AI model fused medical emergency capability digital simulation training system and method
Through the digital simulation training method of medical emergency response capabilities integrating AI models, combined with question-and-answer pairs and AI models, individualized scenario cases are generated, which solves the problem that the existing training platform cannot dynamically combine theory and scenario learning, and realizes the full emergency response capabilities of medical staff Improved position.
Patent Information
- Application Number
- CN202410938795.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-12
- Publication Date
- 2024-11-12
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing medical emergency training platform mainly focuses on theoretical teaching at the knowledge level, and lacks dynamic comprehensive learning of theories and scenarios, resulting in insufficient judgment and rescue capabilities for medical staff when facing emergencies, and each person's weak ability dimensions are different. , it is impossible to conduct targeted individual training.
Using a digital simulation training method for medical emergency ability integrated with AI model, by constructing a Q&A pair of medical emergency skills and theoretical knowledge, generating an evaluation radar chart, identifying categories of weak knowledge, using clinical medical emergency AI models to generate matching scenario cases, and through The intelligent simulation robot conducts simulation drills and automatically generates rescue script programs to strengthen weak knowledge points.
Comprehensive strengthening of knowledge and skills has been achieved, and students’ emergency response capabilities are found through AI algorithms, and individualized scenario cases are generated for targeted training, which has improved the emergency response capabilities and judgment of medical staff.
Smart Images

Figure CN118942297A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of artificial intelligence technology, and in particular to a digital simulation training method for medical emergency response capabilities integrating an AI model, a digital simulation training system for medical emergency response capabilities integrating an AI model, and electronic equipment. Background Art
[0002] Medical emergency response capabilities require knowledge and good practical skills. Only in this way can we have good judgment and rescue capabilities when facing patient emergencies in clinical practice. It can improve patient safety and reduce the occurrence of adverse events. It is of great significance to patients, hospitals and society.
[0003] In the digital training platform in the medical field, the main designs are divided into the following two categories:
[0004] The first category is knowledge-based, mostly apps that play video courses. Teachers can upload courseware, and students can learn through the platform. Some platforms can be associated with tests, while others cannot. Most exam platforms use WJX alone.
[0005] One type is skill application type. The programs of this type of platform are mostly designed with intelligent simulated humans and intelligent simulated emergency equipment (medical simulation equipment).
[0006] However, the existing medical emergency response platform almost always adopts theoretical teaching at the first knowledge level, which makes it impossible for medical staff and other trainees to combine theory with situational learning and drills for dynamic and comprehensive learning. They lack the practice of theory, so that when faced with clinical emergencies in the later stage, they do not have good judgment and rescue capabilities, which delays clinical care and affects treatment.
[0007] In addition, the simulation scenario set up by the simulation robot in the hospital is: the examiner writes the rescue script, and then writes the program according to the rescue script and inputs it into the simulation robot. Finally, the simulation robot conducts drills according to the program to guide the trainees to learn rescue. However, everyone's weak dimensions are different. If each candidate has his own script, he can understand his weak abilities such as condition assessment ability and measure implementation ability, and then he can specifically improve these abilities, so as to conduct targeted dimensional training and strengthen his abilities. Summary of the invention
[0008] In order to solve the above problems, the present application proposes a digital simulation training method for medical emergency response capabilities integrating an AI model, a digital simulation training system for medical emergency response capabilities integrating an AI model, and electronic equipment.
[0009] On the one hand, this application proposes a digital simulation training method for medical emergency response capabilities integrating an AI model, comprising the following steps:
[0010] S1. Construct question-answer pairs that integrate medical emergency skills knowledge and medical emergency theoretical knowledge;
[0011] S2. Using the question-answer pair to assess the user, collecting the user's assessment results on the question-answer pair, and generating a corresponding assessment radar chart;
[0012] S3, traversing the evaluation radar chart to identify the user's knowledge categories in medical emergency skill knowledge and / or medical emergency theoretical knowledge that are below a preset warning line;
[0013] S4. Input the knowledge category into a preset clinical medical emergency AI model, and the clinical medical emergency AI model generates a medical emergency scenario case matching the knowledge category;
[0014] S5. According to the medical emergency scenario case, a corresponding rescue script program is constructed, the rescue script program is imported into the simulation robot and a simulation drill is performed.
