An intelligent medical record analysis and simulated diagnosis and treatment system for medical teaching

Abstract

The application discloses a medical teaching-oriented intelligent medical record analysis and simulated diagnosis and treatment system and relates to the field of intelligent medical treatment, and comprises a cloud database, which is used for uploading patient diagnosis and treatment cases and storing the patient diagnosis and treatment cases; a selection module, which is used for selecting patient diagnosis and treatment cases in the cloud database and taking the selected diagnosis and treatment cases as to-be-simulated diagnosis and treatment cases; and an editing module, which is used for acquiring the to-be-simulated diagnosis and treatment cases selected by the selection module, reading based on the to-be-simulated diagnosis and treatment cases, and manually editing diagnosis logic and medication details. The application collects a plurality of standard and patient-recovered cases, stores the cases after screening and classification, provides massive real and high-quality learning resources for medical teaching, and enables users to select the cases for simulated diagnosis and treatment, manually edit diagnosis logic and medication details, and deepen the understanding and application of medical knowledge in practice.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent medical technology, in particular to an intelligent medical record analysis and simulated diagnosis and treatment system for medical teaching. BACKGROUND

[0002] Medical teaching simulated diagnosis and treatment is to use simulation technology to build a simulated clinical environment, allowing medical students to practice diagnosis and treatment operations in a risk-free scenario. Through the forms of simulated patients, virtual cases, standardized patients, etc., the whole process training of inquiry, physical examination, diagnosis and treatment is covered to help students master clinical thinking and skills, improve communication skills, and make up for the lack of real clinical practice opportunities. It is an important teaching method for the combination of theory and practice in medical education.

[0003] The patent application with application number 202311136970.X discloses an electronic medical record data intelligent analysis system based on artificial intelligence, which includes: an electronic medical record data acquisition module for acquiring structured data and unstructured data of each electronic medical record; an electronic medical record screening module for analyzing the similarity of diseases to which each electronic medical record belongs, and further screening to obtain each electronic medical record corresponding to a newly emerging disease; an electronic medical record classification module for analyzing the similarity of diseases to which each electronic medical record corresponding to a newly emerging disease and other electronic medical records belong, and further classifying to obtain each electronic medical record corresponding to each type of newly emerging disease; a disease risk parameter acquisition module for acquiring risk parameters of each type of newly emerging disease; a disease risk parameter analysis module for analyzing risk assessment coefficients of each type of newly emerging disease; a disease transmission data acquisition module for acquiring the number of patients with each type of newly emerging disease in a set monitoring period and the incubation period of each type of newly emerging disease; a disease transmission data analysis module for analyzing the transmission speed of each type of newly emerging disease; and a disease data analysis module for analyzing the transmission risk coefficient of each type of newly emerging disease according to the risk assessment coefficient and the transmission speed of each type of newly emerging disease, further obtaining the prevention level of each type of newly emerging disease, and feeding back. The application aims to solve the problem of "due to the lack of reference historical cases corresponding to the infrequent disease, the determination of its treatment plan is negatively affected, and the current electronic medical record data analysis also ignores the analysis of the transmission risk of the infrequent disease, so the transmission risk level of the infrequent disease cannot be obtained, and thus specific prevention measures and screening suggestions cannot be provided, and people cannot be reminded to take safety precautions in time, which is not conducive to the health and safety of people".

[0004] However, in the medical teaching scenario, experienced doctors often take interns to see patients to accumulate diagnosis and treatment experience. This method is limited by the energy and other factors of experienced doctors, and cannot provide conditions for interns to learn and accumulate diagnosis and treatment experience.

[0005] To this end, an intelligent medical record analysis and simulated diagnosis and treatment system for medical teaching is proposed. SUMMARY

[0006] In view of the above shortcomings of the prior art, the present application provides an intelligent medical record analysis and simulated diagnosis and treatment system for medical teaching, which can effectively solve the problems of the prior art.

