Automatic medical history recording method and device based on voice questions and answers and electronic equipment
Through a voice-based Q&A method, patients' voice feedback is collected in real time and medical history documents are generated using deep learning models, which solves the problem of time-consuming and susceptible to fatigue in the prior art, and achieves efficient and accurate automated medical history records.
Patent Information
- Application Number
- CN202411018722.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-29
- Publication Date
- 2024-12-06
AI Technical Summary
In existing medical practices, doctors or clinical researchers need to manually record medical history, which is time-consuming and prone to quality impacts due to fatigue or distraction, and lacks automated solutions to improve efficiency and data accuracy.
Using a voice question-and-answer method, we use the method to obtain the patient's real-time voice feedback, convert it into text information, and use the deep learning model to identify key information and intentions, generate current medical history documents in a predetermined format, and realize automated recording.
It significantly reduces the time and labor required by doctors or researchers to manually write medical history, improves the efficiency and accuracy of medical history records, and realizes an automated medical history recording process.
Smart Images

Figure CN119092027A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of data processing technology, and specifically relates to a method, device and electronic equipment for automatically recording medical history based on voice question and answer. Background Art
[0002] In existing medical practice, doctors or clinical researchers need to manually record the history of current illness, which is not only time-consuming but also easily affects the quality of the record due to fatigue or distraction.
[0003] As healthcare demands ever-increasing efficiency and data accuracy, a solution is needed to automate this process. Summary of the invention
[0004] The purpose of this application is to provide a method, device and electronic device for automatically recording medical history based on voice question and answer to realize automatic recording of current medical history and improve the efficiency of recording current medical history.
[0005] According to a first aspect of an embodiment of the present application, a method for automatically recording medical history based on voice question and answer is provided, and the method may include:
[0006] Get voice feedback of patients’ real-time conversations;
[0007] Convert voice feedback into text messages;
[0008] A patient's current medical history document is generated based on the text information, and the current medical history document includes question-and-answer information about the patient's condition in a predetermined format.
[0009] In some optional embodiments of the present application, converting the voice feedback into text information includes:
[0010] Remove redundant information from voice feedback and extract sound features to obtain audio information;
[0011] The audio information is converted into text to obtain text information.
[0012] In some optional embodiments of the present application, redundant information in the voice feedback is removed and sound features are extracted to obtain audio information, including:
[0013] Get the Mel frequency cepstral coefficients of speech feedback;
[0014] The patient's voice characteristics were calculated based on the Mel-frequency cepstral coefficients.
[0015] In some optional embodiments of the present application, the audio information is converted into text to obtain text information, including:
[0016] Use the trained speech recognition model to recognize audio information and obtain text information.
[0017] In some optional embodiments of the present application, a patient's current medical history document is generated based on text information, including:
[0018] Using the trained first deep learning model to identify key information in the text information;
[0019] The trained second deep learning model is used to identify patient intent in text information.
[0020] In some optional embodiments of the present application, after using the trained second deep learning model to identify the patient's intention in the text information, the method further includes:
[0021] Generate follow-up questions based on patient intent and key information
[0022] Continuously convert and record patient response feedback.
[0023] In some optional embodiments of the present application, after the patient's intention and key information, the following is also included:
[0024] The history of present illness generation model is used to generate the patient's history of present illness document based on the patient's intention, key information and answer feedback.
[0025] According to a second aspect of an embodiment of the present application, a device for automatically recording medical history based on voice question and answer is provided, and the device may include:
[0026] An acquisition module is used to obtain voice feedback of patients' real-time conversations;
[0027] A text conversion module, used to convert voice feedback into text information;
[0028] The current medical history generation module is used to generate a patient's current medical history document based on text information, and the current medical history document includes question and answer information about the patient's symptoms in a predetermined format.
[0029] According to a third aspect of an embodiment of the present application, an electronic device is provided, which may include:
[0030] processor;
[0031] a memory for storing processor-executable instructions;
[0032] The processor is configured to execute instructions to implement the method for automatically recording medical history based on voice question and answer as shown in any one of the embodiments of the first aspect.
[0033] According to the fourth aspect of the embodiments of the present application, a storage medium is provided. When the instructions in the storage medium are executed by a processor of an information processing device or a server, the information processing device or the server implements a method for automatically recording medical history based on voice question and answer as shown in any one of the embodiments of the first aspect.
