CN-121999951-A - Electronic medical record generation method, device, computer equipment and storage medium

CN121999951ACN 121999951 ACN121999951 ACN 121999951ACN-121999951-A

Abstract

The application relates to a method, a device, computer equipment and a storage medium for generating an electronic medical record. The method comprises the steps of responding to completion of loading of a voice medical record AI service and triggering operation of a voice acquisition component in an application interface, acquiring audio stream data of a doctor dictation in real time, transmitting the audio stream data of the doctor dictation to a voice recognition model of the voice medical record AI service for voice transcription processing, responding to triggering operation of a medical record generation component in the application interface and receiving the doctor dictation stream data, transmitting patient information, doctor information, treatment record information, a target medical record template, target prompt words and the doctor dictation stream data to a large language model of the voice medical record AI service for medical record generation processing, responding to receiving the electronic medical record text stream data, and generating the electronic medical record according to the electronic medical record text stream data and a medical record version identification number. By adopting the method, the recording efficiency and the accuracy of the electronic medical record can be improved.

Inventors

MAO XIAOWEI
LI YULONG
HU XIAOMING
QIU HUI

Assignees

北京和睦家医院有限公司

Dates

Publication Date: 20260508
Application Date: 20251225

Claims (12)

1. A method of electronic medical record generation, the method comprising: responding to the starting operation of the electronic medical record application, preheating an application interface of the electronic medical record application, and dynamically loading a voice medical record AI service; Responding to the completion of the loading of the voice medical record AI service and triggering a voice acquisition component in the application interface, acquiring audio stream data dictated by a doctor in real time, and transmitting the audio stream data dictated by the doctor to a voice recognition model of the voice medical record AI service for voice transcription processing so that the voice recognition model feeds back the text stream data dictated by the doctor; Responding to triggering operation of a medical record generating component in the application interface and receiving the doctor oral text stream data, acquiring patient information, doctor information, treatment record information, a target medical record template, a target prompt word and a medical record version identification number corresponding to the target medical record template, and transmitting the patient information, the doctor information, the treatment record information, the target medical record template, the target prompt word and the doctor oral text stream data to a large language model of the voice medical record AI service for medical record generating processing so that the large language model feeds back the electronic medical record text stream data; and generating an electronic medical record according to the electronic medical record text stream data and the medical record version identification number in response to receiving the electronic medical record text stream data.
2. The method of claim 1, wherein the pre-heating the application interface of the electronic medical record application comprises: initializing the electronic medical record application; And responding to the completion of the initialization of the electronic medical record application, displaying the application interface, and carrying out preheating treatment on an interface component of the application interface, wherein the interface component comprises one or more of the voice acquisition component, the data transmission component, the voice recognition component and the medical record generation component.
3. The method of claim 1, wherein the dynamically loading the voice medical record AI service comprises: Determining a service model in response to selection operation of a service mode of CHAINLIT AI services applied to the electronic medical record, wherein the service mode comprises the voice medical record AI service or auxiliary medical knowledge question-answer AI service; And responding to the service model to serve the voice medical record AI, and dynamically loading the voice medical record AI service.
4. The method of claim 1, wherein the collecting, in real time, doctor-oral audio stream data comprises: acquiring a doctor user identity number; Inquiring in a local storage information database according to the doctor user identification number to obtain corresponding microphone equipment preference information; acquiring acquisition audio of target microphone equipment in real time in response to acquisition starting operation of the target microphone equipment corresponding to the user identification number of the doctor; And carrying out audio processing on the collected audio according to the preference information of the microphone equipment to obtain audio stream data dictated by the doctor.
5. The method of claim 4, wherein the acquiring the captured audio of the target microphone device in real time comprises: monitoring an audio acquisition state of the target microphone device, wherein the audio acquisition state comprises a recording starting state, a recording state or a recording ending state; Responding to the audio acquisition state as the recording starting state, starting recording duration timing, and acquiring the acquisition audio from the target microphone equipment in real time; Responding to the audio collection state as the recording state, updating recording duration timing, and acquiring the collection audio from the target microphone equipment in real time; and responding to the audio collection state being the recording state, ending recording duration timing, and stopping acquiring the collection audio from the target microphone equipment in real time.
6. The method of claim 1, wherein the obtaining patient information, doctor information, a target medical record template, a target cue word and a medical record version identification corresponding to the target medical record template, comprises: Generating the medical record version identification number according to the patient information, the doctor information and the doctor record information in response to receiving the patient information, the doctor record information and the doctor dictation text request information; determining the medical record template type in response to the selection operation of the medical record template type; Inquiring in a medical record template database according to the medical record template type to obtain the target medical record template; and carrying out matching processing in a prompt word template library according to the target medical record template to obtain the corresponding target prompt word.
7. The method according to claim 1, wherein the method further comprises: responding to the starting operation of the medical record display assembly in the application interface, and displaying the electronic medical record in a preview frame of the application interface in a streaming manner; Responding to selection operation of target electronic medical record text in the preview box, and displaying the target medical record text in an editing box of the application interface; Responding to the editing operation of the target medical record text in the editing box, and updating, displaying and editing the target medical record text in the editing box and the preview box; Responding to the confirmation and storage operation of the edited target medical record text, and updating the electronic medical record according to the edited target medical record text; And storing the electronic medical record to a server according to the medical record version identification number.
8. The method of claim 7, wherein the method further comprises: responding to the history case history version identification number and the case history version identification number to perform case history inquiry processing on the server according to the history case history version identification number and the case history version identification number to obtain a history electronic case history and the electronic case history corresponding to the history case history version identification number; and responding to version comparison operation on the historical electronic medical record and the electronic medical record, obtaining a version processing result after version comparison processing is carried out on the historical electronic medical record and the electronic medical record, and displaying the version processing result on the application interface.
9. The method of claim 7, wherein the method further comprises: and responding to the version rollback operation of the electronic medical record, and updating the electronic medical record in the server into the to-be-rolled historical electronic medical record corresponding to the version identification number of the to-be-rolled medical record according to the result of the version rollback operation.
10. An electronic medical record generating device, characterized in that the device comprises: The interface preheating module is used for responding to the starting operation of the electronic medical record application, carrying out preheating treatment on an application interface of the electronic medical record application and dynamically loading the voice medical record AI service; The audio transcription module is used for responding to the completion of the loading of the voice medical record AI service and triggering the voice acquisition component in the application interface, acquiring the audio stream data dictated by a doctor in real time, and transmitting the audio stream data dictated by the doctor to a voice recognition model of the voice medical record AI service for voice transcription processing so that the voice recognition model feeds back the text stream data dictated by the doctor; The medical record processing module is used for responding to triggering operation of the medical record generating component in the application interface and receiving the doctor oral text stream data, acquiring patient information, doctor information, treatment record information, a target medical record template, a target prompt word and a medical record version identification number corresponding to the target medical record template, and transmitting the patient information, the doctor information, the treatment record information, the target medical record template, the target prompt word and the doctor oral text stream data to a large language model of the voice medical record AI service for medical record generating processing so that the large language model feeds back the electronic medical record text stream data; And the medical record generation module is used for responding to the received electronic medical record text stream data and generating the electronic medical record according to the electronic medical record text stream data and the medical record version identification number.
11. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any one of claims 1 to 9 when the computer program is executed by the processor.
12. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 9.

