A think tank data management system based on emergency medical support

Abstract

The present invention discloses a think tank data management system based on emergency medical support, which includes an information collection module, a data processing module, a visualization management module, and a data set management module. Information collection module: used to collect emergency medical support data information from various field departments and store the data information in the emergency medical support database; Data processing module: used to support the monitoring of the usage of data storage resources; Visualization management module: used to provide Web-based visualization operations on the data information; Data set management module: used to manage the data set in the model training of the data management system. The emergency medical support think tank data management system provided by the present invention can quickly integrate the emergency medical support data of multiple departments and realize the processing of the emergency medical support data. The visualization management module therein facilitates users to view, monitor, and manage at any time.

Description

Technical Field

[0001] The present invention relates to the technical field of emergency management, and particularly to a think tank data management system based on emergency medical support. Background Art

[0002] With the development of technology, informatization has become increasingly important in all aspects. The convenience brought by informatization to mankind has brought earth-shaking changes to our lives. However, informatization not only affects people's lives, but also countries are competing in the aspect of informatization. After entering the 21st century, informatization has become an important reference for a country's comprehensive strength.

[0003] With the expansion of the functions and tasks of the military, the military has become an important force in responding to disaster accidents and public health emergencies, and plays an important role in disaster emergency medical rescue and medical support for public health emergencies. The military's participation in emergency medical support requires research on specific military needs and the provision of corresponding informatization platform support. Since China is a country prone to disasters, the population base of emergency disasters is large, covering many fields, and a large amount of document data has been generated among various field departments. These data are often stored in their self-built systems, making it difficult to search for and upload emergency medical support data resources from different sources, natures, and types, and it is not convenient to form an emergency medical support think tank system for reference and research. Summary of the Invention

[0004] The purpose of the present invention is to provide a think tank data management system based on emergency medical support, so as to achieve the purpose of integrating, storing, and processing emergency medical support data resources from different sources, natures, and types to form an emergency medical support think tank system.

[0005] To solve the above technical problems, the present invention adopts the following technical solutions:

[0006] A think tank data management system based on emergency medical support includes an information collection module, a data processing module, a visualization management module, and a data set management module; among them

[0007] The information collection module: is used to collect emergency medical support data information of each field department, and store the emergency medical support data information in the emergency medical support database;

[0008] The data processing module: is used to support the monitoring of the usage of data storage resources. The data processing module includes a data cleaning module, and the data cleaning module is used to perform basic processing on the data information. The basic processing includes image data clipping, elimination of invalid fields in structured data, deletion of duplicate data, and correction of error data;

[0009] Visualization Management Module: It is used to provide Web-based visualization operations on data information, and the visualization management module meets the requirements of artificial intelligence training, development, and application. The visualization management module includes a data transmission module and a data conversion module. The data transmission module is used to support users in uploading and downloading data files or folders of video, picture, text, and table types regarding emergency medical support data information. The data conversion module is used to convert data files or folders into data sets;

[0010] Data Set Management Module: It is used to manage data sets in the model training of the data management system.

[0011] Furthermore, the information collection module includes a system access module;

[0012] System Access Module: It is used to connect to the systems of various field departments and access the emergency medical support data information of various field departments into the data management system.

[0013] Furthermore, the system access module includes:

[0014] Data Interface Setting Module: It is used to provide a unified API interface for data access and the interface access process, and at the same time implement the scheduling authorization and authentication mechanism of the API.

[0015] Furthermore, the data processing module is connected to the Hadoop distributed file system to provide users with high-throughput data access support.

[0016] Furthermore, the data processing module also includes:

[0017] Data Directory Module: It is used to support users in quickly discovering the required data sources and understanding and using the found data sources.

[0018] Furthermore, the visualization management module also includes:

[0019] Retrieval Module: It is used to provide users with retrieval queries by the name of data files or folders based on the emergency medical support database and obtain query results;

[0020] Preview Module: It is used to provide users with the preview function of videos, pictures, and texts;

[0021] Docking Module: It is used to implement the docking of the visualization management module with the model and algorithm system, facilitating jumping from the visualization management module to the model and algorithm system for model training;

[0022] Permission Setting Module: It is used to support users in setting permissions for their own files, including viewing, calling, and downloading permissions, to protect the security and privacy of data.