[0007] To achieve the above object, the present application is realized by the following technical scheme;

[0008] The present application discloses an intelligent medical record analysis and simulated diagnosis and treatment system for medical teaching, comprising:

[0009] A cloud database is used to upload patient diagnosis and treatment cases and store the patient diagnosis and treatment cases; a selection module is used to select patient diagnosis and treatment cases in the cloud database and select the diagnosis and treatment cases as the simulated diagnosis and treatment cases; an editing module is used to obtain the simulated diagnosis and treatment cases selected by the selection module, read the diagnosis logic and drug details based on the simulated diagnosis and treatment cases, and manually edit the diagnosis logic and drug details; an evaluation module is used to receive the edited diagnosis logic and drug details in the editing module, compare the received diagnosis logic and drug details with the diagnosis logic and drug details contained in the simulated diagnosis and treatment cases, and evaluate the simulated diagnosis and treatment scores of the users who edit the diagnosis logic and drug details; a classification unit is used to obtain the historical evaluation results of the simulated diagnosis and treatment scores of the users in the evaluation module, and classify the users based on the historical evaluation results. Furthermore, the patient diagnosis and treatment cases uploaded in the cloud database come from any system authorized terminal user, and the patient diagnosis and treatment cases are all standard cases with successful patient recovery. The cloud database is further provided with a filtering unit and a management unit. The filtering unit is used to traverse the patient diagnosis and treatment cases uploaded in the cloud database, and clean the low-value cases in the uploaded patient diagnosis and treatment cases. The management unit is used to receive the patient diagnosis and treatment cases after cleaning, distinguish the patient diagnosis and treatment cases based on the department to which the patient diagnosis and treatment cases belong, and further store the patient diagnosis and treatment cases based on the distinguishing results of the patient diagnosis and treatment cases.

[0010] The format of the patient diagnosis and treatment case is text and image, and the content of the patient diagnosis and treatment case includes disease description, diagnosis logic and drug details.

[0011] Furthermore, the determination of the low-value cases of the patient diagnosis and treatment cases in the filtering unit is subject to:

[0012]

[0013] In the formula: SIMM(A, B) is the similarity of the patient diagnosis and treatment case A and the patient diagnosis and treatment case B.

[0014] Reconstruc tionCost(GA ,G B ) is a semantic reconstruction cost; ω is a weight; is the average of the similarity of the image data contained in patient diagnosis case A and patient diagnosis case B, respectively;

[0015] wherein the similarity between each patient diagnosis case is calculated based on the above formula, the patient diagnosis case cleaning target pickup threshold is defined by the system end user, and any one of the two patient diagnosis cases greater than or equal to the patient diagnosis case cleaning target pickup threshold is taken as a deletion target to perform a deletion operation, so as to complete the cleaning of the patient diagnosis case, and ω ∈ (0, 1).

[0016] Further, when any one of the two patient diagnosis cases performing the similarity calculation does not contain image data, the calculation formula of SIMM(A, B) is transformed as

[0017] That is, only the semantic similarity is considered in the similarity calculation process.

[0018] Further, the value logic of the semantic reconstruction cost Reconstruc tionCost(G A ,G B ) is:

[0019] Let the semantic topology graphs corresponding to patient diagnosis case A and patient diagnosis case B be G A (V A ,E A ), G B (V B ,E B ), respectively, wherein V is a semantic node set, E is a semantic relationship edge set, G A (V A ,E A ), G B (V B ,E B ) are abbreviated as G A , G B ; the semantic topology graph construction logic is: using dependency syntax analysis and semantic role labeling, the patient diagnosis case is split into semantic atomic units as nodes V, the directed edges E are constructed according to the semantic relationship type, and the relationship weight of each edge is marked;

[0020] The optimal matching between the nodes of G A , G B is found by using the Hungarian algorithm, the semantic difference of the nodes is minimized, and then the relationship difference of the corresponding edges of the matched node pairs is calculated;

[0021]

[0022] wherein: e A B is an edge in the semantic topology graph G A corresponding to text A, and an edge in the semantic topology graph G B corresponding to text B; Type(e A ), Type(e B ) are the semantic relation types of edges e A , e B ;

[0023] Similarity(Type(e A ), Type(e B )) is the similarity of Type(e A ), Type(e B );

[0024] The final ReconstructionCost(G A , G B ) is calculated as follows:

[0025]

[0026] wherein: (vA, vB) is an element consisting of the matched nodes v A , v B in G A , G B ;

[0027] Matchednodes is the optimal matching set between the nodes in G A , G B found by the Hungarian algorithm;

[0028] NodeCost(v A , v B ) is the semantic difference cost of nodes v A , v B , calculated based on the WordNet synonym set distance method; (e A , e B ) is an element consisting of the edges related to the matched nodes v A , v B in G A , G B ; MatchedEdges is the set of edges corresponding to the matched node pairs; EdgeCost(e A , e B ) is the relation difference cost of edges e A , e B , calculated based on the edge mapping cost calculation method.

