Medical knowledge base knowledge generation method and electronic equipment

Abstract

The embodiment of the invention discloses a medical knowledge base knowledge generation method and electronic equipment. The method comprises the steps of determining a knowledge template of a medical knowledge base under the condition of obtaining input data; and obtaining a knowledge generation model, and according to the input data and the knowledge template, through the knowledge generation model, generating target knowledge to be stored in the medical knowledge base so as to store the target knowledge in the medical knowledge base. According to the technical scheme, the problem that the knowledge generation efficiency of the medical knowledge base is low can be solved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of data processing technology, and in particular to a method for generating medical knowledge base and an electronic device. Background Technology

[0002] A medical knowledge base is a core information system for storing, managing, and sharing medical knowledge such as disease treatment plans, clinical guidelines, drug information, and case data. It is widely used in clinical decision support, medical education, and scientific research analysis.

[0003] However, the current knowledge generation efficiency of medical knowledge bases is low, which urgently needs to be addressed. Summary of the Invention

[0004] This invention provides a method and electronic device for generating medical knowledge bases to address the problem of low efficiency in generating medical knowledge.

[0005] According to one aspect of the present invention, a method for generating medical knowledge base is provided, which may include:

[0006] Once the input data is obtained, the knowledge template for the medical knowledge base is determined;

[0007] The knowledge generation model is obtained, and based on the input data and knowledge template, the target knowledge to be stored in the medical knowledge base is generated through the knowledge generation model, so as to store the target knowledge in the medical knowledge base.

[0008] Store the target knowledge in the medical knowledge base.

[0009] According to another aspect of the present invention, an electronic device is provided, which may include:

[0010] At least one processor; and

[0011] A memory that is communicatively connected to at least one processor; wherein,

[0012] The memory stores a computer program that can be executed by at least one processor, such that when the at least one processor executes the program, it implements the medical knowledge base knowledge generation method provided in any embodiment of the present invention.

[0013] The technical solution of this invention, upon obtaining input data, determines a knowledge template for a medical knowledge base to automatically identify a knowledge template compatible with the medical knowledge base; it then acquires a knowledge generation model and, based on the input data and the knowledge template, generates target knowledge to be stored in the medical knowledge base using the knowledge generation model, thereby storing the target knowledge in the medical knowledge base. This achieves automatic generation of target knowledge for storage in the medical knowledge base through the knowledge generation model and knowledge template. This technical solution eliminates the need for inefficient manual intervention, automatically and efficiently generating target knowledge for storage in the medical knowledge base through the knowledge generation model and knowledge template, thus solving the problem of low knowledge generation efficiency in medical knowledge bases.

[0014] It should be understood that the description in this section is not intended to identify key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart of a medical knowledge base knowledge generation method provided according to an embodiment of the present invention;

[0017] Figure 2 This is a flowchart of another medical knowledge base knowledge generation method provided according to an embodiment of the present invention;

[0018] Figure 3 This is a flowchart of another medical knowledge base knowledge generation method provided according to an embodiment of the present invention;

[0019] Figure 4 This is a schematic diagram of an optional example of another medical knowledge base knowledge generation method provided according to an embodiment of the present invention;

[0020] Figure 5 This is a flowchart of another optional example of a medical knowledge base knowledge generation method provided according to an embodiment of the present invention;

[0021] Figure 6 This is a schematic diagram of yet another optional example of a medical knowledge base knowledge generation method provided in an embodiment of the present invention;

[0022] Figure 7This is a structural block diagram of a medical knowledge base knowledge generation device provided according to an embodiment of the present invention;

[0023] Figure 8 This is a schematic diagram of the structure of an electronic device that implements the medical knowledge base knowledge generation method of this invention. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. The same applies to "target," "original," etc., and will not be repeated here. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] Before introducing the embodiments of the present invention, the implementation process of the current scheme for generating medical knowledge bases and the reasons for the low generation efficiency of medical knowledge bases will be explained by way of example, so as to better understand why the solution proposed in the embodiments of the present invention can solve the problem of low generation efficiency of medical knowledge bases.

[0027] For example, the following two methods are currently commonly used to generate medical knowledge bases: The first method uses traditional editors that support multi-user collaborative editing and employ locking mechanisms or difference merging to resolve version conflicts. This means that only rich text editors based on the World Wide Web (Web) or document management platforms with version control functions such as Git are provided for users to input textual knowledge. However, the textual input may require users to manually consult a large number of literatures, clinical guidelines, and case reports, and organize unstructured knowledge into structured documents that conform to specific templates of the medical knowledge base through copying, pasting, summarizing, and formatting, and then enter the medical knowledge base. However, this method requires users to spend a lot of time manually searching for information. All the work of organizing, summarizing, and formatting the knowledge content must be done manually, which means that it has the problem of low editing efficiency, resulting in low knowledge generation efficiency. Especially when facing massive and rapidly updated multimodal medical knowledge, a lot of time needs to be invested in manual operation, resulting in a long knowledge accumulation cycle and particularly low knowledge generation efficiency, which may also lead to high costs. To improve the efficiency of knowledge generation in the medical knowledge base, a second approach has been proposed: introducing an independent AI-Generated Content (AIGC) tool. This involves inputting the material or instructions to be processed into the AIGC tool outside the editor to generate an initial draft generated by Artificial Intelligence (AI). This draft is then organized into a structured document conforming to a specific template for the medical knowledge base, and copied and pasted into the editor for entry into the medical knowledge base. However, this approach treats the AIGC tool as a separate pre-processing tool, not deeply integrated with the editing environment. Consequently, the AIGC tool cannot automatically generate a structured document conforming to the specific template of the medical knowledge base, requiring manual organization of the AI-generated draft. This results in a persistently low efficiency in knowledge generation. Furthermore, this approach suffers from severe workflow interruptions, requiring frequent switching between the editor and the independent AIGC tool to perform copy and paste operations. This disrupts the flow experience and workflow continuity of knowledge creation, further reducing the efficiency of knowledge generation in the medical knowledge base.