[0023] Furthermore, the dataset management module conducts model training in the model and algorithm prototype system. The dataset management module includes a text annotation module;

[0024] Text annotation module: used to annotate text-type datasets during model training.

[0025] Furthermore, the text annotation module includes a multi-user collaborative annotation module and an annotation result export module;

[0026] Multi-user collaborative annotation module: used to provide the ability of collaborative annotation for multiple users;

[0027] Annotation result export module, used to export the annotated dataset.

[0028] Furthermore, the dataset management module also includes an image and video annotation module;

[0029] Image and video annotation module: used to annotate image and video-type datasets during model training;

[0030] The image and video annotation module includes a multi-user collaborative annotation module and an annotation result export module.

[0031] Furthermore, the dataset management module also includes:

[0032] Annotation recognition module: used to recognize the dataset format generated by annotation in the model and algorithm prototype system;

[0033] Storage module: used to provide storage for the original data of the annotation task in the model and algorithm prototype system;

[0034] Dataset primary processing module: used to browse and delete the datasets generated in the model and algorithm prototype system;

[0035] Dataset secondary processing module: used to provide processing for editing, replacing, deleting, and adding datasets and internal files;

[0036] Dataset acquisition module: used to provide the ability to acquire datasets in the model and algorithm prototype system;

[0037] Dataset tertiary processing module: used to manage the status of datasets. When in the training process of the model and algorithm prototype system, the datasets used in the training process are displayed as occupied and users are prohibited from editing.

[0038] The present invention provides a think tank data management system based on emergency medical support, which can comprehensively integrate the emergency medical support data of multiple departments and can process the emergency medical support data on the think tank data management system for emergency medical support. Since the information processing process of traditional big data platforms is opaque, it is difficult for operators who are not familiar with the system to interact. In the visualization management module of the think tank data management system for emergency medical support, it is convenient for users to view, monitor and manage at any time. The present invention adds a visualization management module. Users do not need to care about the underlying architecture and application implementation, and can view, monitor and manage the platform at any time through this module. In addition, users can also jump to the model and algorithm system through the visualization management module for model training, and complete the development and application of emergency medical support data in the think tank data management system for emergency medical support. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The above content of the present invention and the following specific embodiments will be better understood when read in conjunction with the accompanying drawings. It should be noted that the drawings are only examples of the claimed technical solutions.

[0040] Figure 1 is a schematic structural diagram of a think tank data management system based on emergency medical support according to an embodiment of the present invention;

[0041] Figure 2 is a schematic structural diagram of the visualization management module in the think tank data management system based on emergency medical support according to an embodiment of the present invention;

[0042] Figure 3 is a schematic structural diagram of the dataset management module in the think tank data management system based on emergency medical support according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] The following details the detailed features and advantages of the present invention in the specific embodiments. The content is sufficient for any person skilled in the art to understand the technical content of the present invention and implement it accordingly. According to the description, claims and drawings disclosed in this specification, those skilled in the art can easily understand the related purposes and advantages of the present invention.

[0044] To make the objectives, technical solutions and advantages of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0045] As Figures 1-3 shown in an embodiment of the present invention, a think tank data management system based on emergency medical support includes an information collection module, a data processing module, a visualization management module and a dataset management module.

[0046] Information collection module: used to collect emergency medical support data information from various field departments and store the emergency medical support data information in the emergency medical support database. Among them, the various field departments include emergency medical support departments in multiple professional fields such as ship sanitation and epidemic prevention, medical care, health protection, submarine medicine, diving medicine, and naval aviation medicine.

[0047] Data processing module, used to support the monitoring of the usage of data storage resources.

[0048] Visualization management module, used to provide Web-based visualization operations on data information, and the visualization management module meets the needs of artificial intelligence training, development, and application.

[0049] In a preferred embodiment of the present invention, the information collection module includes a system access module.

[0050] System access module, used to connect to the systems of various field departments and access the emergency medical support data information of various field departments into the data management system. The system access module can also be connected to the grass-roots hardware devices of various field departments, access the grass-roots hardware devices of various field departments into the data management system, and the information collection module has the ability to establish communication with the grass-roots hardware devices and can obtain emergency medical support data information from the hardware facilities.

