Method and device for generating medical record document, equipment and medium

Abstract

The invention discloses a medical record document generation method and device, equipment and a storage medium. The method comprises the following steps: acquiring audio data generated by conversation between a doctor and a patient in a medical diagnosis process; performing voice recognition on the audio data to obtain a dialogue text corresponding to the audio data; inputting the dialogue text into a large language model for analysis, and outputting complaint information, current medical history information, past history information and associated information of the patient through the large language model; and according to the chief complaint information, the present medical history information, the past history information and the associated information, generating a corresponding medical record document of the patient in the medical diagnosis process. According to the method, automatic medical record document generation can be achieved, the medical record document arrangement and output efficiency can be improved, and compared with a traditional manual recording mode, the medical record document obtained through the method is better in accuracy and integrity, and the usability of the medical record document can be improved. The method can be widely applied to the technical field of medical record generation.

Description

Technical Field

[0001] The present application relates to the technical field of medical record generation, and in particular to a method, device, equipment and storage medium for generating medical record documents. Background Art

[0002] Medical records refer to documents that are generated by medical institutions during the diagnosis and treatment of patients and systematically record the patient's health status and medical diagnosis process. It generally includes the patient's personal information, medical history information, treatment plans issued by doctors, examination reports, etc. Medical records provide doctors with the patient's medical records, which can help better understand the patient's health status and formulate reasonable treatment plans. By consulting medical records, doctors can avoid repeated examinations and improve diagnosis and treatment efficiency.

[0003] In the related art, existing medical records are often recorded manually by doctors, for example, by asking patients about their chief complaints, conditions and medical history during communication, and then entering the information into a computer for storage. This implementation method is relatively time-consuming, and doctors can only simply record the general situation, which is prone to inaccurate or missing records, resulting in insufficient usability of medical records.

[0004] In summary, the problems existing in related technologies need to be solved urgently. Summary of the invention

[0005] The purpose of this application is to solve one of the technical problems existing in the related art to at least a certain extent.

[0006] To this end, one purpose of an embodiment of the present application is to provide a method, apparatus, device and storage medium for generating medical case history documents.

[0007] In order to achieve the above technical objectives, the technical solutions adopted by the embodiments of the present application include:

[0008] On the one hand, an embodiment of the present application provides a method for generating a medical record document, the method comprising:

[0009] Acquire audio data generated by the conversation between doctors and patients during medical diagnosis;

[0010] Performing speech recognition on the audio data to obtain a conversation text corresponding to the audio data;

[0011] Inputting the conversation text into a large language model for analysis, and outputting the patient's chief complaint information, current medical history information, past medical history information, and related information through the large language model;

[0012] A medical record document corresponding to the patient in the medical diagnosis process is generated according to the chief complaint information, the current medical history information, the past medical history information and the associated information.

[0013] In addition, the method for generating a medical record document according to the above embodiment of the present application may also have the following additional technical features:

[0014] Further, in one embodiment of the present application, the obtaining of audio data generated by the conversation between the doctor and the patient during the medical diagnosis process includes:

[0015] In response to the doctor's recording operation, starting a recording device;

[0016] The audio data generated by the conversation between the doctor and the patient during the medical diagnosis process is collected through the recording device.

[0017] Further, in one embodiment of the present application, performing speech recognition on the audio data to obtain a conversation text corresponding to the audio data includes:

[0018] Input the audio data into the Whisper-large-v2 model;

[0019] The audio data is subjected to speech recognition by the Whisper-large-v2 model to obtain a conversation text corresponding to the audio data.

[0020] Furthermore, in one embodiment of the present application, the large language model is obtained by the following steps:

[0021] Obtain pre-trained large base models and training datasets in the medical field;

[0022] The parameters of the base large model are fine-tuned and trained using the training data set to obtain a trained large language model.

[0023] Furthermore, in one embodiment of the present application, the large base model is a Qwen-7B model.

