Intelligent electronic medical record generation management system and method, terminal and medium

Abstract

The invention discloses an intelligent electronic medical record generation management system and method, a terminal and a medium. The generation management system comprises a data acquisition module, a template generation module, an intelligent prompt module, an editing and saving module, a data security protection module and a permission retrieval recording module. The generation management method comprises the following steps: performing identity permission verification; integrating to form multi-modal structured data, and screening and matching to generate a template framework; a diagnosis suggestion sorting table is generated, and data is stored and backed up; transmitting and storing data, and recording operation behavior data. According to the invention, real-time automatic acquisition of basic information and examination results of patients is realized; a medical record template is automatically matched and optimized based on disease characteristics of a patient and an examination result, so that the workload of a doctor is reduced, and the medical record structure conforms to clinical specifications; transmission and storage data are encrypted in a layered mode, current account information operation behavior data are recorded based on a timestamp, and safe storage and real-time management of medical record data are effectively ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic medical record data management, and in particular to an intelligent electronic medical record generation and management system, method, terminal and medium. Background Art

[0002] An electronic medical record (EMR), also known as a computerized medical record system or computer-based patient record (CPR), is a digital medical record stored, managed, transmitted, and reproduced using electronic devices (computers, health cards, etc.), replacing handwritten paper medical records. It contains all the information in a paper medical record and is an electronic record of the patient's medical history based on a specific system. This system provides users with access to complete and accurate data, alerts, reminders, and clinical decision support systems.

[0003] When using the existing electronic medical record clinical data verification system, due to the lack of unified interfaces among various systems within the hospital, it is difficult and inefficient to integrate different patient data information for systems such as the Hospital Information System (HIS), Laboratory Information System (LIS), and Picture Archiving and Communication Systems (PACS). Doctors need to spend a lot of time filling out duplicate content, and it is difficult to effectively associate text, voice, image and other information, which can easily lead to conflicts between text and images. Once a system failure or human error occurs, it is very easy to cause the loss of medical record data. Summary of the Invention

[0004] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an intelligent electronic medical record generation and management system, method, terminal and medium.

[0006] To achieve the above objectives, in a first aspect, the present invention provides an intelligent electronic medical record generation and management system, comprising:

[0007] The data acquisition module is used to connect the patient information input device and the hospital data system, transmit the examination result data and medical record information data entered into the hospital database system, obtain the input voice text data and image data collected by the patient information input device, and integrate them into multimodal structured data;

[0008] The template generation module is used to read the entered medical record information data and examination result data, and to generate a basic medical record template by screening the preset medical record template library based on the disease type, severity of the disease and patient characteristics;

[0009] An intelligent prompt module is used to assist in analyzing medical records and examination results. It generates a ranking table of diagnostic suggestions based on probability values based on artificial intelligence algorithms and medical knowledge graphs, recommends personalized treatment plans based on clinical guidelines, and monitors and prompts in real time whether key information is missing and / or logical errors are present.

[0010] The editing and saving module is used to generate a multimodal information entry and editing interface, obtain an editing completion signal, submit and back up medical record information data, and detect hardware status data and / or virus attack data in real time;

[0011] Data security protection module, used to run data encryption algorithm to transmit and store medical record information data and examination result data, and record operation behavior data based on role access permission matrix and timestamp;

[0012] The permission retrieval record module is used to store the access permissions corresponding to the account role and the operation behavior data corresponding to the record timestamp.

[0013] In a second aspect, the present invention further provides an intelligent electronic medical record generation and management method, which is executed by the intelligent electronic medical record generation and management system as described in the first aspect. The generation and management method includes:

[0014] S100, performing identity verification based on the input account information data and reading the test data information security;

[0015] S200, obtaining the input and read medical record information data and integrating them to form multimodal structured data, screening and matching to generate a standardized medical record basic template framework;

[0016] S300 assists in analyzing multimodal structured data to generate a diagnostic suggestion ranking table, and saves and backs up the edited electronic medical record information data;

[0017] S400, encrypts the transmission and storage of electronic medical record information data, and records the current account information operation behavior data.

[0018] In some embodiments, the S100 includes:

[0019] S110, obtaining the input account and password information data, searching for matching account roles, and verifying whether the passwords are consistent;

[0020] S120, if the password is entered incorrectly and exceeds a preset number of times, the system is locked and an alarm signal is sent; if the password is entered correctly, a multimodal information entry and editing interface is generated;

[0021] S130, generating a multimodal information input and editing interface, connecting to the consultation information input device and the hospital data system.

[0022] In some embodiments, the S200 includes:

[0023] S210, transmitting and acquiring the input data information, and integrating it to form multimodal structured data;

[0024] S220, based on the disease type, severity of the disease and patient characteristics, the preset medical record template library is screened, and after matching is completed, a standardized medical record basic template template framework is adjusted to generate.