[0029] ​Further, the selection module runs a stage in which a system user obtains permission to access the cloud database in the selection module, and in the cloud database, first selects a patient treatment case type based on the differentiated storage intervals, and then further selects a patient treatment case in the selected differentiated storage interval.

[0030] Further, the selection module is internally provided with a locking unit, which is used to lock the diagnosis logic and medication details contained in each patient treatment case in the differentiated storage interval during the stage in which the system user selects a patient treatment case in the differentiated storage interval, so that the locked part of the patient treatment case content is unreadable;

[0031] In which, after the system user selects a patient treatment case, the system user synchronously reads the readable part of the patient treatment case, i.e. the reading of the disease description content, and then applies the editing module to complete the editing of the diagnosis logic and medication details, and after the editing of the diagnosis logic and medication details is completed, the locking module reopens the reading permission of the locked diagnosis logic and medication details.

[0032] Further, the evaluation module is sub-provided with a recording unit, which is used to record the user's historical simulation diagnosis and treatment score; the evaluation module evaluates the simulation diagnosis and treatment score through the comparison of the diagnosis logic and the medication details, and the logic for evaluating the simulation diagnosis and treatment score is:

[0033] Taking the diagnosis logic and the medication details as the comparison targets respectively, the results are obtained based on the similarity calculation logic of the patient treatment case, so as to comprehensively evaluate the output simulation diagnosis and treatment score;

[0034] F=[SIMM logic (a,b)×λ+SIMM take (a,b)×(1-λ)]×ε;

[0035] In the formula, F is the simulation diagnosis and treatment score; SIMM logic (a,b) is the similarity between the diagnosis logic edited by the user and the diagnosis logic in the case to be simulated; SIMM take (a,b) is the similarity between the medication details edited by the user and the medication details in the case to be simulated; λ is a weight coefficient; and ε is a simulation diagnosis and treatment score conversion factor;

[0036] In which, the simulation diagnosis and treatment score conversion factor ε>0, and the weight coefficient λ satisfies λ<1-λ.

[0037] Further, the recording unit records the simulation diagnosis scores of the users based on the simulation diagnosis scores, and the classification unit obtains the historical evaluation results of the simulation diagnosis scores of the users from the recording unit, the classification unit sets a simulation diagnosis score threshold, obtains the latest simulation diagnosis score of each user from the recorded simulation diagnosis scores of the users, compares the latest simulation diagnosis score of each user with the simulation diagnosis score threshold, and classifies the users based on the comparison result.

[0038] Further, the cloud database is connected with a filtering unit and a management unit through a wireless network, the cloud database is connected with a selection module through a wireless network, the selection module is connected with a locking unit through a wireless network, the selection module is connected with an editing module and an evaluation module through a wireless network, the evaluation module is connected with a recording unit through a wireless network, the evaluation module is connected with a classification unit through a wireless network, and the classification unit is connected with the recording unit through a wireless network.

[0039] Compared with the prior art, the technical scheme provided by the application has the following beneficial effects:

[0040] The application provides an intelligent medical record analysis and simulation diagnosis system for medical teaching, which collects a large number of standard cases and successfully recovered cases, stores the cases after screening and classification, and provides a large amount of real and high-quality learning resources for medical teaching. Users can select the cases for simulation diagnosis, manually edit diagnosis logic and medication details, deepen the understanding and application of medical knowledge in practice, and compare the edited content with the real cases, give a simulation diagnosis score, and help users to identify their own shortcomings. Meanwhile, the system records the historical scores and classifies them, so as to facilitate the understanding of the progress track of the learners, and the learning achievements of the learners can be distinguished according to the set qualified determination threshold. This not only improves the pertinence of medical teaching and enables teachers to teach students according to their aptitude, but also effectively exercises the diagnosis thinking and practical ability of the learners, greatly improves the quality and efficiency of medical teaching, and helps the cultivation of medical talents. BRIEF DESCRIPTION OF DRAWINGS

[0041] In order to more clearly illustrate the technical scheme in the embodiments of the application or the prior art, the drawings needed in the following embodiment or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0042] Figure 1This is a schematic diagram of the structure of an intelligent medical record analysis and simulation diagnosis and treatment system for medical teaching. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0044] The present invention will be further described below with reference to embodiments.