[0024] Further, in one embodiment of the present application, performing speech recognition on the audio data to obtain a conversation text corresponding to the audio data includes:

[0025] Preprocessing the audio data; wherein the preprocessing includes at least one of noise reduction processing, silence removal processing, normalization processing, and equalization processing;

[0026] Speech recognition is performed on the preprocessed audio data to obtain a conversation text corresponding to the audio data.

[0027] Further, in one embodiment of the present application, generating a medical record document corresponding to the patient in the medical diagnosis process according to the chief complaint information, the current medical history information, the past medical history information and the associated information includes:

[0028] Obtaining basic information and medical record template of the patient;

[0029] The chief complaint information, the current medical history information, the past medical history information, the related information and the basic information are filled into the medical record template to obtain the medical record document.

[0030] On the other hand, an embodiment of the present application provides a device for generating a medical record document, the device comprising:

[0031] An acquisition unit, used to acquire audio data generated by the conversation between the doctor and the patient during the medical diagnosis process;

[0032] A recognition unit, configured to perform speech recognition on the audio data to obtain a conversation text corresponding to the audio data;

[0033] An analysis unit, used for inputting the conversation text into a large language model for analysis, and outputting the patient's chief complaint information, current medical history information, past medical history information, and related information through the large language model;

[0034] A generating unit is used to generate a medical record document corresponding to the patient in the medical diagnosis process according to the chief complaint information, the current medical history information, the past medical history information and the associated information.

[0035] On the other hand, an embodiment of the present application provides an electronic device, including:

[0036] at least one processor;

[0037] at least one memory for storing at least one program;

[0038] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned method for generating a medical case record document.

[0039] On the other hand, an embodiment of the present application further provides a computer-readable storage medium, which stores a program executable by a processor. When the program executable by the processor is executed by the processor, it is used to implement the above-mentioned method for generating a medical case record document.

[0040] The advantages and benefits of the present application will be partially given in the following description, and partially become apparent from the following description, or be understood through the practice of the present application:

[0041] The method, device, equipment and storage medium for generating medical medical record documents disclosed in the embodiments of the present application obtain audio data generated by the conversation between the doctor and the patient during the medical diagnosis process; perform speech recognition on the audio data to obtain the conversation text corresponding to the audio data; input the conversation text into a large language model for analysis, and output the patient's chief complaint information, current medical history information, past medical history information and related information through the large language model; generate the medical medical record document corresponding to the patient in the medical diagnosis process based on the chief complaint information, the current medical history information, the past medical history information and the related information. This method can realize the automated generation of medical medical record documents, improve the efficiency of sorting and outputting medical medical record documents, and, compared with the traditional manual recording method, the medical medical record documents obtained by this method have better accuracy and completeness, which is conducive to improving the usability of medical medical record documents. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following introduction is made to the drawings of the embodiments of the present application or the related technical solutions in the prior art. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solutions of the present application. For technical personnel in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 A schematic diagram of an implementation environment of a method for generating a medical record document provided in an embodiment of the present application;

[0044] Figure 2 A schematic diagram of a process for generating a medical record document provided in an embodiment of the present application;

[0045] Figure 3 A schematic diagram of a medical record document provided in an embodiment of the present application;

[0046] Figure 4 A schematic diagram of an implementation of a method for generating a medical record document provided in an embodiment of the present application;

[0047] Figure 5 A schematic diagram of the structure of a device for generating a medical record document provided in an embodiment of the present application;

[0048] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] The present application is further described below in conjunction with the accompanying drawings and specific embodiments. The described embodiments should not be regarded as limiting the present application, and all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0050] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0052] 1) Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines so that machines have the functions of perception, reasoning and decision-making.