[0025] In some embodiments, the S210 includes:

[0026] S211, transmitting the examination result data and medical record information data entered into the hospital database system;

[0027] S212, obtaining input voice text data and image data collected by the consultation information input device;

[0028] S213, after automatic segmentation by medical record chapter, feature-level association is performed, aligned with the time axis in the hospital database system, and integrated to form multimodal structured data.

[0029] In some embodiments, the S300 includes:

[0030] S310 assists in analyzing medical records and examination results data, generates a ranking table of diagnostic recommendations based on probability values based on artificial intelligence algorithms and medical knowledge graphs, recommends personalized treatment plans in conjunction with clinical guidelines, and monitors and prompts for omissions of key information and / or logical errors;

[0031] S320, saving and backing up the edited electronic medical record information data.

[0032] In some embodiments, the S310 includes:

[0033] S311, assists in analyzing medical records and examination result data to extract patient symptom keywords, matches similar medical records in the medical knowledge graph based on artificial intelligence algorithms, and calculates the confidence probability of different diagnoses;

[0034] S312: Associate patient physiological monitoring data and assess the risk level of treatment options, generate a diagnostic recommendation ranking table, retrieve clinical guidelines to recommend personalized treatment options, and mark the evidence level of evidence-based medicine and the corresponding guideline location;

[0035] S313, based on the user account role access rights, monitor the progress of filling in the medical record information, and provide graded prompts for omissions and logical errors.

[0036] In some embodiments, the S400 includes:

[0037] S410, encrypting and transmitting the electronic medical record information data using a hybrid encryption algorithm, and distributing and storing the electronic medical record information data based on the electronic medical record information data structure;

[0038] S420, recording the current account information operation behavior data based on the timestamp, and monitoring abnormal operation behavior data.

[0039] In a third aspect, the present invention also provides a computer-readable storage medium storing a computer program for running a resource management and release method, wherein the computer program enables a computer to execute a resource management and release method as described in any one of the above technical solutions.

[0040] In a fourth aspect, the present invention further provides an electronic device, comprising:

[0041] one or more processors; memory; and

[0042] One or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the programs include a method for executing resource management and release as described in any one of the above technical solutions.

[0043] The present invention has the following beneficial effects:

[0044] 1. The present invention can automatically connect the patient information input device and the hospital data system to realize the real-time automatic collection of patients' basic information and examination results, effectively solving the inefficiency of traditional manual entry. It can automatically match and optimize medical record templates based on patients' disease characteristics and examination results, reducing doctors' workload while ensuring that the medical record structure complies with clinical standards.

[0045] 2. The present invention can intelligently combine medical knowledge graphs and real-time data analysis to provide diagnostic suggestions and evidence-based treatment plan recommendations sorted by probability. It can also automatically monitor abnormal input of key fields during the medical record writing process and provide graded prompts for omissions and logical errors, effectively reducing the risk of missed diagnosis or misdiagnosis.

[0046] 3. The present invention adopts hybrid encryption technology to perform layered encryption on the transmitted and stored data, records the current account information operation behavior data based on the timestamp, and monitors abnormal operation behavior data, which can ensure the safe storage and real-time management of medical record data. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 The system principle of the intelligent electronic medical record generation and management system proposed by this invention Figure 1 ;

[0048] Figure 2 The system principle of the intelligent electronic medical record generation and management system proposed by this invention Figure 2 ;

[0049] Figure 3 This is a schematic diagram of the process of the intelligent electronic medical record generation and management system proposed by the present invention Figure 1 ;

[0050] Figure 4 This is a schematic diagram of the process of the intelligent electronic medical record generation and management system proposed by the present invention Figure 2 ;

[0051] Figure 5 This is a schematic diagram of the process of the intelligent electronic medical record generation and management system proposed by the present invention Figure 3 ;

[0052] Figure 6 This is a schematic diagram of the process of the intelligent electronic medical record generation and management system proposed by the present invention Figure 4 ;

[0053] Figure 7 This is a schematic diagram of the process of the intelligent electronic medical record generation and management system proposed by the present invention Figure 5 ;

[0054] Figure 8 This is a schematic diagram of the process of the intelligent electronic medical record generation and management system proposed by the present invention Figure 6 ;

[0055] Figure 9 This is a schematic diagram of the process of the intelligent electronic medical record generation and management system proposed by the present invention Figure 7 .

[0056] Legend:

[0057] 1. Data collection module; 2. Template generation module; 3. Intelligent prompt module; 4. Editing and saving module; 5. Data security protection module; 6. Permission retrieval and record module. DETAILED DESCRIPTION

[0058] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0059] The embodiments of the present application provide an intelligent electronic medical record generation and management system, method, terminal and medium, which solve the problem XX in the prior art. The present application XX.

[0060] Please refer to the following examples for details:

[0061] Reference Figure 1-Figure 2 The present invention provides an embodiment of an intelligent electronic medical record generation and management system, the specific structure of which includes:

[0062] (1) Data acquisition module 1, used to connect the patient information input device and the hospital data system, transmit the examination result data and medical record information data entered into the hospital database system, obtain the input voice text data and image data collected by the patient information input device, and integrate them to form multimodal structured data;

[0063] For example, as the data entry point for the medical system, this module develops interface protocols based on standards such as HL7 FHIR to achieve docking and integration to form multimodal structured data. After accepting basic patient information (automatic mapping of key fields such as name, age, gender, contact information, and allergy history), it simultaneously connects to local hospital data systems such as laboratory test data (LIS), imaging reports (PACS), and physiological monitoring waveforms. Subsequently, through data cleaning and normalization, heterogeneous data (such as XML reports from LIS and DICOM images from PACS) are converted into a unified format (such as JSON format), and units, reference ranges, and abnormality markers (for example, abnormal hemoglobin values are marked as "↓") are annotated to ensure data computability. Ultimately, data is automatically collected and aggregated to ensure data timeliness and accuracy. For unstructured data such as imaging reports and text medical records, optical character recognition (OCR) is used to extract key fields (for example, "pulmonary nodule diameter 5mm" in a CT report), and natural language processing (NLP) technology is used to parse semantics (for example, "apical systolic murmur" is converted into structured fields) to achieve semi-automatic data filling.

[0064] During the doctor's examination and filling of medical records, the doctor's oral content can be transcribed in real time through voice input devices (such as microphones, etc.). After the voice generates text, it is reviewed and manually modified by users with corresponding permissions (such as attending physicians, etc.): by loading the language database, it supports Chinese / foreign language mixed input and dialect adaptation, and the attending physician can use the microphone to record while examining. The system generates text in real time and associates it with medical record fields (such as "chief complaint" and "physical examination"). It supports one-click correction of transcription errors (such as misidentified drug names) on the interactive interface, and the corrected data is synchronized back to the database for subsequent learning optimization;

[0065] In addition, it can also support the simultaneous uploading of images (such as photos of skin lesions and endoscopic videos) from other input devices (such as cameras and other shooting devices), forming a unified integration of structured and unstructured data: it supports uploading of image data such as photos of skin lesions and surgical videos through cameras, endoscopes and other devices, and uses convolutional neural networks (CNN) to automatically classify images (such as psoriasis and eczema identification), and dynamically associate them with medical record fields (such as "skin lesion description"); endoscopic videos automatically capture key frames (such as ulcer sites) and match voice descriptions through timestamps (for example, "bleeding spots can be seen here" corresponds to the 30th second of the video).

[0066] It is understandable that voice input reduces manual input time by 70%, automatic image classification reduces manual labeling workload by 60%, and the error rate drops from 15% of traditional manual input to below 0.5%, realizing full-process automated processing from raw data to structured knowledge, laying a high-quality data foundation for subsequent intelligent diagnosis and medical record generation.

[0067] (2) Template generation module 2, which is used to read the entered medical record information data and examination result data, and to generate a basic medical record template template by matching the preset medical record template library based on the disease type, severity of the disease and patient characteristics;

[0068] For example, this module automates the entire process from standardized template matching to personalized framework optimization by integrating medical knowledge graphs, dynamic rule engines, and patient individualized data: the template library constructs a three-level classification system based on disease ICD-10 codes, Charlson Comorbidity Index (CCI), and patient characteristics (e.g., age, gender, and genotype);

[0069] Correspondingly, the system is first designed for common diseases such as pneumonia and diabetes (including standard diagnostic processes, mandatory examination items, and treatment plans). The content complexity is dynamically adjusted based on multiple indicator data (for example, a multidisciplinary consultation module is automatically inserted for critically ill patients). Prompts are provided based on hidden contraindication fields such as allergy history and liver and kidney function status (for example, nephrotoxic drug options are automatically filtered out for patients with renal insufficiency). Authoritative guideline libraries such as NCCN (National Comprehensive Cancer Network) and UpToDate are connected through APIs. When the template content conflicts with the latest clinical evidence (for example, when chemotherapy regimens are updated), template revision suggestions are automatically pushed.

[0070] Then, intelligent analysis algorithms (such as the random forest algorithm) can be used to analyze patient data (such as laboratory abnormalities and imaging lesion size) and calculate weights for features such as disease type and complication risk (for example, a malignant tumor feature weight of 0.8 prioritizes triggering tumor-specific templates).

[0071] Finally, a drag-and-drop interface is provided to support doctors to freely adjust the order of fields and preview the effects in real time. A historical version will be generated for each modification, supporting difference comparison and one-click rollback (to avoid template invalidation due to incorrect operation), and built-in "Basic Specifications for Medical Record Writing" verification rules. If a core paragraph is missing (for example, the "Preoperative Discussion Record" does not have the surgeon's signature filled in), the system will block submission and highlight the prompt.

[0072] It is understandable that the dynamic rule library not only complies with clinical guidelines but also meets individualized diagnosis and treatment needs, thus achieving a balance between standardization and personalization; at the same time, logical consistency can be verified in real time (such as inspection results and diagnosis conflict warnings), and doctors' customized templates can be submitted to the expert committee for review and included in the template library for sharing throughout the hospital, serving as an intelligent bridge connecting clinical data and diagnosis and treatment decisions, and promoting the standardization of diagnosis and treatment experience.

[0073] (3) Intelligent prompt module 3, used to assist in analyzing medical record information data and examination result data, generate a diagnosis suggestion ranking table according to probability values based on artificial intelligence algorithms and medical knowledge graphs, recommend personalized treatment plans in combination with clinical guidelines, and monitor and prompt in real time the omission of key information and / or logical errors;

[0074] For example, this module integrates UpToDate clinical guidelines, PubMed literature, and hospital historical medical records to establish a four-tuple relationship of disease-symptom-examination-treatment (for example, "pneumonia → fever → chest CT → antibiotics") to build a medical knowledge graph. It uses probabilistic reasoning algorithms (such as Bayesian networks) to calculate the joint probability distribution of symptoms (such as cough, fever, etc.) and examination results (such as CT ground-glass opacity, elevated CRP), outputs a diagnosis list with confidence annotations (such as pneumonia 85%, tuberculosis 10%), and dynamically adjusts the model weights in combination with real-time feedback data (such as pathological biopsy results) to improve diagnostic accuracy.

[0075] Then, through the integrated FDA drug database, contraindications (e.g., penicillin allergy indicates the risk of cephalosporins), drug-drug interactions (DDIs), and dosage adjustment rules (e.g., vancomycin dose for patients with renal insufficiency = 15 mg / kg × eGFR / 50) are annotated. Reinforcement learning (RL) is used to optimize treatment strategies (e.g., for patients with EGFR-mutated lung cancer, osimertinib is recommended over traditional chemotherapy, and comparative data such as 5-year survival rate and side effect incidence are presented using Sankey diagrams).

[0076] Then, during the filling process, semantic analysis and logical verification are used to intercept key information omissions (such as an unfilled allergy history) and data inconsistencies (such as "denying a history of diabetes" but abnormal blood sugar levels) in real time, reducing the rate of medical errors. Natural language processing (NLP) technology is used to parse medical record texts, identify logical contradictions (such as mandatory verification of the integrity of core fields, including the surgeon's signature in surgical records), and block medical record submission if the standards are not met (for example, when a doctor enters "cefotaxime", the patient's allergy history database is automatically searched. If there is a record of penicillin allergy, a "cross-allergy risk ≥ 10%" prompt will be displayed.

[0077] It is understandable that by combining the structural dimension (diagnostic process), content dimension (examination data) and interaction dimension (doctor feedback), dynamic prompt strategies are generated (such as highlighting unfinished required items), and a closed-loop quality control system from data to decision-making is constructed, which significantly improves medical quality and safety.

[0078] (4) Editing and saving module 4, used to generate a multimodal information entry and editing interface, obtain an editing completion signal, submit and back up medical record information data, and detect hardware status data and / or virus attack data in real time;

[0079] Exemplarily, the module supports mixed editing of multimodal data such as text, pictures, charts, voice annotations, and medical images (DICOM) (for example, integrating Quill.js or Slate.js frameworks, supporting Markdown syntax rapid typesetting and insertion of medical symbol libraries);

[0080] Combining the dual mechanisms of scheduled saving and event-triggered saving, it balances data security and system performance: the data modification status is automatically detected according to a preset time (for example, 3 minutes), and if it is true, an incremental backup is made to the local database; when the doctor clicks the "Save" button, the entire data is submitted to the cloud, and an operation log (including timestamp and user account information) is generated simultaneously; in the event of an abnormal exit, an emergency cache recovery mechanism is activated, automatically loading the most recently saved draft, and each save generates an independent version number, supporting historical version comparison and one-click rollback (differences are highlighted);

[0081] (5) Data security protection module 5, used to run data encryption algorithm to transmit and store medical record information data and examination result data, and record operation behavior data based on role access permission matrix and time stamp;

[0082] For example, the module prevents data leakage and physical failure risks through layered encryption and hardware status monitoring (for example, the transport layer adopts the national secret SM4 algorithm, and the storage layer uses the AES-256-GCM mode to encrypt medical records; the key is hosted by the hardware security module and biometrics); monitors hard disk indicators (such as remaining life and number of bad sectors) in real time, and automatically migrates data to spare nodes when the probability of failure is high or when it is attacked by a network.

