CN113707304B - Triage data processing method, triage data processing device, triage data processing equipment and storage medium - Google Patents
Triage data processing method, triage data processing device, triage data processing equipment and storage medium Download PDFInfo
- Publication number
- CN113707304B CN113707304B CN202111005310.9A CN202111005310A CN113707304B CN 113707304 B CN113707304 B CN 113707304B CN 202111005310 A CN202111005310 A CN 202111005310A CN 113707304 B CN113707304 B CN 113707304B
- Authority
- CN
- China
- Prior art keywords
- result
- doctor
- patient
- diagnosis
- image
- 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
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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
Abstract
The invention relates to the technical field of artificial intelligence, and discloses a triage data processing method, a triage data processing device, triage data processing equipment and a storage medium, wherein the triage data processing method comprises the following steps: receiving a patient treatment request, and acquiring treatment information containing patient information, symptom description and inspection data; identifying the diagnosis type of the symptom description and the inspection data, and determining the diagnosis type of the patient; performing department recommendation based on patient information to obtain a department recommendation result; performing disorder map construction and multidimensional conversion on patient information, symptom description, diagnosis type, department recommendation result and inspection data to obtain a multidimensional diagnosis waiting map; acquiring a multidimensional image graph associated with doctor identifications in the recommended results of each department; and matching the multi-dimensional to-be-diagnosed image with each multi-dimensional image to obtain a triage result, and recommending the triage result to the patient. Therefore, the invention realizes the departments and doctors for determining the required triage of the patient. The intelligent medical system is suitable for the field of artificial intelligence and can further promote the construction of intelligent medical treatment.
Description
Technical Field
The invention relates to the technical field of intelligent decision making of artificial intelligence, in particular to a triage data processing method, a triage data processing device, triage data processing equipment and a storage medium.
Background
Along with the progress and development of medicine, hospitals are more specialized in setting departments, and the problem brought by the hospitals is that users select departments to bring certain difficulty, so that the number of diagnosis guiding links, including diagnosis guiding staff and autonomous diagnosis guiding services, are increased for each big hospital to solve the problem, and the medical diagnosis guiding links mainly help patients to recommend diagnosis departments.
At present, when a patient goes to a hospital for diagnosis, the patient needs to go to a diagnosis-dividing table for manual diagnosis, a great deal of queuing time is required for the patient in the process, and the depth and breadth of the expertise of the diagnosis-guiding personnel of the diagnosis-dividing table are required to be higher, because the patient often carries the examination contents (or examination reports) of other hospitals for diagnosis, when the patient is in the prior art for diagnosis, the diagnosis-guiding personnel usually need to read the examination contents (or examination reports) first and then conduct diagnosis, at this time, if the diagnosis-guiding personnel does not divide the patient for diagnosis, the diagnosis needs to be conducted again, the time of the patient is greatly wasted, the patient experience is seriously influenced, and when the diagnosis is in the diagnosis-dividing error, reasonable diagnosis-guiding departments or doctors are often difficult to give, and the diagnosis accuracy of the diagnosis is low, so that the patient experience is further reduced.
Disclosure of Invention
The invention provides a triage data processing method, a triage data processing device, computer equipment and a storage medium, which realize that departments and doctors of triage required by patients are automatically, quickly and accurately determined, improve the accuracy of triage and the experience of the patients.
A triage data processing method, comprising:
receiving a patient's diagnosis request, and acquiring diagnosis information in the diagnosis request; the visit information includes patient information, symptom descriptions, and test data;
identifying the diagnosis type of the symptom description and the inspection data, and determining the diagnosis type of the patient;
performing department recommendation on the diagnosis type based on the patient information to obtain a department recommendation result;
performing disorder map construction and multidimensional conversion on the patient information, the symptom description, the visit type, the department recommendation result and the inspection data to obtain a multidimensional consultation map;
acquiring multidimensional image graphs associated with doctor identifications in the department recommendation results;
and matching the multi-dimensional to-be-diagnosed image with each acquired multi-dimensional image to obtain a triage result, and recommending the triage result to a patient.
A triage data processing apparatus comprising:
the receiving module is used for receiving the patient's diagnosis request and acquiring the diagnosis information in the diagnosis request; the visit information includes patient information, symptom descriptions, and test data;
the identification module is used for identifying the diagnosis type of the symptom description and the inspection data and determining the diagnosis type of the patient;
the recommending module is used for recommending departments to the visit type based on the patient information to obtain a recommended result of the departments;
the construction module is used for constructing a disease map and performing multidimensional conversion on the patient information, the symptom description, the diagnosis type, the department recommendation result and the inspection data to obtain a multidimensional diagnosis waiting map;
the acquisition module is used for acquiring a multidimensional image graph associated with the doctor identification in each department recommendation result;
the matching module is used for matching the multi-dimensional to-be-diagnosed image with each acquired multi-dimensional image to obtain a triage result and recommending the triage result to a patient.
A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the triage data processing method described above when the computer program is executed.
A computer readable storage medium storing a computer program which when executed by a processor performs the steps of the triage data processing method described above.
The invention provides a triage data processing method, a triage data processing device, computer equipment and a storage medium, wherein the triage data processing method is used for acquiring the triage information comprising patient information, symptom description and inspection data by receiving the triage request of a patient; identifying the diagnosis type of the symptom description and the inspection data, and determining the diagnosis type of the patient; performing department recommendation on the diagnosis type based on the patient information to obtain a department recommendation result; performing disorder map construction and multidimensional conversion on the patient information, the symptom description, the visit type, the department recommendation result and the inspection data to obtain a multidimensional consultation map; acquiring multidimensional image graphs associated with doctor identifications in the department recommendation results; the multi-dimensional to-be-diagnosed image is matched with each acquired multi-dimensional image to obtain a diagnosis separating result, and the diagnosis separating result is recommended to the patient, so that the methods of diagnosis type identification, department recommendation and multi-dimensional image matching are realized, departments and doctors needing to be separately diagnosed for the patient are automatically, rapidly and accurately determined, diagnosis accuracy is improved, and patient experience is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic view of an application environment of a triage data processing method according to an embodiment of the present invention;
FIG. 2 is a flow chart of a triage data processing method according to an embodiment of the invention;
FIG. 3 is a flowchart of step S20 of a triage data processing method according to an embodiment of the present invention;
FIG. 4 is a flowchart of step S40 of the triage data processing method according to an embodiment of the present invention;
FIG. 5 is a flowchart of step S50 of a triage data processing method according to an embodiment of the present invention;
FIG. 6 is a flowchart of step S60 of the triage data processing method according to an embodiment of the present invention;
FIG. 7 is a schematic block diagram of a triage data processing apparatus in accordance with an embodiment of the present invention;
FIG. 8 is a schematic diagram of a computer device in accordance with an embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. 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.