[0028] To address this issue, embodiments of the present invention can automatically and efficiently generate target knowledge for storage in the medical knowledge base through knowledge generation models and knowledge templates, without relying on inefficient manual intervention, thereby solving the problem of low knowledge generation efficiency in the medical knowledge base. This will be explained in detail below.

[0029] Figure 1This is a flowchart of a medical knowledge base knowledge generation method provided in an embodiment of the present invention. This embodiment is applicable to the generation of medical knowledge base knowledge. The method can be executed by the medical knowledge base knowledge generation device provided in this embodiment of the present invention. This device can be implemented by software and / or hardware, and can be integrated into an electronic device, which can be various user terminals or servers.

[0030] See Figure 1 The method of this invention specifically includes the following steps:

[0031] S110. Given the input data, determine the knowledge template for the medical knowledge base.

[0032] The input data can be understood as the data used to generate the target knowledge; the input data may include at least one of the following: text data, image data, video data, modular content data, and audio data; the input data may be at least one of the following: keywords contained in the target knowledge generated from the requirements, content related to the target knowledge of the requirements, and knowledge outlines, knowledge summaries, and knowledge descriptions.

[0033] In this embodiment of the invention, the input data may not be all the data input by the target object, but may be data selected by the target object from all the data (e.g., data in a region selected by the target object from the editor) or cursor positioning data (e.g., data in a preset region before, after, or before and after the cursor position of the cursor placed by the target object in the editor).

[0034] In this embodiment of the invention, an editor such as a graphical editor can be displayed to allow the target object to input data. It should be noted that the editor allows the target object to directly perform input operations, the editor is context-aware, and it can provide at least one of the following functions: rich text editing, multimodal content embedding (images and / or videos), and modular content block drag-and-drop layout, etc., for the target object to input data. For example, the target object can select a piece of text, click on an image, and / or input data in the displayed editor to obtain input data obtained through the target object's operations.

[0035] In this embodiment of the invention, the acquisition of input data can be dynamic, that is, the acquired input data can be dynamically updated as the target object is modified or edited in the editor; the acquisition of input data can also be implemented in response to instructions, that is, in response to the input data instructions of the target object, the input data is acquired.

[0036] A medical knowledge base can be understood as a database in the medical field where requirements are generated and stored to obtain target knowledge.

[0037] A knowledge template can be understood as a template of knowledge that conforms to the storage format of a medical knowledge base and can be stored in the medical knowledge base.

[0038] In this embodiment of the invention, a knowledge template can be determined after obtaining input data.

[0039] S120. Obtain the knowledge generation model, and based on the input data and knowledge template, generate the target knowledge to be stored in the medical knowledge base through the knowledge generation model, so as to store the target knowledge in the medical knowledge base.

[0040] A knowledge generation model can be understood as a model used to generate target knowledge; a knowledge generation model can be, for example, a large language model (LLM).

[0041] In this embodiment of the invention, the general knowledge generation model can be incrementally fine-tuned in advance based on professional data in the medical field such as massive medical literature, clinical guidelines and drug instructions, to obtain a knowledge generation model for generating target knowledge, so that the target knowledge generated by the knowledge generation model is more professional and accurate, and the occurrence of hallucination problems is reduced.

[0042] It is understood that AIGC refers to various forms of content automatically generated through artificial intelligence technology, such as text, code, images, and audio. In this embodiment of the invention, target knowledge can be generated through AIGC. Specifically, AIGC may include an AI model. Therefore, in this embodiment of the invention, a knowledge generation model can be obtained as an AI model, and target knowledge (such as a set of questions and answers that conform to the standards of the knowledge template) can be generated through the knowledge generation model based on input data and knowledge templates, so as to store the target knowledge in the medical knowledge base.

[0043] In this embodiment of the invention, before storing the target knowledge in the medical knowledge base, the contribution source of the target knowledge can be marked, that is, the part generated, created and / or modified by the target object (which may include input data) and the part generated by AI in the knowledge generation model can be marked as the contribution source, so as to facilitate the traceability of the source of the target knowledge and the evaluation of its contribution, and can also help the target knowledge become a teaching tool.

[0044] The technical solution of this invention, upon obtaining input data, determines a knowledge template for a medical knowledge base to automatically identify a knowledge template compatible with the medical knowledge base; it then acquires a knowledge generation model and, based on the input data and the knowledge template, generates target knowledge to be stored in the medical knowledge base using the knowledge generation model, thereby storing the target knowledge in the medical knowledge base. This achieves automatic generation of target knowledge for storage in the medical knowledge base through the knowledge generation model and knowledge template. This technical solution eliminates the need for inefficient manual intervention, automatically and efficiently generating target knowledge for storage in the medical knowledge base through the knowledge generation model and knowledge template, thus solving the problem of low knowledge generation efficiency in medical knowledge bases.

[0045] An optional technical solution involves determining a knowledge template for a medical knowledge base upon obtaining input data, including: determining a knowledge template for a medical knowledge base corresponding to the target object upon obtaining input data from the target object.

[0046] The target object can be understood as the object into which the input data is input.

[0047] In this embodiment of the invention, when input data from the target object is obtained, instead of determining the knowledge template of any medical knowledge base, the knowledge template of the medical knowledge base corresponding to the target object is determined. For example, when input data from the target object is obtained, the target object's identity identifier can be determined, the medical knowledge base corresponding to the identity identifier in each knowledge base can be determined, and then the knowledge template of the medical knowledge base can be determined. The above technical solution can ensure that the target knowledge is stored in the medical knowledge base corresponding to the target object, thereby avoiding the erroneous storage of the target knowledge.

[0048] Figure 2 This is a flowchart of another medical knowledge base knowledge generation method provided in this embodiment of the invention. This embodiment is based on the above-mentioned technical solutions and optimized. In this embodiment, optionally, the medical knowledge base knowledge generation method further includes: identifying the entities and semantic intent of the input data, and determining at least one knowledge generation function based on the entities and semantic intent, and displaying at least one knowledge generation function; determining the knowledge template of the medical knowledge base includes: responding to a function selection instruction triggered by a target object for a target function in the displayed at least one knowledge generation function, and determining the knowledge template of the medical knowledge base based on the target function.

[0049] The explanations of terms that are the same as or corresponding to those in the above embodiments will not be repeated here.

[0050] See Figure 2 The method in this embodiment may specifically include the following steps:

[0051] S210. When input data is obtained, identify the entities and semantic intent of the input data, determine at least one knowledge generation function based on the entities and semantic intent, and display at least one knowledge generation function.

[0052] In this context, an entity can be understood as a identifiable specific object or attribute in the input data.

[0053] Semantic intent can be understood as the intention that represents the purpose or need in the input data.

[0054] In this embodiment of the invention, entities and semantic intents can be identified upon receiving input data. For example, the editor can integrate a real-time data analysis module. This module can identify input data in real time, performing keyword extraction and entity recognition on the context of the input data or the currently selected area, thereby identifying key entities and performing data semantic recognition on the input data to identify semantic intents.

[0055] The knowledge generation function can be understood as the function of generating target knowledge. The knowledge generation function can be related to the type of target knowledge generated. For example, the knowledge generation function can be a summary function, a question-and-answer (QA) pair, a diagnostic approach, a teaching material or an outline, etc. The knowledge generation function can also be a more detailed function such as generating key points of surgical steps or a list of complications.

[0056] In this embodiment of the invention, at least one knowledge generation function can be determined based on entities and semantic intent. For example, at least one candidate generation function can be determined based on entities and semantic intent, and the relevance of each candidate generation function to the input data can be determined. A preset number of candidate generation functions with the highest relevance can be selected as at least one knowledge generation function, which helps to accurately and on-demand display at least one knowledge generation function in the future.

[0057] In this embodiment of the invention, at least one knowledge generation function can be displayed. For example, function buttons corresponding to at least one contextualized knowledge generation function can be rendered in the sidebar or floating toolbar of the editor's interface.

[0058] S220, In response to a function selection instruction triggered by the target object for at least one of the displayed knowledge generation functions, determine the knowledge template of the medical knowledge base according to the target function.

[0059] The target function can be understood as the knowledge generation function triggered by the target object.

[0060] A function selection instruction can be understood as an instruction that indicates that the target object has selected a target function.

[0061] In this embodiment of the invention, a knowledge template can be determined based on the target function in response to a function selection instruction. For example, a knowledge template corresponding to the target function in a medical knowledge base can be determined in response to a function selection instruction.

[0062] S230. Obtain the knowledge generation model, and based on the input data and knowledge template, generate the target knowledge to be stored in the medical knowledge base through the knowledge generation model, so as to store the target knowledge in the medical knowledge base.

[0063] In this embodiment of the invention, considering that generating target knowledge corresponding to complex target functions may require coordinating multiple AI models or that the knowledge generation model needs to execute the knowledge generation steps in a specific order, a knowledge generation model can be obtained based on the target function. Specifically, at least one sub-model and / or model execution steps can be determined based on the target function, and a knowledge generation model can be obtained based on at least one sub-model and / or model execution steps, thereby realizing the intelligent acquisition of the knowledge generation model.

[0064] The technical solution of this invention identifies the entities and semantic intent of the input data, determines at least one knowledge generation function based on the entities and semantic intent, and displays at least one knowledge generation function; in response to a function selection instruction triggered by a target object for a target function among the displayed at least one knowledge generation function, a knowledge template for the medical knowledge base is determined based on the target function. The above technical solution can achieve dynamic functional interaction, thereby determining a knowledge template that better meets the needs of knowledge generation.

[0065] An optional technical solution involves generating target knowledge to be stored in a medical knowledge base based on input data and a knowledge template using a knowledge generation model. This includes: generating target knowledge to be stored in a medical knowledge base based on input data, a knowledge template, and a target function using a knowledge generation model.

[0066] In this embodiment of the invention, target knowledge can be generated based on input data, a knowledge template, and a target function using a knowledge generation model. For example, based on the input data, the knowledge generation model can generate target knowledge that conforms to the knowledge template according to the target function. The above technical solution can generate target knowledge that better meets the needs of knowledge generation.

[0067] Based on the above solution, another optional technical solution is to generate target knowledge to be stored in the medical knowledge base through a knowledge generation model, based on input data, knowledge templates, and target functions. This includes: generating prompt words based on input data and target functions; and generating target knowledge to be stored in the medical knowledge base through a knowledge generation model based on prompt words and knowledge templates.

[0068] Here, prompt words can be understood as words used to prompt the knowledge generation model to generate target knowledge. For example, prompt words can prompt the knowledge generation model to generate at least one of the following: direction, angle, type, and content of the target knowledge.

[0069] In this embodiment of the invention, prompt words can be generated based on input data and the target function. For example, prompt word templates optimized according to different alternative functions (each alternative function includes at least one knowledge generation function, i.e., the target function) can be preset in advance to determine the prompt word template corresponding to the target function. Prompt words are generated based on the prompt word template and input data, thereby ensuring the professionalism and accuracy of the knowledge generation instructions issued to the knowledge generation model through the prompt words.

[0070] In this embodiment of the invention, target knowledge can be generated based on prompt words and a knowledge template using a knowledge generation model. For example, a knowledge generation instruction can be generated based on prompt words, initial knowledge can be generated based on the knowledge generation instruction using a knowledge generation model, and high-quality, structured target knowledge can be generated by integrating the initial knowledge based on the knowledge template.

[0071] The solution of this invention generates prompt words based on input data and target functions, and then generates target knowledge based on the prompt words and knowledge templates through a knowledge generation model, which can ensure the accuracy of the generated target knowledge.

[0072] Figure 3 This is a flowchart of another medical knowledge base knowledge generation method provided in this embodiment of the invention. This embodiment is based on and optimized from the above-described technical solutions. Optionally, in this embodiment, before storing the target knowledge in the medical knowledge base, the medical knowledge base knowledge generation method further includes: displaying the target knowledge; storing the target knowledge in the medical knowledge base includes: in response to a knowledge saving instruction issued by a target object for the displayed target knowledge, storing the target knowledge in the medical knowledge base. The explanations of terms that are the same as or corresponding to those in the above embodiments will not be repeated here.

[0073] See Figure 3 The method in this embodiment may specifically include the following steps:

[0074] S310. Given the input data, determine the knowledge template for the medical knowledge base.

[0075] S320, Acquiring a knowledge generation model.

[0076] S330. Based on the input data and knowledge template, generate target knowledge to be stored in the medical knowledge base through the knowledge generation model, and display the target knowledge in response to the knowledge saving instruction issued by the target object for the displayed target knowledge, and store the target knowledge in the medical knowledge base.

[0077] In this embodiment of the invention, target knowledge can be displayed. For example, the target knowledge can be rendered as an editable content block with special visual identifiers (e.g., a light blue background with AI badges), and this editable content block can be seamlessly inserted into the editing flow (e.g., input data) in the current editor.

[0078] Among them, the knowledge preservation instruction can be understood as an instruction to preserve the target knowledge.

[0079] In this embodiment of the invention, the target knowledge can be stored in a medical knowledge base in response to a knowledge storage instruction.

[0080] The technical solution of this invention displays target knowledge; in response to a knowledge saving instruction issued by a target object for the displayed target knowledge, the target knowledge is stored in a medical knowledge base. This technical solution ensures that the storage of target knowledge in the medical knowledge base can be determined by the target object, thereby guaranteeing the controllability of the storage of target knowledge in the medical knowledge base.

[0081] An optional technical solution, before storing the target knowledge into the medical knowledge base in response to a knowledge saving instruction issued by the target object for the displayed target knowledge, the medical knowledge base knowledge generation method further includes: modifying the target knowledge in response to a knowledge modification instruction issued by the target object for the target knowledge; and updating the displayed target knowledge according to the modified target knowledge.

[0082] Among them, the knowledge modification instruction can be understood as an instruction that instructs the modification of the target knowledge.

[0083] In this embodiment of the invention, the target knowledge can be modified in response to a knowledge modification instruction.

[0084] In this embodiment of the invention, the target object can manually review, correct, refine, and / or supplement the target knowledge. This human intervention, review, and optimization ensures the professionalism and accuracy of the target knowledge. When the target knowledge is modified (corrected, refined, or supplemented), a knowledge modification instruction is issued. For example, the target object can judge (review) the quality and / or correctness of the target knowledge. If problems are found with the quality and / or correctness, a knowledge modification instruction can be issued to modify the target knowledge (correct or refine). This allows the target object's professional judgment to serve as the core of quality control for the target knowledge, effectively avoiding illusions or errors that AI might produce. Of course, a knowledge modification instruction can also be issued to modify the target knowledge when additional content is needed (supplementation) or in other situations.

[0085] In this embodiment of the invention, before modifying the target knowledge in response to a knowledge modification instruction issued by the target object, the target knowledge can be seamlessly integrated into the editing process of the editor in an editable and traceable form, so that the target object can modify the target knowledge in the editor.

[0086] The technical solution of this invention responds to a knowledge modification instruction, modifies the target knowledge, and then updates the displayed target knowledge based on the modified target knowledge, so as to ensure that the target knowledge stored in the medical knowledge base meets the individual needs of the target object and can guarantee the quality and accuracy of the target knowledge.

[0087] Based on the above solution, another optional technical solution, after storing the target knowledge in the medical knowledge base, also includes: adjusting the knowledge generation model according to the target knowledge before and after modification when the target knowledge is modified.

[0088] In this embodiment of the invention, when the target knowledge has been modified, the knowledge generation model can be adjusted based on the target knowledge before and after the modification. The above process adopts a human-in-the-loop mechanism to adjust the knowledge generation model, that is, to build a human-machine collaborative partnership, embedding the professional knowledge and judgment depth of human experts and other objects (the modified target knowledge is obtained by the object through the professional knowledge and judgment depth of the object) into the AI ​​workflow, and forming an intelligent interaction paradigm of continuous optimization (model adjustment) closed loop.

[0089] In this embodiment of the invention, if the target knowledge has been modified, the knowledge generation model can be adjusted according to the modified target knowledge.

[0090] In this embodiment of the invention, the target knowledge of each modified version can be recorded so as to adjust the knowledge generation model based on the target knowledge of each version.

[0091] In this embodiment of the invention, for each target knowledge in the original target knowledge and the modified target knowledge, the contribution sources in the target knowledge can also be labeled, so as to adjust the knowledge generation model according to the original target knowledge and the modified target knowledge with labeled contribution sources.

[0092] In this embodiment of the invention, it may also involve obtaining feedback data from the target object regarding the target knowledge, and adjusting the knowledge generation model based on the feedback data.

[0093] Understandably, the general AIGC tools in the relevant solutions lack deep adaptation to the medical field. The content they generate may contain factual errors, logical inconsistencies, or fail to comply with medical professional standards, meaning they suffer from illusion problems. Furthermore, the content they generate cannot automatically inherit metadata from the medical knowledge base, such as permissions, tags, and classification systems (which can be reflected in knowledge templates), increasing the complexity of subsequent management of the content generated by the AIGC tools. However, the general AIGC tools in the relevant solutions typically lack learning capabilities, meaning the quality of the AIGC tools is fixed after deployment and cannot acquire knowledge from the modification and feedback of the target knowledge. This causes the AIGC tools to be unable to adapt to rapidly evolving medical practices, resulting in the AI-assisted effect reaching a plateau. To address this, the solution of this invention, when the target knowledge is modified, adjusts the knowledge generation model based on the target knowledge before and after modification. By adjusting the knowledge generation model with high-quality target knowledge templates that conform to the target knowledge, the problems in the aforementioned related solutions can be avoided. Furthermore, the knowledge generation model can become a living model that can continuously learn from use, thereby generating increasingly accurate target knowledge with increasing usage. This improves the accuracy of subsequently generated target knowledge and the quality of the medical knowledge base, while reducing the complexity of subsequent management of generated content (e.g., reducing the complexity of the knowledge generation model organizing and summarizing content generated from input data according to knowledge templates). It is also applicable to rapidly evolving medical practices.

[0094] Based on the above solution, another optional technical solution, a medical knowledge base knowledge generation method, further includes: recording modification behaviors of the target knowledge, wherein the modification behaviors include at least one of modification duration, modification character ratio, and adoption rate; and adjusting the knowledge generation model according to the target knowledge before modification and the target knowledge after modification, including: adjusting the knowledge generation model according to the target knowledge before modification, the target knowledge after modification, and the modification behaviors.

[0095] Modification behavior can be understood as the behavior of modifying the target knowledge.

[0096] Modification time can be understood as the time consumed by the target object to modify the target knowledge.

[0097] The character modification ratio can be understood as the ratio between the number of characters modified and the target knowledge before modification; the character modification ratio can also be called the edit distance.

[0098] The adoption rate can be understood as the percentage of target knowledge that is adopted. Specifically, it can be understood as the percentage of target knowledge that is stored in the medical knowledge base (adopting target knowledge) within a certain time range or in a preset knowledge generation. The adoption rate can also be understood as the percentage of modified target knowledge that adopts the content generated by the knowledge generation model.

[0099] In this embodiment of the invention, when the adoption rate is the percentage of target knowledge that has been adopted, the modification of the target knowledge can also be the clearing or abandonment of the target knowledge (essentially the situational target knowledge), etc. After the target knowledge is cleared or abandoned, the adoption rate can be updated or recorded so as to adjust the knowledge generation model through the adoption rate.

[0100] In this embodiment of the invention, the knowledge generation model may not be performed in every medical knowledge base knowledge generation process. Instead, after a certain period of time or a preset number of knowledge generation sessions, the knowledge generation model may be adjusted based on at least one of the following: the target knowledge before modification, the target knowledge after modification, the modification behavior, and the adoption rate within that period of time or the preset number of knowledge generation sessions.

[0101] The technical solution of this invention can record modification behavior including at least one of modification duration, modified character ratio, and adoption rate. Then, based on the target knowledge before modification, the target knowledge after modification, and the modification behavior, the knowledge generation model is adjusted to more accurately adjust the knowledge generation model, thereby further improving the accuracy of the target knowledge generated subsequently.

[0102] To better understand the technical solutions of the above embodiments of the present invention, an optional example is provided herein. For example, see... Figure 4 The knowledge generation process for the medical knowledge base consists of three stages: The first stage is the AI ​​generation stage, where, given the input data entered by the target object in the editor, the knowledge generation model generates the target knowledge and displays it with added visual tags in the editor; the second stage is the human intervention stage, where the target object reviews the target knowledge, and if there are any issues, the target knowledge is modified and the modification is recorded; the third stage is the model evolution stage, where the modification behavior is stored in an optimization dataset, and the knowledge generation model is periodically fine-tuned through the optimization dataset to continuously improve the AI ​​capabilities of the knowledge generation model, thereby enabling subsequent generation of target knowledge through the improved knowledge generation model.

[0103] To better understand the technical solutions of the above embodiments of the present invention, another optional example is provided here. For example, see... Figure 5When the target user begins editing (inputting) in the editor, the system obtains the target user's identity identifier and verifies their permissions to operate the editor and / or to input knowledge into the medical knowledge base. If verification fails (i.e., the target user does not have the corresponding permissions), an error message is displayed. If verification succeeds (i.e., the target user has the corresponding permissions), the system waits for the target user's action. If the target user selects input data from all data, at least one knowledge generation function is identified, and buttons corresponding to at least one knowledge generation function are displayed. If the target user does not trigger the button corresponding to the target function, the process of waiting for the target user's action is repeated. If the target user triggers the button corresponding to the target function, the target knowledge is generated using the knowledge generation model. In the event of failure, determine if the retry conditions are met (e.g., no more than a preset number of retries and / or a preset duration). If met, repeat the process of generating the target knowledge using the knowledge generation model. If not met, repeat the steps of waiting for the target object's operation. If the target knowledge is successfully generated, display the target knowledge. If the target object clicks the save button on the displayed target knowledge, store the target knowledge in the target database and optimize the knowledge generation model based on the target knowledge. If the target object does not click the save button on the displayed target knowledge, determine if the target object has issued a knowledge modification instruction. If the target object has issued a knowledge modification instruction, modify the target knowledge and repeat the steps of displaying the target knowledge. If the target object has not issued a knowledge modification instruction, repeat the steps of displaying the target knowledge.

[0104] To better understand the technical solutions of the above embodiments of the present invention, another optional example is provided here. For example, see [link to example]. Figure 6The generation of medical knowledge base knowledge can be achieved through a medical knowledge base knowledge generation system. This system includes a client interaction layer with precise awareness of the context of object input, a domain-optimized AIGC service layer providing intelligent assistance functions, and a data persistence layer for achieving self-optimization and closed-loop operation. Target objects can input data by selecting text or moving the cursor through the client editor. The AIGC service layer can determine at least one knowledge generation function based on the input data obtained from the client editor and return it. The client editor displays at least one knowledge generation function in the form of a dynamic menu. Target objects can click on the target function through the client editor. The AIGC service layer can stream-generate and stream-return target knowledge based on the target function obtained from the client editor. The client editor progressively displays the target knowledge (showing the source of contribution). Target objects can review and modify the target knowledge through the client editor. Target objects can save the target knowledge through the client editor. The client editor can save the target knowledge and provide feedback on the target knowledge and modification behavior to the data persistence layer. If the target knowledge is saved successfully, the data persistence layer can return a save success message to the client editor, allowing the client editor to display the save success message.

[0105] To better understand the technical solutions of the above embodiments of the present invention, another optional example is provided here. For example, medical knowledge base generation can be achieved through a medical knowledge base generation system. This system includes a client interaction layer (which can be deployed on the client side), an AIGC service layer (which can be deployed on the server side and is deeply optimized for the medical field), and a data persistence layer. The client interaction layer includes a context-aware graphical editor, a dynamic AIGC function menu module, and an implicit feedback acquisition module. The AIGC service layer includes a prompt word engineering engine, a large language model adapted to the medical field, a workflow orchestrator, a return layer, and a storage layer. The graphical editor is used to provide data input functionality for the target object, acquire the input data input by the target object, and then identify the entities and expressions in the input data. The dynamic AIGC function menu module is used to determine at least one knowledge generation function based on the entity and semantic intent. It renders a contextualized menu of function buttons corresponding to each of the at least one knowledge generation function in the editor's sidebar or floating toolbar. When the target object clicks on the target function, in response to the function selection instruction triggered by the target object, it encapsulates at least one of the following into a structured request object: input data, the target object's identity identifier, the medical knowledge base's library identifier, the project identifier (identitydocument, id) of the target item under the medical knowledge base to be stored, and the target function. This request object is then transmitted through an application programming interface (API). The Programming Interface (API) is sent to the AIGC service layer; the prompt word engineering engine determines the prompt word template corresponding to the target function in the request object, and generates prompt words based on the prompt word template and the input data in the request object; the workflow orchestrator determines at least one sub-model and / or determines the model execution steps based on the target function, and obtains the corresponding large language model based on at least one sub-model and / or determines the model execution steps; the large language model generates target knowledge to be stored in the medical knowledge base based on the prompt words and knowledge template; the return layer returns the target knowledge to the client interaction layer so that the graphical editor can display the target knowledge; the storage layer stores the target knowledge in the storage space corresponding to the target project in the medical knowledge base corresponding to the target object based on the identity identifier and project identifier in the request object; the implicit feedback collection module records the target knowledge before modification, the target knowledge after modification, and the modification behavior;The data persistence layer can include a version management database serving as a medical knowledge base and a model optimization dataset. The version management database can store target knowledge labeled with contribution sources, and can also record various versions of target knowledge (which may be labeled with version numbers) and version history (the historical situation of each version obtained by modifying the target knowledge). The model optimization dataset can be used to store modification behaviors to provide fuel for adjusting the knowledge generation model. Specifically, it can be used to incrementally fine-tune the large language model on a regular basis (e.g., weekly) based on the newly accumulated target knowledge and modification behaviors of the week, so that the large language model can learn from real use, thereby making the large language model increasingly intelligent and in line with the specific needs of the team. Specifically, the client-side interaction layer can respond to cursor movement commands or data selection commands, and obtain at least one knowledge generation function (which may be determined by the server) through a function acquisition interface. The request parameters of this interface may include at least one of the following: library identifier, input data, cursor position information (such as row and column numbers), and the content block identifier of the dragged content block. The AIGC service layer can use a streaming generation request interface, employing streaming transmission methods such as Streaming SIMD Extensions (SSE), to achieve real-time push and display of the generated target knowledge, thereby improving the user experience. The client-side interaction layer and the AIGC service layer can also use a save and feedback collection interface to save the target knowledge to the knowledge database when the target object confirms the target knowledge, and simultaneously submit feedback on modifications to the target knowledge for model optimization. The aforementioned interfaces require unified authentication and secure communication; that is, all API requests used by the interfaces must be authenticated and authorized through an API gateway, using Open Authorization 2.0 (OAuth 2.0) or JSON Web Tokens (JSON Web Tokens). The token mechanism (JWT) must be used, and given the sensitivity of medical data, it is necessary to use Hypertext Transfer Protocol Secure (HTTPS) (Transport Layer Security (TLS)) for encrypted transmission throughout the process, and to encrypt or de-identify stored knowledge and other data.The data requirements mentioned in this embodiment of the invention specifically concern medical data standards and compatibility. Specifically, when integrating with existing hospital systems such as Hospital Information Systems (HIS), Electronic Medical Records (EMR), and Picture Archiving and Communication Systems (PACS), support for medical information exchange standards such as Health Level Seven (HL7) and Fast Healthcare Interoperability Resources (FHIR) should be considered to facilitate standardized data extraction and write-back. The design of the knowledge generation model can refer to FHIR's DocumentReference and Composition resource structures to enhance interoperability. In the process of the solution in this embodiment of the invention, for time-consuming operations such as target knowledge generation, streaming response or asynchronous task mechanisms can be adopted to avoid request timeouts. For frequently accessed but infrequently changed data such as the medical knowledge base directory (used to store target knowledge in the storage space corresponding to the item identifier in the knowledge base directory) and identity identifiers, caching methods such as Redis can be used to significantly improve interface response speed.

[0106] The aforementioned technical solution deeply integrates AIGC-assisted knowledge generation, embedding AIGC capabilities deep into the workflow of the editing context. It supports multimodal data collaborative input and, combined with dynamic context awareness and intelligent content injection, enables one-click intelligent generation of medical knowledge base knowledge. This is expected to save more than 70% of the time, freeing users from tedious data organization and allowing them to focus on professional review and innovation. This improves the efficiency of knowledge accumulation, i.e., the efficiency of medical knowledge base generation, and eliminates interactive gaps, providing a smooth knowledge generation experience. Furthermore, it can achieve self-optimization through domain-adapted AI models and human-in-the-loop mechanisms, ensuring that the generated knowledge undergoes professional review and complies with medical standards, thereby effectively guaranteeing the quality, compliance, relevance, and professionalism of the knowledge.

[0107] Figure 7 This is a structural block diagram of a medical knowledge base generation device provided in an embodiment of the present invention. This device is used to execute the medical knowledge base generation method provided in any of the above embodiments. This device and the medical knowledge base generation methods of the above embodiments belong to the same inventive concept. Details not described in detail in the embodiments of the medical knowledge base generation device can be found in the embodiments of the medical knowledge base generation methods described above. See also... Figure 7Specifically, the device may include: a knowledge template determination module 410 and a target knowledge generation module 420.

[0108] Among them, the knowledge template determination module 410 is used to determine the knowledge template of the medical knowledge base when the input data is obtained;

[0109] The target knowledge generation module 420 is used to acquire the knowledge generation model and, based on the input data and knowledge template, generate the target knowledge to be stored in the medical knowledge base through the knowledge generation model, so as to store the target knowledge in the medical knowledge base.

[0110] Optionally, the device may also include:

[0111] The knowledge generation function display module is used to identify the entities and semantic intent of the input data, and determine at least one knowledge generation function based on the entities and semantic intent, and display at least one knowledge generation function.

[0112] The knowledge template determination module 410 may include:

[0113] The first knowledge template determination submodule is used to determine the knowledge template of the medical knowledge base in response to the function selection instruction triggered by the target object for at least one knowledge generation function in the display.

[0114] Optionally, based on the above-described apparatus, the target knowledge generation module 420 may include:

[0115] The target knowledge generation submodule is used to generate target knowledge to be stored in the medical knowledge base based on input data, knowledge templates, and target functions through a knowledge generation model.

[0116] Optionally, based on the above-described apparatus, the target knowledge generation submodule may include:

[0117] The prompt word generation unit is used to generate prompt words based on the input data and the target function;

[0118] The target knowledge generation unit is used to generate target knowledge to be stored in the medical knowledge base based on prompt words and knowledge templates through a knowledge generation model.

[0119] Optionally, the device may also include:

[0120] The target knowledge display module is used to display target knowledge before it is stored in the medical knowledge base;

[0121] The target knowledge generation module 420 may include:

[0122] The target knowledge storage submodule is used to respond to the knowledge storage command issued by the target object for the displayed target knowledge and store the target knowledge into the medical knowledge base.

[0123] Optionally, based on the above-described apparatus, the apparatus may further include:

[0124] The target knowledge modification module is used to modify the target knowledge in response to the target object's knowledge modification instruction before storing the target knowledge into the medical knowledge base in response to the target object's knowledge saving instruction.

[0125] The target knowledge update module is used to update the displayed target knowledge based on the modified target knowledge.

[0126] Optionally, based on the above-described apparatus, the apparatus may further include:

[0127] The knowledge generation model adjustment module is used to adjust the knowledge generation model based on the original and modified target knowledge after the target knowledge has been stored in the medical knowledge base.

[0128] Optionally, based on the above-described apparatus, the apparatus may further include:

[0129] The character modification ratio recording module is used to record modification behaviors of the target knowledge. The modification behaviors include at least one of modification duration, character modification ratio, and adoption rate.

[0130] The knowledge generation model adjustment module may include:

[0131] The knowledge generation model adjustment submodule is used to adjust the knowledge generation model based on the target knowledge before modification, the target knowledge after modification, and the modification behavior.

[0132] Optionally, the knowledge template determination module 410 may include:

[0133] The second knowledge template determination submodule is used to determine the knowledge template of the medical knowledge base corresponding to the target object when the input data of the target object is obtained.

[0134] The medical knowledge base generation device provided in this invention, through a knowledge template determination module, determines a knowledge template for the medical knowledge base upon receiving input data, thereby automatically identifying a knowledge template compatible with the medical knowledge base. Through a target knowledge generation module, a knowledge generation model is acquired, and based on the input data and the knowledge template, the target knowledge to be stored in the medical knowledge base is generated using the knowledge generation model. This allows for the automatic generation and storage of target knowledge in the medical knowledge base through the knowledge generation model and knowledge template. This device can automatically and efficiently generate target knowledge for storage in the medical knowledge base without relying on inefficient manual intervention, thus solving the problem of low knowledge generation efficiency in medical knowledge bases.

[0135] The medical knowledge base knowledge generation device provided in the embodiments of the present invention can execute the medical knowledge base knowledge generation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0136] It is worth noting that in the embodiments of the above-mentioned medical knowledge base knowledge generation device, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0137] Figure 8 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0138] like Figure 8As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer programs stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0139] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0140] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as medical knowledge base knowledge generation methods.

[0141] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.

[0142] In some embodiments, the medical knowledge base knowledge generation method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the medical knowledge base knowledge generation method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to execute the medical knowledge base knowledge generation method by any other suitable means (e.g., by means of firmware).

[0143] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0144] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0145] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0146] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0147] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0148] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0149] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0150] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A medical knowledge base knowledge generation method characterized by, The method comprises the following steps: In the case of obtaining input data, determining a knowledge template of a medical knowledge base; Obtaining a knowledge generation model, and generating target knowledge to be stored in the medical knowledge base by the knowledge generation model according to the input data and the knowledge template, so as to store the target knowledge in the medical knowledge base.

2. The method of claim 1, wherein, Further comprising: Identifying the entity and semantic intention of the input data, and determining at least one knowledge generation function according to the entity and the semantic intention, and displaying at least one of the knowledge generation functions; The step of determining the knowledge template of the medical knowledge base comprises: In response to a function selection instruction triggered by a target object for a target function in the displayed at least one knowledge generation function, determining a knowledge template of a medical knowledge base according to the target function.

3. The method of claim 2, wherein, The step of generating target knowledge to be stored in the medical knowledge base by the knowledge generation model according to the input data and the knowledge template comprises: Generating target knowledge to be stored in the medical knowledge base by the knowledge generation model according to the input data, the knowledge template and the target function.

4. The method of claim 3, wherein, The step of generating target knowledge to be stored in the medical knowledge base by the knowledge generation model according to the input data and the knowledge template comprises: Generating a prompt word according to the input data and the target function; Generating target knowledge to be stored in the medical knowledge base by the knowledge generation model according to the prompt word and the knowledge template.

5. The method of claim 1, wherein, Before the step of storing the target knowledge in the medical knowledge base, further comprising: Displaying the target knowledge; The step of storing the target knowledge in the medical knowledge base comprises: In response to a knowledge saving instruction issued by a target object for the displayed target knowledge, storing the target knowledge in the medical knowledge base.

6. The method of claim 5, wherein, Before the step of storing the target knowledge in the medical knowledge base in response to the knowledge saving instruction issued by the target object for the displayed target knowledge, further comprising: In response to a knowledge modification instruction issued by the target object for the target knowledge, modifying the target knowledge; Updating the displayed target knowledge according to the modified target knowledge.

7. The method of claim 6, wherein, After the step of storing the target knowledge in the medical knowledge base, further comprising: In the case that the target knowledge is modified, adjusting the knowledge generation model according to the target knowledge before modification and the target knowledge after modification.

8. The method of claim 7, wherein, Further comprising: Recording a modification behavior of modifying the target knowledge, wherein the modification behavior comprises at least one of a modification duration, a modification character ratio and an adoption rate; The step of adjusting the knowledge generation model according to the target knowledge before modification and the target knowledge after modification comprises: Adjusting the knowledge generation model according to the target knowledge before modification, the target knowledge after modification and the modification behavior.

9. The method of claim 1, wherein, The step of determining the knowledge template of the medical knowledge base in the case of obtaining input data comprises: In the case of obtaining input data input by a target object, determining a knowledge template of a medical knowledge base corresponding to the target object.

10. An electronic device, comprising: The method comprises the following steps: At least one processor; and ​ a memory connected with the at least one processor in communication; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the medical knowledge base knowledge generation method according to any one of claims 1-9.

Images