[0015] As an optional implementation scheme of the present application, optionally, S1, constructing a question-answer pair integrating medical emergency skill knowledge and medical emergency theoretical knowledge, including:
[0016] Collect substantive questions about medical emergency skills knowledge and medical emergency theoretical knowledge under different categories;
[0017] Retrieving the answer to the entity question from a database, and establishing a question-answer mapping relationship between the entity question and the answer;
[0018] Manually annotating the question-answer mapping relationship;
[0019] After the marking is completed, sorting is performed to generate the corresponding question-answer pairs.
[0020] As an optional implementation scheme of the present application, optionally, S2, using the question-answer pair to assess the user, collecting the user's assessment results on the question-answer pair, and generating a corresponding evaluation radar chart, including:
[0021] Generate a medical emergency assessment question bank under different categories using the question and answer pairs, and deploy it on the background;
[0022] The user logs in to the backend, randomly selects the medical emergency assessment question bank and answers, and the backend collects the user's assessment results;
[0023] The assessment results are imported into a preset radar chart, and an evaluation radar chart of the user is generated and saved under the user's assessment ID.
[0024] As an optional implementation scheme of the present application, optionally, before step S2, the method further includes:
[0025] According to the category of medical emergency assessment, an initial radar chart is constructed, and the preset warning line is marked on the initial radar chart.
[0026] As an optional implementation scheme of the present application, optionally, S4, inputting the knowledge category into a preset clinical medical emergency AI model, and the clinical medical emergency AI model generates a medical emergency scenario case matching the knowledge category, including:
[0027] Based on clinical medical emergency big data, the corresponding clinical medical emergency AI model is constructed through a convolutional neural network model, wherein the clinical medical emergency AI model is used to identify medical emergency skill knowledge and medical emergency theoretical knowledge under different knowledge categories and their corresponding application scenarios;
[0028] Input the knowledge category of the user below the preset warning line into the preset clinical medical emergency AI model, and the clinical medical emergency AI model identifies and outputs the application scenario matching the knowledge category;
[0029] Edit the medical emergency scenario cases matching the application scenario through the scenario logic editor;
[0030] Among them, the scenario logic editor is embedded in the clinical medical emergency AI model in the form of component nesting.
[0031] On the other hand, the present application proposes a digital simulation training system for medical emergency response capabilities integrating an AI model, including:
[0032] Backend database, used to store medical emergency skills knowledge and medical emergency theory knowledge;
[0033] The backend server is used for users to log in and conduct online assessment of question-answer pairs, collect the assessment results of the user on the question-answer pairs, and generate a corresponding evaluation radar chart; traverse the evaluation radar chart to identify the user's knowledge categories below the preset warning line in the medical emergency skill knowledge and / or medical emergency theoretical knowledge; use the preset clinical medical emergency AI model to generate medical emergency scenario cases matching the knowledge categories;
[0034] An AI editing system is used to construct a corresponding rescue script program based on the medical emergency scenario case;
[0035] An API interface, used to import the rescue script program into the simulation robot;
[0036] A simulation robot is used to activate the rescue script program and perform simulation drills.
[0037] In another aspect, the present application further provides an electronic device, comprising:
[0038] processor;
[0039] a memory for storing processor-executable instructions;
[0040] Among them, the processor is configured to implement the digital simulation training system and method for medical emergency response capabilities that integrates an AI model when executing the executable instructions.
[0041] Technical effects of the present invention:
[0042] This application uses a program system that combines knowledge levels with specific emergency scenario simulation learning, relying on intelligent simulation robots, to import various specialties, public emergency knowledge, scenario cases, etc. for assessment. After the assessment, the system uses AI algorithms to analyze and learn, and finds that the students' emergency response capabilities are insufficient. The clinical medical emergency AI model generates medical emergency scenario cases that match the knowledge category; according to the medical emergency scenario cases, a corresponding rescue script program is constructed, and the rescue script program is imported into the simulation robot and a simulation exercise is performed. It can automatically generate medical emergency scenario cases that students need to strengthen, and then write the emergency procedures of intelligent simulation people according to the scenario cases for real-life drills. In this way, the students' weak emergency knowledge points are strengthened and actual drills are strengthened. Through the comprehensive strengthening of knowledge + skills, the purpose of comprehensively improving the emergency response capabilities of medical staff is achieved. Through algorithms, each person's knowledge blind spots are discovered, and individualized scenarios are generated to achieve teaching in accordance with their aptitude and improve emergency response capabilities.