The diagnosis data processing method provided by the invention can be applied to an application environment as shown in fig. 1, wherein a client (computer equipment or terminal) communicates with a server through a network. Among them, clients (computer devices or terminals) include, but are not limited to, personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (ContentDelivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
In one embodiment, as shown in fig. 2, a method for processing triage data is provided, and the technical scheme mainly includes the following steps S10-S60:
s10, receiving a patient diagnosis request and acquiring diagnosis information in the diagnosis request; the visit information includes patient information, symptom descriptions, and test data.
It is understood that the patient identification is a unique identification code registered and logged by the patient on an application platform, the patient needs to log on the application platform according to the patient identification before sending the treatment request, the treatment request is a request sent by the patient on the application platform, the patient symptom information is information related to symptoms and test reports of the patient input by the patient, the patient can input the symptom description and the test data on an application interface provided by the application platform, or select related symptoms from all symptom sets provided on the application interface as the symptom description of the patient, and take a photograph of a tested paper file report as the test data of the patient, so that the treatment request is triggered after the symptom description and the test data are input.
Wherein the patient information is information related to the patient, such as: positioning information of a patient, expected time of visit, duration information and the like, wherein the positioning information of the patient is the current longitude and latitude position or the selected longitude and latitude position of the patient, the expected time of visit is the time range in which the patient wants to visit, the duration information is the time of finding a disease from the patient, the symptom is described as related to the symptom of the patient, the test data is electronic data of a test report after the patient completes related test, namely, the test report of a paper file after the patient completes related test is imaged as photo imaging data.
S20, carrying out diagnosis type identification on the symptom description and the test data, and determining the diagnosis type of the patient.
Understandably, the diagnosis type identification is a process of identifying a medical type to which a symptom belongs according to the needle description and the test data, wherein the diagnosis type identification may be that the medical condition category related to the symptom description is identified according to the extracted condition feature by extracting the condition feature from the symptom description, the medical condition category related to the test data is identified by performing image-text identification on the test data, the medical condition category related to the test data is identified, the medical conditions related to the test data are combined to classify, and the diagnosis type concentrated after classification is determined, wherein the diagnosis type is the medical condition category, for example: skin allergies, fractures, body temperature abnormalities, and the like.
In one embodiment, as shown in fig. 3, in the step S20, that is, the identifying the diagnosis type of the symptom description and the test data, determining the diagnosis type of the patient includes:
s201, extracting symptom characteristics of the symptom description through a symptom extraction model, and identifying according to the extracted symptom characteristics to obtain a first identification result.
The condition extraction model is a trained machine learning model for extracting keywords related to a condition in an input text, the condition extraction model is used for carrying out Word vector conversion on the symptom description, the Word vector conversion is a conversion process of mapping words or words in each symptom description into N-dimensional Word vectors by using the Word2Vec algorithm, the Word2Vec algorithm is used for predicting vectors corresponding to the words or words through a shallow Word2Vec model, extracting keywords or words from the symptom description after the Word vector conversion, extracting keywords or words related to condition features, carrying out text matching on the extracted keywords or words, and matching the related medical condition category as the first recognition result.
S202, performing image-text recognition on the inspection data through an unstructured disorder recognition model to obtain a second recognition result.
The method comprises the steps of obtaining a first recognition result, namely obtaining a non-structural disease recognition model, wherein the non-structural disease recognition model is a trained model for recognizing medical disease types related to disease in non-structural data, the image-text recognition process is a process of using an OCR technology to extract a test image and a test text from the test data, recognizing a human body part of the test image, recognizing a disease part, and then carrying out disease association recognition according to the test text and the disease part to obtain a second recognition result, wherein the extraction process is a process of using the OCR technology to recognize an area containing an image in the test data, copying the area from the test data to obtain a test image, simultaneously recognizing all characters in the test data, and splicing all the recognized characters to obtain the test text.
In an embodiment, in step S202, the performing image-text recognition on the inspection data through the unstructured disorder recognition model to obtain a second recognition result includes:
And extracting a test image and a test text from the test data by using an OCR technology.
The OCR (Optical Character Recogniti on ) technology is understood to refer to the process of an electronic device (e.g., a scanner or digital camera) checking characters printed on paper, determining their shape by detecting dark and light patterns, then cutting out images of non-characters, and translating the shape into computer text using a character recognition method.
And identifying the human body part of the inspection image, and identifying the disease part.
The human body part is understandably identified as a process of extracting human body features in the input image and identifying a part of the human body to which the human body belongs according to the extracted human body features, thereby determining the identified part of the human body to which the human body belongs as a disease part.
And carrying out disorder association recognition on the test text and the disorder part to obtain the second recognition result.
Understandably, the association is identified as a process of identifying text related to the disorder site from the test text, and classifying medical disorder categories according to the identified text, resulting in the second identification result of the medical disorder category concerned, which second identification result embodies the medical disorder category concerned in the test data.