Description

Electronic medical record generation method, device, computer equipment and storage medium Technical Field The present application relates to the field of artificial intelligence, and in particular, to a method and apparatus for generating an electronic medical record, a computer device, and a storage medium. Background With the popularization of medical electronic informatization, electronic medical records have become a necessary way for various hospitals to record medical information. The existing medical record management system mainly relies on manual input by doctors, and records of medical records are carried out by using paper pens or electronic equipment. However, the current electronic medical record generating method has the problems of low recording efficiency, low electronic medical record accuracy and the like. Disclosure of Invention In view of the foregoing, it is desirable to provide an electronic medical record generating method, apparatus, computer device, and storage medium that can improve recording efficiency and accuracy of electronic medical records. In a first aspect, there is provided a method for generating an electronic medical record, the method comprising: Responding to the starting operation of the electronic medical record application, preheating an application interface of the electronic medical record application, and dynamically loading a voice medical record AI service; Responding to the completion of the loading of the voice medical record AI service and triggering the voice acquisition component in the application interface, acquiring the audio stream data dictated by the doctor in real time, and transmitting the audio stream data dictated by the doctor to a voice recognition model of the voice medical record AI service for voice transcription processing so that the voice recognition model feeds back the text stream data dictated by the doctor; Responding to the trigger operation of the medical record generating component in the application interface and receiving the doctor oral text stream data, acquiring patient information, doctor information, treatment record information, a target medical record template, a target prompt word and a medical record version identification number corresponding to the target medical record template, and transmitting the patient information, the doctor information, the treatment record information, the target medical record template, the target prompt word and the doctor oral text stream data to a large language model of a voice medical record AI service for medical record generating processing so that the large language model feeds back the electronic medical record text stream data; and generating the electronic medical record according to the electronic medical record text stream data and the medical record version identification number in response to receiving the electronic medical record text stream data. In one embodiment, the method comprises the steps of initializing an application interface of an electronic medical record application, displaying the application interface in response to the completion of the initialization of the electronic medical record application, and performing preheating on an interface component of the application interface, wherein the interface component comprises one or more of a voice acquisition component, a data transmission component, a voice recognition component and a medical record generation component. In one embodiment, the dynamic loading of the voice medical record AI service comprises determining a service model in response to a selection operation of a service mode of CHAINLIT AI services applied to the electronic medical record, wherein the service mode comprises the voice medical record AI service or an auxiliary medical knowledge question-answer AI service, and the dynamic loading of the voice medical record AI service in response to the service model for the voice medical record AI service. In one embodiment, acquiring the audio stream data of the dictation of the doctor in real time comprises acquiring a user identification number of the doctor, inquiring in a local storage information database according to the user identification number of the doctor to obtain corresponding microphone equipment preference information, responding to acquisition starting operation on target microphone equipment corresponding to the user identification number of the doctor to acquire the acquired audio of the target microphone equipment in real time, and performing audio processing on the acquired audio according to the microphone equipment preference information to obtain the audio stream data of the dictation of the doctor. In one embodiment, acquiring the acquired audio of the target microphone device in real time comprises monitoring an audio acquisition state of the target microphone device, wherein the audio acquisition state comprises a recording starting state, a recording starting state or a re