[0045] Example:

[0046] This embodiment presents an intelligent medical record analysis and simulated diagnosis system for medical teaching, such as... Figure 1 As shown, it includes: a cloud database used to upload and store patient treatment cases;

[0047] The patient treatment cases uploaded to the cloud database originate from any authorized system terminal user. All patient treatment cases are standard and represent successful patient recovery stories. The cloud database has a filtering unit and a management unit. The filtering unit iterates through the uploaded patient treatment cases, cleaning low-value cases. The management unit receives the cleaned cases and categorizes them based on their department. The cloud database further categorizes and stores the cases based on these categorization results. The patient treatment cases are in text and image format, and their content includes: a description of the patient's condition, diagnostic logic, and medication details.

[0048] The low-value case determination for patient diagnosis and treatment cases in the filtering unit follows the following rules:

[0049]

[0050] In the formula: SIMM(A,B) represents the similarity between patient treatment case A and patient treatment case B;

[0051] ReconstructionCost(G A G B ) represents the semantic reconstruction cost; ω represents the weight; The mean similarity of image data contained in patient treatment case A and patient treatment case B respectively;

[0052] Wherein, the similarity between each patient diagnosis and treatment case is calculated based on the above formula, the patient diagnosis and treatment case cleaning target pickup threshold is defined by the system end user, and the deletion operation is performed on any one of the two patient diagnosis and treatment cases which are greater than or equal to the patient diagnosis and treatment case cleaning target pickup threshold as the deletion target, so as to complete the cleaning of the patient diagnosis and treatment case, ω∈(0,1);

[0053] When any one of the two patient diagnosis and treatment cases for similarity calculation does not contain image data,

[0054] The calculation formula of SIMM(A,B) is changed to

[0055] That is, the similarity calculation process only considers semantic similarity;

[0056] The value logic of semantic reconstruction cost ReconstructionCost(G A ,G B ) is:

[0057] Let the semantic topology graphs corresponding to patient diagnosis and treatment case A and patient diagnosis and treatment case B be G A (V A ,E A ), G B (V B ,E B ) respectively, wherein V is a semantic node set, E is a semantic relationship edge set, G A (V A ,E A ), G B (V B ,E B ) are abbreviated as G A , G B ; the semantic topology graph construction logic is: using dependency syntax analysis and semantic role labeling, the patient diagnosis and treatment case is split into semantic atomic units as nodes V, the directed edges E are constructed according to the semantic relationship type, and the relationship weight is marked for each edge;

[0058] The optimal matching between the nodes of G A , G B is found by the Hungarian algorithm, and the semantic difference of the nodes is minimized, and then the relationship difference of the corresponding edges of the matched node pairs is calculated;

[0059]

[0060] In the formula: e A , e B are edges in the semantic topology graph G A corresponding to text A and edges in the semantic topology graph G B corresponding to text B; Type(eA ), Type(e B ) is the semantic relation type of edge e A , e B ;

[0061] Similarity(Type(e A ), Type(e B )) is the similarity of Type(e A ), Type(e B );

[0062] Finally, the ReconstructionCost(G A , G B ) is calculated as:

[0063]

[0064] In the formula, (vA, vB) is the element composed of the matched nodes v A , v B in G A , G B ;

[0065] Matchednodes is the optimal matching set between the nodes of G A , G B found by the Hungarian algorithm;

[0066] NodeCost(v A , v B ) is the semantic difference cost of nodes v A , v B , which is calculated based on the WordNet synonym set distance method; (e A , e B ) is the element composed of the edges related to the matched nodes v A , v B in G A , G B ; MatchedEdges is the set of edges corresponding to the matched node pairs; EdgeCost(e A , e B ) is the relation difference cost of edges e A , e B , which is obtained based on the edge mapping cost calculation method;

[0067] Through the above logic and formula, it is ensured that the filtering unit can stably complete the cleaning of the patient diagnosis and treatment cases, so that the patient diagnosis and treatment cases retained in the cloud database are more valuable and can be applied to the system users.

[0068] The selection module is configured to select a patient treatment case in the cloud database, and the selected treatment case is used as a to-be-simulated diagnosis and treatment case.

[0069] The selection module is configured to select a patient treatment case in the cloud database, and the selected treatment case is used as a to-be-simulated diagnosis and treatment case.

[0070] The selection module is configured to select a patient treatment case in the cloud database, and the selected treatment case is used as a to-be-simulated diagnosis and treatment case.

[0071] The selection module is configured to select a patient treatment case in the cloud database, and the selected treatment case is used as a to-be-simulated diagnosis and treatment case.

[0072] The selection module is configured to select a patient treatment case in the cloud database, and the selected treatment case is used as a to-be-simulated diagnosis and treatment case.

[0073] The selection module is configured to select a patient treatment case in the cloud database, and the selected treatment case is used as a to-be-simulated diagnosis and treatment case.

[0074] The selection module is configured to select a patient treatment case in the cloud database, and the selected treatment case is used as a to-be-simulated diagnosis and treatment case.

[0075] The selection module is configured to select a patient treatment case in the cloud database, and the selected treatment case is used as a to-be-simulated diagnosis and treatment case.

[0076] The selection module is configured to select a patient treatment case in the cloud database, and the selected treatment case is used as a to-be-simulated diagnosis and treatment case.

[0077] F=[SIMM logic (a,b)×λ+SIMM take (a,b)×(1-λ)]×ε;

[0078] F is the simulation diagnosis and treatment score; SIMM logic (a,b) is the similarity of the diagnosis logic edited by the user and the diagnosis logic in the to-be-simulated diagnosis and treatment case; SIMM take(a, b) is the similarity between the medication details edited by the user and the medication details in the case to be simulated; λ is a weight coefficient; and ε is a simulation diagnosis score conversion factor;

[0079] wherein the simulation diagnosis score conversion factor ε > 0, and the weight coefficient λ satisfies λ < 1 - λ.

[0080] The simulation diagnosis score of the user is evaluated by the above logical formula, which provides support for the further operation of the modules of the system in this embodiment.

[0081] The record unit records the simulation diagnosis scores of the users based on the simulation diagnosis scores. When the classification unit obtains the historical evaluation results of the simulation diagnosis scores of the users, the record unit is accessed. The classification unit sets a simulation diagnosis score threshold at the running stage, obtains the latest simulation diagnosis score of each user from the simulation diagnosis scores of the users, and compares the simulation diagnosis score with the simulation diagnosis score threshold. Based on the comparison result with the simulation diagnosis score threshold, the simulation diagnosis score is classified, that is, the user is classified.

[0082] The classification unit is used to obtain the historical evaluation results of the simulation diagnosis scores of the users in the evaluation module, and classify the users based on the historical evaluation results.

[0083] The cloud database is connected with a filtering unit and a management unit through a wireless network, the cloud database is connected with a selection module through a wireless network, the selection module is connected with a locking unit through a wireless network, the selection module is connected with an editing module and an evaluation module through a wireless network, the evaluation module is connected with a recording unit through a wireless network, the evaluation module is connected with a classification unit through a wireless network, and the classification unit is connected with the recording unit through a wireless network. In the embodiment, the cloud database runs to upload patient diagnosis cases, stores the patient diagnosis cases, the filtering unit synchronously traverses the uploaded patient diagnosis cases in the cloud database, cleans low-value cases in the uploaded patient diagnosis cases, the management unit receives the cleaned patient diagnosis cases in real time, distinguishes the patient diagnosis cases based on the department to which the patient diagnosis cases belong, the cloud database further distinguishes and stores the patient diagnosis cases based on the distinguishing result of the patient diagnosis cases, the selection module runs in the cloud database to select patient diagnosis cases, the selected diagnosis cases are used as to-be-simulated diagnosis cases, the locking unit is synchronized with the system user to select the patient diagnosis cases in the distinguished storage interval, locks the diagnosis logic and the medication details contained in each patient diagnosis case in the distinguished storage interval, makes the locked patient diagnosis case content part unreadable, the editing module obtains the to-be-simulated diagnosis case selected by the selection module, manually edits the diagnosis logic and the medication details based on the to-be-simulated diagnosis case, the evaluation module receives the edited diagnosis logic and the medication details in the editing module, compares the received diagnosis logic and the medication details with the diagnosis logic and the medication details contained in the to-be-simulated diagnosis case, evaluates the simulation diagnosis score of the user who edits the diagnosis logic and the medication details, the recording unit synchronously records the historical simulation diagnosis score of the user, and finally the classification unit obtains the historical evaluation result of the simulation diagnosis score of the user in the evaluation module, and classifies the user based on the historical evaluation result.

