor the user's operation steps to complete the target task, such as mouse clicks and keyboard input, to achieve real-time capture of the user's operation steps and behaviors in the medical information system. The medical information system includes a medical care management system, a human resources management system, a financial asset management system, an equipment and facilities management system, a drug and consumables management system, an operations management system, an operations support management system, a teaching and research management system, an office management system, and a basic and security system.

[0032] In some embodiments, the user operation capture submodule 1120 further includes: a context-aware and multimodal data processing submodule, used to obtain the user's operation step sequence information in the medical information system through log analysis and behavior tracking technology; based on image processing technology, capture the system page and corresponding text information in the system page when the user performs the operation steps according to the operation step sequence information; parse and process the text information through natural language processing technology to obtain the intent information of the user's operation steps and the context information of the corresponding user operation steps; and analyze the system page, the intent information of the user's operation, and the context information of the corresponding user operation steps to obtain user operation step data related to the hospital's smart management rating.

[0033] Furthermore, the specific implementation process for capturing user operation step data includes: First, using log analysis and behavior tracking technologies, the context-aware and multimodal data processing submodule collects the user's operation step sequence information in the medical information system, such as mouse clicks, keyboard input, and browsing operation step sequence information; then, using image processing technology, based on the operation step sequence information, such as screenshots and OCR text recognition, the system page during user operation is captured and the text information in the system page is extracted; then, using natural language processing technology, the text information in the system page is parsed to identify the user's operation intent and the contextual information of the user's operation steps; finally, by combining the system page, text information, and contextual information of the user's operation steps, such as the time, frequency, and sequence of the operation, a comprehensive analysis is performed to capture complete user operation step data, thereby ensuring the integrity and accuracy of the information.

[0034] Furthermore, by setting up an AI automatic recognition and recording submodule 1130, the system pages and key information such as meeting vouchers, purchase orders, and expense reports during user operations are automatically identified and extracted using a trained user behavior recognition AI model and natural language processing technology. These system pages and key information are then added with timestamps and contextual information of the user's operation steps and stored in the database. This provides accurate basic data for subsequent hospital smart management rating and analysis. This process ensures the effective capture and recording of key information and optimizes the working environment of the medical information system and the preparation process of rating materials.

[0035] Furthermore, by setting up an intelligent learning and optimization submodule 1140, a user behavior recognition AI model is constructed using machine learning algorithms such as random forests or neural networks. The machine learning algorithm can be flexibly selected according to actual usage, without any limitations, as long as it can achieve the purpose of recognizing the operation steps of different users. During the training process, multiple user operation step data are collected, and each user operation step data is labeled to obtain labeled data containing user completion of different tasks. Based on the labeled data containing user completion of different tasks, a dataset is constructed, and the dataset is randomly divided into a training set and a validation set in a 7:3 ratio. The training set and validation set are input into the user behavior recognition AI model for training and validation. The training process and hyperparameters, such as the depth of the decision tree or the weights of the neural network, are adjusted to optimize the recognition accuracy, resulting in a trained user behavior recognition AI model. In addition, this system continuously learns from user operation feedback and continuously fine-tunes the user behavior recognition AI model to adapt to changes in user behavior, thereby improving the accuracy of recognizing user operation steps.

[0036] In some embodiments, refer to the appendix Figure 3 The hospital smart management rating indicator setting module 120 is used to obtain rating indicators related to the hospital smart management rating. Based on RPA technology, it associates the rating indicators with user operation step data and generates a comparison table between the rating indicators and the system page.

[0037] Furthermore, the hospital smart management rating indicator setting module 120 includes a rating indicator data integration submodule 1210, used to obtain initial rating indicators related to hospital smart management rating from the National Health Commission website; a rating indicator parsing and mapping submodule 1220, used to establish a mapping relationship between the initial rating indicators and key information based on preset mapping rules between indicators and key information; a user configuration and customization submodule 1230, used to select preset rating indicators from the initial rating indicators according to the target rating requirements of hospital smart management rating, and assign corresponding weight values ​​to the preset rating indicators; a rating indicator dynamic adjustment submodule 1240, used to dynamically adjust the preset rating indicators and corresponding weight values ​​according to the feedback information of hospital smart management rating and the latest rating indicators related to hospital smart management rating; an intelligent association and lookup table generation submodule 1250, used to associate the preset rating indicators with user operation step data based on RPA technology, and generate a lookup table between rating indicators and system pages; and a rating indicator review and release submodule 1260, used to review the lookup table between rating indicators and system pages and the preset rating indicators, and release the preset rating indicators after the review is passed.

[0038] Furthermore, by setting up the rating indicator data integration submodule 1210, this system can obtain initial rating indicators related to hospital smart management rating from the website of the National Health Commission. These initial rating indicators are integrated into this system to provide a basis for subsequent evaluation work.

[0039] Furthermore, by setting up the rating indicator analysis and mapping submodule 1220, the initial rating indicators can be transformed into specific data query requirements. Through the preset mapping relationship between indicators and key information, the module can accurately locate key information on system pages such as accounting vouchers, purchase orders, and reimbursement documents. Key information includes voucher debit and credit amounts, dates, supplier information, etc., so that these key information can be automatically extracted later. Based on this, corresponding screenshots of empirical materials can be obtained, thereby obtaining empirical materials for key information. This supports the visualization of intelligent management rating. This module can ensure that the rating indicators form a corresponding mapping relationship with the hospital's actual operating data, laying the foundation for automated rating.

[0040] Furthermore, by setting the user configuration and customization submodule 1230, users can configure the target rating requirements for hospital smart management rating through the graphical user interface, including selecting preset rating indicators from the initial rating indicators and setting the corresponding weights. This system supports users to customize target rating requirements according to the specific situation of the hospital to adapt to different management objectives.

[0041] Furthermore, by setting up a rating indicator dynamic adjustment submodule 1250, and utilizing RPA technology, the rating indicators can be automatically associated with the user operation steps data recorded in the user operation capture submodule 1120, and a comparison table between the rating indicators and the system page can be intelligently generated to provide accurate data support for automated rating.

[0042] Furthermore, by setting the rating indicator dynamic adjustment submodule 1240, the preset rating indicators and corresponding weight values ​​can be dynamically adjusted based on the feedback information of the hospital's smart management rating and the latest rating indicators related to the hospital's smart management rating. This includes adding, deleting, or modifying preset rating indicators and setting, increasing, or decreasing the weight values ​​of preset rating indicators to ensure the timeliness and accuracy of the rating results.

[0043] Furthermore, by setting up a rating indicator review and release submodule 1260, the generated rating indicators are reviewed and processed in relation to the comparison table on the system page and the preset rating indicators to ensure that they meet the actual situation and rating requirements of hospital smart management rating. After the review is approved, the preset rating indicators are officially released and used for hospital smart management rating work.

[0044] In some embodiments, refer to the appendix Figure 4The automatic screenshot capture module 130 is used to identify and determine the target rating indicators that need to be captured based on the preset rating indicators of the hospital's smart management rating. Based on the comparison table between the rating indicators and system pages, it performs location matching processing on the system pages associated with the target rating indicators. Based on intelligent screenshot optimization technology, it performs screenshot processing on the key information contained in the associated system pages to obtain screenshot image data. It also performs type labeling on the screenshot image data to obtain screenshot image labeling data including the target rating indicators.

