Online inquiry method and device, computer equipment and storage medium

Abstract

The invention discloses an online inquiry method and device, computer equipment and a storage medium, relates to the technical field of artificial intelligence, and is applied to an online inquiry scene related to medical services, and the method comprises the following steps: obtaining inquiry information and a medical picture input by an online user; performing preprocessing, feature extraction, content identification and content extraction on the medical picture to obtain picture content of the medical picture; the inquiry information and the picture content are integrated, and integrated content is generated; and based on the integrated content, performing analysis through a pre-trained disease diagnosis model, and generating an inquiry result of the online user. According to the method provided by the invention, a more accurate inquiry result can be generated by combining the inquiry information of the user and the picture content of the medical picture.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and is applied to online consultation scenarios related to medical services. In particular, it relates to an online consultation method, device, computer equipment, and non-volatile computer-readable storage medium. Background Art

[0003] At present, online consultation, as an emerging medical model, provides a possibility to solve the problems faced by the above-mentioned offline consultation. It can: provide convenient home medical services for the elderly, simplify the diagnosis and treatment process, improve the medical experience, strengthen doctor-patient communication, and improve the content and quality of medical services.

[0004] However, existing online consultation methods mainly rely on text communication, and deviations in patient expression may lead to inaccurate diagnosis. In addition, although there are many OCR (optical character recognition) technologies on the market, there are still problems such as poor recognition efficiency and accuracy in medical image analysis, resulting in poor accuracy of consultation results in existing online consultation methods.

[0005] Based on this, how to provide an online consultation method, device, computer equipment and non-volatile computer-readable storage medium that can generate more accurate consultation results by combining the user's consultation information with the image content of medical images is a problem that urgently needs to be solved by technical personnel in this field. Summary of the invention

[0006] In view of the above-mentioned deficiencies in the prior art, the object of the present invention is to provide an online consultation method, apparatus, computer device and non-volatile computer-readable storage medium, aiming to solve the problem of how to generate more accurate consultation results by combining the user's consultation information with the image content of medical images.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] An online consultation method, comprising:

[0009] Obtain medical consultation information and medical images input by online users;

[0010] After preprocessing, feature extraction, content recognition and content extraction of the medical image, the image content of the medical image is obtained;

[0011] Integrate the medical consultation information with the image content to generate integrated content;

[0012] Based on the integrated content, analysis is performed using a pre-trained disease diagnosis model to generate the online user's consultation results.

[0013] In a further technical solution, the online consultation method, wherein the obtaining of the consultation information and medical images input by the online user, comprises:

[0014] Pre-build the online consultation interface;

[0015] The consultation information and medical pictures input by the online user are obtained through the online consultation interface; wherein, when the medical picture file input by the online user is a PDF file, the PDF file is converted into a picture file as the medical picture.

[0016] In a further technical solution, the online consultation method, wherein the image content of the medical image is obtained after the preprocessing, feature extraction, content recognition and content extraction of the medical image, comprises:

[0017] Preprocessing the acquired medical image to obtain a processed image;

[0018] Performing feature extraction on the processed image to obtain feature information;

[0019] Based on the feature information, performing content recognition on the processed image to obtain content to be extracted;

[0020] Based on the content to be extracted, content extraction is performed on the processed image to obtain the image content of the medical image.

[0021] In a further technical solution, the online consultation method, wherein the step of integrating the consultation information with the image content to generate integrated content, comprises:

[0022] Extracting information from the acquired medical inquiry information to obtain keywords and emotional states of the medical inquiry information;

[0023] Arrange the keywords and the emotional state to obtain text content corresponding to the medical consultation information;

[0024] The text content and the image content are integrated using data fusion technology to generate integrated content.

[0025] In a further technical solution, the online consultation method, wherein the analysis based on the integrated content is performed by a pre-trained disease diagnosis model to generate the consultation result of the online user, comprises:

[0026] Pre-build disease diagnosis models;

[0027] Inputting the integrated content into the pre-trained disease diagnosis model to generate a preliminary diagnosis result for the online user;

[0028] Post-processing the preliminary diagnosis result to generate the consultation result of the online user;

[0029] The consultation result is output or displayed.

[0030] In a further technical solution, the online consultation method, wherein the post-processing of the preliminary diagnosis result to generate the consultation result of the online user includes:

[0031] Verifying the preliminary diagnosis result and generating a verification result;

[0032] Based on the verification result, the preliminary diagnosis result is adjusted to generate the consultation result for the online user.

[0033] In a further technical solution, the online consultation method, wherein the step of outputting or displaying the consultation result comprises:

[0034] Formatting the medical consultation results;

[0035] The formatted consultation results are output or displayed.