[0034] The above technical solution of the present application has the following beneficial technical effects:
[0035] The method of the embodiment of the present application collects the voice feedback of the patient's conversation in real time, converts the voice feedback into text information, and finally generates the patient's current medical history document based on the text information. The method converts the clinical conversation into the current medical history document instantly through an automated process, significantly reducing the time and labor required for doctors or researchers to manually write. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] Figure 1 is a flowchart of a method for automatically recording medical history based on voice question and answer in an exemplary embodiment of the present application;
[0037] Figure 2 It is a structural schematic diagram of a medical history automatic recording device based on voice question and answer in an exemplary embodiment of the present application;
[0038] Figure 3 is a schematic structural diagram of an electronic device in an exemplary embodiment of the present application;
[0039] Figure 4 It is a schematic diagram of the hardware structure of an electronic device in an exemplary embodiment of the present application. DETAILED DESCRIPTION
[0040] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with specific implementations and with reference to the accompanying drawings. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present application. In addition, in the following description, the description of known structures and technologies is omitted to avoid unnecessary confusion of the concepts of the present application.
[0041] The accompanying drawings show schematic diagrams of layer structures according to embodiments of the present application. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clarity. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.
[0042] Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.
[0043] In the description of the present application, it should be noted that the terms "first", "second" and "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.
[0044] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.
[0045] In conjunction with the accompanying drawings, the following detailed description is given of the method, device and electronic device for automatically recording medical history based on voice question and answer provided in the embodiments of the present application through specific embodiments and their application scenarios.
[0046] like Figure 1 As shown, in a first aspect of an embodiment of the present application, a method for automatically recording medical history based on voice question and answer is provided, and the method may include:
[0047] S110: Obtain voice feedback of the patient's real-time conversation;
[0048] S120: converting the voice feedback into text information;
[0049] S130: Generate a patient's current medical history document based on the text information, where the current medical history document includes question-and-answer information about the patient's condition in a predetermined format.
[0050] The method of this embodiment collects the voice feedback of the patient's conversation in real time, converts the voice feedback into text information, and finally generates the patient's current medical history document based on the text information. This method converts the clinical conversation into the current medical history document instantly through an automated process, significantly reducing the time and labor required for doctors or researchers to manually write.
[0051] In some embodiments, converting the speech feedback into text information includes:
[0052] Remove redundant information from voice feedback and extract sound features to obtain audio information;
[0053] The audio information is converted into text to obtain text information.
[0054] This embodiment performs real-time speech recognition on the captured conversation and converts the speech data into text format to ensure the integrity and accuracy of the conversation content.
[0055] In some embodiments, removing redundant information from the voice feedback and extracting sound features to obtain audio information includes:
[0056] Get the Mel frequency cepstral coefficients of speech feedback;
[0057] The patient's voice characteristics were calculated based on the Mel-frequency cepstral coefficients.
[0058] Specifically, each speech signal is first pre-emphasized, frame segmented, and windowed. Fast Fourier transform (FFT) is applied to each frame to obtain the spectrum. The spectrum is mapped to the Mel scale and processed using a Mel filter bank. The logarithm of the output of each Mel filter is taken, and then discrete cosine transform (DCT) is applied to obtain MFCCs. The first N MFCCs are selected as features (N=13), and the 0th coefficient is ignored.
[0059] In some embodiments, converting the audio information into text to obtain text information includes:
[0060] Use the trained speech recognition model to recognize audio information and obtain text information.
[0061] In order to establish a speaker recognition model in this embodiment, specifically, an LSTM model can be used, whose input: the dimension of the MFCCs feature sequence is set to (number of time steps, 13), where 13 is the number of selected MFCC features. LSTM layer: The first LSTM layer has 128 units and returns the output of the entire sequence; the second LSTM layer also has 128 units, but only returns the output of the last time step for classification. Fully connected layer: connected to a Dense layer with 64 units, using the ReLU activation function. Output layer: For binary classification problems, the output layer has 1 unit and uses the sigmoid activation function; for binary classification, the loss function uses binary crossentropy, and the optimizer is recommended to use Adam, and the learning rate is set to 0.001.
[0062] In some embodiments, generating a patient's current medical history document based on text information includes:
[0063] Using the trained first deep learning model to identify key information in the text information;
[0064] The trained second deep learning model is used to identify patient intent in text information.
[0065] The first deep learning model and the second deep learning model in this embodiment can both be BERT models. This embodiment uses a pre-trained BERT model to perform intent recognition and key information extraction on the transcribed text.