[0045] Furthermore, the automatic screenshot capture module 130 includes a rating indicator identification and locking submodule 1310, used to identify and determine the target rating indicator to be captured based on the preset rating indicators of the hospital's smart management rating; a system page lookup table matching submodule 1320, used to locate and match the system pages associated with the target rating indicator based on the lookup table between the rating indicators and system pages, and identify and determine the system pages to be captured; an automated login and navigation submodule 1330, used to automatically log in to the medical information system based on the login credentials information of the medical information system using RPA technology, and navigate to the corresponding system page according to the lookup table between the rating indicators and system pages; and an intelligent screenshot execution submodule 13. 40 is used to identify the attribute information of the corresponding system page after navigation to the corresponding system page, analyze the page elements of the corresponding system page based on the attribute information, identify at least one area containing key information, and automatically adjust the resolution and timing of the screenshot according to the content complexity of the corresponding system page based on the area containing key information, and perform screenshot processing on the area containing key information to obtain at least one screenshot image data; the screenshot data annotation and classification submodule 1350 is used to perform type annotation on the screenshot image data to obtain screenshot image annotation data including target rating indicators, and classify and store the screenshot image annotation data according to the target rating indicators.

[0046] Furthermore, by setting up the rating indicator identification and locking submodule 1310, this system can first identify and lock the specific target rating indicators that need to be screenshotted based on the preset rating indicators of the hospital's smart management rating, so as to ensure that the target of the subsequent screenshot work is clear and closely related to the rating requirements.

[0047] Furthermore, by setting up a system page lookup table matching submodule 1320, the system can automatically match the system page corresponding to each target rating indicator using the generated rating indicator and system page lookup table. This module is the key to achieving automated screenshots, ensuring that the system page that needs to be screenshotted can be accurately found.

[0048] Furthermore, by setting up an automated login and navigation submodule 1330, RPA technology is used to automatically log in to the medical information system and navigate to the corresponding system page according to the lookup table, thereby simulating the user's operation process and preparing the correct operating environment for screenshots.

[0049] Furthermore, by setting up the intelligent screenshot execution submodule 1340, after navigating to the corresponding system page, it first identifies the attribute information of the system page the user has entered, such as accounting vouchers or purchase order pages. Secondly, based on the attribute information of the system page, it analyzes the page elements to identify the area containing key information. Then, according to the content complexity of the corresponding system page, it automatically adjusts the screenshot resolution and timing. For example, it takes a screenshot immediately after the system page loads to avoid capturing incomplete information during loading. If the content complexity of the system page reaches a preset content complexity threshold, the screenshot resolution can be increased to avoid unclear screenshots. Additionally, the content complexity of the system page is determined by the number of characters on the system page. Simultaneously, this module can also intelligently select the screenshot range based on the importance of the system page and the distribution of data points to ensure that no key information is missed. It should be noted that by analyzing the page elements of the system page, if the system page contains multiple key information, it will identify at least one area containing the key information and perform segmented screenshots for each area to ensure that each part is clearly visible. Through intelligent screenshot optimization technology, key information can be captured more accurately, reducing errors and omissions caused by manual operation, improving the quality of screenshots and the efficiency of the automated rating process.

[0050] Furthermore, by setting up a screenshot data annotation and classification submodule 1350, the screenshot image data is annotated with types, including adding target rating indicators and descriptions, and classifying and storing the screenshot image annotation data according to the target rating indicators, which helps with subsequent rating analysis and material organization.

[0051] In some embodiments, refer to the appendix Figure 5 The material collection module 140 is used to acquire supporting material data related to the screenshot image annotation data. The supporting material data is business data related to the screenshot image annotation data. According to the data type and target rating index, the screenshot image annotation data and supporting material data are classified and processed to obtain multiple categories of data. Data extraction is performed on the categories of data to obtain extracted data. According to the target rating requirements, target rating index and data type, the extracted data is archived and index information and directory information are generated.

[0052] Furthermore, the material collection module 140 includes a material identification and classification submodule 1410, used to acquire supporting material data related to the screenshot image annotation data, classify the screenshot image annotation data and supporting material data according to the target rating index to obtain the first category data under the target rating index classification, and classify the first category data according to data type to obtain the second category data corresponding to each data type under each target rating index; a data extraction and organization submodule 1420, used to extract data from the second category data to obtain extracted data, the extracted data including key information extracted from the screenshot image annotation data in the second category data and supporting information related to the key information extracted from the supporting material data in the second category data, the extracted data being structured format data; and a material archiving and indexing submodule 1430, used to archive the extracted data according to the target rating requirements, target rating indexes and data types, and generate index information and catalog information.

[0053] Furthermore, by setting up a material recognition and classification submodule 1410, the screenshot image annotation data and supporting material data are identified and obtained. Using artificial intelligence technology, the identified screenshot image annotation data and supporting material data can be classified according to the target rating index and data type. Among them, data types such as text and images are automatically classified to obtain the second category data corresponding to each data type under each target rating index.

[0054] Furthermore, by setting up a data extraction and organization submodule 1420, key information and supporting information are automatically extracted from the second category data after identification and classification. For example, key information in text format is extracted from the screenshot image annotation data. This extracted information will be organized into a structured format for easy subsequent processing and analysis.

[0055] Furthermore, by setting up the material archiving and indexing submodule 1430, the extracted materials are archived into the corresponding directory structure according to the target rating requirements, target rating indicators, and data types. Simultaneously, an index and directory are generated to enable users to quickly retrieve and access specific materials.

[0056] In some embodiments, refer to the appendix Figure 6 The document generation module 150 is used to create various format document templates that meet the requirements of hospital smart management rating. Using template engine technology, the extracted data is matched with the predefined placeholders in the document template to obtain an automatically filled text file. Based on the formatting tool, the text file is styled and formatted to obtain an initial empirical material text file that meets the target rating requirements. The initial empirical material text file is then quality verified to obtain the target empirical material text file.

[0057] Furthermore, the document generation module 150 includes a template preparation and customization submodule 1510, used to create various format document templates that meet the requirements of hospital smart management rating; a data binding and autofill submodule 1520, used to match extracted data with predefined placeholders in the document template based on template engine technology, according to the target rating requirements, target rating indicators, and data types, to obtain an autofilled text file, wherein the target rating requirements, target rating indicators, and data types correspond to different types of placeholders; a formatting and layout submodule 1530, used to perform style and layout processing on the text file based on a formatting tool, to obtain an initial empirical material text file that meets the target rating requirements; a data verification and quality control submodule 1540, used to obtain detailed information related to hospital smart management rating, and to perform quality verification on the initial empirical material text file based on the detailed information, to obtain a target empirical material text file; and a document saving and version management submodule 1550, used to store and manage the version of the target empirical material text file.

[0058] Furthermore, by setting up the template preparation and customization submodule 1510, before the system is put into use, various format file templates that meet the hospital's smart management rating requirements are first prepared or customized. These file templates include, but are not limited to, Word documents, PDF files, Excel spreadsheets, etc., to adapt to different submission and archiving needs, and to ensure that these text templates contain all necessary rating items and format requirements.

[0059] Furthermore, by setting up the data binding and auto-fill submodule 1520, and utilizing template engine technology, the extracted data is matched with predefined placeholders in the file template according to the target rating requirements, target rating indicators, and data types. For example, key information and supporting information from system pages such as accounting vouchers, purchase orders, and expense reports are automatically bound to placeholders in the file template. Through template engine technology, the system can identify predefined markers (placeholders) in the text template and intelligently match the actual data to the correct position according to the content type and rating requirements. For example, if a placeholder in the file template is used to refer to a purchase order number, the system will identify this position and automatically fill in the extracted purchase order number data. This automated data processing and filling method not only improves the efficiency of report generation but also reduces human error, ensuring the accuracy and consistency of the report content.

[0060] Furthermore, by setting the formatting and layout submodule 1530, the system's built-in formatting tools are used to style and format the text file, such as setting font styles, colors, table borders, chart styles, etc., to ensure the professionalism and readability of the document and obtain the initial empirical material text file that meets the target rating requirements.

[0061] Furthermore, by setting up a data verification and quality control submodule 1540, the system performs a document verification process during document generation. It checks whether the data meets the rating requirements by comparing it against detailed information related to the hospital's smart management rating. These detailed information comes from specific guidelines and standards issued by the National Health Commission. By checking data integrity, the system ensures that the collected information is comprehensive and complete. Logical consistency analysis ensures reasonable relationships between data, such as the matching of dates and amounts. The system also verifies the correctness of data formats, including text alignment, number formatting, and unit usage, to guarantee the professionalism and accuracy of the document content and presentation.

[0062] Furthermore, by setting up the file saving and version management submodule 1550, after verification, the target empirical material text file is stored in a secure file management system, and version management is implemented to record every modification and update of the file for easy tracking and retrospection.

[0063] In some embodiments, the automatic toolbar and tray application module 160 is used to identify the system page and operation step sequence information that the user is currently or about to operate based on the user operation step data, and to identify active toolbars and / or tray applications based on the system page and operation step sequence information that the user is currently or about to operate, and to close inactive toolbars and / or tray applications.

[0064] Furthermore, by setting up an automatic toolbar and tray application closing module 160, and utilizing context-aware technology, the system can understand the user's current tasks and operational flow, predict the user's upcoming actions, and thus determine which toolbars and / or tray applications are active. During this process, inactive toolbars and / or tray applications are intelligently closed to avoid interfering with the screenshot process and improve system response speed. The determination of activity status is based not only on the user's current direct interaction but also on the logical flow of the operation and system prompts, ensuring that business processing and screenshot work are only performed in active toolbars and / or tray applications. This intelligent resource management mechanism optimizes the working environment of the hospital information system and improves the efficiency and accuracy of hospital smart management rating.

[0065] Example 2

[0066] This embodiment, based on Embodiment 1 above, provides a method for generating empirical materials for hospital smart management rating based on RPA. Please refer to [link to previous document]. Figure 7 The method, which is applied to the RPA-based hospital smart management rating empirical material generation system in Example 1, includes the following steps.

[0067] S1. Through the user operation data acquisition module, based on RPA technology, AI technology, and multimodal data fusion technology, user operation step data related to hospital smart management rating is captured in the medical information system, and the system pages contained in the user operation step data and the key information contained in the system pages are identified.

[0068] S2. Obtain rating indicators related to hospital smart management rating through the hospital smart management rating indicator setting module. Based on RPA technology, associate the rating indicators with user operation step data to generate a comparison table between rating indicators and system pages.

[0069] S3. The automatic screenshot capture module identifies and determines the target rating indicator that needs to be captured based on the preset rating indicators of the hospital's smart management rating. Based on the comparison table between the rating indicators and system pages, the module performs location matching processing on the system pages associated with the target rating indicator. Based on intelligent screenshot optimization technology, the module performs screenshot processing on the key information contained in the associated system pages to obtain screenshot image data. The module then performs type labeling on the screenshot image data to obtain screenshot image labeling data including the target rating indicator.

[0070] S4. Obtain supporting material data related to the screenshot image annotation data through the material collection module. The supporting material data is business data related to the screenshot image annotation data. According to the data type and target rating index, classify the screenshot image annotation data and supporting material data to obtain multiple categories of data. Extract data from the categories to obtain extracted data. According to the target rating requirements, target rating index and data type, archive the extracted data and generate index information and directory information.

[0071] S5. Create various formatted file templates that meet the hospital's smart management rating requirements through the file generation module. Using template engine technology, match the extracted data with the predefined placeholders in the file template to obtain an automatically filled text file. Based on the formatting tool, process the style and layout of the text file to obtain the initial empirical material text file that meets the target rating requirements. Then, verify the quality of the initial empirical material text file to obtain the target empirical material text file.

[0072] S6. Based on the user's operation step data, the automatic closing of toolbars and tray applications module identifies the system pages and operation step sequence information that the user is currently or about to operate, and identifies active toolbars and / or tray applications, and closes inactive toolbars and / or tray applications.

[0073] Example 3

[0074] Based on Embodiment 1 described above, this embodiment also provides an electronic device, please refer to the appendix. Figure 8 , Figure 8 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0075] like Figure 8 As shown, the electronic device may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0076] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 8 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have instead. Figure 8 Each box shown can represent a device or multiple devices as needed.

[0077] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 309, or installed from a storage device 308, or installed from a ROM 302. When the computer program is executed by the processing device 301, it performs the functions defined in the methods of some embodiments of this disclosure.

[0078] Example 4

[0079] Based on Embodiment 1 above, this embodiment also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above method.

[0080] It should be noted that, in some embodiments of this disclosure, the computer-readable medium described above may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), or any suitable combination thereof.

[0081] In this embodiment, the client and server can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol), and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0082] The aforementioned computer-readable medium may be included in the aforementioned device or may exist independently without being assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: acquire training data and transform the training data to obtain initial data; determine an initial rule base based on the initial data and optimize the parameters of the initial rule base to obtain a target rule base; calculate activation weights for the rules in the target rule base according to a preset activation weight calculation formula; and determine abnormal information based on test data and the activation weights.

[0083] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0084] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0085] The units described in some embodiments of this disclosure can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor may be described as including a data acquisition unit, a rule determination unit, a weight calculation unit, and an anomaly determination unit. The names of these units do not necessarily limit the specific unit; for example, a data acquisition unit may also be described as a "unit for acquiring training data."

[0086] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), etc.

[0087] Obviously, those skilled in the art will understand that the various steps of the present invention described above can be performed in a manner different from that described above, and the simulation methods and experimental equipment include, but are not limited to, the above description. The steps of the present invention described above can be performed in a different order in certain circumstances, and the steps shown or described above can be performed separately. Therefore, the present invention is not limited to any particular combination of hardware and software.

[0088] The above description, in conjunction with specific embodiments, provides a further detailed explanation of the present invention. It should not be construed that the specific implementation of the present invention is limited to these descriptions. For those skilled in the art, various simple deductions or substitutions can be made without departing from the concept of the present invention, and all such deductions or substitutions should be considered within the scope of protection of the present invention.

Claims

1. A hospital smart management rating empirical material generation system based on RPA, characterized in that, include: The user operation data acquisition module is used to capture user operation step data related to hospital smart management rating in the medical information system based on RPA technology, AI technology, and multimodal data fusion technology, and to identify the system pages contained in the user operation step data and the key information contained in the system pages. The hospital smart management rating indicator setting module is used to obtain rating indicators related to hospital smart management rating. Based on RPA technology, the rating indicators are associated with user operation step data to generate a comparison table between rating indicators and system pages. The automatic screenshot capture module is used to identify and determine the target rating indicators that need to be captured based on the preset rating indicators of the hospital's smart management rating. Based on the comparison table between rating indicators and system pages, it performs location matching processing on the system pages associated with the target rating indicators. Based on intelligent screenshot optimization technology, it performs screenshot processing on the key information contained in the associated system pages to obtain screenshot image data. The screenshot image data is then labeled with its type to obtain screenshot image labeled data including the target rating indicators. The material collection module is used to acquire supporting material data related to the screenshot image annotation data. The supporting material data is business data related to the screenshot image annotation data. According to the data type and target rating index, the screenshot image annotation data and supporting material data are classified and processed to obtain multiple categories of data. Data extraction is performed on the classified data to obtain extracted data. According to the target rating requirements, target rating index and data type, the extracted data is archived and index information and directory information are generated. The document generation module is used to create various format document templates that meet the requirements of hospital smart management rating. Using template engine technology, the extracted data is matched with the predefined placeholders in the document template to obtain an automatically filled text file. Based on the formatting tool, the text file is styled and formatted to obtain an initial empirical material text file that meets the target rating requirements. The initial empirical material text file is then quality verified to obtain the target empirical material text file. The automatic toolbar and tray application closing module is used to identify the system page and operation step sequence information that the user is currently or about to operate based on the user's operation step data, and to identify active toolbars and / or tray applications based on the user's current or upcoming system page and operation step sequence information, and to close inactive toolbars and / or tray applications.

2. The RPA-based hospital smart management rating empirical material generation system according to claim 1, characterized in that, The user operation data acquisition module includes: The system initialization and configuration submodule is used by users to input configuration information related to the hospital's smart management rating through a graphical user interface. The configuration information includes login credentials for the medical information system and the sequence of operation steps for monitoring users to complete target tasks. The medical information system includes a medical and nursing management system, a human resources management system, a financial and asset management system, an equipment and facilities management system, a drug and consumables management system, an operations management system, an operations support management system, a teaching and research management system, an office management system, and a basic and security system. The user operation capture submodule is used to automatically log in to the medical information system based on the login credentials of the medical information system and monitor the user's operation steps to complete the target task based on RPA technology. Based on multimodal data fusion technology, it captures user operation step data and corresponding user operation step context information related to the hospital's smart management rating. The AI ​​automatic recognition and recording submodule is used to identify system pages and key information contained in user operation step data based on the trained user behavior recognition AI model and natural language processing technology, and store the system pages, key information contained in the system pages, timestamps of corresponding user operation steps, and contextual information of corresponding user operation steps in the database. The intelligent learning and optimization submodule is used to build and train a user behavior recognition AI model to obtain the trained user behavior recognition AI model.

3. The RPA-based hospital smart management rating empirical material generation system according to claim 2, characterized in that, The user operation capture submodule also includes: The context-aware and multimodal data processing submodule is used to acquire the sequence information of user operation steps in the medical information system through log analysis and behavior tracking technology. Based on image processing technology, it captures the system page and corresponding text information on the system page when the user performs the operation steps according to the operation step sequence information. Through natural language processing technology, it parses and processes the text information to obtain the intent information of the user operation steps and the corresponding contextual environment information of the user operation steps. It analyzes the system page, the intent information of the user operation, and the contextual environment information of the corresponding user operation steps to obtain user operation step data related to the hospital's smart management rating.

4. The RPA-based hospital smart management rating empirical material generation system according to claim 1, characterized in that, The hospital smart management rating indicator setting module includes: The rating indicator data integration submodule is used to obtain initial rating indicators related to hospital smart management rating from the website of the National Health Commission. The rating indicator analysis and mapping submodule is used to establish a mapping relationship between the initial rating indicators and key information based on the preset mapping rules between indicators and key information. The user configuration and customization submodule is used to select preset rating indicators from the initial rating indicators based on the target rating requirements of the hospital's smart management rating, and to assign corresponding weight values ​​to the preset rating indicators. The rating indicator dynamic adjustment submodule is used to dynamically adjust the preset rating indicators and corresponding weight values ​​based on the feedback information of the hospital's smart management rating and the latest rating indicators related to the hospital's smart management rating. The intelligent association and lookup table generation submodule is used to associate preset rating indicators with user operation step data based on RPA technology, and generate a lookup table between rating indicators and system pages. The rating indicator review and release submodule is used to review the rating indicators against the comparison table on the system page and the preset rating indicators, and release the preset rating indicators after the review is approved.

5. The RPA-based hospital smart management rating empirical material generation system according to claim 4, characterized in that, The automatic screenshot capture module includes: The rating indicator identification and locking submodule is used to identify and determine the target rating indicators that need to be captured based on the preset rating indicators of the hospital's smart management rating. The system page lookup table matching submodule is used to locate and match system pages associated with the target rating indicator based on the lookup table between the rating indicator and the system page, and to identify and determine the system page that needs to be screenshotted. The automated login and navigation submodule is used to automatically log in to the medical information system based on the login credentials information of the medical information system using RPA technology, and navigate to the corresponding system page according to the rating indicators and the system page comparison table. The intelligent screenshot execution submodule is used to identify the attribute information of the corresponding system page after navigating to the corresponding system page, analyze the page elements of the corresponding system page based on the attribute information, identify at least one area containing key information, and automatically adjust the screenshot resolution and timing according to the content complexity of the corresponding system page based on the area containing key information, perform screenshot processing on the area containing key information, and obtain at least one screenshot image data. The screenshot data annotation and classification submodule is used to annotate the screenshot image data by type, obtain screenshot image annotation data including target rating indicators, and classify and store the screenshot image annotation data according to the target rating indicators.

6. The RPA-based hospital smart management rating empirical material generation system according to claim 1, characterized in that, The material collection module includes: The material identification and classification submodule is used to acquire supporting material data related to the screenshot image annotation data. Based on the target rating index, the screenshot image annotation data and supporting material data are classified to obtain the first category data under the target rating index classification. The first category data is then classified according to data type to obtain the second category data corresponding to each data type under each target rating index. The data extraction and processing submodule is used to extract data from the second category data to obtain extracted data. The extracted data includes key information extracted from the screenshot image annotation data in the second category data and proof information related to the key information extracted from the proof material data in the second category data. The extracted data is in structured format. The Materials Archiving and Indexing submodule is used to archive extracted data according to target rating requirements, target rating indicators, and data types, and to generate index and catalog information.

7. The RPA-based hospital smart management rating empirical material generation system according to claim 1, characterized in that, The file generation module includes: The template preparation and customization submodule is used to create various format file templates that meet the requirements of hospital smart management rating; The data binding and autofill submodule is used to match extracted data with predefined placeholders in the file template based on template engine technology, according to the target rating requirements, target rating indicators and data types, to obtain an autofilled text file. The target rating requirements, target rating indicators and data types correspond to different types of placeholders. The formatting and layout submodule is used to style and format text files based on formatting tools to obtain initial empirical material text files that meet the target rating requirements. The data verification and quality control submodule is used to obtain detailed information related to the hospital's smart management rating, and to perform quality verification on the initial empirical material text file based on the detailed information to obtain the target empirical material text file. The File Saving and Version Management submodule is used for storing and managing the version of text files containing the target empirical materials.

8. A method for generating empirical materials for hospital smart management rating based on RPA, characterized in that, include: The user operation data acquisition module uses RPA, AI and multimodal data fusion technologies to capture user operation step data related to hospital smart management rating in the medical information system, and identifies the system pages and key information contained in the system pages in the user operation step data. The rating indicators related to hospital smart management rating are obtained through the hospital smart management rating indicator setting module. Based on RPA technology, the rating indicators are associated with user operation step data to generate a comparison table between rating indicators and system pages. The automatic screenshot capture module identifies and determines the target rating indicators that need to be captured based on the preset rating indicators of the hospital's smart management rating. Based on the comparison table between rating indicators and system pages, it performs location matching processing on the system pages associated with the target rating indicators. Based on intelligent screenshot optimization technology, it performs screenshot processing on the key information contained in the associated system pages to obtain screenshot image data. The screenshot image data is then labeled with its type to obtain screenshot image labeled data including the target rating indicators. The material collection module acquires supporting material data related to the screenshot image annotation data. The supporting material data is business data related to the screenshot image annotation data. According to the data type and target rating index, the screenshot image annotation data and supporting material data are classified and processed to obtain multiple categories of data. Data extraction is performed on the categories of data to obtain extracted data. According to the target rating requirements, target rating index and data type, the extracted data is archived and index information and directory information are generated. The document generation module creates various format document templates that meet the hospital's smart management rating requirements. Using template engine technology, the extracted data is matched with predefined placeholders in the document template to obtain an automatically filled text file. Based on the formatting tool, the text file is styled and formatted to obtain an initial empirical material text file that meets the target rating requirements. The initial empirical material text file is then quality-verified to obtain the target empirical material text file. The automatic toolbar and tray application closing module identifies the system pages and operation sequence information that the user is currently or about to operate based on the user's operation step data. Based on the system pages and operation sequence information that the user is currently or about to operate, it identifies active toolbars and / or tray applications and closes inactive toolbars and / or tray applications.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in claim 8.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in claim 8.

Images