[0036] An online medical consultation device, comprising:

[0037] The acquisition module is used to obtain the consultation information and medical images input by online users;

[0038] A processing module, used for performing preprocessing, feature extraction, content recognition and content extraction on the medical image to obtain the image content of the medical image;

[0039] An integration module, used to integrate the medical consultation information with the image content to generate integrated content;

[0040] The analysis module is used to analyze the integrated content through a pre-trained disease diagnosis model to generate the consultation result of the online user.

[0041] A computer device, wherein the computer device comprises at least one processor; and

[0042] a memory communicatively connected to the at least one processor; wherein,

[0043] The memory stores a computer program that can be executed by the at least one processor. When the computer program is executed by the at least one processor, the online medical consultation method as described in any one of the above items can be implemented.

[0044] A non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by at least one processor, it can implement the online medical consultation method as described in any one of the above items.

[0045] Compared with the prior art, the present invention provides an online consultation method, device, computer equipment and non-volatile computer-readable storage medium, wherein the method includes: obtaining consultation information and medical images input by online users; performing preprocessing, feature extraction, content recognition and content extraction on the medical images to obtain the image content of the medical images; integrating the consultation information with the image content to generate integrated content; and based on the integrated content, analyzing through a pre-trained disease diagnosis model to generate the consultation result of the online user. In this way, the method of the present invention can generate more accurate consultation results by combining the user's consultation information with the image content of the medical images. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1 A flowchart of an online medical consultation method provided by an embodiment of the present invention.

[0048] Figure 2 A schematic diagram of a program module of an online medical consultation device provided in an embodiment of the present invention.

[0049] Figure 3 A schematic diagram of the hardware structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and effect of the present invention clearer and more specific, the present invention is further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0051] In the description of the present invention, the terms "include", "including", "have", "contain", etc. are all open terms, which mean including but not limited to. The descriptions with reference to the terms "one embodiment", "a specific embodiment", "some embodiments", "for example", etc. mean that the specific features, structures 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 representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. The order of steps involved in each embodiment is used to schematically illustrate the implementation of the present application, and the order of steps therein is not limited and can be appropriately adjusted as needed.

[0052] Various non-limiting embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0054] At present, online consultation, as an emerging medical model, provides a possibility to solve the problems faced by the above-mentioned offline consultation. It can: provide convenient home medical services for the elderly, simplify the diagnosis and treatment process, improve the medical experience, strengthen doctor-patient communication, and improve the content and quality of medical services.

[0055] However, existing online consultation methods mainly rely on text communication, and deviations in patient expression may lead to inaccurate diagnosis. In addition, although there are many OCR (optical character recognition) technologies on the market, there are still problems such as poor recognition efficiency and accuracy in medical image analysis, resulting in poor accuracy of consultation results in existing online consultation methods.

[0056] Based on this, how to provide an online consultation method, device, computer equipment and non-volatile computer-readable storage medium that can generate more accurate consultation results by combining the user's consultation information with the image content of medical images is a problem that urgently needs to be solved by technical personnel in this field.

[0057] To solve the above problems, see Figure 1 The embodiment of the present invention provides an online consultation method, wherein the method specifically comprises the following steps:

[0058] S100, obtaining medical consultation information and medical images input by an online user;

[0059] S200, obtaining the image content of the medical image after preprocessing, feature extraction, content recognition and content extraction of the medical image;

[0060] S300, integrating the medical consultation information with the picture content to generate integrated content;

[0061] S400: Based on the integrated content, a pre-trained disease diagnosis model is used for analysis to generate a consultation result for the online user.

[0062] Specifically, in the present invention, the medical consultation information refers to the text information (such as words, numbers, etc.) input by the online user during the interaction with the program; the medical picture refers to the picture containing one or more information such as images, words, numbers, symbols, etc. input by the online user during the interaction with the program, which can be in the format of JPG, PNG, etc., including but not limited to the online user's examination report, test report, physical examination report, affected area photo, etc.; the picture content is the content information contained in the medical picture obtained after preprocessing, feature extraction, content recognition and content extraction of the medical picture.

[0063] Furthermore, the online consultation method, wherein the step S100, obtaining the consultation information and medical images input by the online user, specifically comprises the steps of:

[0064] Pre-build the online consultation interface;

[0065] The consultation information and medical pictures input by the online user are obtained through the online consultation interface; wherein, when the medical picture file input by the online user is a PDF file, the PDF file is converted into a picture file as the medical picture.

[0066] In the specific implementation, in this embodiment, an online consultation interface is pre-built; the consultation information and medical pictures input by the online user are obtained through the online consultation interface; wherein, when the medical picture file input by the online user is a PDF file, the PDF file is converted into a picture file as the medical picture; wherein, the specific implementation process of each of the above steps is roughly as follows:

[0067] 1) Design and develop online consultation interface

[0068] Demand analysis: Determine the needs and functional requirements of online users, including the functions of online users inputting consultation information and medical images;

[0069] Interface design: Design online user-friendly interfaces, including layout, color scheme, and navigation structure;

[0070] Functional implementation: Develop the front-end interface, including text and image input, file upload controls and submit buttons;

[0071] 2) Realize the function of inputting medical information and medical pictures

[0072] Realize the interactive function of real-time chatting with online users;

[0073] Choose file upload technology: Choose the appropriate technology stack (such as HTML, JavaScript, backend framework) to implement the file upload function;

[0074] Develop upload logic: implement the logic for online users to select and upload files;

[0075] Security considerations: Implement file validation and security measures such as file type checking, size restrictions, and virus scanning;

[0076] 3) Process PDF file conversion

[0077] Choose a PDF processing library: Choose a suitable library (such as Apache PDFBox, iText) to process PDF files;

[0078] Among them, Apache PDFBox is an open source Java tool developed by the Apache Software Foundation for processing PDF documents; it provides a wide range of functions, including creating, rendering, printing, splitting, merging PDF files, and extracting text and metadata; PDFBox supports PDF / A and PDF / UA standards, and can process encrypted and signed PDF files;

[0079] iText is a popular Java library for creating and manipulating PDF, HTML, and RTF documents. iText provides a rich API for creating complex PDF documents, including tables, images, fonts, and form fields. It also supports PDF security features such as encryption, digital signatures, and permission control.

[0080] Write conversion logic: Develop the function of converting PDF files to images, including selecting PDF pages and setting conversion parameters (such as resolution and color mode);

[0081] Integrated conversion function: Integrate PDF conversion logic into the backend processing flow of the online consultation interface;

[0082] Through the above process, a fully functional, user-friendly and secure online consultation interface can be built, allowing online users to upload consultation information and medical images, including converting PDF files into images, to facilitate subsequent disease analysis and diagnosis.

[0083] Furthermore, the online consultation method, wherein the step S200, after preprocessing, feature extraction, content recognition and content extraction of the medical image, obtains the image content of the medical image, specifically comprises the steps of:

[0084] Preprocessing the acquired medical image to obtain a processed image;

[0085] Performing feature extraction on the processed image to obtain feature information;

[0086] Based on the feature information, performing content recognition on the processed image to obtain content to be extracted;

[0087] Based on the content to be extracted, content extraction is performed on the processed image to obtain the image content of the medical image.

[0088] In the specific implementation, in this embodiment, the obtained medical image is preprocessed to obtain a processed image; feature extraction is performed on the processed image to obtain feature information; based on the feature information, content recognition is performed on the processed image to obtain content to be extracted; based on the content to be extracted, content extraction is performed on the processed image to obtain the image content of the medical image; wherein the specific implementation process of each of the above steps is roughly as follows:

[0089] 1) Image preprocessing

[0090] Read images: Use image processing libraries (such as OpenCV, PIL / Pillow, etc.) to load medical image data;

[0091] Image denoising: Apply denoising algorithms (such as Gaussian filtering, median filtering) to reduce noise in images;

[0092] Image enhancement: Enhance image features by adjusting brightness, contrast, sharpening, etc., so that subsequent feature extraction is more accurate;

[0093] Image normalization: scaling image pixel values ​​to a uniform range, usually 0 to 255, for easier processing;

[0094] Image conversion: If necessary, convert the image to grayscale or binary to simplify the processing;

[0095] By performing one or more of the above preprocessing processes on the acquired medical images, corresponding processed images can be obtained;

[0096] 2) Feature extraction

[0097] Edge detection: Apply edge detection algorithms (such as Canny edge detector) to identify edge features in the image;

[0098] Texture analysis: Analyze the texture features of the image, which may involve methods such as gray-level co-occurrence matrix (GLCM);

[0099] Shape analysis: extracting shape features of objects in images, such as circles, rectangles, etc.

[0100] Deep learning feature extraction: Use pre-trained deep learning models (such as CNN) to extract deep features of processed images;

[0101] By performing one or more of the above feature extraction processes on the processed image, the corresponding feature information can be obtained;

[0102] 3) Content Identification

[0103] Feature matching: matching the extracted features with a known medical feature database;

[0104] Pattern recognition: using machine learning or deep learning algorithms to identify specific patterns or objects in images;

[0105] Decision support system: using expert systems or decision trees to assist in identifying and classifying image content;

[0106] By performing one or more of the above-mentioned content recognition processes on the processed image based on the feature information, the corresponding content to be extracted can be obtained;

[0107] 4) Content Extraction

[0108] Key area positioning: Identify and locate key areas in the image, such as the corresponding lesion area in the image;

[0109] Labeling and quantification: The identified key areas can be labeled and necessary quantitative analysis can be performed, such as measuring size, shape parameters, etc.

[0110] Structured data generation: Convert the extracted content into a structured data format, such as JSON or XML, for easy storage and further analysis;

[0111] By performing one or more of the above-mentioned content extraction processes on the processed image based on the content to be extracted, the image content of the medical image can be obtained;

[0112] Through the above process, the processing and analysis process of medical images can be standardized and automated, and then through a high-precision and high-efficiency medical image recognition process, the image content of the medical images can be obtained, thereby improving the efficiency and accuracy of subsequent disease analysis and diagnosis.

[0113] Furthermore, the online consultation method, wherein the step S300, integrating the consultation information with the image content to generate integrated content, specifically comprises the steps of:

[0114] Extracting information from the acquired medical inquiry information to obtain keywords and emotional states of the medical inquiry information;

[0115] Arrange the keywords and the emotional state to obtain text content corresponding to the medical consultation information;

[0116] The text content and the image content are integrated using data fusion technology to generate integrated content.

[0117] Furthermore, the online consultation method, wherein the step S400, based on the integrated content, is analyzed by a pre-trained disease diagnosis model to generate the consultation result of the online user, specifically comprises the steps of:

[0118] Pre-build disease diagnosis models;

[0119] Inputting the integrated content into the pre-trained disease diagnosis model to generate a preliminary diagnosis result for the online user;

[0120] Post-processing the preliminary diagnosis result to generate the consultation result of the online user;

[0121] The consultation result is output or displayed.

[0122] Furthermore, the online consultation method, wherein the post-processing of the preliminary diagnosis result to generate the consultation result of the online user, specifically comprises the steps of:

[0123] Verifying the preliminary diagnosis result and generating a verification result;

[0124] Based on the verification result, the preliminary diagnosis result is adjusted to generate the consultation result for the online user.

[0125] Furthermore, the online consultation method, wherein the step of outputting or displaying the consultation result specifically comprises the steps of:

[0126] Formatting the medical consultation results;

[0127] The formatted consultation results are output or displayed.

[0128] In the specific implementation, in this embodiment, information extraction is performed on the obtained medical inquiry information to obtain the keywords and emotional state of the medical inquiry information; the keywords and the emotional state are sorted to obtain the text content corresponding to the medical inquiry information; the text content and the image content are integrated using data fusion technology to generate integrated content; a disease diagnosis model is pre-constructed; the integrated content is input into the pre-trained disease diagnosis model to generate a preliminary diagnosis result for the online user; the preliminary diagnosis result is verified to generate a verification result; based on the verification result, the preliminary diagnosis result is adjusted to generate the medical inquiry result for the online user; the medical inquiry result is formatted; the formatted medical inquiry result is output or displayed; wherein the specific implementation process of each of the above steps is roughly as follows:

[0129] 1) Questioning information processing and sentiment analysis

[0130] 11. Processing of medical consultation information:

[0131] Clean the consultation information, including removing irrelevant characters, correcting typos, and segmenting words;

[0132] Normalize text, such as converting to lowercase, to reduce processing complexity;

[0133] 12. Keyword extraction:

[0134] Use natural language processing (NLP) techniques, such as TF-IDF or Word2Vec, to extract keywords from the medical consultation information;

[0135] Among them, TF-IDF (Term Frequency-Inverse Document Frequency) is a statistical method used to evaluate the importance of a word to a document set or a document in a corpus. It is calculated by multiplying the frequency of a word in a document (TF) by the inverse document frequency (IDF) to obtain the importance score of the word in the document. A high TF-IDF score indicates that the word is relatively important in the document, while a low score indicates that the word appears commonly in the corpus and is not representative enough.

[0136] Word2Vec is a neural network-based algorithm used to learn word vector representations from text corpora. It trains a model by predicting context words, thereby mapping each word to a point in a high-dimensional space. These points (word vectors) can capture the semantic relationship between words. Word2Vec can identify synonyms and antonyms of words, as well as process word analogies. It is one of the commonly used methods of word embedding in natural language processing.

[0137] 13. Emotional state analysis:

[0138] Apply sentiment analysis tools, such as the Sentiment Analysis API or a custom machine learning model, to identify and extract sentiment (positive, negative, or neutral) from text;

[0139] 2) Integration of text content and image content

[0140] The keywords and emotional states of the extracted medical consultation information are sorted to obtain text content corresponding to the medical consultation information, and then the text content is integrated with the image content to generate integrated content;

[0141] Use data fusion techniques, such as decision-level fusion or feature-level fusion, to combine text and image data into a unified dataset;

[0142] 3) Application of disease diagnosis models

[0143] 31. Model training:

[0144] Pre-build and train a disease diagnosis model, either using machine learning or deep learning techniques;

[0145] Use historical medical data to train and validate models;

[0146] 32. Model application:

[0147] Input the integrated content into the pre-trained disease diagnosis model;

[0148] The model analyzes the input and generates a preliminary diagnosis;

[0149] 4) Verification and adjustment of diagnostic results

[0150] 41. Result verification:

[0151] Verify the preliminary diagnosis and generate validation results, which can be done through expert systems or additional clinical data;

[0152] 42. Result adjustment:

[0153] Make necessary adjustments to the initial diagnosis based on the verification results;

[0154] This may involve adjusting model parameters, reanalyzing the data, or incorporating more clinical information;

[0155] 5) Result output or display

[0156] 51.Result formatting:

[0157] Format the final consultation results into a structured, easy to understand and read format;

[0158] 52.Results display:

[0159] The formatted consultation results are displayed to the corresponding online users through the online consultation interface, including the diagnosis conclusion, the recommended treatment plan or further examination suggestions, etc.;

[0160] Alternatively, the formatted consultation results can be output to a designated location as required;

[0161] 53.User feedback:

[0162] A user feedback mechanism can be provided to collect users' opinions and suggestions on the consultation results for further optimization of services and models;

[0163] Through the above process, it can be ensured that the process from generating text and image content to generating the final medical consultation results is a coherent, efficient and user-friendly process, and more accurate medical consultation results can be generated.

[0164] Of course, after generating the corresponding consultation results for online users, the method of the present invention can also be combined with the following subsequent processes:

[0165] 1. Storage of consultation data:

[0166] The core is privacy protection, including data isolation, data encryption and desensitization storage, etc.

[0167] Data isolation is a security measure that involves separating sensitive data or system resources from other data or system resources to reduce unauthorized access and potential security threats. This is usually achieved by storing data in different networks, servers, or databases to ensure that only authorized users can access specific data sets. Data isolation helps prevent data leaks and limit the scope of damage in the event of a security incident.

[0168] Data encryption and desensitization storage refers to encrypting and desensitizing data before storing it to protect the confidentiality and integrity of the data. Encryption is the process of converting data into a format that cannot be read by unauthorized users, so that even if the data is illegally accessed, its content cannot be understood. Desensitization is the removal or modification of sensitive parts of the data, such as personal identity information, to prevent the disclosure of personal privacy. This storage method is an important means of protecting personal and sensitive data from malicious attacks and unauthorized access.

[0169] 2. Processing of consultation data:

[0170] Including the display of consultation data, abnormal consultation label display, and past medical history association;

[0171] 3. Prescription:

[0172] Including diagnosis and treatment recommendations and medical and medication guidance;

[0173] 4. Statistics and analysis of consultation data reports on the management side:

[0174] 1) Regional dimension consultation: data management, statistics and analysis for different geographical regions (such as Northeast China, North China, Central China, South China, East China, Northwest China, and Southwest China);

[0175] 2) Frequent consultation types: According to the classification of medical consultation departments, such as internal medicine, surgery, genetic medicine, pediatrics, gynecology, dentistry, ultrasound, laboratory, traditional Chinese medicine, etc., the user's medical consultation data is analyzed and the data is managed, counted and analyzed;

[0176] 3) Risk identification: Use qualitative research methods such as the Delphi method, expert interviews, and risk matrices, as well as quantitative analysis methods such as infectious disease transmission dynamics models, time series models, and fault tree analysis; combine the patient's medical history and genetic history to analyze and predict the user's medical consultation data, so that the model or medical staff can analyze the condition and provide medical guidance and recommendations;

[0177] Among them, the Delphi method is a systematic qualitative research method that collects and integrates the knowledge and opinions of experts through multiple rounds of anonymous surveys; this method is often used to predict future trends, solve complex problems or reach consensus; in the Delphi method, the researcher first designs a questionnaire containing a series of open-ended questions and then sends it to a group of selected experts; the experts independently provide their answers, and then the researcher summarizes and analyzes these answers and feeds the results back to the experts for further discussion and evaluation; this process may be repeated several times until a consensus is reached or the results are stable; the advantage of the Delphi method is that it can concentrate the wisdom of multiple experts, reduce personal bias, and improve the quality and reliability of decision-making;

[0178] A risk matrix is ​​a risk assessment tool that helps identify, categorize and prioritize risks by depicting the likelihood (or frequency) of a risk and the impact (or severity) it would cause if it occurred. This matrix is ​​usually divided into different risk level areas, such as high, medium and low, so that decision makers can intuitively see which risks require immediate action and which can be monitored or accepted. The risk matrix helps companies or organizations make wise risk management decisions with limited resources, ensuring that key risks receive appropriate attention and control.

[0179] 4) Epidemic reporting: In case of infectious diseases or public health emergencies, reports may be made in accordance with the prescribed time limit, procedures and content; the report content shall include the basic information of the case, symptoms, diagnosis, onset time, medical treatment, etc.;

[0180] 5) The above medical big data has significantly improved the clinical application, medical management application, medical insurance application, and medical research application of the medical system, mainly including:

[0181] 5-1) Support the realization of precision medicine, using big data analysis technology to tailor treatment plans for users to improve treatment effects and prognosis;

[0182] 5-2) Promote the reform of medical and health services, optimize and improve the medical service system through the analysis and mining of medical service data, and improve the level of convenient medical treatment for the people;

[0183] 5-3) Improve medical efficiency, provide hospitals with data-based management solutions through big data technology, and realize refined management of medical resources;

[0184] 5-4) It is of great help to medical research. By mining and analyzing medical research data, it can provide strong support for researchers;

[0185] 5-5) Support medical insurance services and provide better support and management for medical insurance services through analysis and mining of insurance data.

[0186] As can be seen from the above method embodiments, the online consultation method provided by the present invention includes: obtaining the consultation information and medical pictures input by the online user; performing preprocessing, feature extraction, content recognition and content extraction on the medical pictures to obtain the picture content of the medical pictures; integrating the consultation information with the picture content to generate integrated content; and based on the integrated content, analyzing through a pre-trained disease diagnosis model to generate the consultation result of the online user. In this way, the method of the present invention can generate more accurate consultation results by combining the user's consultation information with the picture content of the medical pictures.

[0187] It should be understood that, although the present application provides method operation steps as described in the embodiments or flowcharts, more or less operation steps may be included based on conventional or non-creative labor, and these operation steps are not necessarily performed in sequence according to the embodiment or flowchart. The order of steps listed in the embodiment or flowchart is only one way of executing the order of many steps, and does not represent the only execution order. It should be noted that there is not necessarily a certain order between the above steps. A person of ordinary skill in the art can understand from the description of the embodiment of the present invention that in different embodiments, the above steps may have different execution orders, that is, they may be executed in parallel, or they may be executed in exchange, etc. Moreover, at least a part of the steps in the embodiment or flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but may be executed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but may be executed in turn, alternately or synchronously with other steps or at least a part of the sub-steps or stages of other steps.

[0188] Based on the above method embodiment, please refer to Figure 2 Another embodiment of the present invention further provides an online medical consultation device, wherein the device comprises:

[0189] The acquisition module 11 is used to acquire the medical consultation information and medical images input by the online user;

[0190] A processing module 12 is used to obtain the image content of the medical image after preprocessing, feature extraction, content recognition and content extraction of the medical image;

[0191] An integration module 13, used to integrate the medical consultation information with the image content to generate integrated content;

[0192] The analysis module 14 is used to analyze the integrated content through a pre-trained disease diagnosis model to generate the consultation result of the online user.

[0193] Furthermore, in the online consultation method, the acquisition module 11 specifically includes:

[0194] An interface building unit, used to pre-build an online consultation interface;

[0195] An acquisition unit is used to acquire the consultation information and medical pictures input by the online user through the online consultation interface; wherein, when the medical picture file input by the online user is a PDF file, the PDF file is converted into a picture file as the medical picture.

[0196] Furthermore, in the online consultation method, the processing module 12 specifically includes:

[0197] A preprocessing unit, used to preprocess the acquired medical image to obtain a processed image;

[0198] A feature extraction unit, used to extract features from the processed image to obtain feature information;

[0199] A content recognition unit, configured to perform content recognition on the processed image based on the feature information to obtain content to be extracted;

[0200] A content extraction unit is used to extract content from the processed image based on the content to be extracted to obtain the image content of the medical image.

[0201] Furthermore, in the online consultation method, the integration module 13 specifically includes:

[0202] An information extraction unit, configured to extract information from the acquired medical inquiry information to obtain keywords and emotional states of the medical inquiry information;

[0203] A sorting unit, used for sorting the keywords and the emotional state to obtain text content corresponding to the medical consultation information;

[0204] The integration unit is used to integrate the text content with the image content by using data fusion technology to generate integrated content.

[0205] Furthermore, in the online consultation method, the analysis module 14 specifically includes:

[0206] A model building unit, used to pre-build a disease diagnosis model;

[0207] A content input unit, used for inputting the integrated content into the pre-trained disease diagnosis model to generate a preliminary diagnosis result for the online user;

[0208] A post-processing unit, used to post-process the preliminary diagnosis result to generate a consultation result for the online user;

[0209] The output or display unit is used to output or display the medical consultation result.

[0210] Furthermore, the online consultation method, wherein the post-processing of the preliminary diagnosis result to generate the consultation result of the online user specifically includes:

[0211] Verifying the preliminary diagnosis result and generating a verification result;

[0212] Based on the verification result, the preliminary diagnosis result is adjusted to generate the consultation result for the online user.

[0213] Furthermore, in the online consultation method, the step of outputting or displaying the consultation result specifically includes:

[0214] Formatting the medical consultation results;

[0215] The formatted consultation results are output or displayed.

[0216] The specific implementation process and effects of the device embodiment of the present invention can be found in the above method embodiment, which will not be described in detail here.

[0217] It can be seen from the above device embodiments that the online medical consultation device provided by the present invention includes: an acquisition module for acquiring medical consultation information and medical images input by online users; a processing module for performing preprocessing, feature extraction, content recognition and content extraction on the medical images to obtain the image content of the medical images; an integration module for integrating the medical consultation information with the image content to generate integrated content; and an analysis module for analyzing the integrated content through a pre-trained disease diagnosis model to generate the medical consultation results of the online user. In this way, the device of the present invention can generate more accurate medical consultation results by combining the user's medical consultation information with the image content of the medical images.

[0218] Based on the above method embodiment, please refer to Figure 3 Another embodiment of the present invention further provides a computer device, wherein the computer device 10 comprises:

[0219] memory 120 and one or more processors 110, Figure 3 A processor 110 is used as an example for description. The processor 110 and the memory 120 may be connected via a communication bus or other means. Figure 3 The example of connecting via a communication bus is taken as an example.

[0220] The processor 110 is used to complete various control logics of the computer device 10. It can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a single-chip microcomputer, an ARM (Acorn RISC Machine) or other programmable logic device, a discrete gate or transistor logic, a discrete hardware component, or any combination of these components. In addition, the processor 110 can also be any traditional processor, microprocessor or state machine. The processor 110 can also be implemented as a combination of computing devices, for example, a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors combined with a DSP, or any other such configuration.

[0221] The memory 120, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as the computer program corresponding to the online consultation method in any of the above method embodiments of the present invention. The processor 110 executes various functional applications and data processing of the computer device 10 by running the non-volatile software programs, instructions and units stored in the memory 120, that is, implements the online consultation method in any of the above method embodiments.

[0222] The memory 120 may include a program storage area and a data storage area, wherein the program storage area may store an application required for operating the device or at least one function; the data storage area may store data created according to the use of the computer device 10, etc. In addition, the memory 120 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 120 may optionally include a memory remotely arranged relative to the processor 110, and these remote memories may be connected to the computer device 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0223] One or more units are stored in the memory 120, and when executed by one or more processors 110, the online consultation method in any of the above method embodiments can be implemented, for example, the above described online consultation method can be implemented. Figure 1 The method comprises steps S100 to S400.

[0224] The specific implementation process and effects of the computer device embodiment of the present invention are shown in the above method embodiment, which will not be described in detail here.

[0225] It can be seen from the above computer device embodiments that the computer device provided by the present invention can implement: an acquisition module for acquiring the medical inquiry information and medical images input by online users; a processing module for obtaining the image content of the medical images after preprocessing, feature extraction, content recognition and content extraction of the medical images; an integration module for integrating the medical inquiry information with the image content to generate integrated content; an analysis module for analyzing the integrated content through a pre-trained disease diagnosis model to generate the medical inquiry results of the online user. In this way, the computer device of the present invention can generate more accurate medical inquiry results by combining the user's medical inquiry information with the image content of the medical images.

[0226] Those skilled in the art will understand that Figure 3The hardware structure diagram shown in the figure is only a schematic diagram of a partial structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0227] Based on the above method embodiments, another embodiment of the present invention further provides a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by at least one processor, the online consultation method in any of the above method embodiments can be implemented, for example, the above described Figure 1 The method comprises steps S100 to S400.

[0228] As an example, the non-volatile storage medium can include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable ROM (EEPROM), or a flash memory. Volatile memory can include a random access memory (RAM) as an external cache memory. By way of illustration and not limitation, RAM can be obtained in many forms such as synchronous RAM (SRAM), dynamic RAM, (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synch link DRAM (SLDRAM), and direct Rambus RAM (DRRAM). The disclosed memory components or memories of the operating environment described herein are intended to include one or more of these and / or any other suitable types of memory.

[0229] Based on the above method embodiments, another embodiment of the present invention further provides a computer program product, the computer program product includes a computer program stored on a non-volatile computer-readable storage medium, the computer program includes program instructions, when the program instructions are executed by a processor, the online consultation method in any of the above method embodiments can be implemented, for example, the above described Figure 1 The method comprises steps S100 to S400.

[0230] The embodiments described above are merely illustrative, in which the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0231] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, and of course can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can exist in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0232] Conditional language such as "can," "can," "might," or "may," unless specifically stated otherwise or otherwise understood within the context as used, is generally intended to convey, among other things, that a particular embodiment can include (while other embodiments do not) a particular feature, element, and / or operation. Thus, such conditional language is also generally intended to imply that a feature, element, and / or operation is required for one or more embodiments anyway or that one or more embodiments must include logic for determining, with or without input or prompting, whether such features, elements, and / or operations are included or will be performed in any particular embodiment.

[0233] It should be noted that if there are software tools or components other than those of the company in the embodiments of the present application, they are only used for example introduction and do not represent actual use. The content described in this article, in this specification and in the drawings includes examples that can provide an online consultation method, device, computer equipment and non-volatile computer-readable storage medium. Of course, it is not possible to describe every conceivable combination of elements and / or methods for the purpose of describing the various features of the present disclosure, but it can be recognized that many other combinations and permutations of the disclosed features are possible. Therefore, it is obvious that various modifications can be made to the present disclosure without departing from the scope or spirit of the present disclosure, but all these various modifications should belong to the scope of protection of the claims attached to the present invention. In addition, or in an alternative, other embodiments of the present disclosure may be obvious from consideration of the present specification and the drawings and from the practice of the present disclosure as presented herein. It is intended that the examples proposed in this specification and the drawings are considered to be illustrative and not restrictive in all respects. Although specific terms are used herein, they are used in a general and descriptive sense and are not used for limiting purposes.

Claims

1. An online consultation method, characterized in that: include: Obtain medical consultation information and medical images input by online users; After preprocessing, feature extraction, content recognition and content extraction of the medical image, the image content of the medical image is obtained; Integrate the medical consultation information with the image content to generate integrated content; Based on the integrated content, analysis is performed using a pre-trained disease diagnosis model to generate the online user's consultation results.

2. The online consultation method according to claim 1, characterized in that: The obtaining of the medical consultation information and medical images input by the online user includes: Pre-build online consultation interface; The consultation information and medical pictures input by the online user are obtained through the online consultation interface; wherein, when the medical picture file input by the online user is a PDF file, the PDF file is converted into a picture file as the medical picture.

3. The online consultation method according to claim 1, characterized in that: After the medical image is preprocessed, feature extracted, content identified and content extracted, the image content of the medical image is obtained, including: Preprocessing the acquired medical image to obtain a processed image; Performing feature extraction on the processed image to obtain feature information; Based on the feature information, performing content recognition on the processed image to obtain content to be extracted; Based on the content to be extracted, content extraction is performed on the processed image to obtain the image content of the medical image.

4. The online consultation method according to claim 1, characterized in that: The step of integrating the medical consultation information with the image content to generate integrated content includes: Extracting information from the acquired medical inquiry information to obtain keywords and emotional states of the medical inquiry information; Arrange the keywords and the emotional state to obtain text content corresponding to the medical consultation information; The text content and the image content are integrated using data fusion technology to generate integrated content.

5. The online consultation method according to claim 1, characterized in that: The generating of the online user's consultation result by analyzing the integrated content through a pre-trained disease diagnosis model includes: Pre-build disease diagnosis models; Inputting the integrated content into the pre-trained disease diagnosis model to generate a preliminary diagnosis result for the online user; Post-processing the preliminary diagnosis result to generate the consultation result of the online user; The consultation result is output or displayed.

6. The online consultation method according to claim 5, characterized in that: The post-processing of the preliminary diagnosis result to generate the online user's consultation result includes: Verifying the preliminary diagnosis result and generating a verification result; Based on the verification result, the preliminary diagnosis result is adjusted to generate the consultation result for the online user.

7. The online consultation method according to claim 5 or 6, characterized in that: Outputting or displaying the consultation result includes: Formatting the medical consultation results; The formatted consultation results are output or displayed.

8. An online medical consultation device, characterized in that: include: The acquisition module is used to obtain the consultation information and medical images input by online users; A processing module, used for performing preprocessing, feature extraction, content recognition and content extraction on the medical image to obtain the image content of the medical image; An integration module, used to integrate the medical consultation information with the image content to generate integrated content; The analysis module is used to analyze the integrated content through a pre-trained disease diagnosis model to generate the consultation result of the online user.

9. A computer device, characterized in that: The computer device comprises at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor. When the computer program is executed by the at least one processor, the online medical consultation method according to any one of claims 1 to 7 can be implemented.

10. A non-volatile computer-readable storage medium, characterized in that: The non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by at least one processor, the online medical consultation method according to any one of claims 1 to 7 can be implemented.

Images