[0066] Model Adaptation: Add a custom fully connected layer on top of the BERT model to adapt it to the specific intent recognition task.
[0067] Training data: Fine-tune using a labeled medical conversation dataset with labels including various intents and key information.
[0068] In some embodiments, after identifying the patient's intention in the text information using the trained second deep learning model, the method further includes:
[0069] Generate follow-up questions based on patient intent and key information
[0070] Continuously convert and record patient response feedback.
[0071] This embodiment generates relevant follow-up questions based on the identified intent and key information using predefined rules or templates. For example, if the intent of "reporting symptoms" is identified, detailed follow-up questions can be asked based on the type of symptoms.
[0072] In some embodiments, after the patient's intention and key information, the following is further included:
[0073] The history of present illness generation model is used to generate the patient's history of present illness document based on the patient's intention, key information and answer feedback.
[0074] The detailed training process of the present medical history generation model may include:
[0075] 1. Data preparation
[0076] Collect the dataset:
[0077] Procedure: Collect real records of doctor-patient conversations, which may come from outpatient clinics, telemedicine consultations, or clinical research interviews.
[0078] Example scenario: A conversation record in which a doctor asks a patient about his or her allergy history, current symptoms, and medication use in an outpatient clinic.
[0079] Data cleaning:
[0080] Action: Remove any irrelevant conversations from the chat history, such as small talk or irrelevant medical information, and delete any sensitive personal information.
[0081] Scenario example: Remove personal identifying information such as the patient's name and address from the conversation, and retain content related to the description of the condition and treatment response.
[0082] Improve the focus and efficiency of the model:
[0083] When training a natural language processing model, the goal is to have the model learn and understand language patterns and structures that are directly relevant to the task. Including too much irrelevant information may interfere with the model's learning process, making the model less efficient and accurate in handling the core task. By removing conversations that are not relevant to the generation of the current medical history, such as small talk or irrelevant medical information, the model can be more focused on learning how to extract useful medical information from doctor-patient conversations.
[0084] Protect privacy and comply with laws and regulations:
[0085] Removing sensitive personal information is necessary to protect patient privacy and comply with data protection laws and regulations. Medical data often contains personally identifiable information and other sensitive information, the disclosure of which may have a serious impact on personal privacy. Therefore, it is necessary to remove this information from the dataset.
[0086] To balance the need for data cleaning with maintaining data authenticity, the following measures can be taken:
[0087] Selective cleaning: Instead of removing all non-strictly medical-related conversations, selectively retain information that may be helpful in understanding the context or the patient's emotional state. For example, non-professional descriptions that express the severity of the disease or the degree of pain can be retained. In addition, data augmentation techniques can be used to increase the diversity of input text.
[0088] Data augmentation measures:
[0089] 1). Synonym replacement
[0090] Operation: Randomly select words in the sentence and replace them with their synonyms. This method helps the model learn to understand semantically similar expressions.
[0091] Purpose: To enhance the model's understanding of synonyms and near-synonyms and improve the model's ability to handle natural language variants.
[0092] 2). Back-translation
[0093] Action: Translate text from one language to another and then back to the original language.
[0094] Purpose: To introduce natural language variation through the translation process and increase the diversity of data.
[0095] 3). Sentence Reorganization
[0096] Action: Randomly change the order of words or phrases in a sentence, or split the sentence into shorter segments and reassemble them.
[0097] Purpose: To improve the model's adaptability to different sentence structures. In the specific implementation process, any one of the above enhancement methods can be used, or a combination of multiple methods can be used.
[0098] Annotated data:
[0099] Operation: Process the data into standard input and output formats. The input format should include the complete clinical conversation content, including every question and answer in the conversation.
[0100] The output format should be a structured summary of the history of present illness, including all key medical information mentioned in the conversation, such as symptom description, duration, medication use, etc.
[0101] Input format:
[0102] [Dialogue begins]
[0103] [Doctor]: Do you have any symptoms of discomfort recently?
[0104] [Patient]: I feel a little pain in my chest.
[0105] [Doctor]: How long did this pain last?
[0106] [Patient]: About a week.
[0107] [Doctor]: Are you taking any medication?
[0108] [Patient]: No, I haven’t taken any medicine.