[0053] Artificial intelligence technology is a comprehensive discipline that covers a wide range of fields, including both hardware-level and software-level technologies. Basic artificial intelligence technologies generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, pre-trained model technology, operation / interaction systems, mechatronics, etc. Among them, pre-trained models are also called large models and basic models. After fine-tuning, they can be widely used in downstream tasks in various major directions of artificial intelligence. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0054] 2) Machine Learning (ML) is a multi-disciplinary interdisciplinary subject, involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. It specializes in studying how computers simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications are spread across all areas of artificial intelligence. Machine learning and deep learning usually include artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and self-learning. The pre-trained model is the latest development in deep learning, which integrates the above technologies.

[0055] 3) Language Model (LM) is a probabilistic model for modeling natural language. Its basic task is to evaluate the probability of a given word sequence (i.e., a sentence) appearing in the real world. Specifically, the language model can be a deep learning model trained with text data, which can understand the semantics of the input natural language text, thereby performing natural language processing (NLP) tasks, such as text sentiment analysis, text classification and aggregation, semantic similarity assessment of multiple natural language texts, question answering, text generation, etc.

[0056] 4) Large models refer to large language models (LLMs) in the field of artificial intelligence. Generally speaking, large models have millions to hundreds of billions of parameters, which are variables adjusted during the model learning process to capture patterns and features in the data. A large number of parameters enables the model to better understand and generate various types of data such as natural language, images, audio, etc. Large models can perform well on a variety of tasks through pre-training and fine-tuning, including but not limited to text generation, machine translation, question-answering systems, sentiment analysis, etc.

[0057] 5) Automatic Speech Recognition (ASR), a technology that converts human speech into text. It uses computer algorithms to analyze audio signals, identify and transcribe the speech content, and is widely used in various scenarios.

[0058] Medical records refer to documents that are generated by medical institutions during the diagnosis and treatment of patients and systematically record the patient's health status and medical diagnosis process. It generally includes the patient's personal information, medical history information, treatment plans issued by doctors, examination reports, etc. Medical records provide doctors with the patient's medical records, which can help better understand the patient's health status and formulate reasonable treatment plans. By consulting medical records, doctors can avoid repeated examinations and improve diagnosis and treatment efficiency.

[0059] In the related art, existing medical records are often recorded manually by doctors, for example, by asking patients about their chief complaints, conditions and medical history during communication, and then entering the information into a computer for storage. This implementation method is relatively time-consuming, and doctors can only simply record the general situation, which is prone to inaccurate or missing records, resulting in insufficient usability of medical records.

[0060] In view of this, a method for generating a medical record document is provided in an embodiment of the present application, which obtains audio data generated by the conversation between the doctor and the patient during the medical diagnosis process; performs speech recognition on the audio data to obtain the conversation text corresponding to the audio data; inputs the conversation text into a large language model for analysis, and outputs the patient's chief complaint information, current medical history information, past medical history information, and related information through the large language model; generates the medical record document corresponding to the patient in the medical diagnosis process based on the chief complaint information, the current medical history information, the past medical history information, and the related information. This method can realize the automated generation of medical record documents, improve the efficiency of sorting and outputting medical record documents, and, compared with the traditional manual recording method, the medical record documents obtained by this method have better accuracy and completeness, which is conducive to improving the usability of medical record documents.

[0061] Please refer to Figure 1 , Figure 1 The schematic diagram of the implementation environment of a method for generating a medical record document provided in an embodiment of the present application is shown. In the implementation environment, the main hardware and software entities involved include a terminal device 110 and a backend server 120. The terminal device 110 and the backend server 120 are connected in communication.

[0062] Specifically, the method for generating medical case record documents provided in the embodiments of the present application can be executed solely on the terminal device 110 side, or solely on the background server 120 side, or based on data interaction between the terminal device 110 and the background server 120.

[0063] The terminal device 110 of the above embodiment may include a mobile phone, a computer, a smart wearable device, a PDA device, an intelligent voice interaction device, an intelligent recording device, etc., but is not limited thereto. The backend server 120 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0064] The terminal device 110 and the backend server 120 may establish a communication connection via a wireless network or a wired network. The wireless network or wired network uses standard communication technology and / or protocols, and the network may be set to the Internet or any other network, such as but not limited to a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a private network or any combination of a virtual private network.