[0051] Specifically, the system access module includes a data interface setting module, which is used to provide a unified API interface and interface access process for data access, and at the same time implement the scheduling authorization and authentication mechanism of the API.

[0052] Specifically, the data processing module is docked with the Hadoop distributed file system. The Hadoop distributed file system can be deployed on low-cost general hardware, providing high-throughput data access support for users, and at the same time supporting the monitoring of the usage of data storage resources.

[0053] In a preferred embodiment of the present invention, the data processing module includes a data cleaning module.

[0054] Data cleaning module: used to perform basic processing on data information, where the basic processing includes cropping of emergency medical support image data, elimination of invalid fields in structured data, deletion of duplicate data, and correction of error data.

[0055] Specifically, the data processing module also includes a data catalog module, which is used to help users quickly discover the required data sources and understand and use the found data sources.

[0056] In a preferred embodiment of the present invention, the visualization management module includes a data transmission module, a retrieval module, a preview module, a data conversion module, a docking module, and a permission setting module.

[0057] A data transmission module, which is used to support users to upload and download data files or folders of video, picture, text, and table types regarding emergency medical support data information.

[0058] A retrieval module, which is used to provide users with retrieval queries by the name of data files or folders based on the emergency medical support database and quickly obtain query results.

[0059] A preview module, which is used to provide users with the preview function of videos, pictures, and text regarding emergency medical support data information to help users check whether the data is what they need before downloading. The preview function of text is based on mainstream text formats, and the mainstream text can adopt formats such as txt, word, PPT, excel, etc.

[0060] A data conversion module, which is used to convert data files or folders into data sets.

[0061] A docking module, which is used to realize the docking between the visualization management module and the model and algorithm system, facilitating jumping from the visualization management module to the model and algorithm system for model training.

[0062] A permission setting module: which is used to support users to set permissions for their own files, including viewing, calling, and downloading permissions, to protect the security and privacy of data.

[0063] The emergency medical support think tank data management system provided by the present invention further includes a data set management module, which is used to manage data sets in the model training of the data management system.

[0064] In a preferred embodiment of the present invention, the data set management module conducts model training in the model and algorithm prototype system. The data set management module includes a text annotation module, which is used to annotate data sets of text type during model training. At the same time, the text annotation module supports online text annotation, and users can conduct online annotation by opening a browser, providing high-quality training data support for artificial intelligence training tasks in the field of natural language processing.

[0065] Specifically, the text annotation module includes a multi-user collaborative annotation module and an annotation result export module.

[0066] The multi-user collaborative annotation module is used to provide the ability of collaborative annotation for multiple users.

[0067] The multi-user collaborative annotation module includes a collaborative annotation task module, an annotation application module, and an annotation tool set module.

[0068] Collaborative annotation task module, which is used to manage the annotation process of text-type data sets on a Web-based visual operation interface for collaborative annotation task management. The management of the annotation process includes: supporting the unified creation of collaborative annotation tasks, and classifying the emergency medical support data according to the sources of emergency medical support data on the primary visual operation interface, such as the emergency medical support data of multiple task departments including organization and command, medical treatment, evacuation of the wounded and sick, and needs assessment, and the classification of emergency medical support data, such as being divided into 3 categories including medical treatment, evacuation of the wounded and sick, and organization and command. Providing functions such as task information creation, annotation label creation, and annotation data upload for users, and presenting the upload status and result information of the annotation data therein; providing functions of annotation task division, task distribution, task assignment and feedback, and task progress status presentation; supporting the automatic division of annotation data according to the number of subtasks and the size of data overlap between subtasks, and at the same time supporting three granularities of text annotation data splitting methods, namely sentences, paragraphs, and files, and providing a function of re-dividing tasks; supporting team collaborative annotation, where users can invite their project team members to conduct team collaborative annotation, and for the same group of text annotation tasks, supporting collaborative annotation of no less than 10 people; supporting the management of collaborative annotation task assignment and feedback, providing at least no less than 4 subtask operation methods (such as confirm assignment, cancel assignment, pass, reject) to the task creator, and providing at least no less than 3 subtask operation methods (such as accept, reject, submit) to the personnel assigned with subtasks; supporting the presentation of the annotation progress status of subtasks (such as status types like "annotating", "pending receipt", "rejected", "pending review", "completed", etc.); supporting the real-time monitoring and operation functions of the progress and results of data operations related to the annotation tasks; supporting the classification presentation according to two types of annotation tasks, namely creating tasks and assigned subtasks, providing a task card view and a list view, and the list view method can uniformly present the annotation task information and progress status information; supporting operations such as searching and deleting the created tasks; supporting the management of annotation label templates, providing operations such as label display, editing, modification, deletion, and saving; supporting the data export of the completed annotation tasks.