[0109] [END OF CONVERSATION]
[0110] Output format:
[0111] History of present illness:
[0112] - Symptom description: chest pain
[0113] - Duration: One week
[0114] - Medication use: Not taking any medication
[0115] 2. Preprocessing and feature extraction
[0116] Tokenization and encoding:
[0117] Operation: Use the word segmentation tool of ChatGLM2-6B to segment the annotated conversation data and then encode it.
[0118] Scenario example: Segment and encode a conversation about a patient describing chest pain.
[0119] Construct training samples:
[0120] Operation: Construct a series of training samples from the segmented and encoded conversation data. Each sample contains a conversation and the corresponding summary of the current medical history.
[0121] Example scenario: Construct a sample that includes a patient's description of symptoms and a corresponding summary of the history of present illness.
[0122] 3. Model training
[0123] Load the pre-trained model:
[0124] Action: Load ChatGLM2-6B as the base model.
[0125] Scenario example: Load the ChatGLM2-6B model on the clinical conversation dataset for initial training.
[0126] Fine-tuning:
[0127] Operation: Fine-tune the ChatGLM2-6B model on a specific clinical conversation dataset.
[0128] Scenario example: Use a set of outpatient and telemedicine consultation conversation data to fine-tune the model to make it more suitable for the context of medical conversations.
[0129] Optimize model parameters:
[0130] Action: Adjust parameters based on the model's performance on the training data.
[0131] Example scenario: Adjust the learning rate of a model to improve the understanding of medical terminology and the accuracy of history of present illness generation.
[0132] 4. Evaluate and optimize
[0133] Performance evaluation:
[0134] Action: Use an independent validation dataset to evaluate the model's performance for history of present illness generation.
[0135] Scenario example: Evaluate the accuracy and completeness of the current medical history summary generated by the model on a new set of doctor-patient conversation data.
[0136] 5. Deployment and Application
[0137] Model deployment:
[0138] Operation: Deploy the trained model into the medical information system.
[0139] Example scenario: Deploy the model in a hospital’s electronic medical record system to generate medical histories.
[0140] Through these detailed steps, it can be seen that the application of ChatGLM2-6B in generating current medical history not only reflects technological innovation, but also demonstrates its practicality and feasibility in actual medical scenarios.
[0141] Fine-tune ChatGLM2-6B specifically for the medical domain, especially for the scenario of history of present illness generation. This includes training with specific medical datasets and adjusting the parameters of the model to better suit the characteristics of medical conversations.
[0142] Application example: ChatGLM2-6B can be customized and trained based on the hospital’s specific needs and clinical data to enable it to understand specific medical terms and symptom descriptions.
[0143] Integrating new medical knowledge:
[0144] Innovation: Integrates the latest medical knowledge and guidelines based on ChatGLM2-6B to ensure that the generated history of current illness is not only accurate but also in line with the latest medical standards and practices.
[0145] Application example: Incorporate the latest clinical guidelines and research results into the model training process to improve its professionalism and reliability in generating current medical history.
[0146] It should be noted that the method for automatically recording medical history based on voice question and answer provided in the embodiment of the present application can be executed by an automatic medical history recording device based on voice question and answer, or a control module in the automatic medical history recording device based on voice question and answer for executing the method for automatically recording medical history based on voice question and answer. In the embodiment of the present application, the method for automatically recording medical history based on voice question and answer is executed by an automatic medical history recording device based on voice question and answer as an example to illustrate the device for automatically recording medical history based on voice question and answer provided in the embodiment of the present application.
[0147] like Figure 2 As shown, in a second aspect of the embodiment of the present application, a device for automatically recording medical history based on voice question and answer is provided, and the device may include:
[0148] An acquisition module 210 is used to acquire voice feedback of a patient's real-time conversation;
[0149] A text conversion module 220, used to convert the voice feedback into text information;
[0150] The current medical history generating module 230 is used to generate a patient's current medical history document based on text information, and the current medical history document includes question and answer information about the patient's symptoms in a predetermined format.
[0151] The automatic medical history recording device based on voice question and answer in the embodiment of the present application can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook or a personal digital assistant (personal digital assistant, PDA), etc., and the non-mobile electronic device can be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (personal computer, PC), a television (television, TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.
[0152] The automatic medical history recording device based on voice question and answer in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.
[0153] The automatic medical history recording device based on voice question and answer provided in the embodiment of the present application can achieve Figure 1 To avoid repetition, the various processes implemented by the method embodiment are not described here.
[0154] Alternatively, if Figure 3 As shown, an embodiment of the present application also provides an electronic device 300, including a processor 301, a memory 302, and a program or instruction stored in the memory 302 and executable on the processor 301. When the program or instruction is executed by the processor 301, each process of the above-mentioned embodiment of the automatic recording method of medical history based on voice question and answer is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.
[0155] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.
[0156] Figure 4 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of the present application.
[0157] The electronic device 400 includes but is not limited to components such as a radio frequency unit 401 , a network module 402 , an audio output unit 403 , an input unit 404 , a sensor 405 , a display unit 406 , a user input unit 407 , an interface unit 408 , a memory 409 , and a processor 410 .
[0158] Those skilled in the art will appreciate that the electronic device 400 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 410 through a power management system, thereby implementing functions such as managing charging, discharging, and power consumption management through the power management system. Figure 4 The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be described in detail here.
[0159] It should be understood that in the embodiment of the present application, the input unit 404 may include a graphics processor (GPU) 4041 and a microphone 4042, and the graphics processor 4041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 406 may include a display panel 4061, and the display panel 4061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 407 includes a touch panel 4071 and other input devices 4072. The touch panel 4071 is also called a touch screen. The touch panel 4071 may include two parts: a touch detection device and a touch controller. Other input devices 4072 may include, but are not limited to, a physical keyboard, a function key (such as a volume control button, a switch button, etc.), a trackball, a mouse, and a joystick, which will not be repeated here. The memory 409 may be used to store software programs and various data, including but not limited to applications and operating systems. The processor 410 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, and applications, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 410.
[0160] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned embodiment of the automatic recording method of medical history based on voice question and answer is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.
[0161] The processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0162] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned embodiment of the automatic medical history recording method based on voice question and answer, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.
[0163] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.
[0164] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.
[0165] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.
[0166] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.
Claims
1. A method for automatically recording medical history based on voice question and answer, characterized in that: include: Obtaining voice feedback of the patient's real-time conversation, wherein the voice feedback is an answer to the doctor's question; Converting the voice feedback into text information; A patient's current medical history document is generated according to the text information, wherein the patient's current medical history document includes question-and-answer information about the patient's condition in a predetermined format.
2. The method for automatically recording medical history based on voice question and answer according to claim 1, characterized in that: The converting the voice feedback into text information comprises: Removing redundant information from the voice feedback and extracting sound features to obtain audio information; The audio information is converted into text to obtain text information.
3. The method for automatically recording medical history based on voice question and answer according to claim 2, characterized in that: The removing redundant information in the voice feedback and extracting sound features to obtain audio information includes: Obtaining Mel-frequency cepstral coefficients of the speech feedback; The voice characteristics of the patient are calculated based on the Mel-frequency cepstral coefficients.
4. The method for automatically recording medical history based on voice question and answer according to claim 2, characterized in that: The step of converting the audio information into text to obtain text information includes: The audio information is recognized using a trained speech recognition model to obtain text information.
5. The method for automatically recording medical history based on voice question and answer according to claim 1, characterized in that: Generating the patient's current medical history document according to the text information includes: Using the trained first deep learning model to identify key information in the text information; The trained second deep learning model is used to identify the patient's intent in the text information.
6. The method for automatically recording medical history based on voice question and answer according to claim 5, characterized in that: After using the trained second deep learning model to identify the patient's intention in the text information, the method further includes: Generate follow-up questions based on the patient's intent and the key information The patient's response feedback is continuously converted and recorded.
7. The method for automatically recording medical history based on voice question and answer according to claim 6, characterized in that: After the patient's intention and the key information, the method further includes: The present medical history generation model is used to generate the patient's present medical history document according to the patient's intention, the key information and the answer feedback.
8. An automatic medical history recording device based on voice question and answer, characterized in that: include: An acquisition module is used to obtain voice feedback of patients' real-time conversations; A text conversion module, used for converting the voice feedback into text information; The present medical history generating module is used to generate the patient's present medical history document according to the text information, wherein the present medical history document includes question and answer information about the patient's condition in a predetermined format.
9. An electronic device, characterized in that: include: A processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method for automatic recording of medical history based on voice question and answer as described in any one of claims 1 to 7.
10. A readable storage medium, characterized in that: The readable storage medium stores programs or instructions, and when the programs or instructions are executed by the processor, the steps of the automatic medical history recording method based on voice question and answer as described in any one of claims 1-7 are implemented.
