CN118173287B - Medical video online diagnosis and treatment method and system - Google Patents
Medical video online diagnosis and treatment method and system Download PDFInfo
- Publication number
- CN118173287B CN118173287B CN202410244932.4A CN202410244932A CN118173287B CN 118173287 B CN118173287 B CN 118173287B CN 202410244932 A CN202410244932 A CN 202410244932A CN 118173287 B CN118173287 B CN 118173287B
- Authority
- CN
- China
- Prior art keywords
- data
- doctor
- identification
- diagnosis
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 81
- 238000000034 method Methods 0.000 title claims abstract description 32
- 208000024891 symptom Diseases 0.000 claims abstract description 115
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 74
- 238000012512 characterization method Methods 0.000 claims abstract description 67
- 230000006854 communication Effects 0.000 claims abstract description 31
- 201000010099 disease Diseases 0.000 claims abstract description 25
- 238000004891 communication Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims description 100
- 238000013145 classification model Methods 0.000 claims description 30
- 238000012360 testing method Methods 0.000 claims description 29
- 238000002372 labelling Methods 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 15
- 230000011218 segmentation Effects 0.000 claims description 13
- 238000012795 verification Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000013095 identification testing Methods 0.000 claims description 5
- 238000002405 diagnostic procedure Methods 0.000 claims description 4
- 208000003251 Pruritus Diseases 0.000 description 9
- 230000007803 itching Effects 0.000 description 9
- 208000035824 paresthesia Diseases 0.000 description 7
- 210000000245 forearm Anatomy 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 201000004624 Dermatitis Diseases 0.000 description 1
- 206010035664 Pneumonia Diseases 0.000 description 1
- 208000010668 atopic eczema Diseases 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004171 remote diagnosis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Pathology (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to the technical field of online medical treatment, and discloses a medical video online diagnosis and treatment method and a system, wherein the medical video online diagnosis and treatment method comprises the steps of receiving a medical voice request uploaded by a user side and acquiring the type of a diagnosis and treatment department of a patient according to a pre-configured outpatient diagnosis identification model; acquiring a best matching doctor for finding the type of a department according to the online diagnosis data, and forwarding a medical voice request to a doctor end of the best matching doctor; when the best matching doctor receives a medical voice request through the doctor side, establishing remote video communication through the user side of the patient side and the doctor side of the doctor side; determining a characterization part of a patient according to the symptom part keywords in the medical voice request, acquiring a plurality of characterization part images of the patient according to the characterization part in the remote video communication process, inputting the plurality of characterization part images into a pre-configured disease identification model, and acquiring the cause of the patient; the invention is convenient to use, can assist doctors in inquiring, and improves the inquiring efficiency and accuracy of the inquiring doctors.
Description
Technical Field
The invention relates to the technical field of online medical treatment, in particular to a medical video online diagnosis and treatment method and system.
Background
In the existing medical system, patients need to go to a hospital or a clinic for face-to-face diagnosis and treatment in person, which has certain difficulty for patients in remote areas or patients with inconvenient bodies, and meanwhile, the service pressure of medical institutions and the doctor's cost of the patients are easily increased; most of the existing online medical systems are realized by an image-text inquiry mode; however, the operation of the graphic inquiry is complicated, which is relatively laborious and difficult for the old patients in remote areas; therefore, there is an urgent need for a more flexible and convenient medical video online diagnosis and treatment method and system, so that patients can conduct real-time remote diagnosis and treatment with doctors through a network.
At present, the design of the existing medical video online diagnosis and treatment system still requires a user to have certain operation experience of intelligent equipment, which is not friendly for old patients or low-level culture; there are, of course, some technical improvements, such as chinese patent publication CN114188041B, which discloses a medical system for performing doctor-patient services in a remote dialogue manner, which system, although implementing on-line medical diagnosis, has been found by research and practical application of the above-mentioned method and prior art, which have at least some of the following drawbacks:
(1) The problems of low cultural level and difficult on-line consultation of patients with inconvenient actions are not solved yet, and the use is not convenient enough;
(2) The symptom images of the patient cannot be intelligently captured in the video communication process, and an auxiliary diagnosis basis cannot be provided for doctors according to the intelligently captured images, so that the inquiry efficiency and the accuracy of the inquiring doctors are difficult to further improve.
Disclosure of Invention
In order to overcome the defects in the prior art, the embodiment of the invention provides a medical video online diagnosis and treatment method and system.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a medical video on-line diagnosis and treatment system, the system relies on a server side, the server side is in communication connection with a user side of a patient side and a doctor side of a doctor side, the system comprises:
The outpatient service identification module is used for receiving the medical voice request uploaded by the user side and acquiring the type of a diagnosis-seeking department of a patient according to a pre-configured outpatient service identification model; the medical voice request comprises symptom keywords, wherein the symptom keywords comprise M symptom part keywords and N symptom expression keywords, and M and N are integers larger than zero;
The doctor-patient matching module is used for acquiring on-line diagnosis data of the type of the diagnosis department of the corresponding patient, acquiring the best matching doctor of the type of the diagnosis department according to the on-line diagnosis data, and transmitting a medical voice request to a doctor end of the best matching doctor;
the video inquiry module is used for establishing remote video communication through a user side of a patient side and a doctor side of a doctor side when the best matching doctor receives a medical voice request through the doctor side;
The auxiliary diagnosis module is used for determining the characterization part of the patient according to the symptom part keywords in the medical voice request, collecting a plurality of characterization part images of the patient according to the characterization part in the remote video communication process, inputting the plurality of characterization part images into the pre-configured disease identification model, obtaining the cause of the patient, and sending the cause to the corresponding doctor.
Further, the user side comprises a voice acquisition module and a request generation module, wherein the voice acquisition module is used for acquiring voice data of a patient when the patient triggers a sensitive word; the request generation module is used for analyzing the content of the voice data to generate a medical voice request containing symptom keywords.
Further, the parsing the content of the voice data includes:
converting the voice data of the patient into text data, and word segmentation is carried out on the text data, so that Chinese words, repeated words, stop words, phonetic words and personification are removed, Q phrases are obtained, and Q is an integer larger than zero;
The Q phrase groups are put into a symptom position database for traversing, and M phrase groups obtained through traversing are used as symptom position keywords;
The Q phrase groups are put into a symptom expression database for traversing, and N phrase groups obtained through traversing are used as symptom expression keywords;
and generating a medical voice request according to the symptom part keywords and the symptom expression keywords, and uploading the medical voice request to an outpatient service identification module.
Further, obtaining a diagnosis-seeking department type of the patient according to the pre-configured outpatient identification model, including:
extracting M symptom position keywords and N symptom expression keywords, combining the symptom position keywords with the same word order and the symptom expression keywords into short sentences to obtain R short sentences, wherein R is an integer larger than zero;
inputting R phrases into a pre-configured outpatient identification model for identification to obtain the type of a diagnosis-seeking department of a patient;
the generation logic of the preconfigured outpatient identification model is as follows:
acquiring historical clinic identification data, wherein the historical clinic identification data comprises R phrases and corresponding standard labels thereof;
preprocessing R phrases to obtain a plurality of training data subsets, wherein the training data subsets comprise a first training data subset, a second training data subset, … and an S training data subset, and each training data subset comprises vectorized phrase characteristics and corresponding labeling labels after processing;
Constructing a base learner, wherein the base learner comprises a first base learner, a second base learner, … and an S-th base learner; training the first training data subset, the second training data subset, … and the S training data subset by using a first base learner, a second base learner, … and the S base learner respectively to obtain a first classification model, a second classification model, … and an S classification model;
Inputting a plurality of vectorized phrase features into a first classification model, a second classification model, … and an S-th classification model for recognition to obtain first recognition data, second recognition data, … and S-th recognition data;
Constructing a meta learner, taking the first identification data, the second identification data, … and the S identification data as sample data sets, dividing the sample data sets into an outpatient type training data set and an outpatient type training test set, inputting the outpatient type training data set into the meta learner, and training according to an integrated learning strategy to obtain an integrated learning model;
And carrying out model verification on the integrated learning model by using the clinic type training test set, and outputting the integrated learning model with the test accuracy being greater than or equal to a preset threshold value as a preconfigured clinic identification model.
Further, the online diagnosis data comprises online waiting numbers, offline waiting numbers, online consultation speeds, offline consultation speeds, total consultation duration and used consultation duration of each doctor in the corresponding consultation department type;
Obtaining a best matching physician for the type of department from the on-line diagnostic data, comprising:
Acquiring all doctors belonging to the type of a corresponding patient diagnosis department, extracting on-line diagnosis data of all doctors, and calculating the matching coefficient of each doctor according to the on-line diagnosis data to obtain K matching coefficients, wherein K is an integer larger than zero; the calculation formula is as follows:
Wherein: alpha is a matching coefficient, W online is the number of on-line waiting patients, W offline is the number of off-line waiting patients, V 1 is the on-line consultation speed, V 2 is the off-line consultation speed, T 1 is the total consultation duration, T 2 is the used consultation duration, theta 1 and theta 2 are weight factors larger than zero, and theta 1<θ2;
And sorting the physicians according to the numerical values from small to large, and taking the physicians corresponding to the first matching coefficient of the sorting as the best matching physicians.
Further, acquiring a representation site image of the patient according to the representation site, comprising:
step a: acquiring a real-time picture in a remote video communication process;
Step b: identifying the real-time picture by utilizing a preconfigured human body part identification model, and judging whether the real-time picture contains a characterization part or not according to an identification result; if the real-time image is included, the corresponding real-time image is used as a representation part image; if the real-time image is not included, the corresponding real-time image is not used as the representation part image;
Step c: repeating the steps a-b until the acquisition number of the images of the characterization part reaches a preset number threshold or the acquisition time of the images of the characterization part reaches a preset time threshold, ending the cycle, and obtaining a plurality of images of the characterization part.
Further, the generation logic of the preconfigured condition identification model is as follows:
acquiring historical disorder identification data, and dividing the historical disorder identification data into a disorder identification training set and a disorder identification test set; the historical disorder identification data comprise a plurality of characterization part images and corresponding labeling labels thereof;
Constructing a classifier, taking the representation part images in the disease recognition training set as input data of the classifier, taking the labeling labels in the disease recognition training set as output data of the classifier, and training the classifier to obtain an initial disease recognition network;
and performing model verification on the initial disorder recognition network by using the disorder recognition test set, and outputting the initial disorder recognition network with the accuracy greater than or equal to the preset test accuracy as a pre-configured disorder recognition model.
A medical video on-line diagnosis and treatment method, comprising:
Receiving a medical voice request uploaded by a user side, and acquiring the type of a diagnosis department of a patient according to a pre-configured outpatient identification model; the medical voice request comprises symptom keywords, wherein the symptom keywords comprise M symptom part keywords and N symptom expression keywords, and M and N are integers larger than zero;
Acquiring on-line diagnosis data of the type of a diagnosis-seeking department corresponding to a patient, acquiring a best matching doctor of the type of the diagnosis-seeking department according to the on-line diagnosis data, and forwarding a medical voice request to a doctor end of the best matching doctor;
When the best matching doctor receives a medical voice request through the doctor side, establishing remote video communication through the user side of the patient side and the doctor side of the doctor side;
determining a characterization part of a patient according to the symptom part keywords in the medical voice request, acquiring a plurality of characterization part images of the patient according to the characterization part in the remote video communication process, inputting the plurality of characterization part images into a pre-configured disease identification model, acquiring the cause of the patient, and transmitting the cause to a corresponding doctor.
An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the medical video on-line diagnostic method described above when executing the computer program.
A computer readable storage medium having a computer program stored thereon, which when executed by a processor, implements the medical video on-line diagnostic method described above.
Compared with the prior art, the invention has the beneficial effects that:
The application discloses a medical video online diagnosis and treatment method and a system, which are used for receiving a medical voice request uploaded by a user side and acquiring the type of a diagnosis-seeking department of a patient according to a preconfigured outpatient identification model; acquiring a best matching doctor for finding the type of a department according to the online diagnosis data, and forwarding a medical voice request to a doctor end of the best matching doctor; when the best matching doctor receives a medical voice request through the doctor side, establishing remote video communication through the user side of the patient side and the doctor side of the doctor side; determining a characterization part of a patient according to the symptom part keywords in the medical voice request, acquiring a plurality of characterization part images of the patient according to the characterization part in the remote video communication process, inputting the plurality of characterization part images into a pre-configured disease identification model, and acquiring the cause of the patient; through the process, the application solves the problems of low cultural level and difficult on-line consultation of patients with inconvenient actions, and improves the convenience of use; in addition, through intelligent capturing of symptom images of patients in a video communication process and providing auxiliary diagnosis basis for doctors according to the intelligently captured images, the application is beneficial to improving the inquiry efficiency and accuracy of the inquiring doctors.
Drawings
FIG. 1 is a schematic diagram of a medical video on-line diagnosis and treatment system according to the present invention;
FIG. 2 is a flow chart of a medical video online diagnosis and treatment method provided by the invention;
Fig. 3 is a schematic structural diagram of an electronic device according to the present invention;
fig. 4 is a schematic structural diagram of a computer readable storage medium according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1, the disclosure of the present embodiment provides a medical video online diagnosis and treatment system, the system relies on a server, and the server is communicatively connected with a user end on a patient side and a doctor end on a doctor side, the system includes:
The outpatient service identification module 110 is configured to receive a medical voice request uploaded by a user side, and acquire a diagnosis department type of a patient according to a preconfigured outpatient service identification model; the medical voice request comprises symptom keywords, wherein the symptom keywords comprise M symptom part keywords and N symptom expression keywords, and M and N are integers larger than zero;
Specifically, the user side comprises a voice acquisition module and a request generation module, wherein the voice acquisition module is used for acquiring voice data of a patient when the patient triggers a sensitive word; the request generation module is used for analyzing the content of the voice data to generate a medical voice request containing symptom keywords;
it should be noted that: the sensitive words are determined according to the preset of a technician, such as 'opening XX software' or 'opening XX software for online medical treatment', etc.;
It should be noted that: the voice data of the patient starts to be collected when the sensitive word is triggered, and the collection is finished after a preset time length is reached, namely the speaking content of the patient from the time of triggering the sensitive word to the appointed time is used as the voice data; the predetermined time is set in advance by a technician, such as 5 minutes, 10 minutes, 15 minutes, or the like; illustratively, assuming that the time for triggering the sensitive word is 19:00 and assuming that the predetermined time is 5 minutes, the patient speaking content collected from 19:00 to 19:05 is taken as voice data;
Notably, are: the speech data of the patient must include a presentation of the patient's own symptoms, such as: "itching on arm", "how many reddish spots on arm" or "tingling sensation on forearm" etc.;
specifically, the parsing the content of the voice data includes:
converting the voice data of the patient into text data, and word segmentation is carried out on the text data, so that Chinese words, repeated words, stop words, phonetic words and personification are removed, Q phrases are obtained, and Q is an integer larger than zero;
it should be appreciated that: word segmentation is carried out on the text data, and the word segmentation is realized through one means of dictionary-based word segmentation, statistical-based word segmentation, machine learning-based word segmentation, a rule engine or mixed word segmentation;
The Q phrase groups are put into a symptom position database for traversing, and M phrase groups obtained through traversing are used as symptom position keywords;
The Q phrase groups are put into a symptom expression database for traversing, and N phrase groups obtained through traversing are used as symptom expression keywords;
it should be noted that: the symptom position database and the symptom expression database are set in advance by technicians, a plurality of phrases related to human body parts are stored in the symptom position database in advance, and a plurality of phrases related to symptom expression are stored in the symptom expression database in advance;
In connection with the above examples, it is assumed that the text of "itching of the arm", "how much red spot is on the arm", or "tingling sensation on the arm", etc. is changed into "arm/itching", "arm/upper/having/how much/little/red spot", or "forearm/upper/having/tingling sensation", by the word segmentation process; further, it is assumed that the symptom part database stores phrases such as "arm", and "forearm" in advance, so that when the phrases obtained after word segmentation are input into the symptom part database and subjected to traversal matching, symptom part keywords such as "arm", and "forearm" are obtained; similarly, if the symptom expression database stores words such as "itching", "red spot" and "tingling sensation" in advance, when the word groups obtained after word segmentation are input into the symptom expression database for traversal matching, symptom expression keywords such as "itching", "red spot" and "tingling sensation" are obtained;
Generating a medical voice request according to the symptom part keywords and the symptom expression keywords, and uploading the medical voice request to an outpatient service identification module;
in an implementation, obtaining a diagnosis-seeking department type for a patient according to a pre-configured outpatient identification model includes:
extracting M symptom position keywords and N symptom expression keywords, combining the symptom position keywords with the same word order and the symptom expression keywords into short sentences to obtain R short sentences, wherein R is an integer larger than zero;
It should be noted that: each phrase comprises a symptom site keyword and a symptom expression keyword, and is determined according to the word sequence of the corresponding symptom site keyword and symptom expression keyword in the voice data;
for example, assuming that "how little red is on the arm, and a tingling sensation is on the forearm" is voice data of a patient, by word segmentation, M symptom site keywords are respectively "arm", and "forearm", and N symptom site keywords are respectively "itching", "red, and" tingling sensation ", since the symptom site keyword" arm "is in a first word order among all symptom site keywords of the voice data, and the symptom site keyword" itching "is in a first word order among all symptom site keywords of the voice data, the symptom site keywords" arm "and the symptom site keyword" itching "are combined into one short sentence; similarly, the symptom part keywords 'arms' and the symptom expression keywords 'red points' in the second word order are combined into a short sentence, and the like until all the symptom part keywords and the symptom expression keywords are combined;
inputting R phrases into a pre-configured outpatient identification model for identification to obtain the type of a diagnosis-seeking department of a patient;
Specifically, the generation logic of the preconfigured outpatient identification model is as follows:
acquiring historical clinic identification data, wherein the historical clinic identification data comprises R phrases and corresponding standard labels thereof;
preprocessing R phrases to obtain a plurality of training data subsets, wherein the training data subsets comprise a first training data subset, a second training data subset, … and an S training data subset, and each training data subset comprises vectorized phrase characteristics and corresponding labeling labels after processing;
It should be noted that: the preprocessing comprises Word vector conversion, data labeling and dividing processes, wherein the Word vector conversion refers to converting each phrase into a vector form phrase feature (namely a vectorization phrase feature) to obtain a plurality of vectorization phrase features, such as Word2Vec or GloVe; the data labeling and dividing means that labeling of diagnosis department types is carried out on vector form phrase features so as to obtain a plurality of vector form phrase features with label labels, and the plurality of vector form phrase features with label labels are divided into a plurality of training data subsets; the labeling of the diagnosis department type is carried out on the short sentence characteristics of the vector form, and the labeling is realized by manual definition in advance by a technician, for example: the vectorized phrase characteristics obtained after the conversion of the 'arm itching' are marked as 'dermatology';
Constructing a base learner, wherein the base learner comprises a first base learner, a second base learner, … and an S-th base learner; training the first training data subset, the second training data subset, … and the S training data subset by using a first base learner, a second base learner, … and the S base learner respectively to obtain a first classification model, a second classification model, … and an S classification model;
It should be noted that: the base learner can be a homogeneous base learner or a heterogeneous base learner, and is specifically one or more of model algorithms such as a decision tree classification network, a support vector machine classification network or a random forest classification network;
Inputting a plurality of vectorized phrase features into a first classification model, a second classification model, … and an S-th classification model for recognition to obtain first recognition data, second recognition data, … and S-th recognition data;
it should be understood that: the first identification data, the second identification data, … and the S identification data all comprise a plurality of vectorized phrase features and corresponding labeling labels;
Constructing a meta learner, taking the first identification data, the second identification data, … and the S identification data as sample data sets, dividing the sample data sets into an outpatient type training data set and an outpatient type training test set, inputting the outpatient type training data set into the meta learner, and training according to an integrated learning strategy to obtain an integrated learning model;
performing model verification on the integrated learning model by using an outpatient type training test set, and outputting the integrated learning model with the test accuracy being greater than or equal to a preset threshold value as a preconfigured outpatient identification model;
It should be noted that: the element learner is specifically one of a CNN neural network model or an RNN neural network model, and the integrated learning strategy is specifically a weighted average strategy;
it should be appreciated that: by utilizing the integrated learning model to identify the type of the diagnosis department, the mutual interference caused by the fact that a plurality of different symptom position keywords and symptom expression keywords exist in voice data can be avoided as far as possible;
it should be appreciated that: the number of the types of the departments for the diagnosis is determined according to the number of the departments for the clinic in the actual hospital, such as dermatology, otorhinolaryngology, orthopaedics, stomatology and the like.
The doctor-patient matching module 120 is configured to obtain online diagnosis data corresponding to a patient department type, obtain a best matching physician of the department type according to the online diagnosis data, and forward a medical voice request to a physician end of the best matching physician;
Specifically, the online diagnosis data includes an online waiting number, an offline waiting number, an online consultation speed, an offline consultation speed, a total consultation duration and a used consultation duration of each doctor in the corresponding consultation department type;
It should be appreciated that: the on-line waiting number and the off-line waiting number are recorded according to a hospital background management system, and the on-line inquiry speed and the off-line inquiry speed are calculated according to historical inquiry data of each doctor, for example: the number of on-line consultations of one doctor is 10, and the total time of the consultation of the 10 persons is 60 minutes, so that the on-line consultation speed of the doctor is known to be 6 minutes/person (6=60/10) through calculation, and similarly, the off-line consultation speed acquisition logic is also the same, and redundant description is omitted here; the total inquiry time length is determined according to the actual daily arrangement of each doctor, for example, 4 hours, 5 hours and the like, and the used inquiry time length is obtained through actual recording;
In practice, obtaining a best matching physician for a diagnostic department type based on-line diagnostic data includes:
Acquiring all doctors belonging to the type of a corresponding patient diagnosis department, extracting on-line diagnosis data of all doctors, and calculating the matching coefficient of each doctor according to the on-line diagnosis data to obtain K matching coefficients, wherein K is an integer larger than zero; the calculation formula is as follows:
Wherein: alpha is a matching coefficient, W online is the number of on-line waiting patients, W offline is the number of off-line waiting patients, V 1 is the on-line consultation speed, V 2 is the off-line consultation speed, T 1 is the total consultation duration, T 2 is the used consultation duration, theta 1 and theta 2 are weight factors larger than zero, and theta 1<θ2;
And sorting the physicians according to the numerical values from small to large, and taking the physicians corresponding to the first matching coefficient of the sorting as the best matching physicians.
The video inquiry module 130 is configured to establish remote video communication through the user side on the patient side and the doctor side on the doctor side when the best matching doctor receives the medical voice request through the doctor side;
It should be appreciated that: the user end at the patient side and the doctor end at the doctor side can be any one of terminal equipment such as a desktop computer, a notebook computer, an intelligent television or a smart phone, and the user end at the patient side and the doctor end at the doctor side are both provided with a camera device for supporting remote video communication;
it should also be appreciated that: once the best matching physician is obtained, the system will immediately forward the best matching physician to the physician's side corresponding to the best matching physician, and if the physician's side chooses to agree to the request, the camera devices on the user side and physician's side will be immediately turned on, establishing remote communication for both the patient and physician.
The auxiliary diagnosis module 140 is used for determining a characterization part of the patient according to the symptom part keywords in the medical voice request, collecting a plurality of characterization part images of the patient according to the characterization part in the remote video communication process, inputting the plurality of characterization part images into the pre-configured disease identification model, obtaining the cause of the patient, and sending the cause to the corresponding doctor end;
It will be appreciated that: the characterization part of the patient is determined by the symptom part keywords, and further explanation is that the assumption is carried out, if the symptom part keywords in the medical voice request comprise arms, arms and arms, the human body parts corresponding to the symptom part keywords are taken as the characterization part;
in an implementation, acquiring a representation of a patient from a representation includes:
step a: acquiring a real-time picture in a remote video communication process;
Step b: identifying the real-time picture by utilizing a preconfigured human body part identification model, and judging whether the real-time picture contains a characterization part or not according to an identification result; if the real-time image is included, the corresponding real-time image is used as a representation part image; if the real-time image is not included, the corresponding real-time image is not used as the representation part image;
It should be noted that: any human body part recognition model capable of realizing human body part recognition can be used as an application object of the invention; in order to facilitate understanding and ensure disclosure sufficiency, the present embodiment now proposes a logic for generating a human body part recognition model, specifically: acquiring a human body part data set, dividing the human body part data set into a part recognition training set and a part recognition testing set, wherein the human body part data set comprises a plurality of human body part images and corresponding labeling labels; constructing a classifier, taking a human body part image in part recognition training as input data of the classifier, taking a label in part recognition training as output data of the classifier, training the classifier to obtain an initial part recognition network, testing the classifier by using a part recognition test set, and outputting the initial part recognition network with the accuracy greater than or equal to a preset test as a human body part recognition model; the classifier is a specific one of model algorithms such as a decision tree classification network, a support vector machine classification network or a random forest classification network; the labeling label is a human body part label, and a technician performs labeling determination on the corresponding human body part image in advance;
Also to be described is: in the process of judging whether the real-time picture contains the characterization part according to the identification result, if the human body part output by the identification result is consistent with the human body part mentioned in the symptom part keyword, the corresponding human body part is used as the characterization part of the patient; in contrast, if the human body part output by the recognition result is inconsistent with the human body part mentioned in the symptom part keyword, the corresponding human body part is not used as the characterization part of the patient;
Step c: repeating the steps a-b until the acquisition number of the images of the characterization part reaches a preset number threshold or the acquisition time of the images of the characterization part reaches a preset time threshold, ending the cycle, and obtaining a plurality of images of the characterization part;
In practice, the generation logic of the preconfigured condition identification model is as follows:
acquiring historical disorder identification data, and dividing the historical disorder identification data into a disorder identification training set and a disorder identification test set; the historical disorder identification data comprise a plurality of characterization part images and corresponding labeling labels thereof;
it should be appreciated that: the labeling includes various causes such as eczema, cold or pneumonia, etc.; corresponding labeling labels of each characterization part image in the historical disorder identification data are determined through manual setting in advance;
Constructing a classifier, taking the representation part images in the disease recognition training set as input data of the classifier, taking the labeling labels in the disease recognition training set as output data of the classifier, and training the classifier to obtain an initial disease recognition network;
performing model verification on the initial disorder recognition network by using a disorder recognition test set, and outputting the initial disorder recognition network with the accuracy greater than or equal to a preset test as a pre-configured disorder recognition model;
It should be noted that: the classifier of the pre-configured disease recognition model is the same as the specific type of the classifier, and the detailed description is not repeated here; also to be described is: the above mentioned modules are connected by wire and/or wirelessly.
Example 2
Referring to fig. 2, based on the same inventive concept, referring to the above embodiment 1, the disclosure of this embodiment provides a medical video online diagnosis and treatment method, and the parts of this embodiment not described in detail may refer to the disclosure of the above embodiment 1, where the method includes:
S201: receiving a medical voice request uploaded by a user side, and acquiring the type of a diagnosis department of a patient according to a pre-configured outpatient identification model; the medical voice request comprises symptom keywords, wherein the symptom keywords comprise M symptom part keywords and N symptom expression keywords, and M and N are integers larger than zero;
s202: acquiring on-line diagnosis data of the type of a diagnosis-seeking department corresponding to a patient, acquiring a best matching doctor of the type of the diagnosis-seeking department according to the on-line diagnosis data, and forwarding a medical voice request to a doctor end of the best matching doctor;
s203: when the best matching doctor receives a medical voice request through the doctor side, establishing remote video communication through the user side of the patient side and the doctor side of the doctor side;
S204: determining a characterization part of a patient according to the symptom part keywords in the medical voice request, acquiring a plurality of characterization part images of the patient according to the characterization part in the remote video communication process, inputting the plurality of characterization part images into a pre-configured disease identification model, acquiring the cause of the patient, and transmitting the cause to a corresponding doctor.
Example 3
Referring to fig. 3, the disclosure provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor implements any one of the above methods when executing the computer program.
Since the electronic device described in this embodiment is an electronic device used to implement a medical video online diagnosis and treatment method in this embodiment of the present application, based on the medical video online diagnosis and treatment method described in this embodiment of the present application, those skilled in the art can understand the specific implementation manner of the electronic device and various modifications thereof, so how the electronic device implements the method in this embodiment of the present application will not be described in detail herein. As long as the person skilled in the art implements the electronic device adopted by the medical video online diagnosis and treatment method in the embodiment of the application, the electronic device belongs to the scope of protection required by the application.
Example 4
Referring to fig. 4, the disclosure of the present embodiment provides a computer readable storage medium, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements any one of the above methods when executing the computer program.
The above formulas are all formulas with dimensionality removed and numerical value calculated, the formulas are formulas with the latest real situation obtained by software simulation by collecting a large amount of data, and preset parameters, weights and threshold selection in the formulas are set by those skilled in the art according to the actual situation.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with embodiments of the present invention are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center over a wired network or a wireless network. The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided in the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely one, and there may be additional divisions in actual implementation, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (5)
1. A medical video on-line diagnosis and treatment system, the system relies on a service end, the service end is in communication connection with a user end on a patient side and a doctor end on a doctor side, the system is characterized in that the system comprises:
The outpatient service identification module is used for receiving the medical voice request uploaded by the user side and acquiring the type of a diagnosis-seeking department of a patient according to a pre-configured outpatient service identification model; the medical voice request comprises symptom keywords, wherein the symptom keywords comprise M symptom part keywords and N symptom expression keywords, and M and N are integers larger than zero;
Obtaining the diagnosis-seeking department type of the patient according to the pre-configured clinic identification model, comprising:
extracting M symptom position keywords and N symptom expression keywords, combining the symptom position keywords with the same word order and the symptom expression keywords into short sentences to obtain R short sentences, wherein R is an integer larger than zero;
inputting R phrases into a pre-configured outpatient identification model for identification to obtain the type of a diagnosis-seeking department of a patient;
the generation logic of the preconfigured outpatient identification model is as follows:
acquiring historical clinic identification data, wherein the historical clinic identification data comprises R phrases and corresponding standard labels thereof;
preprocessing R phrases to obtain a plurality of training data subsets, wherein the training data subsets comprise a first training data subset, a second training data subset, … and an S training data subset, and each training data subset comprises vectorized phrase characteristics and corresponding labeling labels after processing;
Constructing a base learner, wherein the base learner comprises a first base learner, a second base learner, … and an S-th base learner; training the first training data subset, the second training data subset, … and the S training data subset by using a first base learner, a second base learner, … and the S base learner respectively to obtain a first classification model, a second classification model, … and an S classification model;
Inputting a plurality of vectorized phrase features into a first classification model, a second classification model, … and an S-th classification model for recognition to obtain first recognition data, second recognition data, … and S-th recognition data;
Constructing a meta learner, taking the first identification data, the second identification data, … and the S identification data as sample data sets, dividing the sample data sets into an outpatient type training data set and an outpatient type training test set, inputting the outpatient type training data set into the meta learner, and training according to an integrated learning strategy to obtain an integrated learning model;
performing model verification on the integrated learning model by using an outpatient type training test set, and outputting the integrated learning model with the test accuracy being greater than or equal to a preset threshold value as a preconfigured outpatient identification model;
The doctor-patient matching module is used for acquiring on-line diagnosis data of the type of the diagnosis department of the corresponding patient, acquiring the best matching doctor of the type of the diagnosis department according to the on-line diagnosis data, and transmitting a medical voice request to a doctor end of the best matching doctor;
the online diagnosis data comprise online waiting numbers, offline waiting numbers, online inquiry speed, offline inquiry speed, total inquiry duration and used inquiry duration of each doctor in the corresponding diagnosis department type;
Obtaining a best matching physician for the type of department from the on-line diagnostic data, comprising:
Acquiring all doctors belonging to the type of a corresponding patient diagnosis department, extracting on-line diagnosis data of all doctors, and calculating the matching coefficient of each doctor according to the on-line diagnosis data to obtain K matching coefficients, wherein K is an integer larger than zero; the calculation formula is as follows:
；
wherein: In order to match the coefficients of the coefficients, For the number of on-line waiting persons,For the number of off-line waiting persons,In order to be an on-line inquiry speed,For the speed of the off-line consultation,For the total duration of the inquiry,For the duration of the used inquiry,AndIs a weight factor greater than zero,；
Sorting according to the values from small to large, and taking the doctor corresponding to the first matching coefficient of the sorting as the best matching doctor;
the video inquiry module is used for establishing remote video communication through a user side of a patient side and a doctor side of a doctor side when the best matching doctor receives a medical voice request through the doctor side;
The auxiliary diagnosis module is used for determining the characterization part of the patient according to the symptom part keywords in the medical voice request, collecting a plurality of characterization part images of the patient according to the characterization part in the remote video communication process, inputting the plurality of characterization part images into the pre-configured disease identification model, obtaining the cause of the patient, and sending the cause to the corresponding doctor end;
acquiring a representation part image of a patient according to the representation part, wherein the method comprises the following steps:
step a: acquiring a real-time picture in a remote video communication process;
Step b: identifying the real-time picture by utilizing a preconfigured human body part identification model, and judging whether the real-time picture contains a characterization part or not according to an identification result; if the real-time image is included, the corresponding real-time image is used as a representation part image; if the real-time image is not included, the corresponding real-time image is not used as the representation part image;
Step c: repeating the steps a-b until the acquisition number of the images of the characterization part reaches a preset number threshold or the acquisition time of the images of the characterization part reaches a preset time threshold, ending the cycle, and obtaining a plurality of images of the characterization part;
the generation logic of the preconfigured disorder identification model is as follows:
acquiring historical disorder identification data, and dividing the historical disorder identification data into a disorder identification training set and a disorder identification test set; the historical disorder identification data comprise a plurality of characterization part images and corresponding labeling labels thereof;
Constructing a classifier, taking the representation part images in the disease recognition training set as input data of the classifier, taking the labeling labels in the disease recognition training set as output data of the classifier, and training the classifier to obtain an initial disease recognition network;
and performing model verification on the initial disorder recognition network by using the disorder recognition test set, and outputting the initial disorder recognition network with the accuracy greater than or equal to the preset test accuracy as a pre-configured disorder recognition model.
2. The medical video online diagnosis and treatment system according to claim 1, wherein the user side comprises a voice acquisition module and a request generation module, and the voice acquisition module is used for acquiring voice data of a patient when the patient triggers a sensitive word; the request generation module is used for analyzing the content of the voice data to generate a medical voice request containing symptom keywords.
3. The medical video on-line diagnostic system according to claim 2, wherein the parsing the content of the voice data comprises:
converting the voice data of the patient into text data, and word segmentation is carried out on the text data, so that Chinese words, repeated words, stop words, phonetic words and personification are removed, Q phrases are obtained, and Q is an integer larger than zero;
The Q phrase groups are put into a symptom position database for traversing, and M phrase groups obtained through traversing are used as symptom position keywords;
The Q phrase groups are put into a symptom expression database for traversing, and N phrase groups obtained through traversing are used as symptom expression keywords;
and generating a medical voice request according to the symptom part keywords and the symptom expression keywords, and uploading the medical voice request to an outpatient service identification module.
4. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the computer program, implements a medical video on-line diagnostic method comprising:
Receiving a medical voice request uploaded by a user side, and acquiring the type of a diagnosis department of a patient according to a pre-configured outpatient identification model; the medical voice request comprises symptom keywords, wherein the symptom keywords comprise M symptom part keywords and N symptom expression keywords, and M and N are integers larger than zero;
Obtaining the diagnosis-seeking department type of the patient according to the pre-configured clinic identification model, comprising:
extracting M symptom position keywords and N symptom expression keywords, combining the symptom position keywords with the same word order and the symptom expression keywords into short sentences to obtain R short sentences, wherein R is an integer larger than zero;
inputting R phrases into a pre-configured outpatient identification model for identification to obtain the type of a diagnosis-seeking department of a patient;
the generation logic of the preconfigured outpatient identification model is as follows:
acquiring historical clinic identification data, wherein the historical clinic identification data comprises R phrases and corresponding standard labels thereof;
preprocessing R phrases to obtain a plurality of training data subsets, wherein the training data subsets comprise a first training data subset, a second training data subset, … and an S training data subset, and each training data subset comprises vectorized phrase characteristics and corresponding labeling labels after processing;
Constructing a base learner, wherein the base learner comprises a first base learner, a second base learner, … and an S-th base learner; training the first training data subset, the second training data subset, … and the S training data subset by using a first base learner, a second base learner, … and the S base learner respectively to obtain a first classification model, a second classification model, … and an S classification model;
Inputting a plurality of vectorized phrase features into a first classification model, a second classification model, … and an S-th classification model for recognition to obtain first recognition data, second recognition data, … and S-th recognition data;
Constructing a meta learner, taking the first identification data, the second identification data, … and the S identification data as sample data sets, dividing the sample data sets into an outpatient type training data set and an outpatient type training test set, inputting the outpatient type training data set into the meta learner, and training according to an integrated learning strategy to obtain an integrated learning model;
performing model verification on the integrated learning model by using an outpatient type training test set, and outputting the integrated learning model with the test accuracy being greater than or equal to a preset threshold value as a preconfigured outpatient identification model;
Acquiring on-line diagnosis data of the type of a diagnosis-seeking department corresponding to a patient, acquiring a best matching doctor of the type of the diagnosis-seeking department according to the on-line diagnosis data, and forwarding a medical voice request to a doctor end of the best matching doctor;
the online diagnosis data comprise online waiting numbers, offline waiting numbers, online inquiry speed, offline inquiry speed, total inquiry duration and used inquiry duration of each doctor in the corresponding diagnosis department type;
Obtaining a best matching physician for the type of department from the on-line diagnostic data, comprising:
Acquiring all doctors belonging to the type of a corresponding patient diagnosis department, extracting on-line diagnosis data of all doctors, and calculating the matching coefficient of each doctor according to the on-line diagnosis data to obtain K matching coefficients, wherein K is an integer larger than zero; the calculation formula is as follows:
；
wherein: In order to match the coefficients of the coefficients, For the number of on-line waiting persons,For the number of off-line waiting persons,In order to be an on-line inquiry speed,For the speed of the off-line consultation,For the total duration of the inquiry,For the duration of the used inquiry,AndIs a weight factor greater than zero,；
Sorting according to the values from small to large, and taking the doctor corresponding to the first matching coefficient of the sorting as the best matching doctor;
When the best matching doctor receives a medical voice request through the doctor side, establishing remote video communication through the user side of the patient side and the doctor side of the doctor side;
Determining a characterization part of a patient according to symptom part keywords in a medical voice request, acquiring a plurality of characterization part images of the patient according to the characterization part in a remote video communication process, inputting the plurality of characterization part images into a pre-configured disease identification model, acquiring the cause of the patient, and transmitting the cause to a corresponding doctor terminal;
acquiring a representation part image of a patient according to the representation part, wherein the method comprises the following steps:
step a: acquiring a real-time picture in a remote video communication process;
Step b: identifying the real-time picture by utilizing a preconfigured human body part identification model, and judging whether the real-time picture contains a characterization part or not according to an identification result; if the real-time image is included, the corresponding real-time image is used as a representation part image; if the real-time image is not included, the corresponding real-time image is not used as the representation part image;
Step c: repeating the steps a-b until the acquisition number of the images of the characterization part reaches a preset number threshold or the acquisition time of the images of the characterization part reaches a preset time threshold, ending the cycle, and obtaining a plurality of images of the characterization part;
the generation logic of the preconfigured disorder identification model is as follows:
acquiring historical disorder identification data, and dividing the historical disorder identification data into a disorder identification training set and a disorder identification test set; the historical disorder identification data comprise a plurality of characterization part images and corresponding labeling labels thereof;
Constructing a classifier, taking the representation part images in the disease recognition training set as input data of the classifier, taking the labeling labels in the disease recognition training set as output data of the classifier, and training the classifier to obtain an initial disease recognition network;
and performing model verification on the initial disorder recognition network by using the disorder recognition test set, and outputting the initial disorder recognition network with the accuracy greater than or equal to the preset test accuracy as a pre-configured disorder recognition model.
5. A computer readable storage medium having a computer program stored thereon, the computer program when executed by a processor implementing a medical video on-line diagnostic method, the method comprising:
Receiving a medical voice request uploaded by a user side, and acquiring the type of a diagnosis department of a patient according to a pre-configured outpatient identification model; the medical voice request comprises symptom keywords, wherein the symptom keywords comprise M symptom part keywords and N symptom expression keywords, and M and N are integers larger than zero;
Obtaining the diagnosis-seeking department type of the patient according to the pre-configured clinic identification model, comprising:
extracting M symptom position keywords and N symptom expression keywords, combining the symptom position keywords with the same word order and the symptom expression keywords into short sentences to obtain R short sentences, wherein R is an integer larger than zero;
inputting R phrases into a pre-configured outpatient identification model for identification to obtain the type of a diagnosis-seeking department of a patient;
the generation logic of the preconfigured outpatient identification model is as follows:
acquiring historical clinic identification data, wherein the historical clinic identification data comprises R phrases and corresponding standard labels thereof;
preprocessing R phrases to obtain a plurality of training data subsets, wherein the training data subsets comprise a first training data subset, a second training data subset, … and an S training data subset, and each training data subset comprises vectorized phrase characteristics and corresponding labeling labels after processing;
Constructing a base learner, wherein the base learner comprises a first base learner, a second base learner, … and an S-th base learner; training the first training data subset, the second training data subset, … and the S training data subset by using a first base learner, a second base learner, … and the S base learner respectively to obtain a first classification model, a second classification model, … and an S classification model;
Inputting a plurality of vectorized phrase features into a first classification model, a second classification model, … and an S-th classification model for recognition to obtain first recognition data, second recognition data, … and S-th recognition data;
Constructing a meta learner, taking the first identification data, the second identification data, … and the S identification data as sample data sets, dividing the sample data sets into an outpatient type training data set and an outpatient type training test set, inputting the outpatient type training data set into the meta learner, and training according to an integrated learning strategy to obtain an integrated learning model;
performing model verification on the integrated learning model by using an outpatient type training test set, and outputting the integrated learning model with the test accuracy being greater than or equal to a preset threshold value as a preconfigured outpatient identification model;
Acquiring on-line diagnosis data of the type of a diagnosis-seeking department corresponding to a patient, acquiring a best matching doctor of the type of the diagnosis-seeking department according to the on-line diagnosis data, and forwarding a medical voice request to a doctor end of the best matching doctor;
the online diagnosis data comprise online waiting numbers, offline waiting numbers, online inquiry speed, offline inquiry speed, total inquiry duration and used inquiry duration of each doctor in the corresponding diagnosis department type;
Obtaining a best matching physician for the type of department from the on-line diagnostic data, comprising:
Acquiring all doctors belonging to the type of a corresponding patient diagnosis department, extracting on-line diagnosis data of all doctors, and calculating the matching coefficient of each doctor according to the on-line diagnosis data to obtain K matching coefficients, wherein K is an integer larger than zero; the calculation formula is as follows:
；
wherein: In order to match the coefficients of the coefficients, For the number of on-line waiting persons,For the number of off-line waiting persons,In order to be an on-line inquiry speed,For the speed of the off-line consultation,For the total duration of the inquiry,For the duration of the used inquiry,AndIs a weight factor greater than zero,；
Sorting according to the values from small to large, and taking the doctor corresponding to the first matching coefficient of the sorting as the best matching doctor;
When the best matching doctor receives a medical voice request through the doctor side, establishing remote video communication through the user side of the patient side and the doctor side of the doctor side;
Determining a characterization part of a patient according to symptom part keywords in a medical voice request, acquiring a plurality of characterization part images of the patient according to the characterization part in a remote video communication process, inputting the plurality of characterization part images into a pre-configured disease identification model, acquiring the cause of the patient, and transmitting the cause to a corresponding doctor terminal;
acquiring a representation part image of a patient according to the representation part, wherein the method comprises the following steps:
step a: acquiring a real-time picture in a remote video communication process;
Step b: identifying the real-time picture by utilizing a preconfigured human body part identification model, and judging whether the real-time picture contains a characterization part or not according to an identification result; if the real-time image is included, the corresponding real-time image is used as a representation part image; if the real-time image is not included, the corresponding real-time image is not used as the representation part image;
Step c: repeating the steps a-b until the acquisition number of the images of the characterization part reaches a preset number threshold or the acquisition time of the images of the characterization part reaches a preset time threshold, ending the cycle, and obtaining a plurality of images of the characterization part;
the generation logic of the preconfigured disorder identification model is as follows:
acquiring historical disorder identification data, and dividing the historical disorder identification data into a disorder identification training set and a disorder identification test set; the historical disorder identification data comprise a plurality of characterization part images and corresponding labeling labels thereof;
Constructing a classifier, taking the representation part images in the disease recognition training set as input data of the classifier, taking the labeling labels in the disease recognition training set as output data of the classifier, and training the classifier to obtain an initial disease recognition network;
and performing model verification on the initial disorder recognition network by using the disorder recognition test set, and outputting the initial disorder recognition network with the accuracy greater than or equal to the preset test accuracy as a pre-configured disorder recognition model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410244932.4A CN118173287B (en) | 2024-03-05 | 2024-03-05 | Medical video online diagnosis and treatment method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410244932.4A CN118173287B (en) | 2024-03-05 | 2024-03-05 | Medical video online diagnosis and treatment method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118173287A CN118173287A (en) | 2024-06-11 |
| CN118173287B true CN118173287B (en) | 2024-08-06 |
Family
ID=91351152
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410244932.4A Active CN118173287B (en) | 2024-03-05 | 2024-03-05 | Medical video online diagnosis and treatment method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118173287B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109065185A (en) * | 2018-07-24 | 2018-12-21 | 合肥同佑电子科技有限公司 | One kind is towards the quick accurate Medical service method and system of patient |
| CN112712906A (en) * | 2020-12-29 | 2021-04-27 | 安徽科大讯飞医疗信息技术有限公司 | Video image processing method and device, electronic equipment and storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107578824A (en) * | 2017-09-08 | 2018-01-12 | 深圳市前海安测信息技术有限公司 | Interactive remote traditional Chinese medical science assisting in diagnosis and treatment system and method |
| CN113077913A (en) * | 2021-04-20 | 2021-07-06 | 北京京东拓先科技有限公司 | Online inquiry and order dispatching method, device and system |
| CN113436723A (en) * | 2021-06-23 | 2021-09-24 | 康键信息技术（深圳）有限公司 | Video inquiry method, device, equipment and storage medium |
| CN114188041B (en) * | 2021-12-02 | 2022-11-15 | 深圳市华美泰科技发展有限公司 | Medical system for completing doctor-patient service in remote dialogue mode |
| CN115482942A (en) * | 2022-10-18 | 2022-12-16 | 康键信息技术（深圳）有限公司 | Triage method, device, equipment and storage medium for online audio and video inquiry |
| CN116884648A (en) * | 2023-05-23 | 2023-10-13 | 深圳汇医必达医疗科技有限公司 | Voice interaction optimization method, device, equipment and medium based on traditional Chinese medicine inquiry |
-
2024
- 2024-03-05 CN CN202410244932.4A patent/CN118173287B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109065185A (en) * | 2018-07-24 | 2018-12-21 | 合肥同佑电子科技有限公司 | One kind is towards the quick accurate Medical service method and system of patient |
| CN112712906A (en) * | 2020-12-29 | 2021-04-27 | 安徽科大讯飞医疗信息技术有限公司 | Video image processing method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118173287A (en) | 2024-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6641532B2 (en) | Computerized medical diagnostic system utilizing list-based processing | |
| CN108899064A (en) | Electronic health record generation method, device, computer equipment and storage medium | |
| WO2020024484A1 (en) | Method and device for outputting data | |
| CN112037910A (en) | Health information management method, device, equipment and storage medium | |
| CN110706786A (en) | Non-contact intelligent analysis and evaluation system for psychological parameters | |
| CN113707323B (en) | Disease prediction method, device, equipment and medium based on machine learning | |
| CN112349435A (en) | Online inquiry method, device, server, medium and system | |
| CN118098482B (en) | Intelligent medical management system and method based on 5G technology | |
| CN116340778B (en) | Medical large model construction method based on multiple modes and related equipment thereof | |
| CN111008269A (en) | Data processing method and device, storage medium and electronic terminal | |
| CN116110566A (en) | Data processing method, device and equipment | |
| CN116049743A (en) | Cognitive recognition method based on multi-modal data, computer equipment and storage medium | |
| CN112802598A (en) | Real-time auxiliary diagnosis and treatment method and system based on voice diagnosis and treatment data | |
| CN118173287B (en) | Medical video online diagnosis and treatment method and system | |
| CN117290596A (en) | Recommendation label generation method, device, equipment and medium for multi-mode data model | |
| CN113345557A (en) | Data processing method and system | |
| CN118173292B (en) | AI self-training-based remote diagnosis and treatment system and method | |
| CN117649933B (en) | Online consultation assistance method and device, electronic equipment and storage medium | |
| CN117316421A (en) | Intelligent medical service platform | |
| Xin et al. | Medical voice question: answering interactive system based on speech recognition technology | |
| CN116825321A (en) | Medical information processing method, device, electronic equipment and storage medium | |
| CN118737358A (en) | Method and device for improving generation accuracy of large model medical record | |
| CN118430771A (en) | System and method for remote diagnosis and treatment by adopting AR (augmented reality) glasses | |
| CN116269226A (en) | Detection early warning method, detection early warning device, computer equipment and storage medium | |
| AU768052B2 (en) | Computerized medical diagnostic and treatment advice system including list based processing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |