Intelligent medical hospital guide method and system, electronic equipment and storage medium

Abstract

The invention discloses an intelligent medical hospital guide method and system, electronic equipment and a storage medium, and relates to the technical field of doctor seeing, and the method comprises the steps: obtaining the inquiry information and personal basic information of a target patient through an interaction platform, and obtaining a target part determined by the target patient through clicking a human body map displayed by the interaction platform; converting all the extracted inquiry key features into a first feature vector, converting the individual key features into a second feature vector, and converting the target part into a third feature vector; and fusing all the feature vectors, inputting the total feature vector into a trained intelligent medical diagnosis guide model to obtain a medical diagnosis guide recommendation result, and providing the medical diagnosis guide recommendation result to the target patient. According to the method, the inquiry information and the personal basic information of the target patient and the accurate target part can be conveniently obtained, so that an accurate medical diagnosis guide recommendation result can be generated.

Description

Background Art

[0002] Traditional medical guidance methods mainly rely on patients' verbal descriptions and doctors' experience and judgment, lacking intelligence and personalization. With the development of information technology, some online guidance systems have begun to appear, but these systems still have deficiencies in patient interaction and intelligent matching, leading to problems such as low appointment efficiency and inaccurate matching. Specifically, the patient's symptom description is not accurate enough, resulting in inaccurate recommended doctors and departments. Summary of the invention

[0003] The technical problem to be solved by the present invention is to address the deficiencies of the prior art and specifically provide an intelligent medical guidance method, system, electronic device and storage medium, as follows:

[0004] 1) In the first aspect, the present invention provides an intelligent medical guidance method, and the specific technical solution is as follows:

[0005] Obtain the target patient's medical consultation information and basic personal information through the interactive platform, and obtain the target part determined by the target patient by clicking on the human body diagram displayed on the interactive platform;

[0006] Extracting key features of the medical consultation from the medical consultation information of the target patient, and determining key personal features from the personal basic information of the target patient;

[0007] Convert all extracted key features of the medical consultation into the first feature vector, convert the personal key features into the second feature vector, and convert the target part into the third feature vector;

[0008] The first eigenvector, the second eigenvector and the third eigenvector are merged to obtain a total eigenvector;

[0009] The total feature vector is input into the trained intelligent medical guidance model to obtain the medical guidance recommendation result, and the medical guidance recommendation result is provided to the target patient.

[0010] The beneficial effects of an intelligent medical guidance method provided by the present invention are as follows:

[0011] First, the target patient's medical information and basic personal information can be easily obtained through the interactive platform, and the target patient can accurately determine the target part through the human body map. Then, the key features of the medical consultation are extracted from the target patient's medical consultation information, and the key features of the medical consultation, basic personal information and target part are converted into corresponding feature vectors, so as to generate accurate medical consultation recommendation results through the trained intelligent medical consultation model.

[0012] Based on the above solution, the intelligent medical guidance method of the present invention can also be improved as follows.

[0013] Furthermore, through the interactive platform, the target patient's consultation information and personal basic information are obtained, including:

[0014] Through the interactive platform, questions are asked to the target patients in an interactive manner and feedback information is received from the target patients. All interactive data are analyzed in real time to obtain the target patients' medical information and personal basic information.

[0015] Furthermore, it also includes:

[0016] Obtain the historical medical records of the target patient, and extract key medical features from the historical medical records of the target patient;

[0017] Convert the key features of the visit into the fourth feature vector;

[0018] Obtain the historical medical records of the target patient, and extract key medical features from the historical medical records of the target patient;

[0019] Convert the key features of the visit into the fourth feature vector;

[0020] The process of obtaining the total eigenvector includes:

[0021] The first eigenvector, the second eigenvector, the third eigenvector and the fourth eigenvector are fused to obtain a total eigenvector.

[0022] Furthermore, it also includes:

[0023] Based on the medical guidance recommendation results, determine the medical appointment recommendation information and provide it to the target patients.

[0024] 2) In the second aspect, the present invention also provides an intelligent medical guidance system, and the specific technical solution is as follows:

[0025] It includes data acquisition module, key feature extraction module, feature vector conversion module, feature vector fusion module and intelligent medical guidance module;

[0026] The data acquisition module is used to: obtain the target patient's medical consultation information and basic personal information through the interactive platform, and obtain the target part determined by the target patient by clicking on the human body diagram displayed on the interactive platform;

[0027] The medical consultation key feature extraction module is used to: extract medical consultation key features from the medical consultation information of the target patient, and determine personal key features from the personal basic information of the target patient;

[0028] The feature vector conversion module is used to: convert all extracted key features of the medical consultation into a first feature vector, convert personal key features into a second feature vector, and convert the target part into a third feature vector;

[0029] The feature vector fusion module is used to: fuse the first feature vector, the second feature vector and the third feature vector to obtain a total feature vector;

[0030] The intelligent medical guidance module is used to: input the total feature vector into the trained intelligent medical guidance model, obtain the medical guidance recommendation result, and provide the medical guidance recommendation result to the target patient.

[0031] Based on the above solution, the intelligent medical guidance system of the present invention can also be improved as follows.

[0032] Furthermore, the data acquisition module is specifically used for:

[0033] Through the interactive platform, questions are asked to the target patients in an interactive manner and feedback information is received from the target patients. All interactive data are analyzed in real time to obtain the target patients' medical information and personal basic information.

[0034] Furthermore, it also includes a module for obtaining key features of medical consultation;

[0035] The data acquisition module is also used to: obtain the historical medical records of the target patient;

[0036] The key features acquisition module for medical consultation is used to: extract key features of medical consultation from the historical medical records of target patients;

[0037] The feature vector conversion module is also used to: convert the key features of the medical consultation into a fourth feature vector;

[0038] The feature vector fusion module is specifically used to fuse the first feature vector, the second feature vector, the third feature vector and the fourth feature vector to obtain a total feature vector.

[0039] Furthermore, it also includes a medical appointment recommendation module, which is used to: determine medical appointment recommendation information based on the medical guidance recommendation results and provide it to the target patient.

[0040] 3) In a third aspect, the present invention further provides an electronic device, comprising a processor, the processor being coupled to a memory, the memory storing at least one computer program, the at least one computer program being loaded and executed by the processor, so that the electronic device implements any one of the above-mentioned intelligent medical guidance methods.

[0041] 4) In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, any of the above-mentioned intelligent medical guidance methods is implemented.

[0042] It should be noted that the beneficial effects achieved by the technical solutions of the second to fourth aspects of the present invention and the corresponding possible implementation methods can be found in the above-mentioned technical effects of the first aspect and its corresponding possible implementation methods, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments of the present invention:

[0044] Figure 1 A schematic diagram of a flow chart of an intelligent medical diagnosis guidance method according to an embodiment of the present invention;

[0045] Figure 2 This is one of the interface diagrams of the intelligent consultation chat box;

[0046] Figure 3 This is the second interface diagram of the intelligent consultation chat box;

[0047] Figure 4 A schematic diagram of a display interface of a human body diagram;

[0048] Figure 5 A schematic diagram of the structure of an intelligent medical guidance system according to an embodiment of the present invention;

[0049] Figure 6 The figure is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The principles and features of the present invention are described below. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0051] The technical solution of the present invention and how the technical solution of the present invention solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0052] like Figure 1 As shown, an intelligent medical guidance method according to an embodiment of the present invention includes the following steps:

[0053] S1. Obtain the target patient's medical consultation information and basic personal information through the interactive platform, and obtain the target part determined by the target patient by clicking on the human body diagram displayed on the interactive platform;

[0054] Among them, the interactive platform is divided into the management side and the patient side. The management side can be an executable program in exe format, which can be installed on a computer device. The management side can also be an APP program, which can be installed on the manager's smartphone or tablet computer. The patient side can be an APP program, which is easy to install on the target patient's smartphone or tablet computer, so that each patient can be consulted in real time.

[0055] The target patient may be any preset patient, and the preset patient is: a patient registered on the interactive platform.

[0056] Among them, through the interactive platform, the target patient's consultation information and personal basic information are obtained. The specific implementation process is as follows:

[0057] Through interactive means, questions are asked to the target patients and feedback is received from them. All interactive data are analyzed in real time to obtain the target patients' complete consultation information and basic personal information.

[0058] Among them, on the display interface of the patient side, there are click boxes for voice, text and image modes. The target patient selects voice, text or image mode by clicking to provide feedback on the questions raised by the interactive platform. The management side and the patient side can also communicate through the intelligent guidance chat box. For example, the interactive platform will ask questions such as "How long has the headache lasted?" and "Are there any other discomfort symptoms?" to obtain more consultation details.

[0059] like Figure 2 and Figure 3 As shown in the figure, when the patient opens the intelligent consultation chat box, it displays three navigation bars: "Where do you feel uncomfortable?", "Recommend department (room) based on symptom description" and "Recommend doctor based on symptoms". Then:

[0060] 1) When the target patient selects the "Where do you feel uncomfortable" navigation bar, the interactive platform will ask corresponding questions to obtain the target patient's feedback, thereby obtaining the target patient's medical information and personal basic information. Then, according to the target patient's medical information and personal basic information, the corresponding diagnosis and treatment plan and health management plan (including diet matching plan) can be matched for the target patient to view.

[0061] 2) When the target patient selects the "Recommend department based on symptom description" navigation bar, the interactive platform will ask corresponding questions to obtain the target patient's feedback, thereby obtaining the target patient's medical consultation information and personal basic information. Then, based on the target patient's medical consultation information and personal basic information, and using the trained intelligent medical guidance model, the department recommendation results can be obtained. The department recommendation results include multiple departments arranged in order of recommendation probability from high to low.

[0062] 3) When the target patient selects the "Recommend a doctor based on symptoms" navigation bar, the interactive platform will ask corresponding questions to obtain the target patient's feedback, thereby obtaining the target patient's medical consultation information and personal basic information. Then, based on the target patient's medical consultation information and personal basic information, and using the trained intelligent medical guidance model, the doctor recommendation results can be obtained. The doctor recommendation results include: multiple doctors arranged in order of recommendation probability from high to low.

[0063] Among them, when the interactive platform asks about the gender of the target patient (patient), the selection boxes of "Male" and "Female" can be displayed to facilitate the target patient to make a selection. When the interactive platform asks about the age of the target patient (patient), the selection boxes of "Child" and "Adult" can be displayed to facilitate the target patient to make a selection, or an input box for entering age can be displayed to facilitate the target patient to directly enter the age.

[0064] When the interactive platform requires the target patient to determine the location of the disease (target location), a human body diagram display interface pops up to facilitate the target patient to make a selection. It should be noted that when the target patient's gender is "male", a male human body diagram is displayed, and when the target patient's gender is "female", a female human body diagram is displayed. Figure 4 As shown, the target patient selects the target site in the following manner:

[0065] 1) The first implementation method:

[0066] A drop-down menu bar is also provided on the display interface of the displayed human body diagram. In the drop-down menu bar, a plurality of candidate parts are provided. When the target patient selects any candidate part, the candidate part will be displayed distinguishably on the human body diagram, such as by color, so that the target patient can determine whether it is the part where the disease is located, until the target patient determines the target part.

[0067] 2) The second implementation method:

[0068] Marks (such as black dots, etc.) for multiple selected parts are preset on the displayed human body map. For example, marks are set on multiple selected parts such as the head, eyes, ears, nose, throat, mouth, shoulders, arms, hands, abdomen, thighs, calves and feet of the human body map. When the target patient clicks on the mark with his finger or mouse, the part corresponding to the clicked mark is determined as the target part.

[0069] 3) The third implementation method:

[0070] Since it is not realistic to set a mark point for each part of the human body map, at this time, the part where the target patient's disease is located is not necessarily the part to be selected, so it is processed in the following way:

[0071] When the display interface of the human body map pops up, the device (smartphone or computer) installed on the patient side of the target patient is recorded in real time. When the target patient's finger or mouse clicks the mark, the part corresponding to the clicked mark is determined as the target part, and the screen recording is stopped at this time; when the target patient's finger or mouse does not click the mark, but clicks other non-marked human body parts, the video frame of the human body part clicked by the target patient is obtained from the screen recording video, and the human body map in the video frame is matched with the complete human body map to determine the human body part clicked by the target patient, thereby obtaining the target part.

[0072] The human body map in the video frame is described as follows: since the target patient may need to enlarge the displayed human body map, the human body map in the video frame may be a partial human body map.

[0073] Among them, through interactive means, questions are asked to the target patients and feedback information is received from the target patients, and all interactive data are analyzed in real time to analyze whether the consultation information and personal basic information are complete, specifically:

[0074] 1) The medical consultation information includes the following:

[0075] ① Whether the patient's main symptoms or discomfort are clearly described, including the time of onset, duration, nature (such as whether the pain is dull, sharp or radiating), location, degree and accompanying symptoms.

[0076] ② The development process of the symptoms, including the starting time, the changing process, the factors that aggravate or relieve the symptoms, etc. Whether the general conditions such as diet, sleep, defecation, urination, weight, etc. are recorded.

[0077] ③ The target patient’s occupation, lifestyle habits (such as smoking, drinking, dietary preferences, etc.), living environment, marital and reproductive history, etc.

[0078] ④Whether there are hereditary diseases, infectious diseases or other diseases in the family that may be related to the current symptoms.

[0079] The interactive platform can ask questions based on the above-mentioned medical information to obtain complete medical information of the target patient. During the questioning process, AI technology is used to analyze in real time whether corresponding feedback is obtained. If no feedback is obtained, the question can be repeated.

[0080] In another embodiment, the interactive platform determines whether the target patient's medical information is complete by asking the question "Do you have other discomfort symptoms?" If the patient reports that he has no other discomfort symptoms, it is determined that the complete medical information has been obtained. If the patient reports that he has other discomfort symptoms, it is determined that the complete medical information has not been obtained, and the interactive platform continues to ask questions until the complete medical information is obtained.

[0081] 2) Basic personal information includes: age, gender, occupation and contact information.

[0082] S2. Extract key features of the medical consultation from the medical consultation information of the target patient, and determine the personal key features from the personal basic information of the target patient.

[0083] Among them, the key personal characteristics determined in the target patient's basic personal information include: age, gender and occupation.

[0084] The specific implementation process of extracting key features of the medical consultation from the medical consultation information of the target patient is as follows:

[0085] 1) The first implementation method:

[0086] S20, pre-processing the target patient's medical information, specifically:

[0087] The target patient's medical information is often unstructured, such as text, voice or image. In order to extract the key features of the medical information, the target patient's medical information needs to be preprocessed first, specifically through text cleaning (removing irrelevant characters, punctuation marks, etc.), word segmentation (segmenting the text into meaningful vocabulary units), part-of-speech tagging (marking each word with its part of speech, such as noun, verb, etc.) and other steps to achieve the preprocessing of the target patient's medical information.

[0088] S21. Extract the initial key features of the medical consultation from the preprocessed medical consultation information based on rules (such as keyword matching) or machine learning (such as deep learning models).

[0089] Among them, rule-based methods rely on predefined knowledge bases or dictionaries, while machine learning methods can automatically identify by training models.

[0090] S22, integrating and optimizing the extracted initial key features of the medical consultation to obtain the key features of the medical consultation, specifically:

[0091] The extracted initial key features of the medical consultation are processed by removing redundant information, merging similar features, correcting erroneous information, etc. to obtain the key features of the medical consultation.

[0092] Among them, the key characteristics of the medical interview include: symptom characteristics (such as pain, fever and cough, etc.), medical history characteristics (such as previous illness, surgical history and allergy history, etc.) and lifestyle characteristics (such as diet, exercise, sleep, etc.).

[0093] 2) The second implementation method:

[0094] Based on medical materials such as textbooks, clinical guidelines, and clinical pathways, we build relationships between entities and entity time. Entities can be diseases, symptoms, drugs, etc., and relationships can be the association between diseases and symptoms, the therapeutic relationship between drugs and diseases, etc. We convert them into structured knowledge representations through natural language processing and other technologies to build a knowledge graph. Based on the needs of the medical field and the characteristics of the consultation information, we predefine the required key features. These predefined key features may include disease names, symptom descriptions, medical history information, examination results, etc.

[0095] First, the knowledge graph is used to perform entity recognition on the medical inquiry information. Then, based on the entity recognition, the relationships in the knowledge graph are used to extract the relationships between the medical inquiry information. The associations between entities can be identified, such as the association between diseases and symptoms, the therapeutic relationship between drugs and diseases, etc. The relationship extraction methods can be template-based methods, supervised learning methods, semi-supervised learning methods, etc.

[0096] The extracted entities and relationships are matched with predefined key features. If the extracted entity or relationship matches a predefined key feature, the predefined key feature is matched to the data in the medical consultation information and defined as a medical consultation key feature, until all medical consultation key features are extracted from the medical consultation information of the target patient.

[0097] S3, convert all extracted key features of the medical consultation into the first feature vector, convert personal basic information into the second feature vector, and convert the target part into the third feature vector. The specific implementation process is as follows:

[0098] 1) Arrange all the extracted key features of the medical consultation in a certain order, assign a numerical value to each key feature of the medical consultation, which can be the original value of the key feature of the medical consultation, the value after some transformation, or the importance score of the feature, and combine these numerical values ​​into a vector, namely the first eigenvector.

[0099] 2) Arrange all the extracted key features of the medical consultation in a certain order, assign a numerical value to each key feature of the medical consultation, which can be the original value of the key feature of the medical consultation, the value after some transformation, or the importance score of the feature, and combine these numerical values ​​into a vector, namely the first eigenvector.

[0100] 3) Pre-construct a feature vector corresponding to each of the preset multiple candidate parts. When the target part is a candidate part, the feature vector corresponding to the target part, that is, the third feature vector, can be directly obtained. When the target part is not a candidate part, the feature vectors of multiple candidate parts around the target part are weightedly merged to obtain the third feature vector. During the weighted merging, the closer the candidate part is to the target part, the higher the weight of the feature vector, and the farther the candidate part is from the target part, the lower the weight of the feature vector. The correlation between the distance and the weight can be set according to the actual situation.

[0101] S4, fusing the first eigenvector, the second eigenvector and the third eigenvector to obtain a total eigenvector, which can be specifically achieved in the following manner:

[0102] 1) The first implementation method:

[0103] The first eigenvector, the second eigenvector and the third eigenvector are serially fused, that is, the first eigenvector, the second eigenvector and the third eigenvector are concatenated to obtain a total eigenvector.

[0104] 2) The second implementation method:

[0105] The first eigenvector, the second eigenvector and the third eigenvector are added or weighted summed to obtain a total eigenvector, wherein during the weighted summation, different weights may be assigned according to the importance of the first eigenvector, the second eigenvector and the third eigenvector.

[0106] 3) The third implementation method:

[0107] The first eigenvector, the second eigenvector and the third eigenvector are normalized to eliminate the dimensional differences between different eigenvectors, and then concatenated, added or weighted summed to obtain a total eigenvector.

[0108] 4) The fourth implementation method:

[0109] The first eigenvector, the second eigenvector and the third eigenvector are reduced in dimension by using the principal component analysis (PCA) method or the linear discriminant analysis (LDA) method, and the main eigenvectors in the first eigenvector, the second eigenvector and the third eigenvector are extracted; the main eigenvectors in the first eigenvector, the second eigenvector and the third eigenvector are normalized to eliminate the dimensional differences between different eigenvectors, and then they are concatenated, added or weightedly summed to obtain the total eigenvector.

[0110] S5. Input the total feature vector into the trained intelligent medical guidance model to obtain the medical guidance recommendation result, and provide the medical guidance recommendation result to the target patient.

[0111] The process of obtaining the trained intelligent medical guidance model includes:

[0112] Obtain historical consultation information and historical personal basic information of multiple preset patients, and then obtain the corresponding historical total feature vector, and mark the historical medical guidance recommendation results corresponding to each preset patient, and then train the preset deep learning model to obtain a trained intelligent medical guidance model. The preset deep learning model can be a convolutional neural network or a long short-term memory artificial neural network, etc., which can be set according to actual actual conditions.

[0113] Among them, the medical guidance recommendation results include: department recommendation results and doctor recommendation results.

[0114] When the historical medical consultation information and historical personal basic information increase, the preset deep learning model can also be retrained to ensure the prediction accuracy of the trained intelligent medical guidance model.

[0115] Optionally, in the above technical solution, it also includes:

[0116] S050. Obtain the historical medical records of the target patient, and extract key medical features from the historical medical records of the target patient;

[0117] Among them, through the historical medical records, the historical health status and preliminary physical examination records of the target patients can be understood. The historical health status of the target patients includes previous diseases, surgeries, trauma, blood transfusions, vaccination history, etc., whether there is a history of long-term medication, especially drugs that may be related to current symptoms; the preliminary physical examination records include: including vital signs (such as body temperature, pulse, respiration, blood pressure), general condition (such as nutrition, development, consciousness, posture, gait, etc.), skin and mucous membranes, lymph nodes, head and facial features, neck, chest, abdomen, spine and limbs, nervous system, etc., which may include blood routine, urine routine, biochemical examination, imaging examination and other examination results.

[0118] Extract key features of medical visits from the historical medical records of the target patient. The specific implementation process is as follows:

[0119] 1) The first implementation method:

[0120] S0500. Preprocess the target patient's medical information, specifically:

[0121] The target patient's medical information is often unstructured, such as text, voice or image. In order to extract the key features of the medical treatment, the target patient's medical information needs to be preprocessed first, specifically through text cleaning (removing irrelevant characters, punctuation marks, etc.), word segmentation (segmenting the text into meaningful vocabulary units), part-of-speech tagging (marking each word with its part of speech, such as noun, verb, etc.) and other steps to achieve the preprocessing of the target patient's medical information.

[0122] S0501. Extract the initial key features of the medical consultation from the preprocessed medical consultation information based on rules (such as keyword matching) or machine learning (such as deep learning models).

[0123] Among them, rule-based methods rely on predefined knowledge bases or dictionaries, while machine learning methods can automatically identify by training models.

[0124] S0502. Integrate and optimize the extracted initial key features of the medical consultation to obtain the key features of the medical consultation. Specifically:

[0125] The extracted initial key features of the medical consultation are processed by removing redundant information, merging similar features, correcting erroneous information, etc. to obtain the key features of the medical consultation.

[0126] Among them, the key characteristics of the visit include: symptom characteristics (such as pain, fever and cough, etc.), medical history characteristics (such as previous illness, surgical history and allergy history, etc.) and lifestyle characteristics (such as diet, exercise, sleep, etc.).

[0127] 2) The second implementation method:

[0128] Based on medical materials such as textbooks, clinical guidelines, and clinical pathways, we build relationships between entities and entity time. Entities can be diseases, symptoms, drugs, etc., and relationships can be the association between diseases and symptoms, the therapeutic relationship between drugs and diseases, etc. We convert them into structured knowledge representations through natural language processing and other technologies to build a knowledge graph. Based on the needs of the medical field and the characteristics of medical information, we predefine the required key features. These predefined key features may include disease names, symptom descriptions, medical history information, test results, etc.

[0129] First, the knowledge graph is used to perform entity recognition on the medical information. Then, based on the entity recognition, the relationships in the knowledge graph are used to extract the relationships between the medical information. The associations between entities can be identified, such as the association between diseases and symptoms, the therapeutic relationship between drugs and diseases, etc. The relationship extraction methods can be template-based methods, supervised learning methods, semi-supervised learning methods, etc.

[0130] The extracted entities and relationships are matched with predefined key features. If the extracted entity or relationship matches a predefined key feature, the predefined key feature is matched to the data in the medical information and defined as a medical key feature, until all medical key features are extracted from the medical information of the target patient.

[0131] S051. Convert the key features of the medical consultation into a fourth feature vector. For the specific implementation process, refer to the specific implementation process of S3 above, which will not be described in detail here.

[0132] The process of obtaining the total eigenvector includes:

[0133] The first eigenvector, the second eigenvector, the third eigenvector and the fourth eigenvector are merged to obtain a total eigenvector. The specific implementation process is referred to the specific implementation process of S4 above, which will not be described in detail here.

[0134] In S5, the total feature vector is input into the trained intelligent medical guidance model to obtain the medical guidance recommendation results, including:

[0135] S50, inputting a total feature vector obtained by fusing the first feature vector, the second feature vector, the third feature vector and the fourth feature vector into a trained intelligent medical guidance model to obtain a medical guidance recommendation result.

[0136] Optionally, in the above technical solution, it also includes:

[0137] S6. Determine the recommended appointment information based on the medical guidance recommendation results and provide it to the target patients, specifically:

[0138] S60. Generate medical appointment recommendation information based on the appointment information and work information of each doctor in the doctor recommendation results in the medical guidance recommendation results, wherein the appointment information includes the appointment time, appointment type (such as initial visit, follow-up visit, routine examination, etc.), appointment status (such as confirmed, pending confirmation, canceled, etc.); the work information includes: work schedule (including working days, rest days, working hours of each working day, etc.) and holiday arrangements (such as special holiday work or rest arrangements), etc.

[0139] S61. Arrange the free time periods of each doctor, specifically:

[0140] According to the doctor's appointment information, the booked time periods are marked, and combined with the doctor's work schedule, the booked time periods are removed from the work hours to obtain the doctor's free time periods.

[0141] S62. According to the patient's appointment request (such as appointment type, expected time, etc.), select the free time periods that meet the requirements from the doctor's free time periods, and use algorithms (such as greedy algorithms, dynamic programming, etc.) to further optimize the appointment recommendation information. Each piece of information in the appointment recommendation information includes: doctor's name, recommended appointment time (date and specific time), appointment type, appointment location (such as hospital name, department name, etc.) and other necessary prompt information (such as bringing ID card, medical record book, etc.). Each piece of information can be sorted according to information such as the praise of each doctor.

[0142] Send the generated appointment recommendation information to the target patient via SMS, email or APP notification. Make sure the notification content is clear and easy for the target patient to understand and operate. Remind the target patient to confirm the appointment as soon as possible after receiving the recommendation information so that the hospital or doctor can make follow-up arrangements. You can set a deadline for confirming the appointment, after which the recommendation information will automatically expire. Update the appointment status of the target patient in real time to ensure that the hospital or doctor can accurately grasp the appointment status of the target patient. For confirmed appointments, inform the patient in advance of the precautions and preparations before the visit.

[0143] Optionally, collect patient feedback on medical appointment recommendation information in order to continuously optimize and improve the recommendation algorithm and service quality.

[0144] Optionally, in addition to recommendation paths such as SMS, email or APP notifications, recommendation paths can also be intelligently increased based on actual situations. For example, when there are too many medical guidance recommendation results and medical appointment recommendation information that need to be recommended, information recommendations can also be made through social platforms.

[0145] In another embodiment, comprising:

[0146] 1) Startup interface:

[0147] Log in through the WeChat official account or APP, enter personal basic information (such as gender, age) and symptom description, and enter the main interface.

[0148] 2) The patient clicks on the "head" area on the human body map to generate a list of symptoms for that area. The patient selects "headache" and a detailed disease explanation and knowledge link are provided.

[0149] 3) Based on the patient's gender (male), age (30 years old), symptom description (headache, fever, cough), combined with historical medical records and expert scores, the most suitable doctor (such as Dr. Zhang from the Department of Neurology and Dr. Li from the Department of Respiratory Medicine) is recommended. Patients can choose the recommended doctor to make an appointment.

[0150] 4) Actively ask questions during the interaction, such as "How long has the headache lasted?", "Are there any other discomfort symptoms?", and extract key information through AI to ensure the completeness and accuracy of the diagnostic information.

[0151] 5) Based on the interactive data, the consultation appointment status is counted and tracked in real time to generate a new appointment process that is more in line with the actual situation. For example, if the number of appointments for a department is too large, the recommendation logic will be automatically adjusted to give priority to recommending other suitable doctors or adjusting the appointment time.

[0152] 6) Provide patients with a variety of appointment methods (such as phone, APP, WeChat), and send appointment confirmation information and reminder notifications to ensure that patients see the doctor on time. At the same time, the system will record the results of each appointment for subsequent process optimization.

[0153] The beneficial effects of the present invention are as follows:

[0154] 1) The system conducts intelligent analysis based on the patient's input of gender, age, symptom description, and clicks on specific parts of the human body map to accurately match the most suitable doctor. Compared with traditional methods, it improves the accuracy of matching, reduces the risk of misdiagnosis and the patient's waiting time.

[0155] 2) Adopt intelligent matching algorithms to guide patients to complete the medical process, actively communicate with patients during the interaction process, extract key information, and ensure the completeness and accuracy of diagnostic information. At the same time, it supports voice and text interaction to improve the convenience and intuitiveness of patients.

[0156] 3) According to the interaction results between the patient and the system, the consultation appointment status will be counted and tracked in real time, and a new appointment process that is more in line with the actual situation will be generated. Through continuous iteration and optimization, the appointment process will be made more intelligent and reliable to meet the personalized needs of different patients.

[0157] 4) Provide detailed disease explanations, prevention suggestions and treatment plans to help patients conduct initial self-diagnosis and enhance their health awareness and self-management capabilities.

[0158] In the above embodiments, although the steps are numbered S1, S2, etc., these are only specific embodiments given by the present invention. Those skilled in the art may adjust the execution order of S1, S2, etc. according to actual conditions, which is also within the protection scope of the present invention. It can be understood that in some embodiments, some or all of the above embodiments may be included.

[0159] like Figure 5 As shown, an intelligent medical guidance system 200 according to an embodiment of the present invention includes a data acquisition module 201, a key feature extraction module 202, a feature vector conversion module 203, a feature vector fusion module 204 and an intelligent medical guidance module 205;

[0160] The data acquisition module 201 is used to: acquire the target patient's medical consultation information and basic personal information through the interactive platform, and acquire the target part determined by the target patient by clicking on the human body diagram displayed on the interactive platform;

[0161] The medical consultation key feature extraction module 202 is used to: extract medical consultation key features from the medical consultation information of the target patient, and determine personal key features from the personal basic information of the target patient;

[0162] The feature vector conversion module 203 is used to: convert all extracted key features of the medical consultation into a first feature vector, convert the personal key features into a second feature vector, and convert the target part into a third feature vector;

[0163] The feature vector fusion module 204 is used to: fuse the first feature vector, the second feature vector and the third feature vector to obtain a total feature vector;

[0164] The intelligent medical guidance module 205 is used to: input the total feature vector into the trained intelligent medical guidance model to obtain the medical guidance recommendation result, and provide the medical guidance recommendation result to the target patient.

[0165] Optionally, in the above technical solution, the data acquisition module 201 is specifically used for:

[0166] Through the interactive platform, questions are asked to the target patients in an interactive manner and feedback information is received from the target patients. All interactive data are analyzed in real time to obtain the target patients' medical information and personal basic information.

[0167] Optionally, in the above technical solution, a module for acquiring key features of medical consultation is also included;

[0168] The data acquisition module 201 is also used to: acquire the historical medical records of the target patient;

[0169] The key features acquisition module for medical consultation is used to: extract key features of medical consultation from the historical medical records of target patients;

[0170] The feature vector conversion module 203 is also used to: convert the key features of the medical consultation into a fourth feature vector;

[0171] The feature vector fusion module 204 is specifically used to fuse the first feature vector, the second feature vector, the third feature vector and the fourth feature vector to obtain a total feature vector.

[0172] Optionally, the above technical solution also includes a medical appointment recommendation module, which is used to determine the medical appointment recommendation information based on the medical guidance recommendation results and provide it to the target patient.

[0173] In another embodiment, comprising:

[0174] 1) Input module: The patient enters the main interface by entering basic personal information (such as gender, age) and symptom description, and selects the body part to be queried

[0175] 2) Human body diagram interactive module: Patients can click on specific structural parts on the human body diagram, and the system will generate a corresponding symptom list based on the selected part. After the patient selects a specific symptom, the system will provide detailed disease explanations and knowledge links.

[0176] 3) Intelligent matching algorithm: The system automatically analyzes and recommends the most suitable doctor and department based on the patient's gender, age, symptom description, and other information, combined with historical medical records and expert scores. Through machine learning and big data analysis, it ensures that the recommended doctors have professional capabilities and rich experience.

[0177] 4) Active communication module: The system actively communicates with the patient during the interaction process, extracts key information through AI, and ensures the completeness and accuracy of the diagnostic information. For example, the system will ask questions such as "How long has the headache lasted?" and "Are there any other discomfort symptoms?" to obtain more details.

[0178] 5) Dynamically optimize the appointment process: The system counts and tracks the consultation appointment status in real time based on the interaction between the patient and the system, and generates a new appointment process that is more in line with the actual situation. Through machine learning algorithms, the appointment process is continuously iterated and optimized to make it more intelligent and reliable. For example, when the number of appointments for a department is too large, the system will give priority to recommending other suitable doctors or adjusting the appointment time.

[0179] 6) Appointment confirmation and reminder module: The system provides patients with a variety of appointment methods (such as phone, APP, WeChat), and sends appointment confirmation information and reminder notifications to ensure that patients see the doctor on time. At the same time, the system will record the results of each appointment for subsequent process optimization.

[0180] 7) Business node sorting module: The system sorts out the common doctor-patient communication information used by patients during their visits to form a business node library. In the process of interaction between patients and the system, the corresponding business nodes are matched to guide patients to complete the appointment process.

[0181] It should be noted that the beneficial effects of the intelligent medical guidance system 200 provided in the above embodiment are the same as the beneficial effects of the above intelligent medical guidance method, which will not be repeated here. In addition, when the system provided in the above embodiment realizes its functions, it only takes the division of the above functional modules as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the system is divided into different functional modules according to actual conditions to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0182] Among them, the intelligent medical guidance system of the present invention can be a computer program (including program code) running in a computer device. For example, the intelligent medical guidance system of the present invention is an application software that can be used to execute the corresponding steps in the intelligent medical guidance method of the present invention.

[0183] In some embodiments, the intelligent medical guidance system of the present invention can be implemented in a combination of software and hardware. As an example, the intelligent medical guidance system of the present invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the intelligent medical guidance method of the present invention. For example, the processor in the form of a hardware decoding processor can adopt one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field programmable gate arrays (FPGAs) or other electronic components.

[0184] The modules involved in the embodiments of the present invention may be implemented in software or hardware. The name of a module does not limit the module itself in some cases.

[0185] An electronic device according to an embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, any one of the above-mentioned intelligent medical guidance methods is implemented. That is to say, an electronic device according to an embodiment of the present invention may include but is not limited to: a processor and a memory; the memory is used to store the computer program; the processor is used to execute the intelligent medical guidance method shown in any embodiment of the present invention by calling the computer program.

[0186] In an alternative embodiment, an electronic device is provided, such as Figure 6 As shown, Figure 6 The electronic device 4000 shown includes: a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, such as through a bus 4002. Optionally, the electronic device 4000 may also include a transceiver 4004, which may be used for data interaction between the electronic device and other electronic devices, such as data transmission and / or data reception. It should be noted that in actual applications, the transceiver 4004 is not limited to one, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present invention.

[0187] Processor 4001 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 the present invention. Processor 4001 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.

[0188] The bus 4002 may include a path to transmit information between the above components. The bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 4002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 In the figure, only one thick line is used to represent the bus 4002, but this does not mean that there is only one bus or one type of bus.

[0189] The memory 4003 can 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 to these.

[0190] The memory 4003 is used to store the application code (computer program) for executing the solution of the present invention, and the execution is controlled by the processor 4001. The processor 4001 is used to execute the application code stored in the memory 4003 to implement the content shown in the above method embodiment.

[0191] Among them, the electronic device can also be a terminal device, and the terminal device can be any device that can install applications, including at least one of a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, a smart TV, and a smart car device.

[0192] It should be noted that Figure 6 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0193] A computer-readable storage medium according to an embodiment of the present invention stores a computer program, and when the computer program is executed by a processor, any of the above-mentioned intelligent medical guidance methods is implemented.

[0194] Optionally, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0195] In an exemplary embodiment, a computer program product or a computer program is also provided, the computer program product or the computer program including computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device performs any of the above-mentioned intelligent medical guidance methods.

[0196] Computer program code for performing the operations of the present invention may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the patient's computer, partially on the patient's computer, as a separate software package, partially on the patient's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the patient's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0197] It should be understood that the flow charts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the module, the program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0198] The computer-readable storage medium provided by the embodiment of the present invention may be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or component.

[0199] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0200] The above description is only a preferred embodiment of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the disclosure scope involved in the present invention is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present invention (but not limited to) by each other.

[0201] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects and represent the definition of a specific order or sequence. The order of use of similar objects can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than the order shown or described.

[0202] Those skilled in the art know that the present invention can be implemented as a system, method or computer program product. Therefore, the present invention can be specifically implemented in the following forms, namely: it can be complete hardware, it can be complete software (including firmware, resident software, microcode, etc.), or it can be a combination of hardware and software, which is generally referred to as "circuit", "module" or "system" herein. In addition, in some embodiments, the present invention can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code.

[0203] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. An intelligent medical guidance method, characterized in that: include: Obtaining the target patient's medical consultation information and basic personal information through the interactive platform, and obtaining the target part determined by the target patient by clicking on the human body diagram displayed on the interactive platform; Extracting key features of the medical consultation from the medical consultation information of the target patient, and determining key personal features from the personal basic information of the target patient; Convert all extracted key features of the medical consultation into a first feature vector, convert the personal key features into a second feature vector, and convert the target part into a third feature vector; Merging the first feature vector, the second feature vector and the third feature vector to obtain a total feature vector; The total feature vector is input into a trained intelligent medical guidance model to obtain a medical guidance recommendation result, and the medical guidance recommendation result is provided to the target patient.

2. The intelligent medical guidance method according to claim 1, characterized in that: Through the interactive platform, the target patient's consultation information and personal basic information are obtained, including: Through the interactive platform, questions are asked to the target patient in an interactive manner and feedback information from the target patient is received, and all interactive data are analyzed in real time to obtain the target patient's consultation information and personal basic information.

3. The intelligent medical guidance method according to claim 2, characterized in that: Also includes: Obtaining the historical medical records of the target patient, and extracting key medical features from the historical medical records of the target patient; Convert the key features of the medical consultation into a fourth feature vector; The process of obtaining the total eigenvector includes: The first eigenvector, the second eigenvector, the third eigenvector and the fourth eigenvector are merged to obtain a total eigenvector.

4. An intelligent medical guidance method according to any one of claims 1 to 3, characterized in that: Also includes: Based on the medical consultation recommendation result, medical consultation appointment recommendation information is determined and provided to the target patient.

5. An intelligent medical guidance system, characterized in that: It includes data acquisition module, key feature extraction module, feature vector conversion module, feature vector fusion module and intelligent medical guidance module; The data acquisition module is used to: acquire the target patient's medical consultation information and basic personal information through the interactive platform, and acquire the target part determined by the target patient by clicking on the human body diagram displayed on the interactive platform; The medical consultation key feature extraction module is used to: extract medical consultation key features from the medical consultation information of the target patient, and determine personal key features from the personal basic information of the target patient; The feature vector conversion module is used to: convert all extracted key features of the medical consultation into a first feature vector, convert the personal key features into a second feature vector, and convert the target part into a third feature vector; The feature vector fusion module is used to: fuse the first feature vector, the second feature vector and the third feature vector to obtain a total feature vector; The intelligent medical guidance module is used to: input the total feature vector into the trained intelligent medical guidance model to obtain a medical guidance recommendation result, and provide the medical guidance recommendation result to the target patient.

6. The intelligent medical guidance system according to claim 5, characterized in that: The data acquisition module is specifically used for: Through the interactive platform, questions are asked to the target patient in an interactive manner and feedback information from the target patient is received, and all interactive data are analyzed in real time to obtain the target patient's consultation information and personal basic information.

7. The intelligent medical guidance system according to claim 6, characterized in that: It also includes a module for obtaining key features of medical consultations; The data acquisition module is also used to: acquire the historical medical records of the target patient; The medical consultation key feature acquisition module is used to: extract medical consultation key features from the historical medical consultation records of the target patient; The feature vector conversion module is also used to: convert the key features of the medical consultation into a fourth feature vector; The feature vector fusion module is specifically used to fuse the first feature vector, the second feature vector, the third feature vector and the fourth feature vector to obtain a total feature vector.

8. An intelligent medical guidance system according to any one of claims 5 to 7, characterized in that: It also includes a medical appointment recommendation module, which is used to determine medical appointment recommendation information based on the medical guidance recommendation result and provide it to the target patient.

9. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, an intelligent medical diagnosis guidance method as claimed in any one of claims 1 to 4 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the intelligent medical guidance method according to any one of claims 1 to 4 is implemented.

Images