[0069] The annotation application module is used to provide an application for the annotation process of text-type datasets, specifically including: supporting the annotation of named entities and their attributes, such as person name + (gender + occupation); supporting the annotation of named entity relationships. If the user adds an incorrect relationship between entities, such as a "native place relationship" between two entities but the user adds another relationship, a reminder function needs to be provided; supporting text classification annotation, text translation annotation, and text summary annotation, and supporting the selection of single sentences or multiple sentences for annotation; supporting annotation in no less than 2 languages such as Chinese and English; supporting the annotation of different labels for the same text (file, paragraph, or sentence); supporting three different granularity annotation modes: file, paragraph, and sentence; supporting the generation of training datasets according to usage scenarios, and the usage scenarios at least include named entity recognition, text classification, text summary, text translation, etc.; being able to meet the requirements of artificial intelligence for training data in multiple scenario tasks in the text application field, including sentiment analysis, named entity recognition, text translation, etc.

[0070] The annotation toolset module is used to provide a toolset for a web-based collaborative annotation task management visualization operation interface. The toolset includes: supporting two annotation methods, one can annotate tag information throughout the text, and the other can randomly add different tags in the reading order; providing auxiliary tools for the text annotation process, supporting functions such as withdrawal, redo, and saving of annotation operations, and supporting the free switching of subtasks under the current annotation task; providing a text annotation statistical information function, supporting the display of the number of created annotation frames for the annotation task, and supporting sorting by tag type; supporting the customization of tool components in a drag-and-drop manner to meet personalized annotation interfaces; supporting the free switching between three annotation mode views of sentences, paragraphs, and files; supporting display according to tag content (all marked tags) and annotation type (all marked tag types), facilitating users to quickly lock a certain tag; supporting the customization of annotation tool components in a drag-and-drop manner to meet users' personalized needs for tools.

[0071] The annotation result export module is used to export the annotated dataset.

[0072] More specifically, the dataset management module also includes a graphic and video annotation module, which is used to annotate datasets of picture and video types during model training. Among them, the graphic and video annotation module can recognize common image dataset formats such as Pascal Voc, CoCo, and YoLo. The graphic and video annotation module can also process using the above multi-user collaborative annotation module and export the annotated picture and video type datasets using the annotation result export module.

[0073] Specifically, the dataset management module also includes:

[0074] The annotation recognition module: used to recognize the dataset format generated by annotation in the model and algorithm prototype system;

[0075] Storage module: used to provide storage for the original data for the annotation tasks in the model and algorithm prototype system;

[0076] Dataset primary processing module: used to browse and delete the datasets generated in the model and algorithm prototype system;

[0077] Dataset secondary processing module: used to provide processing for editing, replacing, deleting, and adding datasets and internal files;

[0078] Dataset acquisition module: used to provide the ability to acquire datasets in the model and algorithm prototype system;

[0079] Dataset tertiary processing module: used for the status management of datasets. When in the training process of the model and algorithm prototype system, when the datasets used in the training process are displayed as occupied, users are prohibited from performing editing operations.

[0080] The terms and expressions used herein are only for description, and the present invention should not be limited to these terms and expressions. The use of these terms and expressions does not mean excluding any equivalent features of the illustration and description (or parts thereof). It should be recognized that various modifications that may exist should also be included within the scope of the claims. Other modifications, variations, and substitutions may also exist. Accordingly, the claims should be regarded as covering all such equivalents.

[0081] Similarly, it should be noted that although the present invention has been described with reference to the current specific embodiments, those of ordinary skill in the art in this technical field should recognize that the above embodiments are only used to illustrate the present invention, and various equivalent changes or substitutions can be made without departing from the spirit of the present invention. Therefore, as long as the changes and variations of the above embodiments are within the scope of the spirit of the present invention, they will fall within the scope of the claims of the present invention.

Claims

1. A think tank data management system based on emergency medical support, characterized in that, It includes an information collection module, a data processing module, a visualization management module, and a dataset management module; among them The information collection module: is used to collect data information of each department in the emergency medical rescue operation, and store the emergency medical support data information into the emergency medical support database; The data processing module: is used to support the monitoring of the usage of data storage resources, where the data processing module includes a data cleaning module, and the data cleaning module is used to perform basic processing on the data information, and the basic processing includes image data cropping, elimination of invalid fields in structured data, deletion of duplicate data, and correction of error data; The visualization management module: is used to provide a Web-based visualization operation for the data information, and the visualization management module meets the needs of artificial intelligence training, development, and application. Among them, the visualization management module includes a data transmission module and a data conversion module. The data transmission module is used to support the user to upload and download data files or folders of video, picture, text, and table types regarding the emergency medical support data information, and the data conversion module is used to convert the data file or the folder into a dataset; The dataset management module: is used to manage the dataset in the model training of the data management system; The dataset management module conducts the model training in the model and algorithm prototype system, and the dataset management module includes: The text annotation module: is used to annotate the text-type dataset in the model training; The annotation recognition module: is used to recognize the dataset format generated by annotation in the model and algorithm prototype system; The storage module: is used to provide storage of the original data for the annotation task in the model and algorithm prototype system; The dataset primary processing module: is used to browse and delete the dataset generated by annotation in the model and algorithm prototype system; The dataset secondary processing module: is used to provide processing such as editing, replacing, deleting, and adding of the dataset and the files inside; The dataset acquisition module: is used to provide the ability to acquire the dataset in the model and algorithm prototype system; The dataset tertiary processing module: is used to manage the state of the dataset. When in the training process in the model and algorithm prototype system, when the dataset used in the training process is displayed as an occupied state, the user is prohibited from editing.

2. The think tank data management system based on emergency medical support according to claim 1, wherein The information collection module includes a system access module; The system access module: is used to connect with the systems of each field department, and access the emergency medical support data information of each field department into the data management system.

3. The think tank data management system based on emergency medical support according to claim 2, wherein The system access module includes: The data interface setting module: is used to provide a unified API interface for data access and the interface access process, and at the same time implement the scheduling authorization and authentication mechanism of the API.

4. The think tank data management system based on emergency medical support according to claim 1, characterized in that, The data processing module is connected to the Hadoop distributed file system to provide high-throughput data access support for the user.

5. The think tank data management system based on emergency medical support according to claim 4, wherein The data processing module also includes: The data directory module: is used to help the user quickly discover the required data sources and understand and use the found data sources.

6. The think tank data management system based on emergency medical support according to claim 1, characterized in that, The visualization management module also includes: Retrieval module: used to provide the user with retrieval queries by the name of the data file or folder based on the emergency medical support database, and obtain query results; Preview module: used to provide the user with preview functions for the video, the picture, and the text; Docking module, used to implement the docking between the visualization management module and the model and algorithm system, facilitating jumping from the visualization management module to the model and algorithm system for model training; Permission setting module: used to support the user in setting permissions for their own files, including viewing, calling, and downloading permissions, to protect data security and privacy.

7. The think tank data management system based on emergency medical support according to claim 1, characterized in that, The text annotation module includes a multi-user collaborative annotation module and an annotation result export module; The multi-user collaborative annotation module: used to provide the ability of collaborative annotation for multiple users; Annotation result export module: used to export the annotated dataset.

8. The think tank data management system based on emergency medical support according to claim 7, characterized in that, The dataset management module further includes a graphic and video annotation module; The graphic and video annotation module: used to annotate the dataset of the picture and the video types during the model training; The graphic and video annotation module includes the multi-user collaborative annotation module and the annotation result export module.

Images