[0043] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.
[0045] Figure 1 It is shown as a schematic diagram of the implementation process of the present invention;
[0046] Figure 2 It is shown as a schematic diagram of the application system composition of the present invention;
[0047] Figure 3 Shown is a schematic diagram of a radar of the present invention;
[0048] Figure 4 It is a schematic diagram showing the application of the electronic device of the present invention. DETAILED DESCRIPTION
[0049] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.
[0050] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.
[0051] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the main purpose of the present disclosure.
[0052] Example 1
[0053] This plan intends to design a program system that integrates knowledge level and specific emergency scenario simulation learning. Relying on intelligent simulation robots, a digital platform is designed and developed. The research and development content includes knowledge level, importing various specialties, public emergency knowledge, scenario cases, etc. for assessment. After the assessment, the system will analyze and learn through algorithms, find out the shortcomings of the student's emergency response ability and prominent problems, automatically generate the parts that the candidate needs to strengthen, generate a scenario case, and then write the emergency procedures of the intelligent simulation person based on the scenario case for real-life drills.
[0054] like Figure 1 As shown, on the one hand, the present application proposes a digital simulation training method for medical emergency response capability integrating an AI model, comprising the following steps:
[0055] S1. Construct question-answer pairs that integrate medical emergency skills knowledge and medical emergency theoretical knowledge;
[0056] S2. Using the question-answer pair to assess the user, collecting the user's assessment results on the question-answer pair, and generating a corresponding assessment radar chart;
[0057] S3, traversing the evaluation radar chart to identify the user's knowledge categories in medical emergency skill knowledge and / or medical emergency theoretical knowledge that are below a preset warning line;
[0058] S4. Input the knowledge category into a preset clinical medical emergency AI model, and the clinical medical emergency AI model generates a medical emergency scenario case matching the knowledge category;
[0059] S5. According to the medical emergency scenario case, a corresponding rescue script program is constructed, the rescue script program is imported into the simulation robot and a simulation drill is performed.
[0060] The main idea of this application is to construct a question-and-answer pair that integrates medical emergency skill knowledge and medical emergency theoretical knowledge, generate a corresponding question bank, and assess the trainees. The radar chart shows the trainees' lack of knowledge points in different knowledge categories, and then use AI editing to perform corresponding medical emergency scenario cases for the lack of knowledge points, and further edit the corresponding rescue script program, import the rescue script program into the simulation robot and perform simulation exercises. In this way, through the comprehensive assessment of knowledge + skills, the purpose of comprehensively improving the emergency response capabilities of medical staff is achieved. And through algorithms, each person's knowledge blind spots are discovered, and individualized scenarios are generated to achieve teaching in accordance with their aptitude and improve emergency response capabilities.
[0061] Integrate the knowledge level and the skill operation level; through knowledge-level testing, through the integrated analysis of big data / AI / algorithms, discover individual problems and generate corresponding scenario cases.
[0062] Combined with Figure 2 As shown, the corresponding medical emergency skill knowledge and medical emergency theoretical knowledge can be stored in advance on the hospital's background database, which can be specifically configured by the administrator, or knowledge can be extracted during the medical process and corresponding learning knowledge can be generated.
[0063] The construction of question-answer pairs can be achieved by extracting knowledge entities from different types of knowledge, answering them through a think tank (self-selected), and combining them with manual annotation to generate corresponding question-answer pairs.
[0064] After generating the question-answer pairs, a question bank of corresponding knowledge categories can be generated on the background server based on the question-answer pairs. After generating the corresponding question bank, the administrator can construct a corresponding question bank (equivalent to a test paper) for different categories of medical emergency skill knowledge and medical emergency theoretical knowledge, and notify the students to take the exam.
[0065] Students can log in to the backend server through the APP or applet on the user side, view the question bank distributed by the administrator, and take skill or theoretical knowledge tests. The test results of each student are collected on the backend server and displayed using a radar chart.
[0066] The administrator sets the preset warning line of the assessment standard on the radar chart in advance. On the radar chart, the assessment result below the warning line will be used as the knowledge deficiency of the trainee. For the lack of knowledge point, the AI editing system is used to generate a corresponding emergency scenario and build a corresponding rescue program. The rescue program is sent to the simulation robot through the API interface by the background to conduct simulation exercises and strengthen the drill learning of the lack of knowledge.
[0067] As an optional implementation scheme of the present application, optionally, S1, constructing a question-answer pair integrating medical emergency skill knowledge and medical emergency theoretical knowledge, including:
[0068] Collect substantive questions about medical emergency skills knowledge and medical emergency theoretical knowledge under different categories;
[0069] Retrieving the answer to the entity question from a database, and establishing a question-answer mapping relationship between the entity question and the answer;
[0070] Manually annotating the question-answer mapping relationship;
[0071] After the marking is completed, sorting is performed to generate the corresponding question-answer pairs.
[0072] The medical emergency skills knowledge and medical emergency theoretical knowledge under different categories can be the following categories of knowledge:
[0073] Specialized knowledge, general knowledge, assessment, diagnosis, measures, ethics, emergency procedures, hospital system, and emergency scenario simulation.
[0074] For entity problems of different knowledge, text recognition algorithms can be used to identify the features of entity problems in each knowledge.
[0075] Entity recognition is an important task in natural language processing, which aims to identify entities with specific meanings from text, such as names of people, places, organizations, dates, times, etc. The following are several common entity recognition methods:
[0076] 1. Rule-based approach: This approach usually relies on manually written rules or templates for matching and extracting entities from text. Rules can be based on regular expressions, string matching, part-of-speech tagging, etc. This approach is simple and intuitive, but usually requires a lot of manual labor and may not be flexible enough for complex texts and new entity types.
[0077] 2. Statistical-based methods: This method uses statistical models to model text and learn the rules of identifying entities. Common statistical models include hidden Markov models (HMMs) and conditional random fields (CRFs). This method can automatically learn rules from data, but usually requires a large amount of labeled data for training.
[0078] 3. Methods based on deep learning: In recent years, deep learning has achieved remarkable success in entity recognition tasks. By training deep neural network models such as convolutional neural networks (CNN), recurrent neural networks (RNN) or variants (such as LSTM, GRU), the representation of text and the recognition rules of entities can be automatically learned. This method usually requires a large amount of labeled data for training and requires certain computing resources.
[0079] 4. Methods based on transfer learning: Transfer learning is a method that uses knowledge learned on other tasks to help solve new tasks. In entity recognition, models pre-trained on other datasets (such as BERT, ERNIE, etc.) can be used for transfer learning to improve the generalization ability and performance of the model. This method can make full use of existing knowledge and reduce the need for labeled data for new tasks.
[0080] In addition to the above methods, there are some other entity recognition methods, such as graph-based methods, knowledge base-based methods, etc. Different methods have their own advantages and disadvantages, and need to be selected according to specific application scenarios and requirements, which are not limited in this embodiment.
[0081] Administrators can browse the initial question-and-answer pairs, manually annotate the answers matched by the think tank, and obtain question-and-answer pairs of medical emergency knowledge.
[0082] The corresponding examination question bank (exam paper) is set by the question and answer pair, and the administrator completes the examination task by himself and publishes it through the background. Students log in to the background to take the examination through the user end such as a smartphone or computer.
[0083] As an optional implementation scheme of the present application, optionally, S2, using the question-answer pair to assess the user, collecting the user's assessment results on the question-answer pair, and generating a corresponding evaluation radar chart, including:
[0084] Generate a medical emergency assessment question bank under different categories using the question and answer pairs, and deploy it on the background;
[0085] The user logs in to the backend, randomly selects the medical emergency assessment question bank and answers, and the backend collects the user's assessment results;
[0086] The assessment results are imported into a preset radar chart, and an evaluation radar chart of the user is generated and saved under the user's assessment ID.
[0087] On the radar chart, you can first construct a corresponding blank radar chart according to the categories of each knowledge (skill or theory), and then set the warning line, for example Figure 3 The passing score is 80 points. After obtaining the student's assessment score, you can check the assessment results under different knowledge categories and determine whether they have reached the preset warning line.
[0088] As an optional implementation scheme of the present application, optionally, before step S2, the method further includes:
[0089] According to the category of medical emergency assessment, an initial radar chart is constructed, and the preset warning line is marked on the initial radar chart.
[0090] The specific value of the preset warning line is set by the administrator.
[0091] The preset warning line may be adjusted by the administrator after multiple assessments.
[0092] When candidates answer questions, they are randomly selected from the question bank of each module. After the candidates answer the questions, an algorithm is used to draw a radar chart of the candidates' abilities. Each module can have its own radar chart (which can be further classified according to the major categories. For example, the specialist knowledge category can have internal medicine, surgery, gynecology, pediatrics, or the above major categories can be used to draw radar charts. The algorithm calculates the worst categories of candidates to generate scenario assessment cases, which can cover one or more of the above problems. These scenario assessment cases are then input into the program end of the intelligent simulator. Through the simulator, the scenario is restored and the candidates enter the actual operation practice (ie the hands-on part). The knowledge level is strengthened and reviewed through scenario simulation.
[0093] like Figure 3 As shown, the two categories of hospital system and evaluation knowledge can be strengthened for training. Later, application scenarios related to hospital system and evaluation knowledge can be edited for scenario drills.
[0094] As an optional implementation scheme of the present application, optionally, S4, inputting the knowledge category into a preset clinical medical emergency AI model, and the clinical medical emergency AI model generates a medical emergency scenario case matching the knowledge category, including:
[0095] Based on clinical medical emergency big data, the corresponding clinical medical emergency AI model is constructed through a convolutional neural network model, wherein the clinical medical emergency AI model is used to identify medical emergency skill knowledge and medical emergency theoretical knowledge under different knowledge categories and their corresponding application scenarios;
[0096] Input the knowledge category of the user below the preset warning line into the preset clinical medical emergency AI model, and the clinical medical emergency AI model identifies and outputs the application scenario matching the knowledge category;
[0097] Edit the medical emergency scenario cases matching the application scenario through the scenario logic editor;
[0098] Among them, the scenario logic editor is embedded in the clinical medical emergency AI model in the form of component nesting.
[0099] AI scene editing usually involves using specific software or tools to create, modify, and optimize AI-generated scenes. These tools can help users adjust various parameters of the scene, including lighting, texture, object position, etc., to achieve the desired effect.
[0100] The clinical medical emergency AI model mainly recommends corresponding application scenarios based on the types of knowledge that students lack, and then uses its embedded "AI scenarios" to build corresponding medical emergency scenario cases, automatically write corresponding rescue script programs, import the rescue script programs into simulation robots and perform simulation drills.
[0101] The final manifestation of emergency response capabilities is on the patients, so no matter what the knowledge level is, it must be reflected in the skills level. The inspection of this data platform is to dig out personalized problems from the knowledge level, generate corresponding scenarios, and enable medical staff to practice repeatedly. The traditional knowledge level and technical level are separated and integrated. AI / algorithms are added for deduction, and individual problems are found for practice and improvement.
[0102] The clinical medical emergency AI model can be generated through training based on the CNN model using emergency scenario data under different knowledge categories. Specifically, it can be generated in combination with the network architecture of the convolutional neural network model.
[0103] By building corresponding application scenarios through AI, you can make full use of the functions and advantages of different AI tools such as WPSAI to improve work efficiency and quality. The following are some common AI scene editing methods:
[0104] 1. Use professional 3D modeling software: such as Blender, Maya, etc. These software provide powerful scene editing tools that users can use to create and edit AI scenes.
[0105] 2. Use AI generation tools: Some AI generation tools, such as DeepDream, GANs, etc., can automatically generate scenes. Users can generate the required scenes by adjusting the parameters of these tools, such as input images, model architecture, etc.
[0106] 3. Use scene editors: Some software provides dedicated scene editors that users can use to easily edit AI scenes. These editors usually provide some preset scene elements and parameters, and users can create the desired scene by dragging, dropping and adjusting these elements.
[0107] 4. Use machine learning libraries: such as TensorFlow, PyTorch, etc. These libraries provide some tools for training and optimizing AI models. Users can use these libraries to train models to generate the required scenarios and use them to optimize the generated scenarios.
[0108] In this solution, the scenario logic editor is embedded in the clinical medical emergency AI model in the form of component nesting.
[0109] The functions of the scene logic editor can be understood and applied in conjunction with the existing "scene AI", which will not be elaborated in this embodiment.
[0110] AI script editing refers to the process of using artificial intelligence technology to assist in script creation. In recent years, with the continuous development of artificial intelligence technology, more and more AI script editing tools have begun to appear, which can help screenwriters to create scripts more efficiently and improve the quality and efficiency of creation.
[0111] AI script editing tools usually have natural language processing capabilities, which can understand human language and generate corresponding responses. They can automatically generate drafts or fragments of the script based on the keywords, storyline, character settings and other information entered by the user, thereby providing creative inspiration and support for the screenwriter. In addition, AI script editing tools can also perform intelligent analysis and evaluation of the script, provide modification suggestions and optimization plans, help screenwriters grasp the storyline and character personality more accurately, and improve the quality and readability of the script.
[0112] The tools and methods for automatically writing scripts based on scenarios can be realized with the help of artificial intelligence (AI) technology. At present, there are already some AI tools and platforms that can provide the function of automatically writing scripts based on scenarios.
[0113] Here are some tools and methods:
[0114] 1. AI script writing software: This type of software can automatically generate corresponding scene descriptions based on scene features (such as time, location, atmosphere, etc.) input by the user. The user only needs to simply describe the scene, and the software can generate a variety of vivid scenes, which not only expands the screenwriter's imagination, but also reduces the screenwriter's workload in building scenes. Some software can even provide script modification and optimization suggestions.
[0115] 2. Natural Language Processing (NLP) Technology: NLP technology allows computers to understand and parse human language. By training models, AI can identify key elements in a scene, such as characters, actions, dialogues, etc., and automatically generate corresponding script content. This technology can also generate relevant plot developments based on keywords or phrases entered by users.
[0116] 3. AI collaboration platform: Some AI collaboration platforms allow multiple screenwriters to co-create scripts on the same platform. These platforms usually provide functions such as real-time synchronization, version control, comments and feedback, enabling screenwriters to collaborate and communicate more efficiently.
[0117] This application preferably uses NLP technology to implement a method for constructing a corresponding rescue script program based on medical emergency scenario cases.
[0118] Therefore, this solution can comprehensively improve the emergency response capabilities of medical staff. Through algorithms, each person's knowledge blind spots can be discovered, and individualized scenarios can be generated to achieve teaching in accordance with their aptitude and improve emergency response capabilities.
[0119] Obviously, those skilled in the art should understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. Those skilled in the art can understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk (Hard Disk Drive, abbreviated as: HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.
[0120] Example 2
[0121] Based on the implementation principle of Example 1, on the other hand, the present application proposes a digital simulation training system for medical emergency response capabilities integrating an AI model, including:
[0122] Backend database, used to store medical emergency skills knowledge and medical emergency theory knowledge;
[0123] The backend server is used for users to log in and conduct online assessment of question-answer pairs, collect the assessment results of the user on the question-answer pairs, and generate a corresponding evaluation radar chart; traverse the evaluation radar chart to identify the knowledge categories of the user in medical emergency skill knowledge and / or medical emergency theoretical knowledge that are below the preset warning line;
[0124] An AI editing system is used to generate medical emergency scenario cases matching the knowledge category using a preset clinical medical emergency AI model; and to construct a corresponding rescue script program based on the medical emergency scenario cases;
[0125] An API interface, used to import the rescue script program into the simulation robot;
[0126] A simulation robot is used to activate the rescue script program and perform simulation drills.
[0127] The modules or steps of the present invention described above can be implemented by a general-purpose computing system, they can be concentrated on a single computing system, or distributed on a network composed of multiple computing systems, and optionally, they can be implemented by a program code executable by a computing system, so that they can be stored in a storage system and executed by the computing system, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.
[0128] Example 3
[0129] like Figure 4 As shown, further, in another aspect, the present application also proposes an electronic device, including:
[0130] processor;
[0131] a memory for storing processor-executable instructions;
[0132] Among them, the processor is configured to implement the digital simulation training method for medical emergency response capabilities that integrates an AI model when executing the executable instructions.
[0133] The electronic device of the embodiment of the present disclosure includes a processor and a memory for storing instructions executable by the processor. The processor is configured to implement a digital simulation training method for medical emergency capability integrating an AI model as described in the above embodiment 1 when executing the executable instructions.
[0134] Here, it should be noted that the number of processors can be one or more. At the same time, the electronic device of the embodiment of the present disclosure may also include an input system and an output system. Among them, the processor, memory, input system and output system may be connected through a bus or in other ways, which are not specifically limited here.
[0135] As a computer-readable storage medium, the memory can be used to store software programs, computer executable programs and various modules, such as the program or module corresponding to the digital simulation training method for medical emergency response capability integrating an AI model in the embodiment of the present disclosure. The processor executes various functional applications and data processing of the electronic device by running the software programs or modules stored in the memory.
[0136] The input system can be used to receive input numbers or signals. The signal can be a key signal related to user settings and function control of the device / terminal / server. The output system can include display devices such as display screens.
[0137] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.
Claims
1. A digital simulation training method for medical emergency response capability integrating AI model, characterized in that: The steps include: S1. Construct question-answer pairs that integrate medical emergency skills knowledge and medical emergency theoretical knowledge; S2. Using the question-answer pair to assess the user, collecting the user's assessment results on the question-answer pair, and generating a corresponding assessment radar chart; S3, traversing the evaluation radar chart to identify the user's knowledge categories in medical emergency skill knowledge and / or medical emergency theoretical knowledge that are below a preset warning line; S4. Input the knowledge category into a preset clinical medical emergency AI model, and the clinical medical emergency AI model generates a medical emergency scenario case matching the knowledge category; S5. According to the medical emergency scenario case, a corresponding rescue script program is constructed, the rescue script program is imported into the simulation robot and a simulation drill is performed.
2. According to the medical emergency response capability digital simulation training system and method integrating AI model in claim 1, it is characterized in that: S1. Construct a question-answer pair that integrates medical emergency skills knowledge and medical emergency theory knowledge, including: Collect substantive questions about medical emergency skills knowledge and medical emergency theoretical knowledge under different categories; Retrieving the answer to the entity question from a database, and establishing a question-answer mapping relationship between the entity question and the answer; Manually annotating the question-answer mapping relationship; After the marking is completed, sorting is performed to generate the corresponding question-answer pairs.
3. According to claim 1, a digital simulation training system and method for medical emergency response capability integrating an AI model is characterized in that: S2. Using the question-answer pair to assess the user, collecting the user's assessment results on the question-answer pair, and generating a corresponding evaluation radar chart, including: Generate a medical emergency assessment question bank under different categories using the question and answer pairs, and deploy it on the background; The user logs in to the backend, randomly selects the medical emergency assessment question bank and answers, and the backend collects the user's assessment results; The assessment results are imported into a preset radar chart, and an evaluation radar chart of the user is generated and saved under the user's assessment ID.
4. According to claim 1, a digital simulation training system and method for medical emergency response capability integrating an AI model is characterized in that: Before step S2, the method further includes: According to the category of medical emergency assessment, an initial radar chart is constructed, and the preset warning line is marked on the initial radar chart.
5. According to claim 1, a digital simulation training system and method for medical emergency response capability integrating an AI model is characterized in that: S4. Input the knowledge category into a preset clinical medical emergency AI model, and the clinical medical emergency AI model generates a medical emergency scenario case matching the knowledge category, including: Based on clinical medical emergency big data, the corresponding clinical medical emergency AI model is constructed through a convolutional neural network model, wherein the clinical medical emergency AI model is used to identify medical emergency skill knowledge and medical emergency theoretical knowledge under different knowledge categories and their corresponding application scenarios; Input the knowledge category of the user below the preset warning line into the preset clinical medical emergency AI model, and the clinical medical emergency AI model identifies and outputs the application scenario matching the knowledge category; Edit the medical emergency scenario cases matching the application scenario through the scenario logic editor; Among them, the scenario logic editor is embedded in the clinical medical emergency AI model in the form of component nesting.
6. A digital simulation training system for medical emergency response capabilities integrating AI models, characterized in that: include: Backend database, used to store medical emergency skills knowledge and medical emergency theory knowledge; The backend server is used for users to log in and conduct online assessment of question-answer pairs, collect the assessment results of the user on the question-answer pairs, and generate a corresponding evaluation radar chart; traverse the evaluation radar chart to identify the user's knowledge categories below the preset warning line in the medical emergency skill knowledge and / or medical emergency theoretical knowledge; use the preset clinical medical emergency AI model to generate medical emergency scenario cases matching the knowledge categories; An AI editing system is used to construct a corresponding rescue script program based on the medical emergency scenario case; An API interface, used to import the rescue script program into the simulation robot; A simulation robot is used to activate the rescue script program and perform simulation drills.
7. An electronic device, characterized in that include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement a digital simulation training method for medical emergency response capabilities integrating an AI model as described in any one of claims 1-5 when executing the executable instructions.
