Internet-based remote online hospital guide method, device and equipment

Abstract

The invention relates to a remote online hospital guide method, device and equipment based on the Internet, and the method comprises the steps: carrying out the data extraction of a laboratory sheet, obtaining an abnormal item, extracting multiple items of information from an electronic medical record, searching a plurality of to-be-selected patients from a preset database based on the abnormal item and the multiple items of information, and determining the inquiry file of each to-be-selected patient, calculating relevancy between each inquiry file and the abnormal items of the patient and multiple items of information, determining a target file with the highest relevancy, extracting question and answer information of each inquiry file from the plurality of inquiry files, and determining inquiry strategies of the doctor and the patient based on the question and answer information, the method comprises the steps of obtaining abnormal items and multiple items of information, mapping the abnormal items and the multiple items of information into a target file to obtain a to-be-improved inquiry file about a patient, outputting the to-be-improved inquiry file and an inquiry strategy about the doctor to the doctor who inquires the patient, and outputting the inquiry strategy about the patient to the patient. According to the application, the situation that the patient or the doctor misses questions during online inquiry can be reduced.

Description

Technical Field

[0001] The present application relates to the field of computer data processing, and in particular to a remote online diagnosis guidance method, device and equipment based on the Internet. Background Art

[0002] With the development of Internet technology, the forms of medical treatment have become more diversified, such as online video consultations through mobile phone apps.

[0003] When patients and doctors have online consultations, they usually do so through video or video conferencing, with the patient asking questions to the doctor or the doctor asking questions to the patient. However, after the consultation, the patient or doctor may miss or forget to ask some questions, resulting in reduced quality of the consultation and the need to conduct another online video consultation. Summary of the invention

[0004] In order to reduce the situation where patients or doctors miss questions during online consultations, the present application provides an Internet-based remote online consultation method, device and equipment.

[0005] In the first aspect, the present application provides a remote online diagnosis guidance method based on the Internet, which adopts the following technical solution: A remote online diagnosis guidance method based on the Internet, comprising: Obtain the test results and electronic medical records uploaded by the patient; Extracting data from the test report to obtain abnormal items of the patient, and extracting multiple pieces of information from the electronic medical record; Based on the abnormal item and the multiple pieces of information, searching for multiple patients to be selected from a preset database, and determining the medical consultation file of each patient to be selected; Calculate the relevance of each medical consultation file to the abnormal items and multiple pieces of information of the patient, and determine the target file with the highest relevance; Extracting question and answer information of each consultation file from the plurality of consultation files, and determining a consultation strategy of the doctor and the patient based on the question and answer information; Mapping the abnormal items and multiple pieces of information to the target file to obtain a consultation file to be completed for the patient; The consultation file to be completed and the consultation strategy of the doctor are output to the doctor who is consulting the patient, and the consultation strategy of the patient is output to the patient.

[0006] By adopting the above technical solution, the patient's test report and electronic medical record are obtained to facilitate subsequent analysis of the patient's valuable information, data extraction is performed on the test report to obtain the patient's abnormal items, and multiple information is extracted from the electronic medical record to facilitate subsequent analysis of the patient's general situation. A large amount of patient data and files are stored in the preset database. Therefore, based on the abnormal items and multiple information, multiple candidate patients with similar conditions to the patient are searched from the preset database and the medical records of the candidate patients are determined, and the correlation between each medical record and the patient's abnormal items and multiple information is calculated, so as to determine the target file with the highest correlation, and extract the question and answer questions from the medical records of multiple candidate patients with similar conditions to the patient. Questions, based on these questions and answers, it is easy to determine the corresponding consultation strategies for doctors and patients respectively, and the determined target file is the one with the highest relevance to the patient. Therefore, the patient's abnormal items and multiple information are mapped to the target file to obtain the patient's consultation file to be improved, and the consultation file to be improved is output to the consulting doctor, thereby improving the doctor's consultation efficiency and the convenience of subsequently improving the patient's condition and consultation records. Outputting the doctor's consultation strategy is convenient for reminding the doctor whether there are any missed issues, and outputting the patient's consultation strategy is convenient for reminding the patient whether there are any missed issues, thereby reducing the situation where patients or doctors miss questions during online consultations, thereby improving the quality of online consultations.

[0007] In another possible implementation, the plurality of pieces of information include the main symptoms, the main diseases, and medication status, and searching for a plurality of candidates from a preset database based on the abnormal items and the plurality of pieces of information includes: Determine the symptom number corresponding to the main complaint symptom, the disease number of the main complaint disease, and the drug number corresponding to the medication situation; Determine a first characteristic value of the patient based on the symptom number, the disease number, and the drug number; Based on a first similarity between the first feature value and each second feature value, the second feature value is a feature value of each historical patient in the preset database; Determining a plurality of target historical patients whose first similarity reaches a preset similarity threshold; Determine the item number of each abnormal item of the patient, and obtain the item number of the abnormal items corresponding to each of the multiple target historical patients; A plurality of patients to be selected including the item number are determined from the plurality of target historical patients based on the item number of the patient and the item numbers of the plurality of target historical patients.

[0008] In another possible implementation, the calculation of the correlation between each medical consultation file and the abnormal item and multiple pieces of information of the patient includes: Determine the ratio of the number of abnormal items of the patient to the number of abnormal items in each consultation file; Determine the value of each abnormal item from each medical consultation file, and calculate the difference between the value of each abnormal item and the data of the abnormal item of the corresponding patient; Determine the data corresponding to each of the plurality of information in each medical consultation file, and calculate the second similarity between each piece of information and the corresponding data in each medical consultation file; The correlation between the patient and each medical consultation file is determined based on the proportion, the difference and the second similarity.

[0009] In another possible implementation, determining the relevance between the patient and each medical consultation file based on the proportion, the difference, and the second similarity includes: Calculate the average of all second similarities in each consultation file; Obtaining a first similarity between the candidate patient corresponding to each medical consultation file and the patient; A score is calculated based on the proportion, the difference of each abnormal item, the first similarity, the second similarity and the corresponding coefficients, and the score represents the correlation between the patient and each medical consultation file.

[0010] In another possible implementation, determining the consultation strategy of the doctor and the patient based on the question and answer information includes: Extracting all questions from the question-answer information of each consultation file, wherein the questions include a first question asked by the doctor and a second question asked by the patient; Calculate the similarity between each first question and the remaining first questions, and use a clustering algorithm to determine the type of the first question; Calculate the similarity between each second question and the remaining second questions, and use a clustering algorithm to determine the type of the second question; Obtaining the time point of the first question in each category during each consultation process, and determining the average time point corresponding to each category based on the time point; Determining a target first question from the first questions in each category, and sorting each target first question based on the average time point to obtain a questioning strategy for the doctor; Obtaining the time point of the second question in each category during each consultation process, and determining the average time point corresponding to each category based on the time point; A target second question is determined from the second questions in each category, and each target second question is sorted based on the average time point to obtain a questioning strategy for the patient.

[0011] In another possible implementation, the doctor who interviews the patient outputs the doctor's interview strategy, and outputs the patient's interview strategy to the patient, including: Real-time acquisition of audio information during video consultation between the doctor and the patient; Converting the audio information into text to obtain first text information of the patient and second text information of the doctor; Performing tone recognition on the audio information to obtain the third question in the first text information and the fourth question in the second text information; When it is detected that the number of the third questions reaches a first preset number proportion, a target second question identical to the third question is deleted from the medical consultation strategy for the patient, a first medical consultation strategy after deletion is obtained, and the first medical consultation strategy after deletion is output to the terminal device of the patient; When it is detected that the number of the fourth questions reaches a second preset number, the target first question that is the same as the fourth question is deleted from the doctor's inquiry strategy, a second deleted inquiry strategy is obtained and the second deleted inquiry strategy is output to the doctor's terminal device.

[0012] In another possible implementation manner, the step of outputting the first deleted medical consultation strategy to the terminal device of the patient further includes: Sending a first prompt message to the terminal device of the patient, so that the patient triggers an instruction on whether to consult a question in the first deleted consultation strategy; If an instruction is received that there is no need to consult the questions in the first deleted consultation strategy, a second prompt message is sent to the patient's terminal device so that the patient triggers an instruction on whether to consult other questions.

[0013] In the second aspect, the present application provides an Internet-based remote online medical guidance device, which adopts the following technical solution: A remote online diagnosis guidance device based on the Internet, comprising: Data acquisition module, used to obtain the test reports and electronic medical records uploaded by patients; A data extraction module, used to extract data from the test report to obtain abnormal items of the patient, and extract multiple pieces of information from the electronic medical record; A search module, used for searching a plurality of candidates from a preset database based on the abnormal item and the plurality of information, and determining the medical consultation file of each candidate; A file determination module is used to calculate the correlation between each medical consultation file and the abnormal items and multiple pieces of information of the patient, and determine the target file with the highest correlation; A strategy determination module, configured to extract the question and answer information of each consultation file from the plurality of consultation files, and determine the consultation strategy of the doctor and the patient based on the question and answer information; A data mapping module, used for mapping the abnormal items and multiple pieces of information to the target file, to obtain a consultation file to be completed about the patient; The strategy output module is used to output the consultation file to be completed and the doctor's consultation strategy to the doctor who consults the patient, and output the patient's consultation strategy to the patient.

[0014] By adopting the above technical solution, the data acquisition module obtains the patient's test report and electronic medical record to facilitate the subsequent analysis of the patient's valuable information. The data extraction module extracts data from the test report to obtain the patient's abnormal items and extracts multiple information from the electronic medical record to facilitate the subsequent analysis of the patient's general situation. A large amount of patient data and files are stored in the preset database. Therefore, the search module searches for multiple candidate patients with similar conditions to the patient from the preset database based on the abnormal items and multiple information and determines the medical records of the candidate patients. The file determination module calculates the correlation between each medical record and the patient's abnormal items and multiple information, thereby determining the target file with the highest correlation, and extracts question and answer questions from the medical records of multiple candidate patients with similar conditions to the patient. The strategy The determination module determines the corresponding consultation strategies for doctors and patients based on these questions and answers. The determined target file is the one with the highest relevance to the patient. Therefore, the data mapping module maps the patient's abnormal items and multiple information to the target file to obtain the patient's consultation file to be improved. The strategy output module outputs the consultation file to be improved to the consulting doctor, thereby improving the doctor's consultation efficiency and the convenience of subsequently improving the patient's condition and consultation records. The strategy output module outputs the doctor's consultation strategy to remind the doctor whether there are any missed issues. The strategy output module outputs the patient's consultation strategy to remind the patient whether there are any missed issues, thereby reducing the situation where patients or doctors miss questions during online consultations, thereby improving the quality of online consultations.

[0015] In another possible implementation, the plurality of information includes the main complaint symptoms, the main complaint diseases and medication status, and the search module searches for multiple candidates from a preset database based on the abnormal items and the plurality of information, specifically for: Determine the symptom number corresponding to the main complaint symptom, the disease number of the main complaint disease, and the drug number corresponding to the medication situation; Determine a first characteristic value of the patient based on the symptom number, the disease number, and the drug number; Based on a first similarity between the first feature value and each second feature value, the second feature value is a feature value of each historical patient in the preset database; Determining a plurality of target historical patients whose first similarity reaches a preset similarity threshold; Determine the item number of each abnormal item of the patient, and obtain the item number of the abnormal items corresponding to each of the multiple target historical patients; A plurality of patients to be selected including the item number are determined from the plurality of target historical patients based on the item number of the patient and the item numbers of the plurality of target historical patients.

[0016] In another possible implementation, when calculating the correlation between each medical consultation file and the abnormal item and multiple pieces of information of the patient, the file determination module is specifically used to: Determine the ratio of the number of abnormal items of the patient to the number of abnormal items in each consultation file; Determine the value of each abnormal item from each medical consultation file, and calculate the difference between the value of each abnormal item and the data of the abnormal item of the corresponding patient; Determine the data corresponding to each of the plurality of information in each medical consultation file, and calculate the second similarity between each piece of information and the corresponding data in each medical consultation file; The correlation between the patient and each medical consultation file is determined based on the proportion, the difference and the second similarity.

[0017] In another possible implementation, when the file determination module determines the relevance between the patient and each consultation file based on the proportion, the difference, and the second similarity, it is specifically used to: Calculate the average of all second similarities in each consultation file; Obtaining a first similarity between the candidate patient corresponding to each medical consultation file and the patient; A score is calculated based on the proportion, the difference of each abnormal item, the first similarity, the second similarity and the corresponding coefficients, and the score represents the correlation between the patient and each medical consultation file.

[0018] In another possible implementation, when the strategy determination module determines the consultation strategy of the doctor and the patient based on the question and answer information, it is specifically used to: Extracting all questions from the question-answer information of each consultation file, wherein the questions include a first question asked by the doctor and a second question asked by the patient; Calculate the similarity between each first question and the remaining first questions, and use a clustering algorithm to determine the type of the first question; Calculate the similarity between each second question and the remaining second questions, and use a clustering algorithm to determine the type of the second question; Obtaining the time point of the first question in each category during each consultation process, and determining the average time point corresponding to each category based on the time point; Determining a target first question from the first questions in each category, and sorting each target first question based on the average time point to obtain a questioning strategy for the doctor; Obtaining the time point of the second question in each category during each consultation process, and determining the average time point corresponding to each category based on the time point; A target second question is determined from the second questions in each category, and each target second question is sorted based on the average time point to obtain a questioning strategy for the patient.

[0019] In another possible implementation, when the strategy output module outputs the doctor's consultation strategy to the doctor who consults the patient and outputs the patient's consultation strategy to the patient, it is specifically used to: Real-time acquisition of audio information during video consultation between the doctor and the patient; Converting the audio information into text to obtain first text information of the patient and second text information of the doctor; Performing tone recognition on the audio information to obtain the third question in the first text information and the fourth question in the second text information; When it is detected that the number of the third questions reaches a first preset number proportion, a target second question identical to the third question is deleted from the medical consultation strategy for the patient, a first medical consultation strategy after deletion is obtained, and the first medical consultation strategy after deletion is output to the terminal device of the patient; When it is detected that the number of the fourth questions reaches a second preset number, the target first question that is the same as the fourth question is deleted from the doctor's inquiry strategy, a second deleted inquiry strategy is obtained and the second deleted inquiry strategy is output to the doctor's terminal device.

[0020] In another possible implementation, the device further includes: A first sending module, configured to send a first prompt message to the terminal device of the patient, so that the patient triggers an instruction on whether to consult a question in the first deleted consultation strategy; The second sending module is used to send a second prompt message to the patient's terminal device when receiving an instruction that there is no need to consult the questions in the first deleted consultation strategy, so that the patient triggers an instruction on whether to consult other questions.

[0021] In a third aspect, the present application provides an electronic device, which adopts the following technical solution: An electronic device, comprising: at least one processor; Memory; At least one application, wherein at least one application is stored in a memory and configured to be executed by at least one processor, and at least one is configured to: execute an Internet-based remote online guidance method shown in any possible implementation of the first aspect.

[0022] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium, when the computer program is executed in a computer, enables the computer to execute the Internet-based remote online medical guidance method described in any one of the first aspects.

[0023] In summary, the present application includes at least one of the following beneficial technical effects: Obtaining the patient's test report and electronic medical record facilitates subsequent analysis of the patient's valuable information, extracting data from the test report to obtain the patient's abnormal items and extracting multiple information from the electronic medical record facilitates subsequent analysis of the patient's general condition. A large amount of patient data and files are stored in the preset database. Therefore, based on the abnormal items and multiple information, multiple candidate patients with similar conditions to the patient are searched from the preset database and the medical records of the candidate patients are determined. The correlation between each medical record and the patient's abnormal items and multiple information is calculated, so as to determine the target file with the highest correlation, and question and answer questions are extracted from the medical records of multiple candidate patients with similar conditions to the patient. Based on these Questions and answers are useful for determining the consultation strategies that correspond to the doctor and the patient respectively. The target file determined is the one that has the highest relevance to the patient. Therefore, the patient's abnormal items and multiple information are mapped to the target file to obtain the patient's consultation file to be completed. The consultation file to be completed is output to the consulting doctor, thereby improving the doctor's consultation efficiency and the convenience of subsequently completing the patient's condition and consultation records. Outputting the doctor's consultation strategy is useful for reminding the doctor whether there are any missed issues. Outputting the patient's consultation strategy is useful for reminding the patient whether there are any missed issues, thereby reducing the situation where patients or doctors miss questions during online consultations, thereby improving the quality of online consultations. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a flowchart of a remote online medical guidance method based on the Internet in an embodiment of the present application.

[0025] Figure 2 It is a structural schematic diagram of a remote online medical guidance device based on the Internet in an embodiment of the present application.

[0026] Figure 3 It is a structural schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] The present application is further described in detail below in conjunction with the accompanying drawings.

[0028] After reading this specification, those skilled in the art may make non-creative modifications to this embodiment as needed, but such modifications are protected by patent law as long as they are within the scope of the claims of this application.

[0029] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0030] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0031] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0032] The embodiment of the present application provides a remote online medical guidance method based on the Internet, which is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited to this. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, and the embodiment of the present application does not limit this. Figure 1 As shown, the method includes step S101, step S102, step S103, step S104, step S105, step S106 and step S107, wherein: S101, obtain the test results and electronic medical records uploaded by the patient.

[0033] In the embodiment of the present application, the patient uploads his or her own test report and electronic medical record to the cloud server through a terminal device such as a mobile phone or a computer, and the electronic device is connected to the cloud server in communication, so that the electronic device can obtain the patient's test report and electronic medical record in the cloud server. Test reports include blood routine, urine routine, liver function, and kidney function test reports, and electronic medical records record the patient's medical experience, diseases, symptoms, and prescriptions.

[0034] S102, extract data from the test report to obtain abnormal items of the patient, and extract multiple pieces of information from the electronic medical record.

[0035] For the embodiment of the present application, the electronic device extracts the data in the test form through OCR (Optical Character Recognition) technology to obtain the name of each item in the test form, such as white blood cells and hemoglobin in a routine blood test, and total bilirubin and indirect bilirubin in liver function. Then the electronic device identifies the items with arrows in the test form. The items with arrows are items that are not in the normal value range, that is, abnormal items. The electronic device also extracts the text in the electronic medical record through OCR technology to obtain multiple information in the electronic medical record, such as diagnosed diseases, prescriptions, pathological results, patient symptoms, etc.

[0036] S103, searching for multiple candidates from a preset database based on the abnormal item and multiple pieces of information, and determining the medical consultation file of each candidate.

[0037] For the embodiment of the present application, there are a large number of patient consultation files in the preset database, which record the consultation process between the patient and the doctor and the patient's personal specific conditions such as abnormal items and multiple information in the electronic medical record. Since the abnormal items and multiple information are key information to characterize the patient's specific conditions, the electronic device can find multiple candidate patients with similar conditions to the patient from the preset database based on the abnormal items and multiple information of the current patient to be consulted, and then obtain the consultation file of each candidate patient.

[0038] S104, calculating the correlation between each medical consultation file and the abnormal items and multiple pieces of information of the patient, and determining the target file with the highest correlation.

[0039] For the embodiment of the present application, since there are individual differences and differences in specific circumstances between the determined patients to be selected and the patients to be interviewed, the electronic device calculates the correlation between each medical consultation file and the patient's abnormal items and multiple pieces of information, and then determines the target file with the highest correlation. The target file with the highest correlation is the one that is closest to the situation of the patient to be interviewed.

[0040] S105, extracting the question and answer information of each medical consultation file from the plurality of medical consultation files, and determining the medical consultation strategy of the doctor and the patient based on the question and answer information.

[0041] With respect to the embodiment of the present application, after the electronic device determines the patients to be selected, it performs text extraction on the medical consultation files of the patients to be selected to obtain the question and answer information in each medical consultation file. The question and answer information records the conversation and questions asked between the patient and the doctor, including the questions asked by the patient to the doctor and the questions asked by the doctor to the patient. Since the patients to be selected are all patients with similar conditions to the patients to be consulted, the questions asked between the patients to be consulted and the doctors are also the questions that the patients to be consulted may encounter when consulting with the doctors. Therefore, the electronic device can accurately determine the consultation strategies of the doctors and the patients based on the question and answer information.

[0042] S106, mapping the abnormal items and multiple pieces of information into the target file, and obtaining the patient's consultation file to be completed.

[0043] For the embodiment of the present application, after the electronic device determines the target file with the highest relevance, it can copy the target file as the file template of the patient to be consulted, and then the electronic device maps the abnormal items and multiple information of the patient to be consulted to the file template and reduces the font of each item of the original patient in the file template and moves it to the right or end of each item area, thereby leaving space for the abnormal items and multiple information of the patient to be consulted. Thus, the consultation file of the patient to be consulted, that is, the consultation file to be improved, is obtained.

[0044] S107, outputting the consultation file to be completed and the consultation strategy of the doctor to the doctor who is consulting the patient, and outputting the consultation strategy of the patient to the patient.

[0045] For the embodiment of the present application, after the electronic device determines the patient's consultation file to be completed and the doctor's consultation strategy, it outputs the consultation file to be completed and the doctor's consultation strategy to the doctor's terminal device, so that the doctor is not likely to miss questions when conducting online video consultations with the patient. When there are missed questions, it is convenient to ask the patient according to the consultation strategy, and the doctor can use the consultation file to be completed to facilitate the doctor to subsequently complete the patient's consultation and record it, thereby improving the consultation efficiency. The electronic device sends the patient's consultation strategy to the patient's terminal device to remind the patient whether there are any missed questions. When there are missed questions, the patient can ask the doctor according to the question items in the consultation strategy, ultimately reducing the situation where patients or doctors miss questions during online consultations, thereby improving the quality of online consultations.

[0046] In a possible implementation of the embodiment of the present application, the multiple pieces of information include the main symptoms, the main diseases and the medication status. In step S103, multiple patients to be selected are searched from a preset database based on the abnormal items and the multiple pieces of information, specifically including step S1031 (not shown in the figure), step S1032 (not shown in the figure), step S1033 (not shown in the figure), step S1034 (not shown in the figure), step S1035 (not shown in the figure) and step S1036 (not shown in the figure), wherein: S1031, determine the symptom number corresponding to the main complaint symptom, the disease number of the main complaint disease, and the drug number corresponding to the medication situation.

[0047] For the embodiment of the present application, the electronic device stores a symptom number corresponding to each symptom. Symptoms such as dizziness, nausea, fatigue, etc., each symptom has a corresponding symptom number. Similarly, different diseases have corresponding disease numbers and are stored in the storage medium in the electronic device, and the medication conditions, that is, the different drugs in the prescription, have corresponding drug numbers. The numbers of symptoms, diseases, and drugs can be set by relevant personnel and stored in the storage medium in the electronic device. After the electronic device determines the chief complaint symptoms, chief complaint diseases, and medication conditions from the patient's electronic medical record, it can find out the corresponding symptom numbers, disease numbers, and drug numbers.

[0048] In other implementations, the multiple pieces of information also include other information such as examination items such as color ultrasound and electrocardiogram, pathological results, etc.

[0049] S1032, determining a first characteristic value of the patient based on the symptom number, disease number, and medication number.

[0050] For the embodiment of the present application, after the electronic device determines the symptom number, disease number and drug number, it can concatenate these numbers to obtain the first characteristic value of the patient. For example, if the symptom number is 2, the disease number is b5, and the drug number is n7, then the first characteristic value of the patient is 2b5n7.

[0051] S1033: Based on a first similarity between the first eigenvalue and each second eigenvalue.

[0052] The second characteristic value is the characteristic value of each historical patient in the preset database.

[0053] For the embodiment of the present application, each patient in the preset database, that is, the historical patient, also corresponds to the main symptoms, the main disease, and the medication situation, so the electronic device can determine the second feature value of each historical patient in the preset database. The electronic device can calculate the text similarity between the first feature value and each second feature value, such as calculating the first similarity by calculating the cosine similarity and the Euclidean distance.

[0054] S1034, determining a plurality of target historical patients whose first similarity reaches a preset similarity threshold.

[0055] For the embodiment of the present application, after the electronic device calculates the first similarity between the first feature value and each second feature value, it sorts all the first similarities to determine multiple target historical patients whose first similarities reach a preset similarity threshold. The preset similarity threshold is used as a dividing point for whether the similarity reaches a higher level. If the first similarity reaches the preset similarity threshold, it means that the target historical patient is close to the patient to be interviewed.

[0056] S1035, determining the item number of each abnormal item of the patient, and obtaining the item numbers of the abnormal items corresponding to each of the multiple target historical patients.

[0057] For the embodiment of the present application, each item in the test form also corresponds to an item number, so the electronic device determines the item number of each abnormal item of the patient to be interviewed. The abnormal items of the target historical patients are also determined by the electronic device and stored in the preset database, so the electronic device can obtain the item number of the abnormal item corresponding to each target historical patient through the preset database.

[0058] S1036, based on the patient's item number and the item numbers of the multiple target historical patients, determine multiple candidates including the item numbers from the multiple target historical patients.

[0059] For the embodiment of the present application, after the electronic device determines the item number of the patient to be interviewed and the item numbers of multiple target historical patients, the electronic device can screen out whether there is a target historical patient whose number is the same as the number of the abnormal item of the patient to be interviewed among the abnormal items of the multiple target historical patients, that is, the final candidate patient. The electronic device first determines the first characteristic value of the patient to be interviewed based on the number of multiple pieces of information, and preliminarily screens out target historical patients with similar situations by calculating the first similarity between the first characteristic value and the second characteristic value of the historical patient, and then further analyzes the target historical patient based on the abnormal items in the test report to obtain a closer candidate patient, so that the determined candidate patient is more accurate.

[0060] In a possible implementation of the embodiment of the present application, in step S104, the correlation between each medical consultation file and the abnormal items and multiple pieces of information of the patient is calculated, which specifically includes step S1041 (not shown in the figure), step S1042 (not shown in the figure), step S1043 (not shown in the figure), and step S1044 (not shown in the figure), wherein: S1041, determining the ratio of the number of abnormal items of the patient to the number of abnormal items in each medical consultation file.

[0061] For the embodiment of the present application, the electronic device counts the abnormal items of the patient to be interviewed to obtain the number of abnormal items of the patient to be interviewed, and counts the number of abnormal items in the medical consultation file of each patient to be selected to obtain the number of abnormal items of the patient to be selected. Then the electronic device calculates the ratio of the number of abnormal items of the patient to be interviewed to the number of abnormal items of each patient to be selected. The closer the ratio is to 1, the closer the abnormal test results of the patient to be interviewed are to the abnormal test results of the patient to be selected, that is, the closer the physical condition is, and vice versa.

[0062] S1042, determining the value of each abnormal item from each medical consultation file, and calculating the difference between the value of each abnormal item and the data of the abnormal item of the corresponding patient.

[0063] For the embodiment of the present application, the electronic device extracts the numerical value of each abnormal item in each medical consultation file and extracts the data of the abnormal items of the patient to be consulted, and then calculates the difference between the same abnormal items. The smaller the difference, the closer the abnormality degree of the abnormal items of the patient to be consulted and the selected patient is.

[0064] S1043, determining data corresponding to each of the multiple pieces of information in each medical consultation file, and calculating a second similarity between each piece of information and the corresponding data in each medical consultation file.

[0065] For the embodiment of the present application, the medical consultation file is usually in the form of a table or a text box, and the electronic device extracts the data in each table or text box, that is, the data consistent with the data type of the multiple data of the patient to be consulted, such as the symptom description, disease description and description of the medication taken by the patient to be selected in the medical consultation file. Then the electronic device calculates the second similarity between each patient to be selected and the data of the same data type of the patient to be consulted. Specifically, the electronic device performs text vectorization on the data corresponding to each of the multiple information in the medical consultation file, for example, using the bag of words model (Bag of Words, BoW): ignoring grammar and order, representing the text as a frequency vector of all words that appear, or using TF-IDF (Term Frequency-Inverse Document Frequency): considering the term frequency (TF) and the inverse document frequency (IDF) to evaluate the importance of a word to a document set or a document in a corpus. Word2Vec, GloVe or FastText can also be used. These models can learn the continuous vector representation of words and capture the contextual meaning of words. Then the second similarity is calculated by calculating cosine similarity, Euclidean distance and Manhattan distance. The higher the second similarity, the higher the correlation between the medical consultation file of the selected patient and the patient to be consulted.

[0066] S1044, determining the correlation between the patient and each medical consultation file based on the proportion, the difference and the second similarity.

[0067] For the embodiments of the present application, in summary, the proportion, difference and second similarity of abnormal items are all key factors affecting the correlation between the selected patients and the patients to be interviewed. Therefore, the electronic device can comprehensively determine a more accurate correlation between each consultation file and the patient to be interviewed based on the proportion, difference and second similarity.

[0068] In a possible implementation of the embodiment of the present application, in step S1044, the correlation between the patient and each medical consultation file is determined based on the proportion, the difference and the second similarity, specifically including step Sa (not shown in the figure), step Sb (not shown in the figure) and step Sc (not shown in the figure), wherein: Sa, calculate the average of all second similarities in each consultation file.

[0069] For the embodiment of the present application, each medical consultation file includes multiple pieces of information, and each piece of information corresponds to a second similarity. Therefore, the electronic device calculates the average value of all second similarities in each medical consultation file. It is more accurate to use the average value to characterize the overall similarity of multiple pieces of information in each medical consultation file, that is, the degree of closeness between each medical consultation file and the multiple pieces of information of the patient to be consulted.

[0070] Sb, obtains the first similarity between the candidate patient and the patient corresponding to each medical consultation file.

[0071] For the embodiment of the present application, the first similarity is obtained according to the method disclosed in steps S1031 to S1033. After the electronic device determines the first similarity corresponding to each medical consultation file, it stores the first similarity, so as to facilitate the subsequent electronic device to call the first similarity for calculation. The height of the first similarity is also related to the correlation, so the electronic device obtains the first similarity.

[0072] Sc, the score is calculated based on the proportion, the difference of each abnormal item, the first similarity, the second similarity and their corresponding coefficients.

[0073] The score represents the correlation between the patient and each consultation file.

[0074] For the embodiments of the present application, in summary, the proportion of abnormal items, the difference of abnormal items, the first similarity and the second similarity are all key factors affecting the degree of correlation, and these four factors have different degrees of influence on the correlation, so the relevant personnel set different coefficients for these four factors and store them in the local storage medium in the electronic device. After the electronic device determines these four factors, it calls the corresponding coefficients for weighted calculation to obtain a score, which is the correlation between the patient to be interviewed and each consultation file. Since the smaller the difference, the higher the correlation, that is, the difference is inversely proportional to the correlation, in order to facilitate calculation and ensure the authenticity of the score, the electronic device can use the inverse of the difference for weighted calculation to obtain the score.

[0075] In a possible implementation of the embodiment of the present application, in step S105, the doctor and the patient's consultation strategy is determined based on the question-answer information, specifically including step S1051 (not shown in the figure), step S1052 (not shown in the figure), step S1053 (not shown in the figure), step S1054 (not shown in the figure), step S1055 (not shown in the figure), step S1056 (not shown in the figure) and step S1057 (not shown in the figure), wherein: S1051, extract all the questions from the question and answer information of each medical consultation file.

[0076] The questions include a first question asked by a doctor and a second question asked by a patient.

[0077] For the embodiment of the present application, the question and answer information includes multiple question and answer rounds, each question and answer round includes a question and an answer, so the electronic device can extract all the questions in each medical consultation file through the punctuation of the question mark, and all the questions include the first question asked by the doctor and the second question asked by the patient.

[0078] S1052, calculating the similarity between each first question and the remaining first questions, and determining the type of the first question using a clustering algorithm.

[0079] For the embodiment of the present application, the electronic device also calculates the similarity between each first question and the remaining first questions by calculating the cosine distance, Euclidean distance, etc., i.e., the method disclosed in step S1043. The higher the similarity, the higher the similarity between the texts of the first questions, and the higher the possibility that they belong to the same question. Then the electronic device divides the first questions into multiple groups based on the similarity through clustering algorithms such as K-means, DBSCAN, and hierarchical clustering. The first questions in each group represent the same question, the number of types of first questions is the number of questions, and the first questions in each type represent the same question. In this way, multiple questions encountered by doctors when asking candidates are obtained.

[0080] S1053, calculating the similarity between each second question and the remaining second questions, and determining the type of the second question using a clustering algorithm.

[0081] For the embodiment of the present application, the electronic device also calculates the similarity between each second question and the remaining second questions by calculating the cosine distance, Euclidean distance, etc., i.e., the method disclosed in step S1043. The higher the similarity, the higher the similarity between the texts of the second questions, and the higher the possibility that they belong to the same question. Then the electronic device divides the second questions into multiple groups based on the similarity through clustering algorithms such as K-means, DBSCAN, and hierarchical clustering. The second questions in each group represent the same question, the number of types of second questions is the number of questions, and the second questions in each type represent the same question. In this way, multiple questions asked by the selected patient to the doctor are obtained.

[0082] S1054, obtaining the time point of the first question in each category during each medical consultation process, and determining the average time point corresponding to each category based on the time point.

[0083] For the embodiment of the present application, each first question has a time point recorded in the medical consultation file, that is, the time point of the first question in the entire process of the consultation between the candidate patient and the doctor. Therefore, the electronic device can determine the time point of each first question from the medical consultation file, and then the electronic device calculates the average time point of the time point of the first question in each category through the average value calculation formula. The average time point is the time point at which most of the questions corresponding to each category appear in all consultations. By determining the average time point of each question, the time point at which the same question may appear in the consultation process with the candidate patient can be determined.

[0084] S1055, determining a target first question from the first questions in each category, and sorting each target first question based on the average time point to obtain a consultation strategy for the doctor.

[0085] For the embodiment of the present application, after the electronic device determines the first question of each category through a clustering algorithm, it maps the first question in each category as a coordinate point to a preset plane rectangular coordinate system to determine the first question in the center of each category, that is, the target first question. The similarity between the target first question and other first questions is relatively balanced, and it is suitable as an example sentence when the doctor asks the question. After the electronic device determines the average time point of each question, the electronic device sorts the target first question of each question (category) in the progressive order of the average time point to obtain the doctor's consultation strategy.

[0086] S1056, obtaining the time point of the second question in each category during each medical consultation process, and determining the average time point corresponding to each category based on the time point.

[0087] For the embodiment of the present application, each second question has a time point recorded in the medical consultation file, that is, the time point of the second question in the entire process of the consultation between the patient to be selected and the doctor. Therefore, the electronic device can determine the time point of each second question from the medical consultation file, and then the electronic device calculates the average time point of the time point of the second question in each category through the average value calculation formula. The average time point is the time point at which the questions corresponding to each category appear in the entire consultation. By determining the average time point of each question, the time point at which the same question may appear in the consultation process with the patient to be consulted can be determined, that is, the possible time point when the patient to be consulted asks the question.

[0088] S1057, determining a target second question from the second questions in each category, and sorting each target second question based on the average time point to obtain a questioning strategy for the patient.

[0089] For the embodiment of the present application, after the electronic device determines the second question of each category through a clustering algorithm, it maps the second question in each category as a coordinate point to a preset plane rectangular coordinate system to determine the second question at the center of each category, i.e., the target second question. The target second question has a relatively balanced similarity with other second questions, and is suitable as an example sentence for the patient to be asked when consulting the question. After the electronic device determines the average time point of each question, the electronic device sorts the target second question of each question (category) in the progressive order of the average time point to obtain a consultation strategy for the patient to be consulted. It is more accurate to determine the consultation strategy for the doctor and the consultation strategy for the patient by determining the average time point and the standard example sentence.

[0090] In other embodiments, the electronic device may also obtain a score for each question based on a comprehensive weighted calculation according to the average time point and the number of occurrences of the first question or the second question of each question (type), and the score represents the priority of each question. The electronic device then determines the target first question or the target second question corresponding to each question, and then sorts the target first question or the target second question according to the priority to obtain the doctor's consultation strategy and the patient's consultation strategy.

[0091] In a possible implementation of the embodiment of the present application, in step S107, the doctor who consults the patient outputs the doctor's consultation strategy, and outputs the patient's consultation strategy to the patient, specifically including step S1071 (not shown in the figure), step S1072 (not shown in the figure), step S1073 (not shown in the figure), step S1074 (not shown in the figure) and step S1075 (not shown in the figure), wherein: S1071, real-time acquisition of audio information during video consultation between doctors and patients.

[0092] For the embodiment of the present application, once the electronic device detects that a video communication connection has been established between the patient and the doctor, it indicates that the doctor and the patient have started a consultation, and the electronic device starts to obtain audio information during the video consultation in real time.

[0093] S1072, convert the audio information into text to obtain the patient's first text information and the doctor's second text information.

[0094] For the embodiment of the present application, after the electronic device obtains the audio information, it can input the audio information into the trained network model for text conversion to obtain the first text information about the patient and the second text information about the doctor. Specifically, the network model can be a convolutional neural network model, a recurrent neural network model, or other types of network models.

[0095] S1073, performing tone recognition on the audio information to obtain the third question in the first text information and the fourth question in the second text information.

[0096] For the embodiment of the present application, the electronic device inputs the audio information into the trained network model for voice recognition, thereby identifying the questions in the entire consultation process, namely, the third question asked by the patient and the fourth question asked in the first instance. Similarly, the network model can be a convolutional neural network model, a recurrent neural network model, or other types of network models.

[0097] S1074, when it is detected that the number of third questions reaches a first preset number, the target second question that is the same as the third question is deleted from the patient's medical consultation strategy, a first medical consultation strategy after deletion is obtained and the first medical consultation strategy after deletion is output to the patient's terminal device.

[0098] For the embodiment of the present application, the first preset number ratio is set by relevant personnel as a demarcation point for whether the patient's consultation questions in the entire consultation process are about to end. The electronic device determines the number of questions asked by patients in each candidate file, and then calculates the average value of the number of questions asked by patients in all candidate files, and uses the average value to characterize the number of consultation questions of the candidate patients as a whole, and the average value is also the number of questions that the current patient may ask during the consultation process. The electronic device counts the third questions asked by the patient, and calculates the ratio of the number of third questions asked by the patient to the average value. The electronic device compares the ratio with the first preset number ratio in real time. When the ratio of the number of third questions to the average value reaches the first preset number ratio, it indicates that the consultation is likely to end soon. Therefore, the electronic device deletes the target second question with the same question as the third question in the patient's consultation strategy. Specifically, the electronic device can determine whether the third question appears in the patient's consultation strategy by calculating the cosine distance or the Euclidean distance. The electronic device deletes the target second question that has been asked and has the same semantics as the third question in the patient's inquiry strategy, and then obtains the inquiry strategy after the first deletion. The electronic device then sends the inquiry strategy after the first deletion to the patient's terminal device, and controls the patient's terminal device to display it, so that the patient can view the inquiry strategy after the first deletion. The patient can find out whether he or she has any missing questions based on the inquiry strategy after the first deletion. If there are any missing questions, the patient can consult the doctor for additional information based on the inquiry strategy after the first deletion.

[0099] S1075, when it is detected that the number of fourth questions reaches the second preset number proportion, the target first question that is the same as the fourth question is deleted from the doctor's consultation strategy, the second deleted consultation strategy is obtained and the second deleted consultation strategy is output to the doctor's terminal device.

[0100] For the embodiment of the present application, the second preset number ratio is also set by relevant personnel as the demarcation point for whether the doctor's questioning of the patient is about to end during the entire consultation process. The electronic device determines the number of questions asked by the doctor in each candidate file, and then calculates the average number of questions asked by the doctor in all candidate files, and uses the average value to characterize the overall number of questions asked by the doctor to each candidate patient, and the average value is also the number of questions that the current doctor may ask the patient during the consultation process. The electronic device counts the fourth question asked by the doctor, and calculates the ratio of the number of the fourth question asked by the doctor to the average value, and the electronic device compares the ratio with the second preset number ratio in real time. When the ratio of the number of the fourth question to the average value reaches the second preset number ratio, it means that the doctor is likely to end asking questions to the current patient. Therefore, the electronic device deletes the target first question that is the same as the fourth question in the doctor's consultation strategy. Specifically, the electronic device can determine whether the fourth question appears in the doctor's consultation strategy by calculating the cosine distance or the Euclidean distance. The electronic device deletes the target first question that has been asked and has the same semantics as the fourth question in the doctor's inquiry strategy, and obtains the second deleted inquiry strategy. The electronic device then sends the second deleted inquiry strategy to the doctor's terminal device, and controls the doctor's terminal device to display it, so that the doctor can view the second deleted inquiry strategy. Based on the second deleted inquiry strategy, the doctor can find out whether there are any missing questions that need to be asked to the patient. If there are any missing questions, the doctor can make additional inquiries to the patient based on the second deleted inquiry strategy.

[0101] In a possible implementation of the embodiment of the present application, step S1074 includes step S108 (not shown in the figure) and step S109 (not shown in the figure), wherein: S108, sending a first prompt message to the patient's terminal device, so that the patient triggers an instruction on whether to consult a question in the first deleted consultation strategy.

[0102] For the embodiment of the present application, after the electronic device outputs the first deleted consultation strategy to the patient's terminal device, it sends the first prompt information to the patient's terminal device. Specifically, the first prompt information can be a text prompt information of "Do you need to consult the questions in the first deleted consultation strategy?", and control the patient's terminal device to display the text prompt information, and at the same time display link buttons of "yes" and "no" on the patient's terminal device. The patient can trigger the corresponding instruction by clicking the corresponding button according to his or her actual situation.

[0103] S109, if an instruction is received regarding the question in the consultation strategy after the first deletion that does not need to be consulted, a second prompt message is sent to the patient's terminal device so that the patient triggers an instruction regarding whether other questions need to be consulted.

[0104] For the embodiment of the present application, if the electronic device receives a question instruction in the consultation strategy after the first deletion that does not require consultation, that is, the patient clicks the "No" link button in step S108, it means that the patient may have completed the consultation, and the electronic device sends a second prompt message to the patient's terminal device. The second prompt message can be a text prompt message of "Do you need to consult other questions?" and control the patient's terminal device to display the text prompt message, and at the same time display link buttons with two options of "Yes" and "No" on the patient's terminal device. The patient can trigger the corresponding instruction by clicking the corresponding button according to his or her actual situation and whether he or she needs to consult other questions. If the patient triggers the "No" instruction, it means that the patient's consultation purpose has been achieved, and the electronic device can control the video communication connection between the patient and the doctor to be disconnected, thereby completing the consultation.

[0105] The above embodiment introduces a remote online medical guidance method based on the Internet from the perspective of the method flow, and the following embodiment introduces a remote online medical guidance device based on the Internet from the perspective of a virtual module or a virtual unit. For details, please refer to the following embodiment.

[0106] The present application embodiment provides a remote online medical guidance device 20 based on the Internet, such as Figure 2 As shown, the Internet-based remote online medical guidance device 20 may specifically include: Data acquisition module 201, used to acquire the test results and electronic medical records uploaded by the patient; The data extraction module 202 is used to extract data from the test report to obtain abnormal items of the patient and extract multiple pieces of information from the electronic medical record; A search module 203 is used to search for multiple patients to be selected from a preset database based on the abnormal items and multiple information, and determine the medical consultation file of each patient to be selected; The file determination module 204 is used to calculate the correlation between each medical consultation file and the abnormal items and multiple information of the patient, and determine the target file with the highest correlation; A strategy determination module 205 is used to extract the question and answer information of each consultation file from the plurality of consultation files, and determine the consultation strategy of the doctor and the patient based on the question and answer information; The data mapping module 206 is used to map the abnormal items and multiple pieces of information to the target file to obtain the patient's consultation file to be completed; The strategy output module 207 is used to output the consultation file to be completed and the doctor's consultation strategy to the doctor who consults the patient, and output the patient's consultation strategy to the patient.

[0107] The embodiment of the present application discloses a remote online medical guidance device 20 based on the Internet, wherein a data acquisition module 201 acquires a patient's test report and an electronic medical record for subsequent analysis of valuable information about the patient, a data extraction module 202 extracts data from the test report to obtain abnormal items of the patient and extracts multiple pieces of information from the electronic medical record for subsequent analysis of the patient's general condition, a large amount of patient data and files are stored in a preset database, so a search module 203 searches for multiple candidate patients with similar conditions to the patient from the preset database based on the abnormal items and multiple pieces of information and determines the medical consultation files of the candidate patients, a file determination module 204 calculates the correlation between each medical consultation file and the abnormal items and multiple pieces of information of the patient, thereby determining the target file with the highest correlation, and extracting the target file from the medical consultation files of multiple candidate patients with similar conditions to the patient. Questions and answers are asked, and the strategy determination module 205 is convenient for determining the consultation strategies corresponding to the doctor and the patient according to these questions and answers. The determined target file is the one with the highest relevance to the patient. Therefore, the data mapping module 206 maps the patient's abnormal items and multiple information to the target file to obtain the patient's consultation file to be improved. The strategy output module 207 outputs the consultation file to be improved to the consulting doctor, thereby improving the doctor's consultation efficiency and the convenience of subsequently improving the patient's condition and consultation records. The strategy output module 207 outputs the doctor's consultation strategy to remind the doctor whether there are any missing issues. The strategy output module 207 outputs the patient's consultation strategy to remind the patient whether there are any missing issues, thereby reducing the situation where patients or doctors miss questions during online consultations, thereby improving the quality of online consultations.

[0108] In a possible implementation of the embodiment of the present application, the multiple pieces of information include the main complaint symptoms, the main complaint diseases and the medication status. When the search module 203 searches for multiple candidates from the preset database based on the abnormal items and the multiple pieces of information, it is specifically used to: Determine the symptom number corresponding to the main complaint, the disease number of the main complaint, and the drug number corresponding to the medication; Determine a first characteristic value of the patient based on the symptom number, the disease number, and the medication number; Based on a first similarity between the first feature value and each second feature value, the second feature value is a feature value of each historical patient in a preset database; Determining a plurality of target historical patients whose first similarity reaches a preset similarity threshold; Determine the item number of each abnormal item of the patient, and obtain the item number of the abnormal item corresponding to each of the plurality of target historical patients; A plurality of patients to be selected including the item numbers are determined from the plurality of target historical patients based on the item number of the patient and the item numbers of the plurality of target historical patients.

[0109] In a possible implementation of the embodiment of the present application, the file determination module 204 is specifically used to calculate the correlation between each medical consultation file and the abnormal item and multiple pieces of information of the patient: Determine the ratio of the number of abnormal items in each patient's medical records to the number of abnormal items in each medical record; Determine the value of each abnormal item from each medical consultation file, and calculate the difference between the value of each abnormal item and the data of the abnormal item of the corresponding patient; Determine the data corresponding to each of the multiple pieces of information from each medical consultation file, and calculate the second similarity between each piece of information and the corresponding data in each medical consultation file; The relevance between the patient and each medical consultation file is determined based on the proportion, the difference, and the second similarity.

[0110] In a possible implementation of the embodiment of the present application, when the file determination module 204 determines the relevance between the patient and each consultation file based on the proportion, the difference, and the second similarity, it is specifically used to: Calculate the average of all second similarities in each consultation file; Obtain the first similarity between the candidate patient and the patient corresponding to each medical consultation file; The score is calculated based on the proportion, the difference of each abnormal item, the first similarity, the second similarity and the corresponding coefficients, and the score represents the correlation between the patient and each medical consultation file.

[0111] In a possible implementation of the embodiment of the present application, when the strategy determination module 205 determines the consultation strategy of the doctor and the patient based on the question and answer information, it is specifically used to: Extract all the questions from the question-answer information of each consultation file, including the first question asked by the doctor and the second question asked by the patient; Calculate the similarity between each first question and the remaining first questions, and use a clustering algorithm to determine the type of the first question; Calculate the similarity between each second question and the remaining second questions, and use a clustering algorithm to determine the type of the second question; Obtain the time point of the first question in each category during each consultation process, and determine the average time point corresponding to each category based on the time point; Determine a target first question from the first questions in each category, and sort each target first question based on the average time point to obtain a doctor's questioning strategy; Obtain the time point of the second question in each category during each consultation process, and determine the average time point corresponding to each category based on the time point; A target second question is determined from the second questions in each category, and each target second question is sorted based on the average time point to obtain a questioning strategy for the patient.

[0112] In a possible implementation of the embodiment of the present application, when the strategy output module 207 outputs the doctor's consultation strategy to the doctor who is consulting the patient, and outputs the patient's consultation strategy to the patient, it is specifically used to: Real-time acquisition of audio information during video consultations between doctors and patients; Convert the audio information into text to obtain the first text information of the patient and the second text information of the doctor; Perform tone recognition on the audio information to obtain the third question in the first text information and the fourth question in the second text information; When it is detected that the number of the third questions reaches a first preset number proportion, a target second question identical to the third question is deleted from the patient's questioning strategy, a first deleted questioning strategy is obtained, and the first deleted questioning strategy is output to the patient's terminal device; When it is detected that the number of fourth questions reaches a second preset number, the target first question that is the same as the fourth question is deleted from the doctor's consultation strategy, and the second deleted consultation strategy is obtained and output to the doctor's terminal device.

[0113] In a possible implementation of the embodiment of the present application, the device 20 further includes: A first sending module, configured to send a first prompt message to a terminal device of the patient, so that the patient triggers an instruction on whether to consult a question in the first deleted consultation strategy; The second sending module is used to send a second prompt message to the patient's terminal device when receiving an instruction that there is no need to consult the questions in the consultation strategy after the first deletion, so that the patient triggers an instruction on whether to consult other questions.

[0114] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the Internet-based remote online medical guidance device 20 described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0115] An electronic device is provided in an embodiment of the present application, such as Figure 3 As shown, Figure 3The electronic device 30 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 30 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 30 does not constitute a limitation on the embodiments of the present application.

[0116] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0117] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but it does not mean that there is only one bus or only one type of bus.

[0118] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0119] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0120] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0121] The embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer-readable storage medium is run on a computer, the computer can execute the corresponding contents in the aforementioned method embodiment. Compared with the related art, in the embodiment of the present application, obtaining the patient's test report and electronic medical record facilitates the subsequent analysis of the patient's valuable information, extracting data from the test report to obtain the patient's abnormal items, and extracting multiple information from the electronic medical record facilitates the subsequent analysis of the patient's general condition, and a large amount of patient data and files are stored in the preset database. Therefore, based on the abnormal items and multiple information, multiple candidate patients with similar conditions to the patient are searched from the preset database and the medical records of the candidate patients are determined, and the correlation between each medical record and the patient's abnormal items and multiple information is calculated, thereby determining the target file with the highest correlation, and extracting the medical records from the multiple medical records of the candidate patients with similar conditions to the patient. Answer questions. Based on these questions and answers, it is easy to determine the corresponding consultation strategies for doctors and patients. The determined target file is the one with the highest relevance to the patient. Therefore, the patient's abnormal items and multiple information are mapped to the target file to obtain the patient's consultation file to be completed. The consultation file to be completed is output to the consulting doctor, thereby improving the doctor's consultation efficiency and the convenience of subsequently improving the patient's condition and consultation records. Outputting the doctor's consultation strategy is convenient for reminding the doctor whether there are any missed issues. Outputting the patient's consultation strategy is convenient for reminding the patient whether there are any missed issues, thereby reducing the situation where patients or doctors miss questions during online consultations, thereby improving the quality of online consultations.

[0122] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0123] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A remote online medical guidance method based on the Internet, characterized in that: include: Obtain the test results and electronic medical records uploaded by the patient; Extracting data from the test report to obtain abnormal items of the patient, and extracting multiple pieces of information from the electronic medical record; Based on the abnormal item and the multiple pieces of information, searching for multiple patients to be selected from a preset database, and determining the medical consultation file of each patient to be selected; Calculate the relevance of each medical consultation file to the abnormal items and multiple pieces of information of the patient, and determine the target file with the highest relevance; Extracting question and answer information of each consultation file from the plurality of consultation files, and determining a consultation strategy of the doctor and the patient based on the question and answer information; Mapping the abnormal items and multiple pieces of information to the target file to obtain a consultation file to be completed for the patient; The consultation file to be completed and the consultation strategy of the doctor are output to the doctor who is consulting the patient, and the consultation strategy of the patient is output to the patient.

2. The method for remote online medical consultation based on the Internet according to claim 1, characterized in that: The plurality of information includes the main symptoms, the main diseases and the medication status, and searching for a plurality of candidates from a preset database based on the abnormal items and the plurality of information includes: Determine the symptom number corresponding to the main complaint symptom, the disease number of the main complaint disease, and the drug number corresponding to the medication situation; Determine a first characteristic value of the patient based on the symptom number, the disease number, and the drug number; Based on a first similarity between the first feature value and each second feature value, the second feature value is a feature value of each historical patient in the preset database; Determining a plurality of target historical patients whose first similarity reaches a preset similarity threshold; Determine the item number of each abnormal item of the patient, and obtain the item number of the abnormal items corresponding to each of the multiple target historical patients; A plurality of patients to be selected including the item number are determined from the plurality of target historical patients based on the item number of the patient and the item numbers of the plurality of target historical patients.

3. The method for remote online diagnosis based on the Internet according to claim 1, characterized in that: The calculation of the correlation between each medical consultation file and the abnormal item and multiple pieces of information of the patient includes: Determine the ratio of the number of abnormal items of the patient to the number of abnormal items in each consultation file; Determine the value of each abnormal item from each medical consultation file, and calculate the difference between the value of each abnormal item and the data of the abnormal item of the corresponding patient; Determine the data corresponding to each of the plurality of information in each medical consultation file, and calculate the second similarity between each piece of information and the corresponding data in each medical consultation file; The correlation between the patient and each medical consultation file is determined based on the proportion, the difference and the second similarity.

4. The method for remote online diagnosis based on the Internet according to claim 3, characterized in that: The determining the relevance between the patient and each consultation file based on the proportion, the difference and the second similarity includes: Calculate the average of all second similarities in each consultation file; Obtaining a first similarity between the candidate patient corresponding to each medical consultation file and the patient; A score is calculated based on the proportion, the difference of each abnormal item, the first similarity, the second similarity and the corresponding coefficients, and the score represents the correlation between the patient and each medical consultation file.

5. The method of remote online medical consultation based on the Internet according to claim 1, characterized in that: Determining the doctor and patient's consultation strategy based on the question and answer information includes: Extracting all questions from the question-answer information of each consultation file, wherein the questions include a first question asked by the doctor and a second question asked by the patient; Calculate the similarity between each first question and the remaining first questions, and use a clustering algorithm to determine the type of the first question; Calculate the similarity between each second question and the remaining second questions, and use a clustering algorithm to determine the type of the second question; Obtaining the time point of the first question in each category during each consultation process, and determining the average time point corresponding to each category based on the time point; Determining a target first question from the first questions in each category, and sorting each target first question based on the average time point to obtain a questioning strategy for the doctor; Obtaining the time point of the second question in each category during each consultation process, and determining the average time point corresponding to each category based on the time point; A target second question is determined from the second questions in each category, and each target second question is sorted based on the average time point to obtain a questioning strategy for the patient.

6. The method for remote online diagnosis based on the Internet according to claim 1, characterized in that: The doctor who interviews the patient outputs the doctor's interview strategy, and outputs the patient's interview strategy to the patient, including: Real-time acquisition of audio information during video consultation between the doctor and the patient; Converting the audio information into text to obtain first text information of the patient and second text information of the doctor; Performing tone recognition on the audio information to obtain the third question in the first text information and the fourth question in the second text information; When it is detected that the number of the third questions reaches a first preset number proportion, a target second question identical to the third question is deleted from the medical consultation strategy for the patient, a first medical consultation strategy after deletion is obtained, and the first medical consultation strategy after deletion is output to the terminal device of the patient; When it is detected that the number of the fourth questions reaches a second preset number, the target first question that is the same as the fourth question is deleted from the doctor's inquiry strategy, a second deleted inquiry strategy is obtained and the second deleted inquiry strategy is output to the doctor's terminal device.

7. The method of remote online medical consultation based on the Internet according to claim 6, characterized in that: The step of outputting the first deleted consultation strategy to the terminal device of the patient comprises: Sending a first prompt message to the terminal device of the patient, so that the patient triggers an instruction on whether to consult a question in the first deleted consultation strategy; If an instruction is received that there is no need to consult the questions in the first deleted consultation strategy, a second prompt message is sent to the patient's terminal device so that the patient triggers an instruction on whether to consult other questions.

8. A remote online medical guidance device based on the Internet, characterized in that: include: Data acquisition module, used to obtain the test reports and electronic medical records uploaded by patients; A data extraction module, used to extract data from the test report to obtain abnormal items of the patient, and extract multiple pieces of information from the electronic medical record; A search module, used for searching a plurality of candidates from a preset database based on the abnormal item and the plurality of information, and determining the medical consultation file of each candidate; A file determination module is used to calculate the correlation between each medical consultation file and the abnormal items and multiple pieces of information of the patient, and determine the target file with the highest correlation; A strategy determination module, configured to extract the question and answer information of each consultation file from the plurality of consultation files, and determine the consultation strategy of the doctor and the patient based on the question and answer information; A data mapping module, used for mapping the abnormal items and multiple pieces of information to the target file, to obtain a consultation file to be completed about the patient; The strategy output module is used to output the consultation file to be completed and the doctor's consultation strategy to the doctor who consults the patient, and output the patient's consultation strategy to the patient.

9. An electronic device, characterized in that: It includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in the memory and is configured to be executed by the at least one processor, and the at least one application is used to execute an Internet-based remote online medical guidance method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the Internet-based remote online medical guidance method according to any one of claims 1 to 7.

Images