[0083] In addition, based on the role-based access control (RBAC) and attribute-based access control (ABAC) models, field-level permission control and real-time permission recovery are implemented: the role permission matrix includes nurses and managers. Doctors can read and write diagnostic reports and examination results, but are prohibited from deleting medical records; nurses can only view nursing records and the execution status of medical orders; managers have data export permissions, but require multi-factor authentication (such as SMS verification code plus dynamic token and other verification operations); adopt dynamic permission strategies (for example, when an intern sees a patient for the first time, only the editing permission of the "current medical history" field is open, and after the attending physician reviews and approves it, advanced permissions such as "treatment plan" are gradually opened) and permissions are dynamically adjusted in combination with time, location, and device type (for example, when a doctor accesses the system from a non-hospital IP address, sensitive fields such as the patient's ID number are automatically hidden).

[0084] Finally, all operation behaviors are recorded (including timestamp, user ID, and access data range), and blockchain technology is used to store evidence on the chain to prevent medical records from being tampered with.

[0085] (6) a permission retrieval recording module 6, which is used to store the access rights corresponding to the account role and the operation behavior data corresponding to the recording timestamp;

[0086] Exemplarily, the module adopts a five-table association model (user table, role table, permission table, user-role association table, role-permission association table), supports dynamic permission allocation and real-time updates (for example, when an administrator modifies the permission of a role, the system synchronously updates the association table through the transaction mechanism to ensure data consistency); generates an independent version number for each permission change, stores the permission differences before and after the change, supports historical version backtracking and permission status comparison; sets independent permission labels for sensitive data (such as patient privacy fields), and supports field-granular access control.

[0087] Reference Figure 3-9 The present invention further provides an embodiment of an intelligent electronic medical record generation and management method, which is executed by the intelligent electronic medical record generation and management system in the above embodiment. The generation and management method includes:

[0088] S100, performing identity verification based on the input account information data and reading the test data information security;

[0089] S200, obtaining the input and read medical record information data and integrating them to form multimodal structured data, screening and matching to generate a standardized medical record basic template framework;

[0090] S300 assists in analyzing multimodal structured data to generate a diagnostic suggestion ranking table, and saves and backs up the edited electronic medical record information data;

[0091] S400, encrypts the transmission and storage of electronic medical record information data, and records the current account information operation behavior data.

[0092] It is understandable that in the identity and authority verification and security detection stage, the system verifies the doctor's identity through a multiple authentication mechanism, uses a permission model to accurately control field-level access rights, and automatically locks the account and triggers an alarm when the password error exceeds the preset number of times; after the verification is passed, the system dynamically generates a multimodal interface that supports mixed editing of voice, text, and images; in the multimodal data integration link, the system collects medical record information data in real time through the message queue, performs timeline alignment and structured integration; then intelligently matches the standardized medical record basic template template framework from the template library; in the intelligent auxiliary diagnosis stage, by analyzing multimodal structured data, a diagnostic suggestion ranking table is generated, and the edited electronic medical record information data is saved and backed up; finally, in the secure storage and audit link, a layered encryption strategy is used to encrypt and store electronic medical record information data, and record current account information operation behavior data.

[0093] Please continue reading Figure 4-Figure 9 In this embodiment, S100 includes:

[0094] S110, obtaining the input account and password information data, searching for matching account roles, and verifying whether the passwords are consistent;

[0095] S120, if the password is entered incorrectly and exceeds a preset number of times, the system is locked and an alarm signal is sent. If the password is entered correctly, a multi-modal information entry and editing interface is generated.

[0096] S130, generating a multimodal information input and editing interface, connecting to the consultation information input device and the hospital data system.

[0097] For example, first, through the two-factor authentication of dynamic password (OTP) and static password, combined with the RBAC (role-based access control) model, the user's input account password is verified in multiple dimensions: the Pydantic model is used for type conversion and constraint checking, and the password length (10-128 characters) and format compliance are verified; the user role permission matrix is dynamically loaded (for example, the attending physician can access the complete medical record, while the intern can only view the basic fields); the password hash is stored using the national secret SM3 algorithm, and sensitive data is encapsulated using the SecretStr type to prevent the leakage of plaintext passwords in logs;

[0098] Subsequently, intelligent risk control rules are set up to deal with abnormal login behaviors: three consecutive input errors will trigger account lock, and SMS alerts will be simultaneously pushed to the hospital information department security center; through IP geographic location analysis (visits from unfamiliar cities), time window detection (logging in during non-working hours) and other strategies, suspected brute force hacking behaviors are blocked in real time; after verification, the system generates a differentiated editing interface based on the user role.

[0099] Then, a heterogeneous data fusion channel is built to achieve efficient integration of multi-source information: it supports the HL7 / FHIR standard to connect to the hospital system, and synchronizes test reports and captured images in real time; it extracts keywords by real-time transcription of the doctor's oral content to automatically fill in the medical record fields; and it uses timestamps to connect test data, vital sign waveforms and text records to build a spatiotemporal map of patient diagnosis and treatment.

[0100] Please continue reading Figure 4-Figure 9 In this embodiment, S200 includes:

[0101] S210, transmitting and acquiring the input data information, and integrating it to form multimodal structured data;

[0102] S220, based on the disease type, severity of the disease and patient characteristics, the preset medical record template library is screened, and after matching is completed, a standardized medical record basic template template framework is adjusted to generate.

[0103] Among them, S210 includes:

[0104] S211, transmitting the examination result data and medical record information data entered into the hospital database system;

[0105] S212, obtaining input voice text data and image data collected by the consultation information input device;

[0106] S213, after automatic segmentation by medical record chapter, feature-level association is performed, aligned with the time axis in the hospital database system, and integrated to form multimodal structured data.

[0107] For example, the system achieves real-time communication with the hospital system through an industrial-grade data transmission protocol, synchronizes data in a standard format, and integrates it to form multimodal structured data; matches the corresponding system disease template library according to the chief complaint keywords, and determines whether to trigger a specific monitoring template based on the score; uses vector similarity calculation (RAG technology) to screen multiple candidate templates from the template library according to the confidence threshold, and adjusts and generates a standardized medical record basic template framework after the matching is completed.

[0108] Please continue reading Figure 4-Figure 9 In this embodiment, S300 includes:

[0109] S310 assists in analyzing medical records and examination results data, generates a ranking table of diagnostic recommendations based on probability values based on artificial intelligence algorithms and medical knowledge graphs, recommends personalized treatment plans in conjunction with clinical guidelines, and monitors and prompts for omissions of key information and / or logical errors;

[0110] S320, saving and backing up the edited electronic medical record information data.

[0111] Among them, S310 includes:

[0112] S311, assists in analyzing medical records and examination result data to extract patient symptom keywords, matches similar medical records in the medical knowledge graph based on artificial intelligence algorithms, and calculates the confidence probability of different diagnoses;

[0113] S312: Associate patient physiological monitoring data and assess the risk level of treatment options, generate a diagnostic recommendation ranking table, retrieve clinical guidelines to recommend personalized treatment options, and mark the evidence level of evidence-based medicine and the corresponding guideline location;

[0114] S313, based on the user account role access rights, monitor the progress of filling in the medical record information, and provide graded prompts for omissions and logical errors.

[0115] For example, extract the patient's main complaint keywords (e.g. chest pain > 30 minutes), combine the disease-symptom association model of the medical knowledge graph (including ICD-11 disease codes and SNOMED CT terminology system), calculates the diagnosis probability (such as the probability of acute myocardial infarction is 78%) through Bayesian networks, and screens and matches similar diagnosis and treatment pathways in the historical medical record library; synchronously integrates real-time monitoring data (such as dynamic electrocardiogram ST-segment elevation waveforms and abnormal myocardial enzyme spectrum values), calls the drug knowledge graph to generate risk-stratified treatment plans (such as the bleeding risk assessment of aspirin + clopidogrel dual anti-treatment is moderate), and dynamically optimizes the recommendation model through a learning framework, automatically annotating the evidence-based basis (evidence level I); at the same time, it forces interns to intercept logical filling errors (such as the patient's allergy history is not filled in when prescribing penicillin), implements differentiated prompts for attending physicians (only verifies the integrity of key fields), and prevents and controls medical errors through a three-level early warning mechanism (red box on the interface → pop-up window → text message); finally, the electronically signed medical record data is stored using hybrid encryption - structured data is encrypted and stored in the local cluster, and the imaging data is divided into blocks by the data encryption algorithm and uploaded to the cloud, realizing full-link operation log blockchain notarization and data recovery.

[0116] Please continue reading Figure 4-Figure 9 In this embodiment, S400 includes:

[0117] S410, encrypting and transmitting the electronic medical record information data using a hybrid encryption algorithm, and distributing and storing the electronic medical record information data based on the electronic medical record information data structure;

[0118] S420, recording the current account information operation behavior data based on the timestamp, and monitoring abnormal operation behavior data.

[0119] For example, a hybrid encryption strategy is adopted in the data transmission link - structured data (such as test reports) is encrypted and transmitted through data transmission protocols and encryption algorithms; the storage layer implements differentiated processing based on data types, structured medical record fields are encrypted and distributedly stored in sharded clusters, unstructured imaging data are encrypted in blocks and stored in object storage arrays, and cross-modal retrieval is accelerated through inverted indexes; then four-dimensional operation logs (user + operation type + resource object + device fingerprint) are recorded, and the operation mode is analyzed in real time by combining the rule engine and behavioral model. When it is detected that interns frequently access cross-departmental medical records during non-working hours, permission recovery is automatically triggered and blockchain evidence is generated. The operation logs are solidified and stored after being signed to support tracing the data leakage path; at the same time, an emergency response mechanism is established. When ransomware characteristic traffic is identified, it immediately switches to read-only mode and starts offline backup and recovery to ensure business continuity.

[0120] Working principle:

[0121] Based on the full-process intelligent diagnosis and treatment scenario of the electronic medical record system implemented in a grassroots hospital (taking patient Li as an example), the system realizes closed-loop management of diagnosis and treatment and data security protection through a modular technical architecture. When the patient completes the registration, the identity authentication module activates the two-factor verification mechanism (account password + dynamic token), and dynamically controls field-level access rights through the permission model - interns can only see basic fields such as current medical history, and attending physicians can view complete test image data. After the verification is passed, the system generates a multimodal interface that supports mixed editing of voice, handwriting, and images, and realizes real-time data docking with the system;

[0122] Subsequently, the system collects Li's test data, imaging data, and voice-recorded medical history text in real time through the message queue, performs timeline alignment and structural integration, and matches the corresponding standard template based on the coding. When filling in the form, the algorithm calculates the joint probability of symptoms, associates the test data, and generates a treatment plan ranking table. The model accuracy is optimized through the intelligent learning framework. When it is detected that a field is missing, a three-level prompt mechanism is triggered (a red box flashes on the interface → a pop-up reminder → a text message notifies the superior doctor); incremental backup is performed after a preset time period, and array storage is used to save data, supporting version difference comparison by timeline.

[0123] Completed medical records are encrypted and distributedly stored in blocks. All operations are recorded in a four-dimensional log (doctor's identity information + millisecond timestamp + operation type + resource object). When frequent access to medical records is detected during non-working hours, the blockchain audit module automatically triggers permission recovery and generates a security report. Throughout the entire process, Li's medical records were specifically encrypted to ensure data security. At the same time, appropriate access rights were assigned based on the doctor's role. Only the attending physician and the reviewing physician can access and modify Li's medical records. Other personnel cannot view them, thus protecting the patient's privacy.

[0124] Also included is a computer-readable storage medium storing a computer program for executing the intelligent electronic medical record generation and management method, wherein the computer program causes a computer to execute the following steps:

[0125] S100, performing identity verification based on the input account information data and reading the test data information security;

[0126] S200, obtaining the input and read medical record information data and integrating them to form multimodal structured data, screening and matching to generate a standardized medical record basic template framework;

[0127] S300 assists in analyzing multimodal structured data to generate a diagnostic suggestion ranking table, and saves and backs up the edited electronic medical record information data;

[0128] S400, encrypts the transmission and storage of electronic medical record information data, and records the current account information operation behavior data.

[0129] Among them, the computer-readable storage medium can be a computer storage medium or a communication medium. The communication medium includes any medium that facilitates the transmission of a computer program from one place to another. The computer storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer. For example, a computer-readable storage medium is coupled to a processor so that the processor can read information from the computer-readable storage medium and write information to the computer-readable storage medium. Of course, the computer-readable storage medium can also be an integral part of the processor. The processor and the computer-readable storage medium can be located in an application-specific integrated circuit (ASIC). In addition, the ASIC can be located in a user device. Of course, the processor and the computer-readable storage medium can also exist in a communication device as discrete components.

[0130] Specifically, the computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof: such as static random-access memory (SRAM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0131] In addition, the functional units in the various embodiments of the present application can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of the various embodiments of the present application.

[0132] Also included is an electronic device comprising:

[0133] one or more processors; memory; and

[0134] One or more programs, wherein the one or more programs are stored in a memory and configured to be executed by one or more processors, the programs comprising steps for performing the following steps:

[0135] S100, performing identity verification based on the input account information data and reading the test data information security;

[0136] S200, obtaining the input and read medical record information data and integrating them to form multimodal structured data, screening and matching to generate a standardized medical record basic template framework;

[0137] S300 assists in analyzing multimodal structured data to generate a diagnostic suggestion ranking table, and saves and backs up the edited electronic medical record information data;

[0138] S400, encrypts the transmission and storage of electronic medical record information data, and records the current account information operation behavior data.

[0139] It should be noted that the memory is used to store computer programs. The memory may include high-speed random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk memory. It can also be a USB flash drive, a mobile hard drive, a read-only memory, a magnetic disk, or an optical disk.

[0140] Furthermore, the processor is used to execute the computer program stored in the memory to implement the resource management and release method in the above embodiment. The processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention can be directly implemented as a hardware processor, or can be implemented by a combination of hardware and software modules in the processor.

[0141] Optionally, the memory can be independent or integrated with the processor. The above-mentioned processor may include one or more processing units, for example: the processor may include an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Among them, different processing units can be independent devices or integrated into one or more processors. The controller can generate an operation control signal based on the instruction opcode and timing signal to complete the control of instruction fetching and execution.

[0142] When the memory is a device independent of the processor, the electronic device may further include a bus. The bus is used to connect the memory and the processor. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be divided into address buses, data buses, control buses, etc.

[0143] It should be noted that, through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus the necessary general hardware platform. Based on this understanding, the above technical solution, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiment. In this document, relational terms such as first and second are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises", "comprising" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. Without further constraints, an element defined by the phrase "comprises a..." does not preclude the existence of additional identical elements in the process, method, article or apparatus that includes the element.

[0144] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An intelligent electronic medical record generation and management system, characterized in that: include: The data acquisition module is used to connect the patient information input device and the hospital data system, transmit the examination result data and medical record information data entered into the hospital database system, obtain the input voice text data and image data collected by the patient information input device, and integrate them into multimodal structured data; The template generation module is used to read the entered medical record information data and examination result data, and to generate a basic medical record template by screening the preset medical record template library based on the disease type, severity of the disease and patient characteristics; An intelligent prompt module assists in analyzing medical record data and examination result data. It generates a ranking table of diagnostic recommendations based on probability values based on artificial intelligence algorithms and medical knowledge graphs, recommends personalized treatment plans based on clinical guidelines, and monitors and prompts for omissions of key information and / or logical errors in writing in real time. The editing and saving module is used to generate a multimodal information entry and editing interface, obtain an editing completion signal, submit and back up medical record information data, and detect hardware status data and / or virus attack data in real time; Data security protection module, used to run data encryption algorithm to transmit and store medical record information data and examination result data, and record operation behavior data based on role access permission matrix and timestamp; The permission retrieval record module is used to store the access permissions corresponding to the account role and the operation behavior data corresponding to the record timestamp.

2. An intelligent electronic medical record generation and management method, characterized in that: The generation management method is executed via the intelligent electronic medical record generation management system according to claim 1, and the generation management method includes: S100, performing identity verification based on the input account information data and reading the test data information security; S200, obtaining the input and read medical record information data and integrating them to form multimodal structured data, screening and matching to generate a standardized medical record basic template framework; S300 assists in analyzing multimodal structured data to generate a diagnostic suggestion ranking table, and saves and backs up the edited electronic medical record information data; S400, encrypts the transmission and storage of electronic medical record information data, and records the current account information operation behavior data.

3. The intelligent electronic medical record generation and management method according to claim 2, characterized in that: The S100 includes: S110, obtaining the input account and password information data, searching for matching account roles, and verifying whether the passwords are consistent; S120, if the password is entered incorrectly and exceeds a preset number of times, the system is locked and an alarm signal is sent; if the password is entered correctly, a multimodal information entry and editing interface is generated; S130, generating a multimodal information input and editing interface, connecting to the consultation information input device and the hospital data system.

4. The intelligent electronic medical record generation and management method according to claim 2, characterized in that: The S200 includes: S210, transmitting and acquiring the input data information, and integrating it to form multimodal structured data; S220, based on the disease type, severity of the disease and patient characteristics, the preset medical record template library is screened, and after matching is completed, a standardized medical record basic template template framework is adjusted to generate.

5. The intelligent electronic medical record generation and management method according to claim 4, characterized in that: The S210 includes: S211, transmitting the examination result data and medical record information data entered into the hospital database system; S212, obtaining input voice text data and image data collected by the consultation information input device; S213, after automatic segmentation by medical record chapter, feature-level association is performed, aligned with the time axis in the hospital database system, and integrated to form multimodal structured data.

6. The intelligent electronic medical record generation and management method according to claim 2, characterized in that: The S300 includes: S310 assists in analyzing medical records and examination results data, generates a ranking table of diagnostic recommendations based on probability values based on artificial intelligence algorithms and medical knowledge graphs, recommends personalized treatment plans in conjunction with clinical guidelines, and monitors and prompts for omissions of key information and / or logical errors; S320, saving and backing up the edited electronic medical record information data.

7. The intelligent electronic medical record generation and management method according to claim 6, characterized in that: The S310 includes: S311, assists in analyzing medical records and examination result data to extract patient symptom keywords, matches similar medical records in the medical knowledge graph based on artificial intelligence algorithms, and calculates the confidence probability of different diagnoses; S312: Associate patient physiological monitoring data and assess the risk level of treatment options, generate a diagnostic recommendation ranking table, retrieve clinical guidelines to recommend personalized treatment options, and mark the evidence level of evidence-based medicine and the corresponding guideline location; S313, based on the user account role access rights, monitor the progress of filling in the medical record information, and provide graded prompts for omissions and logical errors.

8. The intelligent electronic medical record generation and management method according to claim 2, characterized in that: The S400 includes: S410, encrypting and transmitting the electronic medical record information data using a hybrid encryption algorithm, and distributing and storing the electronic medical record information data based on the electronic medical record information data structure; S420, recording the current account information operation behavior data based on the timestamp, and monitoring abnormal operation behavior data.

9. A computer-readable storage medium, characterized in that It stores a computer program for running the intelligent electronic medical record generation and management method, wherein the computer program enables a computer to execute the intelligent electronic medical record generation and management method as described in any one of claims 2 to 8.

10. An electronic device, characterized in that: include: one or more processors; Memory; as well as One or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the programs include instructions for executing the intelligent electronic medical record generation and management method according to any one of claims 2 to 8.

Images