The invention realizes that the test image and the test text are extracted from the test data by applying the OCR technology; identifying the human body part of the inspection image to identify the disease part; and carrying out disorder association recognition on the test text and the disorder part to obtain the second recognition result, so that the non-structured test data information can be extracted by utilizing an OCR technology, and the medical disorder category related in the test data can be automatically recognized through human body part recognition and disorder association recognition, thereby improving the accuracy and reliability for subsequent triage processing.
S203, performing diagnosis classification on the first identification result and the second identification result, and determining the diagnosis type.
Understandably, the medical condition categories in the first identification result and the second identification result are aggregated, and finally the medical condition category corresponding to the most dense aggregation point is obtained and recorded as the visit type.
The invention realizes the condition feature extraction of the symptom description through the condition extraction model, and the first recognition result is obtained by recognizing the extracted condition feature; performing image-text recognition on the inspection data through an unstructured disorder recognition model to obtain a second recognition result; the first identification result and the second identification result are subjected to diagnosis classification to determine the diagnosis type, so that the diagnosis type can be automatically classified by using a text matching and image-text identification method, the accurate diagnosis type is provided for subsequent diagnosis, the diagnosis direction is clear, the occurrence of the condition of wrong diagnosis is avoided, and the diagnosis accuracy is improved.
S30, performing department recommendation on the visit type based on the patient information to obtain a department recommendation result.
Understandably, the department recommendation is performed on the diagnosis type through a trained deep learning department recommendation model, the department recommendation process is to extract mapping features between symptoms and departments through the deep learning department recommendation model, identify departments related to the diagnosis type according to the extracted mapping features between the symptoms and the departments, search all doctor identifications associated with the identified departments in a preset range according to positioning information in the patient information, and take the departments related to the identified diagnosis type and searched results as department recommendation results.
S40, constructing a disease map and performing multidimensional conversion on the patient information, the symptom description, the diagnosis type, the department recommendation result and the inspection data to obtain a multidimensional diagnosis waiting map.
Understandably, the process of constructing the symptom map is to firstly extract keywords for quantifying the symptom of the symptom description and the test text extracted from the test data, and identify the quantified result; secondly, identifying the degree grade of the inspection text extracted from the inspection data and corresponding to the diagnosis type, and identifying a grade result; finally, a process of constructing a patient disease map of the patient according to the identified quantified result, the identified grade result, the identified visit type, the identified department recommended result and the identified time length information and the identified positioning information in the patient information, wherein the patient disease map is a picture with a plurality of attributes centered on the patient, the plurality of attributes include attributes related to the disease, such as the quantified result, the identified grade result, the identified visit type, the identified department recommended result, the identified time length information and the identified positioning information in the identified patient information, and the identified time length information in the identified patient disease map are set according to requirements, and the identified time length information and the identified positioning information in the identified patient information are set according to the identified time length information and the identified time length information in the identified patient information, wherein the identified time length information and the identified time length information are set according to requirements, and the identified time: five dimensions, including a place dimension, a time dimension, a department dimension, a visit direction dimension and a light and heavy dimension, respectively, so as to obtain the multi-dimensional consultation chart.
In one embodiment, as shown in fig. 4, in the step 40, the performing the condition map construction and the multidimensional transformation on the patient information, the symptom description, the visit type, the department recommendation result and the test data to obtain a multidimensional diagnosis waiting map includes:
s401, carrying out quantitative recognition on the symptom description and the test text to obtain a quantitative result.
Understandably, the condition quantization and recognition are that the condition description and the test text are spliced to form a text, the text is subjected to the word segmentation and recognition through a word segmentation detection model, the words in the text are recognized, and classification is carried out according to the recognized words twice, so that a severity quantization result is obtained.
And S402, performing degree grade identification corresponding to the diagnosis type on the inspection image to obtain a grade result.
Understandably, a grade image recognition model corresponding to the type of the visit is obtained, focus area recognition is carried out on the inspection image through the obtained grade image recognition model, grade characteristics corresponding to the type of the visit are extracted from focus area, risk assessment is carried out according to the extracted grade characteristics, and the grade result of the risk grade corresponding to the inspection image is predicted, wherein the risk grade comprises high, medium and low.
S403, constructing a patient disease map of the patient according to the quantitative result, the grade result, the visit type, the department recommendation result and the time length information and the positioning information in the patient information.
Understandably, the quantified result, the grade result, the visit type, the department recommendation result, the duration information, and the positioning information are centered on the patient identification, and all attributes are associated to the patient identification.
S404, performing multidimensional conversion treatment on the patient disease map through a multidimensional consultation map conversion model to obtain a multidimensional consultation map corresponding to the patient disease map.
Understandably, the multi-dimensional consultation map conversion model is a model that maps each attribute in the patient disease map to a value of each dimension in the multi-dimensional consultation map according to the correlation between each other, which is learned through a large amount of historical data, and the preset dimension may be set according to requirements, for example: five dimensions, including place dimension, time dimension, department dimension, direction of visit dimension and light and heavy dimension respectively, through quantitative result, rank result and the correlation between the duration information, measure the value of light and heavy dimension, measure the value of time dimension through current time and duration information, measure the value of department dimension through department recommendation result and the type of visit, measure the value of direction of visit dimension through the type of visit, quantitative result and rank result, confirm the value of place dimension through positioning information, so, can measure the multidimensional map of treating with a doctor scientifically, rationally, can objectively reflect the current disease state of patient through multidimensional conversion processing.
The invention realizes quantitative recognition of the illness state through the symptom description and the test text to obtain a quantitative result; performing degree grade identification corresponding to the diagnosis type on the inspection image to obtain a grade result; constructing a patient disease map of the patient according to the quantitative result, the grade result, the visit type, the department recommendation result and the time length information and the positioning information in the patient information; the multi-dimensional to-be-diagnosed map of the patient is subjected to multi-dimensional conversion treatment through the multi-dimensional to-be-diagnosed map conversion model, so that the multi-dimensional to-be-diagnosed map of the patient can be automatically generated through quantitative identification of the disease condition, degree grade identification, construction of the patient's disorder map and a multi-dimensional conversion method, the current disorder state of the patient can be accurately, objectively and rapidly measured, a data basis is provided for the follow-up triage result, and the triage accuracy and reliability are improved.
S50, acquiring a multidimensional image graph associated with doctor identifications in the department recommendation results.
Understandably, each doctor identifier in the department recommendation result is searched from a portrait gallery, the doctor identifier is a unique identifier code given to each doctor, the multi-dimensional portrait map associated with the searched doctor identifier is obtained, the multi-dimensional portrait map represents a multi-dimensional map obtained after the corresponding doctor identifier is portrait with one-to-one corresponding dimension to the dimension in the multi-dimensional portrait, the portrait process can be a process of carrying out portrait and diagnosis point confirmation by combining the diagnosis point, the diagnosis state table and the doctor history data associated with the doctor identifier, constructing a multi-dimensional portrait map, and drawing an index map in the multi-dimensional portrait map and recording diagnosis points in the multi-dimensional portrait map.
Wherein the image gallery stores the multi-dimensional image associated with all of the doctor's identifications.
In one embodiment, as shown in fig. 5, before the step S50, that is, before the step of obtaining the multidimensional image associated with the doctor identifier in each of the department recommendation results, the method includes:
s501, acquiring a consultation point, a consultation state table and doctor historical data associated with the doctor mark.
Understandably, the visit point is the latitude and longitude position of the doctor corresponding to the doctor identifier, the visit status table is the date schedule of the doctor visit corresponding to the doctor identifier, the doctor history data is the doctor title, the visit record and the history corresponding to the doctor identifier, the doctor title is the grade of the research degree of the medical field of the doctor, the visit record is the history visit record of the doctor, the visit record comprises the score of each visit record, and the doctor history data is the data related to the medical research direction such as the prize, the journal, the paper and the like of the doctor.
S502, doctor portrait is carried out on the consultation state table and the doctor history data associated with the doctor mark, and an index map of the multidimensional portrait associated with the doctor mark is constructed.
Understandably, the doctor portraying process predicts a time matching degree based on the expected time of the doctor's visit in the patient information and the visit status table, and simultaneously carries out department portraying and expertise portraying based on the doctor's title and the visit record associated with the doctor's identification, so as to determine the adept department and expertise direction; and performing grade grading based on the doctor title and the doctor biographical data associated with the doctor identification to obtain a grade score; and integrating the time matching degree, the specialization direction and the grade score to create the index graph, wherein the index graph is a graph which reflects index values corresponding to the time matching degree, the specialization direction and the grade score one by one through quadrangles.
In one embodiment, the doctor's history data includes a doctor's title, a visit record, and a history, and understandably, the doctor's title is a grade representing a degree of study in a medical field of a doctor, the visit record is a history visit record of the doctor, the visit record includes a score for each visit record, and the doctor's history data is data related to a medical study direction, such as a doctor's prize, journal, paper, and the like.
In the step S502, that is, the step of creating an index map of the multidimensional map associated with the doctor identifier by performing doctor mapping on the consultation status table and the doctor history data associated with the doctor identifier includes:
and predicting the consultation state table associated with the doctor identifier based on the expected consultation time in the patient information to obtain the time matching degree associated with the doctor identifier.
Understandably, the desired time of visit is the time of desired visit of the patient, the process of predicting the visit status table associated with the doctor identification identifies the time conforming to the desired visit of the patient from the visit status table, and the process of measuring the time matching degree of the visit of the patient, which represents the degree of matching of the patient with the doctor in the time dimension, according to the reserved number corresponding to the identified time.
And carrying out department portraits and specialty portraits according to the doctor title and the consultation records associated with the doctor mark, and obtaining the good department and specialty associated with the doctor mark.
It is to be understood that the doctor title and the visit record are subjected to text extraction, the feature related to the department and the feature related to the exclusive direction are extracted, the feature related to the department and the feature related to the exclusive direction are weighted according to the score in the visit record, the weighted feature related to the department is subjected to department portraits, and the weighted feature related to the exclusive direction is subjected to exclusive image, wherein the department portraits are clustered on each department according to the weighted feature related to the department, the department with the best evidence is obtained, namely, the first department after clustering is regarded as the department with good evidence, the exclusive image is selected in each study direction under the department with good evidence according to the weighted feature related to the exclusive direction, and the study direction with the largest number or the largest number of votes is selected as the exclusive direction according to the study direction with the greatest evidence after the choice.
Wherein, the department with good treatment shows the department with the doctor with the best treatment in the department dimension, and the specialty direction shows the medical research direction with the deepest doctor research degree in the treatment direction dimension.
And grading according to the doctor title and the doctor resume data associated with the doctor mark, and obtaining a grade score associated with the doctor mark.
The grade score is understandably that a grade value corresponding to the doctor title is determined from the doctor title and the doctor resume data, the grade score is determined based on the grade value by correspondingly adding each piece of data in the doctor resume data, and the grade score represents an index of a doctor on a risk grade of a light degree and a heavy degree in a light dimension.
The index map associated with the doctor's identification is created based on the time matching degree, the department of expertise, the direction of expertise, and the rank score associated with the doctor's identification.
The invention realizes that the time matching degree associated with the doctor identifier is obtained by predicting the consultation state table associated with the doctor identifier based on the expected time of the consultation in the patient information; performing department portraits and specialty portraits according to the doctor title and the consultation records associated with the doctor mark, and obtaining a good department and specialty associated with the doctor mark; performing grade grading according to the doctor title and the doctor resume data associated with the doctor mark to obtain a grade score associated with the doctor mark; according to the time matching degree, the specialization direction and the grade score associated with the doctor mark, the index map associated with the doctor mark is created, so that indexes of a doctor in the time dimension, the department dimension, the research direction dimension and the light and heavy dimension can be intuitively and objectively embodied, and the comprehensive capability of the doctor is quickly improved through the index map, so that the accuracy of follow-up diagnosis is improved.
S503, determining a diagnosis point associated with the doctor mark as a diagnosis point of the multi-dimensional portrait drawing associated with the doctor mark.
The invention realizes the diagnosis and treatment method by acquiring the diagnosis and treatment points, the diagnosis and treatment state table and the doctor history data which are associated with the doctor mark; performing doctor portrayal on the consultation state table and the doctor history data associated with the doctor identifier, and constructing an index map of the multidimensional picture associated with the doctor identifier; the diagnosis point associated with the doctor identifier is determined to be the diagnosis dividing point of the multi-dimensional portrait drawing associated with the doctor identifier, so that the index conditions of a doctor in the site dimension, the time dimension, the department dimension, the diagnosis direction dimension and the light and heavy dimension can be objectively embodied, and the accuracy rate and the correct rate of outputting the doctor in the follow-up diagnosis dividing are improved.
S60, matching the multi-dimensional to-be-diagnosed image with each acquired multi-dimensional image to obtain a triage result, and recommending the triage result to a patient.
It can be understood that the matching process may be to calculate the distance between the positioning point in the multi-dimensional to-be-diagnosed image and the diagnosis point in each multi-dimensional image by using a euclidean distance method, and determine the distance matching value corresponding to the range according to the range of the segment, i.e. the range of which segment the distance value falls into (wherein, the range of each segment may be set as required, for example, the first segment is 0 to 200m corresponding to 100%, the second segment is 200m to 500m corresponding to 95%, etc.), and the percentage corresponding to the range falling into is determined; calculating the coincidence degree of the index image in the multi-dimensional to-be-diagnosed image and the image in each multi-dimensional image, and outputting the coincidence value of the multi-dimensional to-be-diagnosed image and each multi-dimensional image; measuring the matching degree of the multi-dimensional to-be-diagnosed image and each multi-dimensional image by combining the distance matching value and the superposition value; finally, the multidimensional portrait graph with the highest matching degree is selected as the triage result and recommended to the patient, so that the situations of wrong number hanging, wrong hospital running, multi-run hospital running, wrong doctor watching and the like can be greatly reduced.
The invention realizes that the patient information, symptom description and inspection data of the patient are contained in the patient treatment request by receiving the patient treatment request; identifying the diagnosis type of the symptom description and the inspection data, and determining the diagnosis type of the patient; performing department recommendation on the diagnosis type based on the patient information to obtain a department recommendation result; performing disorder map construction and multidimensional conversion on the patient information, the symptom description, the visit type, the department recommendation result and the inspection data to obtain a multidimensional consultation map; acquiring multidimensional image graphs associated with doctor identifications in the department recommendation results; the multi-dimensional to-be-diagnosed image is matched with each acquired multi-dimensional image to obtain a diagnosis separating result, and the diagnosis separating result is recommended to the patient, so that the methods of diagnosis type identification, department recommendation and multi-dimensional image matching are realized, departments and doctors needing to be separately diagnosed for the patient are automatically, rapidly and accurately determined, diagnosis accuracy is improved, and patient experience is improved.
In an embodiment, as shown in fig. 6, in step S60, the matching the multi-dimensional to-be-diagnosed image with each acquired multi-dimensional image to obtain a diagnosis result includes:
S601, calculating the distance between the locating point in the multi-dimensional to-be-diagnosed picture and the diagnosis dividing point in each multi-dimensional image picture by using a Euclidean distance method, and obtaining the distance matching value of the multi-dimensional to-be-diagnosed picture and each multi-dimensional image picture.
The euclidean distance method is an euclidean distance algorithm or an euclidean measurement algorithm, and also refers to an algorithm of a real distance between two points or a natural length of a vector (i.e. a distance from the point to an origin) in a multidimensional space, a value of a distance between a locating point in the multidimensional to-be-diagnosed map and a point to be diagnosed in the multidimensional image map is calculated by applying the euclidean distance algorithm, the calculated value can be inverted and converted into a percentage, so as to obtain a distance matching value of the multidimensional to-be-diagnosed map and the multidimensional image map, or a matching degree of the locating point in the multidimensional to-be-diagnosed map can be determined according to a segmented range in which the distance falls, i.e. a range of which segment the distance value falls (wherein, the range of each segment can be set according to requirements, for example, the first segment is 0 to 200m corresponds to 100%, the second segment is 200m to 500m corresponds to 95%, and so on).
S602, calculating the coincidence degree of the index graph in the multi-dimensional to-be-diagnosed graph and the image graph in each multi-dimensional image graph, and outputting the coincidence value of the multi-dimensional to-be-diagnosed graph and each multi-dimensional image graph.
Understandably, the coincidence ratio is calculated by aligning an origin of each dimension in the multi-dimensional to-be-diagnosed diagram with an origin of a corresponding dimension in the multi-dimensional image diagram, placing the multi-dimensional to-be-diagnosed diagram and the multi-dimensional image diagram on the same plane, calculating an intersection area between the multi-dimensional to-be-diagnosed diagram and the multi-dimensional image diagram, and an area of the multi-dimensional to-be-diagnosed diagram, dividing the intersection area with the area of the multi-dimensional to-be-diagnosed diagram to obtain a percentage of the intersection area to the multi-dimensional to-be-diagnosed diagram, and recording the percentage as the coincidence value of the multi-dimensional to-be-diagnosed diagram and the multi-dimensional image diagram, wherein the coincidence value represents the coincidence degree between the multi-dimensional to-be-diagnosed diagram and the multi-dimensional image diagram.
And S603, obtaining a final matching value of the multi-dimensional to-be-diagnosed image and each multi-dimensional image according to the distance matching value and the superposition value of the multi-dimensional to-be-diagnosed image and each multi-dimensional image.
Understandably, the distance matching value and the coincidence value of the multi-dimensional to-be-diagnosed image and the multi-dimensional portrait image are weighted and summed, and the final matching value of the multi-dimensional to-be-diagnosed image and the multi-dimensional portrait image is calculated, wherein the weight of the distance matching value and the weight of the coincidence value can be set according to requirements, and can also be output according to historical statistics, for example: the weight of the distance matching value is 0.4, the weight of the coincidence value is 0.6, and the sum of the weight of the distance matching value and the weight of the coincidence value is one, so that the final matching value of the multi-dimensional to-be-diagnosed image and each multi-dimensional image can be obtained, and the final matching value measures the matching degree between the multi-dimensional to-be-diagnosed image and the multi-dimensional image.
S604, sorting all the final matching values, and determining the multi-dimensional image corresponding to the sorted final matching values as the triage result.
Understandably, all the final matching values are sorted in a descending order, that is, the largest final matching value is arranged in the first sequence, the multi-dimensional image corresponding to the sorted final matching values is determined as the diagnosis result, for example, the multi-dimensional image corresponding to the sorted last preset number of final matching values is determined as the diagnosis result.
The invention realizes that the distance between the locating point in the multi-dimensional to-be-diagnosed picture and the diagnosis dividing point in each multi-dimensional image picture is calculated by applying the Euclidean distance method, so as to obtain the distance matching value of the multi-dimensional to-be-diagnosed picture and each multi-dimensional image picture; calculating the coincidence degree of the index image in the multi-dimensional to-be-diagnosed image and the image in each multi-dimensional image, and outputting the coincidence value of the multi-dimensional to-be-diagnosed image and each multi-dimensional image; obtaining a final matching value of the multi-dimensional to-be-diagnosed image and each multi-dimensional image according to the distance matching value and the superposition value of the multi-dimensional to-be-diagnosed image and each multi-dimensional image; and sorting all the final matching values, determining the multi-dimensional image graph corresponding to the sorted final matching values as the triage result, so that the final matching values are calculated through a Euclidean distance method and a coincidence degree calculation method, and sorting the final matching values to obtain the most matched triage result, so that the triage result which is most in line with the doctor of the patient can be accurately matched, and the triage accuracy are improved.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.
In an embodiment, a triage data processing apparatus is provided, where the triage data processing apparatus corresponds to the triage data processing method in the above embodiment one by one. As shown in fig. 7, the triage data processing apparatus includes a receiving module 11, an identifying module 12, a recommending module 13, a constructing module 14, an acquiring module 15, and a matching module 16. The functional modules are described in detail as follows:
a receiving module 11, configured to receive a patient's diagnosis request, and obtain diagnosis information in the diagnosis request; the visit information includes patient information, symptom descriptions, and test data;
an identification module 12, configured to identify a diagnosis type of the patient based on the symptom description and the inspection data;
a recommending module 13, configured to recommend a department to the type of the visit based on the patient information, so as to obtain a recommended result of the department;
a construction module 14, configured to perform disorder map construction and multidimensional transformation on the patient information, the symptom description, the visit type, the department recommendation result and the inspection data, so as to obtain a multidimensional diagnosis waiting chart;
An obtaining module 15, configured to obtain a multidimensional image associated with a doctor identifier in each department recommendation result;
and the matching module 16 is configured to match the multi-dimensional to-be-diagnosed image with each acquired multi-dimensional image to obtain a diagnosis result, and recommend the diagnosis result to the patient.
The specific limitation of the triage data processing apparatus may be referred to the limitation of the triage data processing method hereinabove, and will not be described herein. The above-mentioned individual modules in the triage data processing apparatus may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a client or a server, and the internal structure of which may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a readable storage medium, an internal memory. The readable storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the readable storage media. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by a processor, implements a triage data processing method.
In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the triage data processing method in the above embodiments when executing the computer program.
In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, which when executed by a processor, implements the triage data processing method in the above embodiment.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.
Claims (9)
1. A triage data processing method, comprising:
receiving a patient's diagnosis request, and acquiring diagnosis information in the diagnosis request; the visit information includes patient information, symptom descriptions, and test data; the inspection data includes an inspection image and inspection text;
Identifying the diagnosis type of the symptom description and the inspection data, and determining the diagnosis type of the patient;
performing department recommendation on the diagnosis type based on the patient information to obtain a department recommendation result;
performing disorder map construction and multidimensional conversion on the patient information, the symptom description, the visit type, the department recommendation result and the inspection data to obtain a multidimensional consultation map;
acquiring multidimensional image graphs associated with doctor identifications in the department recommendation results;
matching the multi-dimensional to-be-diagnosed image with each acquired multi-dimensional image to obtain a triage result, and recommending the triage result to a patient;
the performing disorder map construction and multidimensional conversion on the patient information, the symptom description, the visit type, the department recommendation result and the inspection data to obtain a multidimensional consultation map, comprising:
carrying out quantitative recognition on the symptom description and the test text to obtain a quantitative result;
performing degree grade identification corresponding to the diagnosis type on the inspection image to obtain a grade result;
constructing a patient disease map of the patient according to the quantitative result, the grade result, the visit type, the department recommendation result and the time length information and the positioning information in the patient information;
Multidimensional conversion treatment is carried out on the patient disease map through a multidimensional consultation map conversion model, so as to obtain a multidimensional consultation map corresponding to the patient disease map; the multidimensional conversion processing process of the patient disease map is characterized in that the association relationship among the quantized result, the level result and the time length information is used for measuring the value of the light dimension and the heavy dimension, the value of the time dimension is measured through the current time and the time length information, the value of the department dimension is measured through the department recommendation result and the visit type, the value of the visit direction dimension is measured through the visit type, the quantized result and the level result, the value of the place dimension is determined through the positioning information, and finally the multidimensional to-be-diagnosed map is obtained.
2. The triage data processing method of claim 1, wherein said performing a triage type identification of said symptom description and said test data, determining a triage type of a patient, comprises:
extracting symptoms according to the symptoms by using a symptoms extraction model, and identifying according to the extracted symptoms to obtain a first identification result;
performing image-text recognition on the inspection data through an unstructured disorder recognition model to obtain a second recognition result;
And carrying out diagnosis classification on the first identification result and the second identification result, and determining the diagnosis type.
3. The method for processing diagnosis-by-diagnosis data according to claim 2, wherein the performing image-text recognition on the inspection data by using the unstructured disorder recognition model to obtain a second recognition result comprises:
extracting a test image and a test text from the test data by using an OCR technology;
identifying the human body part of the inspection image to identify the disease part;
and carrying out disorder association recognition on the test text and the disorder part to obtain the second recognition result.
4. The method of claim 1, wherein prior to obtaining the multi-dimensional image associated with the doctor's identification in each of the department recommendations, the method comprises:
acquiring a consultation point, a consultation state table and doctor historical data associated with the doctor mark;
performing doctor portrayal on the consultation state table and the doctor history data associated with the doctor identifier, and constructing an index map of the multidimensional picture associated with the doctor identifier;
a point of visit associated with the doctor identification is determined as a point of triage of the multi-dimensional representation associated with the doctor identification.
5. The triage data processing method according to claim 4, wherein the doctor's biographical data includes doctor's title, visit record, and historical biography;
the step of creating an index map of the multidimensional map associated with the doctor identifier by performing doctor portrayal on the consultation status table and the doctor history data associated with the doctor identifier, includes:
predicting the consultation state table associated with the doctor identifier based on the expected consultation time in the patient information to obtain the time matching degree associated with the doctor identifier;
performing department portraits and specialty portraits according to the doctor title and the consultation records associated with the doctor mark, and obtaining a good department and specialty associated with the doctor mark;
performing grade grading according to the doctor title and the doctor resume data associated with the doctor mark to obtain a grade score associated with the doctor mark;
the index map associated with the doctor's identification is created based on the time matching degree, the department of expertise, the direction of expertise, and the rank score associated with the doctor's identification.
6. The method for processing triage data according to claim 1, wherein said matching the multi-dimensional to-be-diagnosed map with each of the acquired multi-dimensional image maps to obtain a triage result comprises:
calculating the distance between the locating point in the multi-dimensional to-be-diagnosed picture and the diagnosis dividing point in each multi-dimensional image picture by using an Euclidean distance method to obtain a distance matching value of the multi-dimensional to-be-diagnosed picture and each multi-dimensional image picture;
calculating the coincidence degree of the index image in the multi-dimensional to-be-diagnosed image and the image in each multi-dimensional image, and outputting the coincidence value of the multi-dimensional to-be-diagnosed image and each multi-dimensional image;
obtaining a final matching value of the multi-dimensional to-be-diagnosed image and each multi-dimensional image according to the distance matching value and the superposition value of the multi-dimensional to-be-diagnosed image and each multi-dimensional image;
and sequencing all the final matching values, and determining the multi-dimensional image map corresponding to the sequenced final matching values as the triage result.
7. A triage data processing apparatus, comprising:
the receiving module is used for receiving the patient's diagnosis request and acquiring the diagnosis information in the diagnosis request; the visit information includes patient information, symptom descriptions, and test data; the inspection data includes an inspection image and inspection text;
The identification module is used for identifying the diagnosis type of the symptom description and the inspection data and determining the diagnosis type of the patient;
the recommending module is used for recommending departments to the visit type based on the patient information to obtain a recommended result of the departments;
the construction module is used for constructing a disease map and performing multidimensional conversion on the patient information, the symptom description, the diagnosis type, the department recommendation result and the inspection data to obtain a multidimensional diagnosis waiting map;
the acquisition module is used for acquiring a multidimensional image graph associated with the doctor identification in each department recommendation result;
the matching module is used for matching the multi-dimensional to-be-diagnosed image with each acquired multi-dimensional image to obtain a triage result and recommending the triage result to a patient;
the building module is also for:
carrying out quantitative recognition on the symptom description and the test text to obtain a quantitative result;
performing degree grade identification corresponding to the diagnosis type on the inspection image to obtain a grade result;
constructing a patient disease map of the patient according to the quantitative result, the grade result, the visit type, the department recommendation result and the time length information and the positioning information in the patient information;
Multidimensional conversion treatment is carried out on the patient disease map through a multidimensional consultation map conversion model, so as to obtain a multidimensional consultation map corresponding to the patient disease map; the multidimensional conversion processing process of the patient disease map is characterized in that the association relationship among the quantized result, the level result and the time length information is used for measuring the value of the light dimension and the heavy dimension, the value of the time dimension is measured through the current time and the time length information, the value of the department dimension is measured through the department recommendation result and the visit type, the value of the visit direction dimension is measured through the visit type, the quantized result and the level result, the value of the place dimension is determined through the positioning information, and finally the multidimensional to-be-diagnosed map is obtained.
8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the triage data processing method according to any one of claims 1 to 6 when executing the computer program.
9. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the triage data processing method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111005310.9A CN113707304B (en) | 2021-08-30 | 2021-08-30 | Triage data processing method, triage data processing device, triage data processing equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111005310.9A CN113707304B (en) | 2021-08-30 | 2021-08-30 | Triage data processing method, triage data processing device, triage data processing equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113707304A CN113707304A (en) | 2021-11-26 |
| CN113707304B true CN113707304B (en) | 2023-08-01 |
Family
ID=78656902
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111005310.9A Active CN113707304B (en) | 2021-08-30 | 2021-08-30 | Triage data processing method, triage data processing device, triage data processing equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113707304B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116936058A (en) * | 2023-09-14 | 2023-10-24 | 北京健康有益科技有限公司 | Intelligent diagnosis guiding method and system based on deep learning and knowledge graph |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108922608A (en) * | 2018-06-13 | 2018-11-30 | 平安医疗科技有限公司 | Intelligent hospital guide's method, apparatus, computer equipment and storage medium |
| CN109102867A (en) * | 2018-08-13 | 2018-12-28 | 贵阳叁玖互联网医疗有限公司 | The intelligent diagnosis method and intelligent diagnosis platform of tele-medicine |
| CN109166618A (en) * | 2017-06-28 | 2019-01-08 | 京东方科技集团股份有限公司 | System for distribution of out-patient department and point examine method |
| CN110470303A (en) * | 2019-08-14 | 2019-11-19 | 新疆维吾尔自治区人民医院 | It goes to a doctor in a kind of hospital air navigation aid and device |
| CN110993081A (en) * | 2019-12-03 | 2020-04-10 | 济南大学 | Doctor online recommendation method and system |
| CN111326243A (en) * | 2020-02-05 | 2020-06-23 | 安徽科大讯飞医疗信息技术有限公司 | Triage recommendation method and device, electronic equipment and storage medium |
| CN111724888A (en) * | 2020-06-19 | 2020-09-29 | 上海依智医疗技术有限公司 | Information processing method for grading diagnosis guide, diagnosis guide system and storage medium |
| CN111785368A (en) * | 2020-06-30 | 2020-10-16 | 平安科技（深圳）有限公司 | Triage method, device, equipment and storage medium based on medical knowledge map |
| CN112035674A (en) * | 2020-08-28 | 2020-12-04 | 康键信息技术（深圳）有限公司 | Diagnosis guide data acquisition method and device, computer equipment and storage medium |
-
2021
- 2021-08-30 CN CN202111005310.9A patent/CN113707304B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109166618A (en) * | 2017-06-28 | 2019-01-08 | 京东方科技集团股份有限公司 | System for distribution of out-patient department and point examine method |
| CN108922608A (en) * | 2018-06-13 | 2018-11-30 | 平安医疗科技有限公司 | Intelligent hospital guide's method, apparatus, computer equipment and storage medium |
| CN109102867A (en) * | 2018-08-13 | 2018-12-28 | 贵阳叁玖互联网医疗有限公司 | The intelligent diagnosis method and intelligent diagnosis platform of tele-medicine |
| CN110470303A (en) * | 2019-08-14 | 2019-11-19 | 新疆维吾尔自治区人民医院 | It goes to a doctor in a kind of hospital air navigation aid and device |
| CN110993081A (en) * | 2019-12-03 | 2020-04-10 | 济南大学 | Doctor online recommendation method and system |
| CN111326243A (en) * | 2020-02-05 | 2020-06-23 | 安徽科大讯飞医疗信息技术有限公司 | Triage recommendation method and device, electronic equipment and storage medium |
| CN111724888A (en) * | 2020-06-19 | 2020-09-29 | 上海依智医疗技术有限公司 | Information processing method for grading diagnosis guide, diagnosis guide system and storage medium |
| CN111785368A (en) * | 2020-06-30 | 2020-10-16 | 平安科技（深圳）有限公司 | Triage method, device, equipment and storage medium based on medical knowledge map |
| WO2021139232A1 (en) * | 2020-06-30 | 2021-07-15 | 平安科技（深圳）有限公司 | Medical knowledge graph-based triage method and apparatus, device, and storage medium |
| CN112035674A (en) * | 2020-08-28 | 2020-12-04 | 康键信息技术（深圳）有限公司 | Diagnosis guide data acquisition method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113707304A (en) | 2021-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108899064A (en) | Electronic health record generation method, device, computer equipment and storage medium | |
| CN111145910A (en) | Abnormal case identification method and device based on artificial intelligence and computer equipment | |
| WO2021164388A1 (en) | Triage fusion model training method, triage method, apparatus, device, and medium | |
| CN112652386A (en) | Triage data processing method and device, computer equipment and storage medium | |
| CN111767192B (en) | Business data detection method, device, equipment and medium based on artificial intelligence | |
| US20190340473A1 (en) | Pattern recognition method of autoantibody immunofluorescence image | |
| CN113705685B (en) | Disease feature recognition model training, disease feature recognition method, device and equipment | |
| CN112150298A (en) | Data processing method, system, device and readable medium | |
| Shenoy et al. | Utilizing smartphone-based machine learning in medical monitor data collection: seven segment digit recognition | |
| CN114913942A (en) | Intelligent matching method and device for patient recruitment projects | |
| CN113707304B (en) | Triage data processing method, triage data processing device, triage data processing equipment and storage medium | |
| CN115858886A (en) | Data processing method, device, equipment and readable storage medium | |
| CN113707296B (en) | Medical scheme data processing method, device, equipment and storage medium | |
| CN111898528B (en) | Data processing method, device, computer readable medium and electronic equipment | |
| CN116913549A (en) | Adverse reaction event early warning method, device, system and electronic equipment | |
| CN116469505A (en) | Data processing method, device, computer equipment and readable storage medium | |
| US11430236B1 (en) | Computer-implemented segmented numeral character recognition and reader | |
| US20230022030A1 (en) | Systems and methods for processing images for image matching | |
| CN111582404B (en) | Content classification method, device and readable storage medium | |
| CN115662562A (en) | Medical record diagnosis and treatment data management method, device, equipment and storage medium | |
| CN115880702A (en) | Data processing method, device, equipment, program product and storage medium | |
| CN115311216A (en) | Method, device, equipment and storage medium for interpreting fluorescent picture of antinuclear antibody | |
| CN111401055B (en) | Method and apparatus for extracting context information from financial information | |
| CN115700826A (en) | Receipt processing method, receipt display method, receipt processing device, receipt display device, computer equipment and storage medium | |
| CN113688854A (en) | Data processing method and device and computing equipment |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220920 Address after: Room 2601 (Unit 07), Qianhai Free Trade Building, No. 3048, Xinghai Avenue, Nanshan Street, Qianhai Shenzhen-Hong Kong Cooperation Zone, Shenzhen, Guangdong 518000 Applicant after: Shenzhen Ping An Smart Healthcare Technology Co.,Ltd. Address before: 1-34 / F, Qianhai free trade building, 3048 Xinghai Avenue, Mawan, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong 518000 Applicant before: Ping An International Smart City Technology Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |