AI-based nursing knowledge interesting courseware generation method and system

Abstract

The invention relates to the field of artificial intelligence, in particular to an AI-based nursing knowledge interesting courseware generation method and system. The method comprises the following steps: firstly, constructing an AI model library, and packaging input parameters and output parameters of each AI model in the model library; the nursing knowledge is uploaded to the system; creating a corresponding abstract task for nursing knowledge, and operating an AI model to obtain high-quality knowledge key points; supplementing cue words for the knowledge key points, and providing the cue words to an AI large model to generate materials; performing structured arrangement on courseware themes, chapters and contents by applying a mind mapping method, packaging the courseware themes, chapters and contents into AI model input parameters, and performing automatic layout through the AI model to generate a PPT file; and adjusting the PPT file, outputting the PPT file as courseware, and editing and processing courseware content. The AI model technology is utilized, key knowledge content can be quickly extracted, rich teaching materials can be generated, the courseware making method is optimized, the input of teaching group course making is effectively reduced, the courseware quality is improved, and the professional level of nursing personnel can be effectively promoted to be improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and in particular to a method and system for generating interesting nursing knowledge courseware based on AI. Background Art

[0002] The medical care industry has a wide variety of knowledge and updates rapidly. Nurses often need to spend a lot of time learning new knowledge and adapting to new technologies after work, so as to provide more professional and efficient patient care, disease prevention, health management, rehabilitation care and other services.

[0003] The current nursing teaching model typically involves each department developing a training plan based on its own expertise and staff quality, assigning experienced instructors as lecturers, and conducting regular training for all staff. This model requires lecturers to devote significant time to reading literature, textbooks, and journals, summarizing knowledge, and creating training materials. Nursing knowledge itself is highly specialized, and conventional training methods struggle to capture students' interest, resulting in poor training results. Frequent training can also create resistance among nursing staff, further reducing training efficiency. The existing teaching model is difficult to implement in a systematic, structured, and standardized manner, hindering advancement of the nursing industry's technical proficiency. Summary of the Invention

[0004] In response to the problems existing in the existing technology, the present invention provides an AI-based method and system for generating interesting nursing knowledge courseware. Through large model summary technology, picture and animation video intelligent generation technology, combined with mind map conversion courseware technology, it helps teaching staff to quickly extract key knowledge content, generate rich teaching materials, and optimize courseware production methods, effectively reducing the investment in course production of teaching groups, improving the quality of courseware, increasing learning interest, and effectively promoting the professional level of nursing staff.

[0005] The present invention adopts the following technical solution to achieve: a method for generating interesting nursing knowledge courseware based on AI, comprising the following steps:

[0006] S1. Build an AI model library and encapsulate the input and output parameters of each AI model in the model library;

[0007] S2. Collect and record nursing knowledge, upload nursing knowledge to the system, and record its knowledge source, knowledge classification, file type, and knowledge name as personal knowledge data; or submit nursing knowledge to the public knowledge base as shared knowledge;

[0008] S3. Create a corresponding summary task for nursing knowledge, select the nursing knowledge to be summarized, and add prompt words to each nursing knowledge; select the AI model used for summarization from the AI model library, use the knowledge information and prompt word information as input to the AI model, run the AI model, and obtain the knowledge summary;

[0009] S4. Generate knowledge materials. Based on the output information of the summary task and the training target group, generate dynamic pictures or animation videos of corresponding scenarios as knowledge materials for use in different occasions.

[0010] S5. Generate courseware. Use mind mapping to organize the courseware into themes, chapters, and content. Themes express the core ideas of the courseware and are placed at the first level of the mind map. Chapters organize and differentiate the training content according to a preset logic and are placed at the second level of the mind map. Content is the specific information or materials presented in the courseware, which is filled with generated summary information and knowledge materials and is placed at the third level of the mind map.

[0011] According to the nodes and content at each level of the mind map, the mind map data is encapsulated into the input parameter structure required by the model, and the AI model is called to convert the mind map into a PPT format file;

[0012] S6. Manage the generated courseware and edit the courseware content.

[0013] The embodiment of the present invention also adopts the following technical solution: an AI-based nursing knowledge interesting courseware generation system, including the following modules:

[0014] AI model library construction module, used to encapsulate the input and output parameters of each AI model in the model library;

[0015] The nursing knowledge collection module uploads nursing knowledge to the system and records its knowledge source, knowledge classification, file type, and knowledge name as personal knowledge data; or submits nursing knowledge to the public knowledge base as shared knowledge;

[0016] The summary task creation module is used to create corresponding summary tasks for nursing knowledge, select the nursing knowledge to be summarized, and supplement each nursing knowledge with prompt words; select the AI model used for summarization from the AI model library, use the knowledge information and prompt word information as input of the AI model, run the AI model, and obtain the knowledge summary;

[0017] The knowledge material generation module generates dynamic images or animated videos of corresponding scenarios as knowledge materials based on the output information of the summary task and the training target group, which can be used in different occasions.

[0018] The courseware generation module uses the mind map method to organize the courseware into themes, chapters, and content. The theme of the courseware expresses the core idea of the courseware and is placed on the first level of the map. The chapters are used to organize and differentiate the training content according to the preset logic and are placed on the second level of the map. The content is the information or materials presented in the courseware, which is filled with the generated summary information and knowledge materials and is placed on the third level of the map.

[0019] According to the nodes and content at each level of the mind map, the mind map data is encapsulated into the input parameter structure required by the model, and the AI model is called to convert the mind map into a PPT format file;

[0020] The courseware editing and management module manages the generated courseware and edits and processes the courseware content.

[0021] As can be seen from the above technical solutions, the method and system for generating interesting courseware of the present invention utilize AI intelligent generation technology to make the courseware production process more efficient, the content richer, and the knowledge management more systematic and complete. Compared with the existing technology, it has the following main advantages and beneficial effects:

[0022] 1. Greatly improved the efficiency of courseware production. Traditional courseware production requires lecturers to read a lot of materials, summarize the key content in the materials, conceive the outline of the training, and also need to find various training materials to improve the quality of training. This process consumes a lot of time and energy, and generates a lot of repetitive work, and the output value is low. Using the generation method and system of the present invention, lecturers can quickly refine the knowledge content of the lectures and generate various training materials. The original manual step-by-step reading, refining and summarizing of knowledge and searching for materials is transformed into the output effect of the comparison model of the present invention, mining potential knowledge, and combining the materials generated by the model. The efficiency of courseware production has been greatly improved, and the quality has also made a big leap.

[0023] 2. Effectively improve learning efficiency. Most of the existing training contents are quite standard. Apart from introducing knowledge points, there are few other innovative contents that can improve learning interest. The learning process is boring and tedious. Long-term and repeated training makes both lecturers and trainees physically and mentally exhausted. The uneven level of lecturers further reduces the learning efficiency of training, and students often forget the content after the training is completed. Through the generation method and system of the present invention, the training materials can be greatly enriched, the teaching content will become more vivid and interesting, and the originally boring text can be converted into tables, pictures, animations, videos, etc. to attract the attention of students, and change the original passive learning of knowledge into active understanding of knowledge, thereby greatly improving the learning efficiency.

[0024] 3. It helps to build the department’s knowledge base. The existing training system does not have complete knowledge management, and the knowledge is relatively scattered. When you need to understand a certain aspect of professional knowledge, you need to ask experienced teachers or search various documents on the Internet. The efficiency of knowledge acquisition is low and difficult, and it is impossible to learn knowledge and improve skills in a systematic and professional way. With the support of the present invention, teachers can store the knowledge used in the training courses, continuously accumulate it, and form the department’s knowledge base. At the same time, they can also share the process of converting knowledge into courseware with others, so that others can better understand, learn, and learn from it, effectively improve the overall ability level of the department’s personnel, make knowledge management more systematic, professional, and standardized, and promote the information and digital transformation within the department.

[0025] 4. Expand the depth and breadth of knowledge and promote innovation. The quality of existing training courses depends largely on the ability of the instructors, and the human brain has limited ability to absorb knowledge. There is subjective consciousness, and people will pay more attention to the content that they are interested in or think is important, while ignoring other important information. With the support of this invention, with the help of the AI model's ability to master existing knowledge, it can help us to explore important knowledge and extract key information more comprehensively and deeply, and leave the consolidation of existing knowledge to the AI model, so that we can focus more on the research of knowledge innovation. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only part of the embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the contents of the embodiments of the present invention and these drawings without any creative work.

[0027] Figure 1 It is a flow chart of the method for generating interesting courseware in an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The present invention will be further described below with reference to the embodiments and accompanying drawings. It is apparent that the embodiments described are only some, not all, of the embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are intended to fall within the scope of protection of the present invention.

[0029] The present invention is based on an AI-based method for generating interesting nursing knowledge courseware. With the help of an AI big model, users can quickly generate knowledge summaries, training materials, etc. The user first uploads the knowledge involved in the training content to the system, or can reference the knowledge content that has been uploaded in the past. The knowledge can be a text file, a picture or a video, and then selects a suitable big model to extract the knowledge summary information. At the same time, the model can also output some interactive content, such as classroom knowledge questions and answers, etc. The user can also add appropriate prompt words to make the model output content more in line with expectations. After extracting the key knowledge content, these key contents are sorted out to form a training outline, and then the sorted knowledge content is provided to the big model to generate training materials, such as pictures, animations, videos, etc., to output some vivid and interesting materials that meet the training theme, thereby increasing the fun of the training process. After obtaining these basic information, a training course can be created. Using the mind mapping method, the training theme, training outline, knowledge chapters, content and materials are combined to form a logical tree, which is then converted into a PPT file and adjusted to form the final training courseware.

[0030] Example

[0031] This embodiment is a method for generating interesting nursing knowledge courseware based on AI. Figure 1 , including the following steps:

[0032] S1. Build an AI model library and encapsulate the input and output parameters of each AI model in the model library.

[0033] The AI models in the AI model library can be general-purpose commercial AI models or private models built using open-source pre-trained models combined with RAG technology. Specifically, you can integrate mainstream AI models or open-source pre-trained models that have been processed and fine-tuned by RAG, encapsulating the model's input and output parameters. To use an AI model, you only need to select the input data and the AI model name to run the model and obtain the output data.

[0034] AI models are integrated in the backend, such as Wenxin Yiyan, Tongyi Qianwen, and DeepSeek for summary generation; Tongyi Wanxiang, Sora, and MidJourney for image and video generation; and Beautiful.AI, DesignScape, and DeepSeek for PPT generation. Users simply follow the template in the user interface dialog box to enter information such as necessary prompts, desired results, knowledge content, and the model to be used. The system automatically displays the results returned by the model in the user interface, such as knowledge summaries, images, and videos. Users can then simply preview the results online.

[0035] For commercial models, the integration method is mainly API. The model input parameter encapsulation can be abstracted into three types of attributes: API address, commercial authorization information, and conversation parameters.

[0036] In this embodiment, taking the summary generation model as an example, the request parameter format is:

[0037]

[0038]

[0039] The response parameter format is:

[0040]

[0041] In this embodiment, taking the material generation model as an example, the request parameter format is:

[0042] Parameter name Parent node parameter name Data Type Is this field required? illustrate api_addr - String yes Model request address auth_token - Object no Authorization Information access_key auth_token String yes Access Key secret_key auth_token String yes Security Key req_message - Object yes Dialog Parameters prompt req_message String yes Prompt word

[0043] The format of the response parameters is:

[0044]

[0045] Taking the PPT generation model as an example, its request parameter format is:

[0046]

[0047] The format of the response parameter is:

[0048] Parameter name Parent node parameter name Data Type Is this field required? illustrate success - Boolean yes Result Status message - String no Prompt information data - String no PPT file link returned by the model

[0049] The above content is an abstract interface encapsulation for business model integration. Connecting to a specific model involves implementing abstract parameters. The request and response parameters of different business models may differ. Connecting to specific models is accomplished through code implementation. For example, the names of conversation parameters differ. The abstract interface parameter is req_message, while Wenxin Yiyan uses message and Tongyi Qianwen uses query. Simply adjust the corresponding names during implementation.

[0050] When general commercial models cannot meet the needs, private large models can also be built based on open source pre-trained models combined with RAG (retrieval-augmented generation) technology. For example, general large models have not been pre-trained on data from certain knowledge bases within the hospital, or lack training on specialized nursing knowledge. Through the RAG method, based on the langchain large model application framework, the hospital's internal knowledge content can be segmented into text blocks using spacy. The segmented data obtained from the text is stored in the chroma vector database using the bge-large-zh-v1.5 vector model. When the user generates a summary, RAG first matches the user's required content to the relevant knowledge data in the vector database, and then provides the data to the large model to generate the final result, which can effectively improve the accuracy of the summary.

[0051] S2. Collect and record nursing knowledge.

[0052] Users upload nursing knowledge to the system, recording information such as its source, classification, file type, and name as personal knowledge data. They can also submit knowledge to a public management repository for review by knowledge managers and shared knowledge. Knowledge sources include professional books and textbooks, academic journals or papers, clinical practice experience, and nursing guidelines. Knowledge classification is based on nursing specialty, stage of care, and type of nursing technology. File types include text, images, videos, and PDFs.

[0053] S3. Create corresponding summary tasks for nursing knowledge.

[0054] Select the nursing knowledge to be summarized and add prompt words to each piece of nursing knowledge. For example, output a summary of less than 300 words, focusing on the wound healing section. Select an AI model from the AI model library to extract the summary. The system can also automatically match available AI models based on the knowledge file type. The knowledge information and prompt word information are used as input to the AI model, and the AI model is run to generate a knowledge summary. The summary information is mainly a textual summary of the knowledge content, helping users to extract the key essence from a large amount of information sources.

[0055] This example allows you to input nursing knowledge into multiple AI models to generate summaries, comparing the outputs of different AI models. If the summary isn't ideal, you can adjust the prompts, rerun the AI model to generate the summary, select the appropriate summary information, and create a summary task.

[0056] In addition, this embodiment also supports the generation of knowledge questions and answers. Select the nursing knowledge for which knowledge questions and answers need to be generated, add prompt word information (generate knowledge questions and answers based on key knowledge content, and provide two multiple-choice questions), select the AI model used to generate the knowledge questions and answers, use the knowledge information and prompt word information as model input, run the AI model, and obtain the knowledge question and answer content. Knowledge questions and answers can effectively increase the interactivity of training courses, motivate students to think, and improve training effectiveness.

[0057] S4. Generate knowledge materials.

[0058] Based on the output of the summary task and the training target group, dynamic images or animated videos corresponding to the scenario are generated, which are called knowledge materials. Knowledge materials can express knowledge content in a more vivid and interesting way. The same nursing knowledge can be generated into a variety of images and videos for different occasions.

[0059] In this embodiment, based on the output information of the summary task, the knowledge materials corresponding to the nursing knowledge (such as generating pictures or videos of the corresponding scenes) and material elements (a more detailed description of the knowledge materials, such as animation or simulation effects, video length, picture resolution, subject content, etc.) can be supplemented as the input information of the model; according to the input information, the available AI model is selected (or the system automatically loads) and the selected AI model is run to generate the material. The generated material can be previewed in the user interface, and the material content can be saved to the system.

[0060] The generation of materials can also be done by calling different models, or adjusting the input parameters and re-running the model, comparing the output results of the model, and selecting the appropriate material content.

[0061] S5. Generate courseware.

[0062] Using the mind mapping method, the courseware themes, chapters, and contents are arranged. The courseware themes express the core ideas of the courseware and are placed on the first level of the map. Chapters organize and differentiate the training content according to preset logic, such as time logic (historical summary, current content, future planning), or by goals (problem identification, cause analysis, solutions, and optimization of results display), etc., and are placed on the second level of the map. Content refers to the specific information or materials presented in the courseware, which can be filled with generated summary information and knowledge materials (pictures, videos), and is placed on the third level of the map. Content is mainly obtained from summary tasks and materials. Summary information is output as text, and materials are a supplement to the text, expressed in pictures or videos, to present the text content more vividly.

[0063] Using mind mapping can help users better organize their thoughts, strengthen their structure, and make modifications and optimizations more flexible. Based on the nodes and content at each level of the mind map, the system encapsulates the mind map data into the input parameter structure required by the model; referring to the request parameter format of the PPT generation model in step S1, where the theme corresponds to the parameter theme attribute, the chapter corresponds to the parameter chapter attribute, and the content corresponds to the parameter content attribute, the mind map structure data is converted into parameter structure data, and the AI model is called to convert the mind map into a PPT format file.

[0064] Preferably, the AI model can be further used to help users optimize layout, color matching, etc. to form training courseware materials. Users only need to fine-tune the generated files to achieve the effect of formal courseware.

[0065] S6. Manage the generated courseware and edit the courseware content.

[0066] Among them, editing and processing courseware content specifically includes operations such as "courseware version management", "courseware review and release", "courseware sharing", and "courseware collection".

[0067] S61. Courseware Version Management. After generating a PPT courseware using a mind map, if the user is dissatisfied with the structure or needs to adjust the courseware materials, they can return to the mind map interface to modify and edit it again. Once completed, the courseware will be generated again to form a new courseware version. By adjusting the mind map to regenerate the PPT, the system will automatically generate a major version number, such as V1 or V2.

[0068] Users can also adjust PPT content and save it as a new version directly in the user interface. Editing a generated PPT file directly will automatically add a minor version number after the major version number, such as V1.1 or V1.2. Multi-version management makes it easy for users to trace historical records.

[0069] S62. Courseware review and release: The generated PPT courseware can be sent to teachers and other higher-level nursing staff for online review of the courseware content. The reviewers will review the unreasonable parts of the courseware content and can enter the review opinions at the bottom of each PPT page or mark them in the PPT content. The courseware production staff can view the review opinions in real time and adjust and optimize the relevant courseware according to the feedback from the review. The adjusted and optimized content can be further notified to the reviewers for re-review. After the reviewers confirm that it is correct, it will be submitted for review and approval. The courseware that has passed the review can be published as official courseware and provided to other staff in the department for review.

[0070] S63. Courseware Sharing: After publishing a courseware, courseware creators can share it with other departmental staff. Sharing scope includes both user scope and content scope. User scope refers to sharing with specific users and roles; content scope includes PPT courseware, the mind map used to generate the courseware, and process files such as the knowledge, summaries, and models used to generate the courseware. Sharing process files helps others learn and draw on the courseware creation process, ultimately improving overall courseware production quality and efficiency. Sharing of shared courseware can also be canceled or the scope of sharing can be modified.

[0071] S64. Courseware collection: Users can collect some excellent courseware, and the collected courseware can be viewed in a separate folder.

[0072] On the one hand, courseware collection can help users quickly find the courseware they are interested in. On the other hand, department managers can further analyze the courseware with high collection volume. As an important indicator for evaluating high-quality courseware, some high-quality courseware can be added to the knowledge base as part of knowledge management.

[0073] Based on the same inventive concept, this embodiment also provides an AI-based nursing knowledge interesting courseware generation system, including the following modules:

[0074] AI model library construction module, used to encapsulate the input and output parameters of each AI model in the model library;

[0075] The nursing knowledge collection module uploads nursing knowledge to the system and records its knowledge source, knowledge classification, file type, and knowledge name as personal knowledge data; or submits nursing knowledge to the public knowledge base as shared knowledge;

[0076] The summary task creation module is used to create corresponding summary tasks for nursing knowledge, select the nursing knowledge to be summarized, and supplement each nursing knowledge with prompt words; select the AI model used for summarization from the AI model library, use the knowledge information and prompt word information as input of the AI model, run the AI model, and obtain the knowledge summary;

[0077] The knowledge material generation module generates dynamic images or animated videos of corresponding scenarios as knowledge materials based on the output information of the summary task and the training target group, which can be used in different occasions.

[0078] The courseware generation module uses the mind map method to organize the courseware into themes, chapters, and content. The theme of the courseware expresses the core idea of the courseware and is placed on the first level of the map. The chapters are used to organize and differentiate the training content according to the preset logic and are placed on the second level of the map. The content is the information or materials presented in the courseware, which is filled with the generated summary information and knowledge materials and is placed on the third level of the map.

[0079] According to the nodes and content at each level of the mind map, the mind map data is encapsulated into the input parameter structure required by the model, and the AI model is called to convert the mind map into a PPT format file;

[0080] The courseware editing and management module manages the generated courseware and edits and processes the courseware content.

[0081] The above modules are respectively used to execute the corresponding steps of the courseware generation method.

[0082] From the above implementation process, it can be seen that the present invention first integrates the AI model; uploads nursing knowledge to the system; edits prompt words for the specified knowledge, selects the appropriate AI big model to generate knowledge summary information, edits and improves the generated summary to form high-quality knowledge points; supplements prompt words for the knowledge points, and provides them to the AI big model to generate materials, such as pictures, animation videos, etc.; uses the mind mapping method to structure the courseware themes, chapters, and contents, encapsulates them into AI model input parameters, and generates PPT files through automatic layout of the AI model; adjusts the PPT files and outputs them as courseware, and performs version management, approval / publishing, sharing, collection and other operations on the courseware.

[0083] Based on AI technology, this invention gradually transforms knowledge into training courseware. Users simply upload the knowledge source information to the system and add necessary prompts to the AI model, which then outputs a knowledge summary and other information, providing the basic information required for the courseware. This invention also allows users to construct a courseware framework through mind mapping, organizing the courseware content in a structured manner, and generating PPT files using an AI automated layout model.

[0084] The AI models used in this invention are all integrated in an API manner. The system encapsulates various parameters. Users only need to select the model and necessary input parameters through the interface window to call the model. The integrated AI model can be an open and general model, or it can be fine-tuned through an open source model. For example, some unique elements such as animation materials or PPT templates can be added based on the Deepseek model for training to make the model more suitable for the usage scenario.

[0085] The above description is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. For those skilled in the art, improvements or changes can be made based on the above description without creativity, and all such improvements and changes should fall within the scope of protection requested by the claims of the present invention.

Claims

1. A method for generating interesting nursing knowledge courseware based on AI, characterized by: The following steps are involved: S1. Build an AI model library and encapsulate the input and output parameters of each AI model in the model library; S2. Collect and record nursing knowledge, upload nursing knowledge to the system, and record its knowledge source, knowledge classification, file type, and knowledge name as personal knowledge data; or submit nursing knowledge to the public knowledge base as shared knowledge; S3. Create a corresponding summary task for nursing knowledge, select the nursing knowledge to be summarized, and add prompt words to each nursing knowledge; select the AI model used for summarization from the AI model library, use the knowledge information and prompt word information as input to the AI model, run the AI model, and obtain the knowledge summary; S4. Generate knowledge materials. Based on the output information of the summary task and the training target group, generate dynamic pictures or animation videos of corresponding scenarios as knowledge materials for use in different occasions. S5. Generate courseware. Use mind mapping to organize the courseware into themes, chapters, and content. Themes express the core ideas of the courseware and are placed at the first level of the mind map. Chapters organize and differentiate the training content according to a preset logic and are placed at the second level of the mind map. Content is the specific information or materials presented in the courseware, which is filled with generated summary information and knowledge materials and is placed at the third level of the mind map. According to the nodes and content at each level of the mind map, the mind map data is encapsulated into the input parameter structure required by the model, and the AI model is called to convert the mind map into a PPT format file; S6. Manage the generated courseware and edit the courseware content.

2. The method for generating interesting nursing knowledge courseware according to claim 1, characterized in that: Step S3 also includes generating knowledge questions and answers, selecting nursing knowledge for which knowledge questions and answers need to be generated, supplementing prompt word information, selecting the AI model used to generate knowledge questions and answers, using the knowledge information and prompt word information as input to the model, running the AI model, and obtaining the knowledge question and answer content.

3. The method for generating interesting nursing knowledge courseware according to claim 1, characterized in that: The editing and processing of the courseware content in step S6 includes courseware version management. When the user uses the mind map method to generate the PPT courseware, but is not satisfied with the structure of the courseware, or needs to adjust the materials used in the courseware, he or she returns to the mind map interface to modify and edit it again. After completion, the courseware is generated again to form a new courseware version.

4. The method for generating interesting nursing knowledge courseware according to claim 1, characterized in that: The editing and processing of the courseware content in step S6 includes courseware review and release, sending the generated PPT courseware to higher-level nursing staff for online review of the courseware content, and reviewing the unreasonable parts of the courseware content. The courseware production staff adjusts and optimizes the courseware according to the feedback from the review until it passes the review.

5. The method for generating interesting nursing knowledge courseware according to claim 1, characterized in that: The editing and processing of the courseware content in step S6 includes courseware sharing. After the courseware is released, the courseware producer shares the courseware with other staff in the department. The sharing scope includes the user scope and content scope, where the user scope includes specific users and roles; the content scope includes PPT courseware, the mind map used to generate the courseware, and the nursing knowledge, summary, and AI model used to generate the courseware.

6. The method for generating interesting nursing knowledge courseware according to claim 1, characterized in that: Each AI model in the AI model library in step S1 is a general commercial AI large model, or a private large model built based on an open source pre-trained model combined with RAG technology.

7. The method for generating interesting nursing knowledge courseware according to claim 6, characterized in that: In step S1, when building a private large model, the RAG method is used to segment the internal knowledge content of the hospital into text blocks through spacy based on the langchain large model application framework, and the segmented data obtained by the text segmentation is stored in the chroma vector database using the bge-large-zh-v1.5 vector model. When the user generates a summary, the user's required content is first matched to the relevant knowledge data in the vector database through RAG, and then the data is provided to the large model to generate the final result.

8. An AI-based nursing knowledge interesting courseware generation system, characterized by: Includes the following modules: AI model library construction module, used to encapsulate the input and output parameters of each AI model in the model library; The nursing knowledge collection module uploads nursing knowledge to the system and records its knowledge source, knowledge classification, file type, and knowledge name as personal knowledge data; or submits nursing knowledge to the public knowledge base as shared knowledge; The summary task creation module is used to create corresponding summary tasks for nursing knowledge, select the nursing knowledge to be summarized, and supplement each nursing knowledge with prompt words; select the AI model used for summarization from the AI model library, use the knowledge information and prompt word information as input of the AI model, run the AI model, and obtain the knowledge summary; The knowledge material generation module generates dynamic images or animated videos of corresponding scenarios as knowledge materials based on the output information of the summary task and the training target group, which can be used in different occasions. The courseware generation module uses the mind map method to organize the courseware into themes, chapters, and content. The theme of the courseware expresses the core idea of the courseware and is placed on the first level of the map. The chapters are used to organize and differentiate the training content according to the preset logic and are placed on the second level of the map. The content is the information or materials presented in the courseware, which is filled with the generated summary information and knowledge materials and is placed on the third level of the map. According to the nodes and content at each level of the mind map, the mind map data is encapsulated into the input parameter structure required by the model, and the AI model is called to convert the mind map into a PPT format file; The courseware editing and management module manages the generated courseware and edits and processes the courseware content.

Images