[0084] Through the system in the above embodiment, an online diagnosis experience accumulation way is provided for interns, so that the interns can accumulate diagnosis experience faster and put it into the diagnosis work.

[0085] To sum up, in the running process of the system in the above embodiments, a large number of standard cases and patient successful recovery cases are collected, filtered and classified for storage, thereby providing a large amount of real and high-quality learning resources for medical teaching. Users can select and perform simulated diagnosis and treatment from these cases, manually edit diagnosis logic and medication details, deepen the understanding and use of medical knowledge in practice, and the system will compare the edited content with the real cases, give a simulated diagnosis and treatment score, help users to identify their own shortcomings, at the same time, the system will also record the historical scores and classify them, so as to understand the progress trajectory of the learners. According to the set qualified judgment threshold, the learning achievements of the learners can be distinguished. This not only improves the pertinence of medical teaching and enables teachers to teach students in accordance with their aptitude, but also effectively exercises the diagnosis and treatment thinking and practical ability of the learners, greatly improves the quality and efficiency of medical teaching, and helps the cultivation of medical talents.

[0086] The above embodiments are only used to illustrate the technical solutions of the present application, but not limit it; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements will not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A medical teaching-oriented intelligent medical record analysis and simulated diagnosis and treatment system, characterized in that, The application relates to a cloud database for uploading patient treatment cases and storing the patient treatment cases. The patient treatment cases uploaded in the cloud database are from any system authorized terminal user, and the patient treatment cases are all standard cases with successful patient recovery; the cloud database is provided with a filtering unit and a management unit; the filtering unit is used for traversing the patient treatment cases uploaded in the cloud database, cleaning low-value cases in the uploaded patient treatment cases, the management unit is used for receiving the cleaned patient treatment cases, distinguishing the patient treatment cases based on the department to which the patient treatment cases belong, and further distinguishing and storing the patient treatment cases based on the distinguishing result of the patient treatment cases. The format of the patient treatment cases is text and image, and the content of the patient treatment cases comprises disease description, diagnosis logic and drug details. The filtering unit is subjected to the following low-value case judgment of the patient treatment cases: A selection module is used for selecting patient treatment cases in the cloud database, and the selected treatment cases are used as to-be-simulated diagnosis and treatment cases; ； In the formula: is a similarity of patient diagnosis and treatment case A and patient diagnosis and treatment case B; is a semantic reconstruction cost; is a weight; is an average of image data similarity that patient diagnosis and treatment case A and patient diagnosis and treatment case B each contain. The similarity between each patient diagnosis and treatment case is calculated based on the above formula, a patient diagnosis and treatment case cleaning target pickup threshold is defined by a system end user, and a deletion operation is performed on any one of the two patient diagnosis and treatment cases that are greater than or equal to the patient diagnosis and treatment case cleaning target pickup threshold as a deletion target, so as to complete the cleaning of the patient diagnosis and treatment case. ∈(0, 1); An editing module is used for obtaining the to-be-simulated diagnosis and treatment cases selected by the selection module, reading the to-be-simulated diagnosis and treatment cases, and manually editing diagnosis logic and drug details; An evaluation module is used for receiving the edited diagnosis logic and drug details in the editing module, comparing the received diagnosis logic and drug details with the diagnosis logic and drug details contained in the to-be-simulated diagnosis and treatment cases, and evaluating the simulation diagnosis and treatment score of the editing source user of the diagnosis logic and drug details; A classification unit is used for obtaining historical evaluation results of the simulation diagnosis and treatment score of the user in the evaluation module, and classifying the user based on the historical evaluation results. The semantic topology graph construction logic is that the patient treatment cases are split into semantic atomic units as nodes V by using dependency syntax analysis and semantic role labeling, directed edges E are constructed according to the semantic relationship type, and the relationship weight of each edge is marked; 2. The intelligent medical record analysis and simulated diagnosis and treatment system for medical teaching according to claim 1, characterized in that, when any one of the two patient diagnosis and treatment cases performing the similarity calculation does not contain image data, the calculation formula is transformed as that is, the similarity calculation process only considers semantic similarity. 3.The medical teaching-oriented intelligent medical record analysis and simulated diagnosis and treatment system according to claim 1, characterized in that, the semantic reconstruction cost The value logic is: The semantic topology graph corresponding to patient diagnosis case A and patient diagnosis case B is respectively , wherein V is a semantic node set, E is a semantic relationship edge set, , wherein V is a semantic node set, E is a semantic relationship edge set, ; In the selection module running stage, the system user obtains permission to access the cloud database in the selection module, first selects the type of the patient treatment cases in the cloud database based on the distinguished storage interval, and then further selects the patient treatment cases in the selected distinguished storage interval. The optimal matching between nodes is found by Hungarian algorithm The semantic difference between nodes is minimized, and for the matched node pair, the relationship difference of the corresponding edge is calculated; ； In the formula: is the semantic topology graph corresponding to text A is the semantic topology graph corresponding to text B is the edge in the semantic topology graph is the edge is the semantic relation type of the edge is the semantic relation type of the edge is the similarity between the two Final calculation : ； In the formula: is The nodes matched in the element composed of respective edges; is the optimal matching set between nodes found by the Hungarian algorithm is the semantic difference cost of the node is the node , calculated based on the WordNet synonym set distance method; is The nodes matched in the element composed of respective edges; is the set of edges corresponding to the matched node pair; is the relationship difference cost of the edge , derived based on the edge mapping cost calculation method.

4. The intelligent medical teaching case analysis and simulated diagnosis and treatment system according to claim 1, wherein, The selection module is internally provided with a locking unit, the locking unit is used for locking the diagnosis logic and drug details contained in each patient treatment case in the distinguished storage interval when the system user selects the patient treatment case in the distinguished storage interval, and the locked part of the patient treatment case content is unreadable; 5. The intelligent medical teaching case analysis and simulated diagnosis and treatment system according to claim 1, wherein, After the system user selects the patient treatment case, the readable part of the patient treatment case is read synchronously, that is, the disease description content is read, the editing module is applied to complete the editing of the diagnosis logic and drug details, and after the editing of the diagnosis logic and drug details is completed, the locking module reopens the reading permission of the locked diagnosis logic and drug details. The evaluation module is provided with a recording unit, the recording unit is used for recording the historical simulation diagnosis and treatment score of the user; 6. The intelligent medical teaching case analysis and simulated diagnosis and treatment system according to claim 1, wherein, The evaluation module is provided with a recording unit, the recording unit is used for recording the historical simulation diagnosis and treatment score of the user; ​ The diagnostic logic and the medication details are respectively taken as the comparison targets, and the similarity calculation logic based on the patient diagnosis and treatment cases is respectively used to obtain the results, so as to comprehensively evaluate the simulation diagnosis and treatment score; ； In the formula: is the simulation diagnosis score; is the similarity between the user-edited diagnosis logic and the diagnosis logic in the case to be simulated; is the similarity between the user-edited medication details and the medication details in the case to be simulated; is the weight coefficient; is the simulation diagnosis score conversion factor; Wherein the simulation diagnosis and treatment score conversion factor > 0, the weight coefficient Subject to < .

7. The intelligent medical teaching case analysis and simulated diagnosis and treatment system according to claim 6, wherein, The record unit records the simulation diagnosis and treatment scores of the users based on the simulation diagnosis and treatment scores, and the classification unit obtains the simulation diagnosis and treatment score history evaluation results in the record unit. The classification unit sets the simulation diagnosis and treatment score threshold value, obtains the latest simulation diagnosis and treatment score of each user from the simulation diagnosis and treatment scores of the users, and compares the simulation diagnosis and treatment score threshold value. Based on the comparison result of the simulation diagnosis and treatment score threshold value, the simulation diagnosis and treatment score is classified, that is, the user is classified.

8. The intelligent medical teaching case analysis and simulated diagnosis and treatment system according to claim 1, wherein, The cloud database is connected with the filtering unit and the management unit through the wireless network interaction, the cloud database is connected with the selection module through the wireless network interaction, the selection module is connected with the locking unit through the wireless network interaction, the selection module is connected with the editing module and the evaluation module through the wireless network interaction, the evaluation module is connected with the record unit through the wireless network interaction, the evaluation module is connected with the classification unit through the wireless network interaction, and the classification unit is connected with the record unit through the wireless network interaction.

Images