[0065] Of course, it is understandable that Figure 1 The implementation environment in the present application is only some optional application scenarios of the method for generating medical records provided in the embodiment of the present application, and the actual application is not fixed. Figure 1 The hardware and software environment shown.

[0066] Below, in combination with the introduction of the aforementioned implementation environment, a method for generating a medical case record document provided in an embodiment of the present application is introduced and explained.

[0067] Please refer to Figure 2 , Figure 2 : is a schematic diagram of a method for generating a medical record document provided in an embodiment of the present application. The method for generating a medical record document includes but is not limited to:

[0068] Step 210: Acquire audio data generated by the conversation between the doctor and the patient during the medical diagnosis process;

[0069] Step 220: Perform speech recognition on the audio data to obtain a conversation text corresponding to the audio data;

[0070] Step 230: input the conversation text into a large language model for analysis, and output the patient's chief complaint information, current medical history information, past medical history information, and related information through the large language model;

[0071] Step 240: Generate a medical record document corresponding to the patient in the medical diagnosis process based on the chief complaint information, the current medical history information, the past medical history information and the associated information.

[0072] In an embodiment of the present application, a method for generating a medical record document is provided. The method can improve the efficiency, accuracy and intelligence level of medical record document generation by deeply integrating automatic speech recognition (ASR) and a generative large language model (LLM).

[0073] In the embodiment of the present application, when generating a medical record document, audio data generated by the conversation between the doctor and the patient during the medical diagnosis process can be obtained. The audio data can be generated during the diagnosis process of the patient and the doctor regarding the relevant condition, and the specific content of the audio data is not limited. Specifically, in the embodiment of the present application, a suitable recording device can be selected to collect and obtain audio data. In the embodiment of the present application, there is no limitation on the type of recording device used.

[0074] It should be noted that in the embodiments of this application, the patient's explicit written or verbal consent must be obtained before recording, and the patient must be informed of the purpose, scope of use, storage method, and possible sharing objects (such as other doctors or researchers) of the recording. In addition, the processing of these audio data must comply with relevant laws and regulations, which will not be elaborated in this application.

[0075] After obtaining the audio data, the audio data can be subjected to speech recognition and converted into text content. In the embodiment of the present application, the obtained text is recorded as a dialogue text. Specifically, in some embodiments, before the audio data is subjected to speech recognition, it can be preprocessed, and the preprocessing can include at least one of noise reduction processing, silence removal processing, normalization processing, and equalization processing. Among them, noise reduction processing refers to removing background noise by filtering or other techniques to retain useful sound signals. Common noise reduction processing methods include spectral subtraction, wavelet transform, Kalman filtering, etc. Silence removal processing refers to detecting and removing non-speech parts (such as long silence) in the audio to reduce unnecessary calculations. For example, it can be determined whether there is speech by features such as energy thresholds and zero crossing rates, thereby achieving the deletion of silent part segments. Normalization processing is to adjust the amplitude or energy of the audio signal to a fixed range to ensure that the audio under different recording conditions has a similar dynamic range. Equalization processing is to adjust the spectral characteristics of the audio so that certain frequency bands are more prominent or smooth, thereby facilitating subsequent applications. In the embodiment of the present application, the method of preprocessing the audio data can be flexibly selected according to demand and is not limited to the examples given above. By preprocessing the audio data, we can effectively deal with a variety of environmental noises and ensure accurate speech-to-text conversion in complex clinical environments.

[0076] When performing speech recognition on audio data, a suitable speech recognition engine or model can be selected according to the needs. In the embodiments of the present application, there is no restriction on the specific engine or model category. For example, in some embodiments, the Whisper-large-v2 model can be used to implement speech recognition of audio data. The Whisper-large-v2 model is a version in the multilingual speech recognition model series developed by OpenAI and belongs to the Whisper model family. The Whisper model is designed to solve the problem of large-scale multilingual speech recognition and performs well in multiple benchmark tests. The model is built on the Transformer architecture and captures long-range dependencies in audio signals through a self-attention mechanism. Compared with general speech recognition engines or models, the application in the embodiments of the present application can implement speech recognition in a multilingual environment to meet the needs of users with different languages ​​and accents.

[0077] By performing speech recognition on audio data, the corresponding conversation text can be obtained. At present, some commercial automatic speech recognition technologies can realize speech recognition to a certain extent, especially in simplified contexts. However, in the medical field, there are many professional terms and the conversation environment is more complex. The use of automatic speech recognition technology to convert relevant audio data as medical records has obvious deficiencies in accuracy. Moreover, the text obtained by speech recognition itself contains redundant or interfering information, and the quality is low. It is not suitable as a medical record document. It may also need to be edited and modified by doctors, and its practicality is poor.

[0078] Taking the above into consideration, in an embodiment of the present application, the conversation text is also input into a large language model for analysis. Based on the powerful analysis capability of the large language model, the recognized conversation text can be parsed and organized to output the required information. Exemplarily, in an embodiment of the present application, the large language model may be required to output the patient's chief complaint information, current medical history information, past medical history information, and related information based on the conversation text, but is not limited to this. Among them, the chief complaint information is the main symptom or problem described by the patient. The current medical history information is a detailed description of the current disease or symptoms, including time, changes, etc. Past medical history information is a record of the patient's past health status, including past diseases, surgeries, etc. Related information is other information related to the current symptoms or diseases to help doctors comprehensively judge the condition.

[0079] Specifically, when using a large language model, you can input a prompt to it to instruct the large language model to process related tasks. For example, you can set the prompt to "If you are a doctor, you currently need to organize relevant medical records based on the dialogue text generated by the conversation with the patient. Please output the patient's chief complaint information, current medical history information, past medical history information, and related information based on the input dialogue text." Then, you can input the dialogue text and the prompt together into the large language model, and use the large language model to perform semantic recognition and processing to obtain the required information.

[0080] In the embodiment of the present application, according to the patient's chief complaint information, current medical history information, past medical history information and related information output by the large language model, a medical record document corresponding to the patient in the medical diagnosis process can be generated. Figure 3 , Figure 3 A schematic diagram of a medical record document provided in an embodiment of the present application is shown, based on Figure 3 It can be seen that the present application can easily generate corresponding medical records by analyzing the audio data generated by the conversation between doctors and patients, which can effectively improve the efficiency of organizing and outputting medical records. Moreover, compared with the traditional manual recording method, the medical records obtained by this method have better accuracy and completeness, which is conducive to improving the usability of medical records.

[0081] In some embodiments, after obtaining the patient's chief complaint information, current medical history information, past medical history information, and related information output by the large language model, a medical record document corresponding to the patient in the current medical diagnosis process can be generated. Specifically, for example, the system can automatically obtain the patient's basic information, such as name, gender, age, etc., and obtain a pre-set medical record template, which may include positions reserved for various types of information to be filled in. After obtaining the medical record template, the patient's chief complaint information, current medical history information, past medical history information, and related information output by the large language model can be filled into the medical record template together with the patient's basic information to obtain a medical record document. Of course, it is understandable that other information may also be included in the medical record document, and this application does not limit this.

[0082] Specifically, in some embodiments, the step of obtaining audio data generated by a conversation between a doctor and a patient during a medical diagnosis process includes:

[0083] In response to the doctor's recording operation, starting a recording device;

[0084] The audio data generated by the conversation between the doctor and the patient during the medical diagnosis process is collected through the recording device.

[0085] In an embodiment of the present application, when acquiring audio data, the doctor may know when to start recording. For example, the doctor may perform a recording operation, which may be a key operation, a touch operation, etc., and the present application does not limit this. Then, in response to the doctor's recording operation, the recording device may be started, so that the recording device may be used to collect the audio data generated by the conversation between the doctor and the patient during the medical diagnosis process. The doctor's recording operation is used to determine when to collect audio data, which can facilitate the distinction of audio data corresponding to different patients, and can also accurately and completely collect all audio data in a medical diagnosis process, which can improve efficiency during subsequent identification and analysis.

[0086] Specifically, in some embodiments, the large language model is obtained by the following steps:

[0087] Obtain pre-trained large base models and training datasets in the medical field;

[0088] The parameters of the base large model are fine-tuned and trained using the training data set to obtain a trained large language model.

[0089] In the embodiment of the present application, the large language model can be obtained through fine-tuning training of the base large model. The base large model can be of any type, and the present application does not limit this. When fine-tuning the base large model, a training data set in the medical field can be obtained, and its parameters can be fine-tuned using the training data set in the medical field to obtain a trained large language model. It is understandable that conventional large language models can achieve good results in ordinary text processing tasks, but the medical field is highly professional and has high performance requirements for large language models. In the embodiment of the present application, by fine-tuning the parameters of the base large model, the large language model can be helped to learn medical field knowledge, which is conducive to improving its text processing performance in the medical field.

[0090] Exemplarily, for the base large model, it can adopt the Qwen-7B model, which is a large-scale pre-trained language model based on the Transformer architecture, developed by Alibaba Cloud, with 7 billion parameters, so it is called Qwen-7B. This large language model is designed to handle various natural language processing (NLP) tasks, including but not limited to text generation, question answering, dialogue systems, translation, and summarization. The model has been extensively pre-trained and performs well on multiple language tasks. It can share knowledge between different tasks, so that it can perform better on new tasks.

[0091] Reference Figure 4 , Figure 4A schematic diagram of the implementation of the method provided in the embodiment of the present application is shown. The method provided in the embodiment of the present application effectively solves the problems existing in the prior art, such as insufficient voice recognition accuracy, inefficient manual recording, data privacy risks, and insufficient multi-language support, and provides the medical industry with an efficient and accurate solution for generating medical medical records. When the method of the present application is executed, a modular system architecture can be constructed, including an input component, a voice recognition component, and a medical record text generation component, which can bring an efficient workflow and a convenient operating experience. This structured design allows efficient connection between modules, simplifies the information flow process, improves the response speed of the overall system, enables doctors to quickly generate medical medical record documents, and reduces the clinical workload.

[0092] Reference Figure 5 In an embodiment of the present application, a device for generating a medical record document is also provided, comprising:

[0093] An acquisition unit 510 is used to acquire audio data generated by the conversation between the doctor and the patient during the medical diagnosis process;

[0094] The recognition unit 520 is used to perform speech recognition on the audio data to obtain a conversation text corresponding to the audio data;

[0095] An analysis unit 530 is used to input the conversation text into a large language model for analysis, and output the patient's chief complaint information, current medical history information, past medical history information, and related information through the large language model;

[0096] The generating unit 540 is used to generate a medical record document corresponding to the patient in the medical diagnosis process according to the chief complaint information, the current medical history information, the past medical history information and the associated information.

[0097] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0098] Reference Figure 6 , an embodiment of the present application provides an electronic device, including:

[0099] at least one processor 610;

[0100] At least one memory 620, used to store at least one program;

[0101] When at least one program is executed by at least one processor 610, at least one processor 610 implements the above-mentioned method for generating a medical case record document.

[0102] Similarly, the contents of the above method embodiments are all applicable to the electronic device embodiments. The functions specifically implemented by the electronic device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0103] The embodiment of the present application also provides a computer-readable storage medium, which stores a program executable by the processor 610. The program executable by the processor 610 is used to execute the above-mentioned method for generating a medical case record document when executed by the processor 610.

[0104] Similarly, the contents of the above method embodiments are all applicable to the computer-readable storage medium embodiments. The functions specifically implemented by the computer-readable storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0105] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the application is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part described as a larger operation is performed independently.

[0106] In addition, although the present application is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present application. More specifically, in view of the properties, functions, and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional techniques of the engineer. Therefore, those skilled in the art can implement the present application set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present application, which is determined by the full scope of the attached claims and their equivalents.

[0107] 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, 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 several instructions for a device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0108] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0109] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0110] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0111] In the above description of this specification, the description with reference to the terms "one embodiment / example", "another embodiment / example" or "certain embodiments / examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0112] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.

[0113] The above is a specific description of the preferred implementation of the present application, but the present application is not limited to the embodiments. Technical personnel familiar with the field can make various equivalent modifications or substitutions without violating the spirit of the present application. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present application.

Claims

1. A method for generating a medical record document, characterized in that: The method comprises: Acquire audio data generated by the conversation between doctors and patients during medical diagnosis; Performing speech recognition on the audio data to obtain a conversation text corresponding to the audio data; Inputting the conversation text into a large language model for analysis, and outputting the patient's chief complaint information, current medical history information, past medical history information, and related information through the large language model; A medical record document corresponding to the patient in the medical diagnosis process is generated according to the chief complaint information, the current medical history information, the past medical history information and the associated information.

2. A method for generating a medical record document according to claim 1, characterized in that: The acquisition of audio data generated by the conversation between the doctor and the patient during the medical diagnosis process includes: In response to the doctor's recording operation, starting a recording device; The audio data generated by the conversation between the doctor and the patient during the medical diagnosis process is collected through the recording device.

3. A method for generating a medical record document according to claim 1, characterized in that: The performing speech recognition on the audio data to obtain a conversation text corresponding to the audio data includes: Input the audio data into the Whisper-large-v2 model; The audio data is subjected to speech recognition by the Whisper-large-v2 model to obtain a conversation text corresponding to the audio data.

4. A method for generating a medical record document according to claim 1, characterized in that: The large language model is obtained by the following steps: Obtain pre-trained large base models and training datasets in the medical field; The parameters of the base large model are fine-tuned and trained using the training data set to obtain a trained large language model.

5. A method for generating a medical record document according to claim 4, characterized in that: The large base model is the Qwen-7B model.

6. A method for generating a medical record document according to claim 1, characterized in that: The performing speech recognition on the audio data to obtain a conversation text corresponding to the audio data includes: Preprocessing the audio data; wherein the preprocessing includes at least one of noise reduction processing, silence removal processing, normalization processing, and equalization processing; Speech recognition is performed on the preprocessed audio data to obtain a conversation text corresponding to the audio data.

7. A method for generating a medical record document according to claim 1, characterized in that: Generating a medical record document corresponding to the patient in the medical diagnosis process according to the chief complaint information, the current medical history information, the past medical history information and the associated information includes: Obtaining basic information and medical record template of the patient; The chief complaint information, the current medical history information, the past medical history information, the related information and the basic information are filled into the medical record template to obtain the medical record document.

8. A device for generating medical records, characterized in that: The device comprises: An acquisition unit, used to acquire audio data generated by the conversation between the doctor and the patient during the medical diagnosis process; A recognition unit, configured to perform speech recognition on the audio data to obtain a conversation text corresponding to the audio data; An analysis unit, used for inputting the conversation text into a large language model for analysis, and outputting the patient's chief complaint information, current medical history information, past medical history information, and related information through the large language model; A generating unit is used to generate a medical record document corresponding to the patient in the medical diagnosis process according to the chief complaint information, the current medical history information, the past medical history information and the associated information.

9. An electronic device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements a method for generating a medical case record document as described in any one of claims 1-7.

10. A computer-readable storage medium storing a program executable by a processor, characterized in that: The processor-executable program is used to implement a method for generating a medical case record document as described in any one of claims 1-7 when executed by the processor.

Images