Electronic case intelligent generation method, system and equipment

Abstract

The invention provides an electronic case intelligent generation method, system and device, and relates to the field of electronic case intelligent generation, and the method comprises the steps: inputting a skin disease image of a patient into a multi-modal model, and outputting the text description of the skin disease image; based on an electronic case template, recognizing a dialogue record when a doctor and a patient are in online inquiry, and extracting patient reply content related to the electronic case template in the dialogue record; adding the patient reply content and the text description to the electronic case template to generate an electronic case; judging whether the electronic case is complete or not; if yes, outputting the electronic case; and if not, automatically generating a regularized question corresponding to default information existing in the electronic case, outputting the regularized question to the patient, and re-identifying a dialogue record of the doctor and the patient during online inquiry until the electronic case is complete. According to the invention, the time for sorting electronic cases can be shortened.

Description

Technical Field

[0001] This invention relates to the field of intelligent electronic medical record generation, and in particular to a method, system and device for intelligent electronic medical record generation. Background Technology

[0002] Online consultations greatly simplify the process compared to in-person consultations at medical institutions and increase the number of patients doctors can see. However, organizing electronic medical records is a time-consuming and laborious task for doctors. Summary of the Invention

[0003] The purpose of this invention is to provide a method, system, and device for intelligent generation of electronic medical records, in order to solve the problem of time-consuming electronic medical record processing.

[0004] To achieve the above objectives, the present invention provides the following solution:

[0005] A method for intelligent generation of electronic medical records, comprising:

[0006] The patient's skin disease images are input into a multimodal model, which outputs a text description of the skin disease images.

[0007] Based on the electronic medical record template, the dialogue records between doctors and patients during online consultations are identified, and the patient's response content related to the electronic medical record template is extracted from the dialogue records.

[0008] Add the patient's response and the text description to the electronic medical record template to generate an electronic medical record;

[0009] Determine whether the electronic medical record is complete;

[0010] If so, output the electronic medical record;

[0011] If not, the system automatically generates a rule-based question corresponding to the default information in the electronic medical record and outputs it to the patient, and re-identifies the online consultation records between the doctor and the patient until the electronic medical record is complete.

[0012] Optionally, the patient's skin disease image is input into the multimodal model, and a text description of the skin disease image is output, specifically including:

[0013] The patient's skin disease images are input into the multimodal model, which outputs a textual description of the global features of the skin lesions.

[0014] The patient's skin disease images are input into the skin lesion detection model to determine the local skin lesion detection box;

[0015] The local lesion area of ​​the skin disease image is cropped according to the local lesion detection frame;

[0016] The local skin lesion area is input into the multimodal model, and a textual description of the local texture features of the skin lesion is output.

[0017] Optionally, based on the electronic medical record template, the dialogue records between the doctor and the patient during online consultations are identified, and the patient's responses related to the electronic medical record template are extracted from the dialogue records, specifically including:

[0018] Identify online consultation records between doctors and patients;

[0019] Determine whether the keywords in the electronic medical record template appear in the doctor's questions;

[0020] If so, extract the patient's response to the doctor's question;

[0021] If not, ignore the doctor's question.

[0022] Optionally, the system automatically generates rule-based questions corresponding to the default information in the electronic medical record and outputs them to the patient, specifically including:

[0023] Automatically generate rule-based questions corresponding to the default information in the electronic medical record, and display the rule-based questions to the doctor;

[0024] The doctor selectively decides whether to continue asking questions based on the established set of questions.

[0025] If so, the standardized questions will be automatically output to the patient;

[0026] If not, end the conversation.

[0027] An intelligent electronic medical record generation system includes:

[0028] The text description output module is used to input the patient's skin disease image into the multimodal model and output a text description of the skin disease image;

[0029] The patient response content extraction module is used to identify the dialogue records between doctors and patients during online consultations based on electronic medical record templates, and extract the patient response content related to the electronic medical record templates from the dialogue records.

[0030] An electronic medical record generation module is used to add the patient's response content and the text description to the electronic medical record template to generate an electronic medical record.

[0031] The judgment module is used to determine whether the electronic medical record is complete;

[0032] Electronic medical record output module, used to output the electronic medical record if so;

[0033] The automatic questioning module is used to automatically generate rule-based questions corresponding to the default information in the electronic medical record and output them to the patient if no, and to re-identify the online consultation records between the doctor and the patient until the electronic medical record is complete.

[0034] Optional, a text description output module, specifically including:

[0035] The text description output unit for global features of skin lesions is used to input the patient's skin disease image into the multimodal model and output a text description of global features of skin lesions.

[0036] The local lesion detection bounding box determination unit is used to input the patient's skin disease image into the lesion detection model and determine the local lesion detection bounding box.

[0037] The cropping unit is used to crop the local lesion area of ​​the skin disease image according to the local lesion detection box;

[0038] The text description output unit for the local texture features of the skin lesion is used to input the local skin lesion area into the multimodal model and output a text description of the local texture features of the skin lesion.

[0039] Optionally, the patient response content extraction module specifically includes:

[0040] The identification unit is used to identify the dialogue records between doctors and patients during online consultations.

[0041] The keyword judgment unit is used to determine whether the keywords in the electronic medical record template appear in the doctor's questions;

[0042] The extraction unit is used to extract the patient's response content corresponding to the doctor's question if the question is answered correctly.

[0043] The ignore unit is used to ignore the doctor's question if no.

[0044] Optionally, the automatic questioning module specifically includes:

[0045] The rule-based question generation and display unit is used to automatically generate rule-based questions corresponding to the default information existing in the electronic medical record, and display the rule-based questions to the doctor;

[0046] The questioning decision unit is used by the doctor to selectively determine whether to continue asking questions based on the rule-based questions.

[0047] An automatic output unit is used to automatically output the rule-based question to the patient if necessary.

[0048] End Dialogue Unit, used to end the dialogue if no.

[0049] An electronic device includes a memory and a processor, the memory storing a computer program and the processor running the computer program to enable the electronic device to perform the above-described intelligent electronic medical record generation method.

[0050] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described intelligent electronic medical record generation method.

[0051] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects: The present invention inputs a patient's skin disease image into a multimodal model to obtain a text description of the skin disease image, and based on an electronic medical record template, identifies online consultation records, extracts patient response information related to the electronic medical record template from the dialogue records, adds the text description and patient response information to the electronic medical record template, generates an electronic medical record, and continues until the electronic medical record is complete, eliminating the step of doctors manually inputting medical records, improving doctors' work efficiency, and shortening the time spent compiling electronic medical records. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 The flowchart of the intelligent electronic medical record generation method provided by the present invention is shown below;

[0054] Figure 2 This is a schematic diagram of an electronic medical record. Detailed Implementation

[0055] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0056] The purpose of this invention is to provide a method, system, and device for intelligent generation of electronic medical records, which can shorten the time required to organize electronic medical records.

[0057] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0058] Example 1

[0059] like Figure 1 As shown, the present invention provides an intelligent electronic medical record generation method, comprising:

[0060] Step 101: Input the patient's skin disease image into the multimodal model and output a text description of the skin disease image.

[0061] In practical applications, step 101 specifically includes: inputting the patient's skin disease image into the multimodal model and outputting a text description of the global features of the skin lesions; inputting the patient's skin disease image into the skin lesion detection model and determining local skin lesion detection boxes; cropping the local skin lesion region of the skin disease image according to the local skin lesion detection boxes; inputting the local skin lesion region into the multimodal model and outputting a text description of the local texture features of the skin lesions.

[0062] In practical applications, multimodal model training involves collecting relevant web pages containing information on dermatological diseases, including publicly available datasets of dermatological images and corresponding text information. Annotators clean and label the collected content, constructing image-text pairs as the training set for the multimodal model. The chosen multimodal model is Blip, based on the Transformer. First, a pre-trained Blip model is downloaded, and then fine-tuned using the collected image-text dataset. This allows the Blip model to learn knowledge related to dermatological diseases.

[0063] As an optional implementation of the present invention, image content understanding: When a patient consults online, they can upload an image of their skin condition. This image is used as input to the Blip model, which outputs a text description of the input image. For example, if an image of psoriasis is input, the Blip model outputs the text description "thick, raised patches on the skin surface; irregularly shaped red patches".

[0064] Next, skin lesion region detection was performed on the dermatology images. Specifically, skin disease images were collected from relevant web pages containing dermatology information and publicly available datasets containing dermatology pictures. Annotators cleaned and labeled the collected content. The labeled dermatology images were then used as training data to train the lesion detection model. The lesion detection model is a Transformer-based object detection model called DINO. The model outputs bounding boxes for local lesions, and then the corresponding regions are cropped from the dermatology images based on the coordinates of the bounding boxes. Similarly, the cropped lesion images are also input into the Blip model, which outputs text descriptions. The text descriptions generated by the Blip model twice are recorded in the electronic medical record.

[0065] Step 102: Based on the electronic medical record template, identify the dialogue records between the doctor and the patient during the online consultation, and extract the patient's reply content related to the electronic medical record template from the dialogue records.

[0066] In practical applications, step 102 specifically includes: identifying the dialogue records between doctors and patients during online consultations; determining whether the keywords in the electronic medical record template appear in the doctor's question; if so, extracting the patient's response content corresponding to the doctor's question; if not, ignoring the doctor's question.

[0067] As an optional implementation of the present invention, dialogue content understanding: identify the dialogue records between doctors and patients during online consultations, and if the doctor's questions contain keywords from the medical record, then fill the patient's answers into the electronic medical record.

[0068] For example, the doctor asks, "Have you ever had a drug allergy before?" and the patient replies, "Adapalene." The doctor's question uses "drug allergy" as a keyword in the case file, so the patient should enter "Adapalene" in the case file.

[0069] Step 103: Add the patient's response and the text description to the electronic medical record template to generate an electronic medical record.

[0070] By understanding image content and dialogue content, doctor-patient dialogue information is organized into standardized electronic medical records.

[0071] Step 104: Determine whether the electronic medical record is complete. If yes, proceed to step 105; otherwise, proceed to step 106.

[0072] After steps 101-103, some information in the electronic medical record has been completed. If any relevant information is still missing, such as "onset period," the corresponding standardized questions will be automatically output after the doctor's consultation, such as "How long is your onset period?", and displayed to the doctor. The doctor can choose whether to continue asking questions. If so, steps 102 and 103 will be repeated until the doctor ends the consultation. After the consultation ends, the revised electronic medical record will be displayed to the doctor.

[0073] The steps to determine if an electronic medical record is complete are as follows: When implementing this in code, all information in the record is stored in the form of a dictionary, where "Name" is the key and "Zhang San" is the corresponding value. Initially, all key values ​​are empty strings. To determine if the record is complete, iterate through each key in the dictionary. If its corresponding value is an empty string, it means that no information has been entered for that key, indicating that the dictionary is incomplete. If all key values ​​are not empty strings, it means the record is complete.

[0074] Step 105: Output the electronic medical record.

[0075] Step 106: Automatically generate rule-based questions corresponding to the default information in the electronic medical record and output them to the patient, and re-identify the online consultation records between the doctor and the patient until the electronic medical record is complete.

[0076] In practical applications, step 106 specifically includes: automatically generating rule-based questions corresponding to the default information existing in the electronic medical record, and displaying the rule-based questions to the doctor; the doctor selectively determines whether to continue asking questions based on the rule-based questions; if yes, the rule-based questions are automatically output to the patient; if no, the dialogue ends.

[0077] Figure 2 This is a schematic diagram of an electronic medical record, such as... Figure 2 As shown, "lesion images" are skin disease images uploaded by the patient, "patient self-report" is the patient's description of their condition, and "lesion characteristics" is the text description output by the Blip model in step 2. If questions such as "relevant medical history" and "drug allergy history" are mentioned in the doctor-patient dialogue, the corresponding answers are extracted in step 3 and filled into the case file. If the relevant questions are not mentioned, the corresponding questions are automatically sent to the patient after the doctor-patient dialogue ends, and the patient's answers are extracted (step 4). "Pathological diagnosis" and "treatment suggestions" are filled in by the doctor.

[0078] This invention uses complete skin disease images and local skin lesion images as input to a multimodal model, enabling the text description output by the multimodal model to include both global and local texture features of the skin lesions.

[0079] Image content understanding and dialogue content understanding can completely organize doctor-patient dialogue information into standardized electronic medical record information, eliminating the need for manual input of medical records. This allows doctors to complete medical record information while communicating with patients, saving doctors time in organizing medical records after consultation, improving doctors' work efficiency, and facilitating doctors to review patients' conditions during follow-up visits.

[0080] Example 2

[0081] In order to implement the method corresponding to Embodiment 1 above and achieve the corresponding functions and technical effects, an intelligent electronic medical record generation system is provided below.

[0082] An intelligent electronic medical record generation system includes:

[0083] The text description output module is used to input the patient's skin disease image into the multimodal model and output a text description of the skin disease image.

[0084] The patient response content extraction module is used to identify the dialogue records between doctors and patients during online consultations based on electronic medical record templates, and extract the patient response content related to the electronic medical record template from the dialogue records.

[0085] The electronic medical record generation module is used to add the patient's response and the text description to the electronic medical record template to generate an electronic medical record.

[0086] The judgment module is used to determine whether the electronic medical record is complete.

[0087] An electronic medical record output module is used to output the electronic medical record if the condition is met.

[0088] The automatic questioning module is used to automatically generate rule-based questions corresponding to the default information in the electronic medical record and output them to the patient if no, and to re-identify the online consultation records between the doctor and the patient until the electronic medical record is complete.

[0089] In practical applications, the text description output module specifically includes: a text description output unit for global features of skin lesions, used to input the patient's skin disease image into the multimodal model and output a text description of the global features of the skin lesions; a local skin lesion detection box determination unit, used to input the patient's skin disease image into the skin lesion detection model and determine local skin lesion detection boxes; a cropping unit, used to crop the local skin lesion region of the skin disease image according to the local skin lesion detection boxes; and a text description output unit for local texture features of skin lesions, used to input the local skin lesion region into the multimodal model and output a text description of the local texture features of the skin lesions.

[0090] In practical applications, the patient response content extraction module specifically includes: an identification unit for identifying the dialogue records between doctors and patients during online consultations; a keyword judgment unit for determining whether the keywords in the electronic medical record template appear in the doctor's question; an extraction unit for extracting the patient response content corresponding to the doctor's question if the question appears; and an ignore unit for ignoring the doctor's question if the question does not appear.

[0091] In practical applications, the automatic questioning module specifically includes: a rule-based question generation and display unit, used to automatically generate rule-based questions corresponding to the default information existing in the electronic medical record, and display the rule-based questions to the doctor; a continue questioning judgment unit, used by the doctor to selectively judge whether to continue questioning based on the rule-based questions; an automatic output unit, used to automatically output the rule-based questions to the patient if yes; and an end dialogue unit, used to end the dialogue if no.

[0092] Example 3

[0093] This invention provides an electronic device including a memory and a processor. The memory stores a computer program, and the processor runs the computer program to enable the electronic device to execute the intelligent electronic medical record generation method provided in Embodiment 1.

[0094] In practical applications, the aforementioned electronic devices can be servers.

[0095] In practical applications, electronic devices include: at least one processor, memory, bus, and communication interface.

[0096] The processor, communication interface, and memory communicate with each other via a communication bus.

[0097] A communication interface is used to communicate with other devices.

[0098] The processor is used to execute programs, specifically the methods described in the above embodiments.

[0099] Specifically, the program may include program code, which includes computer operation instructions.

[0100] The processor may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The electronic device may include one or more processors of the same type, such as one or more CPUs; or it may include processors of different types, such as one or more CPUs and one or more ASICs.

[0101] Memory is used to store programs. Memory may include high-speed RAM, and may also include non-volatile memory, such as at least one disk drive.

[0102] Based on the description of the above embodiments, this application provides a storage medium storing computer program instructions thereon, which can be executed by a processor to implement the methods described in any embodiment.

[0103] The electronic medical record intelligent generation system provided in this application exists in various forms, including but not limited to:

[0104] (1) Mobile communication devices: These devices are characterized by their mobile communication capabilities and primarily aim to provide voice and data communication. These terminals include: smartphones (e.g., iPhones), multimedia phones, feature phones, and low-end phones, etc.

[0105] (2) Ultra-mobile personal computer devices: These devices fall under the category of personal computers, possessing computing and processing capabilities, and generally also have mobile internet access capabilities. These terminals include PDAs, MIDs, and UMPCs, such as the iPad.

[0106] (3) Portable entertainment devices: These devices can display and play multimedia content. This category includes: audio and video players (such as iPods), handheld game consoles, e-books, as well as smart toys and portable car navigation devices.

[0107] (4) Other electronic devices with data interaction functions.

[0108] Specific embodiments of the subject matter have now been described. Other embodiments are within the scope of the appended claims. In some cases, the actions described in the claims can be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing can be advantageous.

[0109] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0110] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware components. Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0111] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0112] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0113] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0114] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0115] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0116] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0117] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0118] This application can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific transactions or implement specific abstract data types. This application can also be practiced in distributed computing environments where transactions are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0119] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to the method section.

[0120] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for intelligently generating electronic medical records, characterized in that, include: The patient's skin disease images are input into a multimodal model, which outputs a text description of the skin disease images. Based on the electronic medical record template, the dialogue records between doctors and patients during online consultations are identified, and the patient's response content related to the electronic medical record template is extracted from the dialogue records. Add the patient's response and the text description to the electronic medical record template to generate an electronic medical record; Determine whether the electronic medical record is complete; If so, output the electronic medical record; If not, the system automatically generates a rule-based question corresponding to the default information in the electronic medical record and outputs it to the patient, and re-identifies the online consultation records between the doctor and the patient until the electronic medical record is complete.

2. The method for intelligent generation of electronic medical records according to claim 1, characterized in that, The patient's skin disease images are input into a multimodal model, which outputs a text description of the skin disease images, specifically including: The patient's skin disease images are input into the multimodal model, which outputs a textual description of the global features of the skin lesions. The patient's skin disease images are input into the skin lesion detection model to determine the local skin lesion detection box; The local lesion area of ​​the skin disease image is cropped according to the local lesion detection frame; The local skin lesion area is input into the multimodal model, and a textual description of the local texture features of the skin lesion is output.

3. The method for intelligent generation of electronic medical records according to claim 1, characterized in that, Based on the electronic medical record template, the system identifies the dialogue records between doctors and patients during online consultations, and extracts the patient's responses related to the electronic medical record template from the dialogue records, specifically including: Identify online consultation records between doctors and patients; Determine whether the keywords in the electronic medical record template appear in the doctor's questions; If so, extract the patient's response to the doctor's question; If not, ignore the doctor's question.

4. The method for intelligent generation of electronic medical records according to claim 1, characterized in that, Automatically generate rule-based questions corresponding to the default information in the electronic medical record and output them to the patient, specifically including: Automatically generate rule-based questions corresponding to the default information in the electronic medical record, and display the rule-based questions to the doctor; The doctor selectively decides whether to continue asking questions based on the established set of questions. If so, the standardized questions will be automatically output to the patient; If not, end the conversation.

5. An intelligent electronic medical record generation system, characterized in that, include: The text description output module is used to input the patient's skin disease image into the multimodal model and output a text description of the skin disease image; The patient response content extraction module is used to identify the dialogue records between doctors and patients during online consultations based on electronic medical record templates, and extract the patient response content related to the electronic medical record templates from the dialogue records. An electronic medical record generation module is used to add the patient's response content and the text description to the electronic medical record template to generate an electronic medical record. The judgment module is used to determine whether the electronic medical record is complete; Electronic medical record output module, used to output the electronic medical record if so; The automatic questioning module is used to automatically generate rule-based questions corresponding to the default information in the electronic medical record and output them to the patient if no, and to re-identify the online consultation records between the doctor and the patient until the electronic medical record is complete.

6. The intelligent electronic medical record generation system according to claim 5, characterized in that, The text description output module specifically includes: The text description output unit for global features of skin lesions is used to input the patient's skin disease image into the multimodal model and output a text description of global features of skin lesions. The local lesion detection bounding box determination unit is used to input the patient's skin disease image into the lesion detection model and determine the local lesion detection bounding box. The cropping unit is used to crop the local lesion area of ​​the skin disease image according to the local lesion detection box; The text description output unit for the local texture features of the skin lesion is used to input the local skin lesion area into the multimodal model and output a text description of the local texture features of the skin lesion.

7. The intelligent electronic medical record generation system according to claim 5, characterized in that, The patient response content extraction module specifically includes: The identification unit is used to identify the dialogue records between doctors and patients during online consultations. The keyword judgment unit is used to determine whether the keywords in the electronic medical record template appear in the doctor's questions; The extraction unit is used to extract the patient's response content corresponding to the doctor's question if the question is answered correctly. The ignore unit is used to ignore the doctor's question if no.

8. The intelligent electronic medical record generation system according to claim 5, characterized in that, The automatic questioning module specifically includes: The rule-based question generation and display unit is used to automatically generate rule-based questions corresponding to the default information existing in the electronic medical record, and display the rule-based questions to the doctor; The questioning decision unit is used by the doctor to selectively determine whether to continue asking questions based on the rule-based questions. An automatic output unit is used to automatically output the rule-based question to the patient if necessary. End Dialogue Unit, used to end the dialogue if no.

9. An electronic device, characterized in that, The device includes a memory and a processor, the memory being used to store a computer program, and the processor running the computer program to cause the electronic device to perform the electronic medical record intelligent generation method as described in any one of claims 1-4.

10. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the electronic medical record intelligent generation method as described in any one of claims 1-4.

Images