WO2023178971A1 - Procédé, appareil et dispositif d'inscription par internet destinés à demander un conseil médical, et support d'informations - Google Patents

Procédé, appareil et dispositif d'inscription par internet destinés à demander un conseil médical, et support d'informations Download PDF

Info

Publication number
WO2023178971A1
WO2023178971A1 PCT/CN2022/121725 CN2022121725W WO2023178971A1 WO 2023178971 A1 WO2023178971 A1 WO 2023178971A1 CN 2022121725 W CN2022121725 W CN 2022121725W WO 2023178971 A1 WO2023178971 A1 WO 2023178971A1
Authority
WO
WIPO (PCT)
Prior art keywords
registration
condition
target
user
symptom
Prior art date
Application number
PCT/CN2022/121725
Other languages
English (en)
Chinese (zh)
Inventor
张海艳
Original Assignee
康键信息技术（深圳）有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 康键信息技术（深圳）有限公司 filed Critical 康键信息技术（深圳）有限公司
Publication of WO2023178971A1 publication Critical patent/WO2023178971A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/02—Reservations, e.g. for tickets, services or events
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/005—Language recognition
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems
    • 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
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
    • 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
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y10/00—Economic sectors
    • G16Y10/60—Healthcare; Welfare
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y20/00—Information sensed or collected by the things
    • G16Y20/40—Information sensed or collected by the things relating to personal data, e.g. biometric data, records or preferences
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/20—Analytics; Diagnosis
    • 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

Definitions

  • This application relates to the field of big data technology, and in particular to an Internet registration method, device, equipment and storage medium for medical treatment.
  • appointment registration there are two common registration systems for online Internet hospitals: appointment registration and same-day registration.
  • the operation steps of the two registration plans are similar.
  • the method of obtaining the number source is relatively simple. The user needs to first select the department, then select the corresponding doctor, and then select the time to view To get to the real number source, there are many steps, and you cannot quickly and intuitively find the number source you need.
  • the inventor realized that users cannot compare the number sources horizontally and vertically. Especially for some new users who do not know how to operate or do not know which department number source they need to call, it is difficult to call the appropriate number, which often results in patients being called by the wrong number.
  • appointment registration and same-day registration use different operating systems, users need to constantly switch entrances to find a suitable number source for them, which makes it more difficult for users to seek medical treatment. Therefore, how to solve user registration difficulties and improve registration efficiency has become a technical problem that those skilled in the art currently need to solve.
  • This application provides an Internet registration method, device, equipment and storage medium for medical treatment.
  • the main purpose is to improve the efficiency of online registration for users by shortening the user's registration operation steps and only needing to enter the expected conditions to find the number source and register directly.
  • the first aspect of this application provides an Internet registration method for medical treatment, which includes: receiving an appointment registration request, obtaining the user's condition data and identity information according to the appointment registration request; and performing feature extraction on the condition data. , obtain multiple condition characteristics of the condition data; perform matching in the preset medical database according to the multiple condition characteristics, and obtain candidate symptoms that match the multiple condition characteristics; determine the candidate symptoms according to the candidate symptoms.
  • the target registration department matched by the user; obtain all doctors in the target registration department, calculate the matching degree of all the doctors according to the condition characteristics, and determine the target registration object from all the doctors based on the matching degree ; According to the identity information and the target registration object, generate the user's registration information and push it to the client.
  • the second aspect of this application provides an Internet registration device for medical treatment, including: a memory and at least one processor, instructions are stored in the memory, and the memory and the at least one processor are interconnected through lines; the at least A processor calls the instruction in the memory to cause the Internet registration device for medical treatment to perform the following steps: receive an appointment registration request, obtain the user's condition data and identity information according to the appointment registration request; Feature extraction is performed on the data to obtain multiple condition characteristics of the condition data; matching is performed in a preset medical database based on the multiple condition characteristics to obtain candidate symptoms that match the multiple condition characteristics; based on the candidate symptoms
  • the symptom determines the target registration department that matches the user; obtains all doctors in the target registration department, calculates the matching degree of all the doctors according to the condition characteristics, and selects the matching degree from all the doctors according to the matching degree.
  • Determine the target registration object generate the user's registration information according to the identity information and the target registration object, and push it to the client.
  • the third aspect of the present application provides a computer-readable storage medium.
  • a computer program is stored on the computer-readable storage medium. It is characterized in that when the computer program is executed by a processor, the following steps are implemented: receiving a reservation registration request; Obtain the user's condition data and identity information according to the appointment registration request; perform feature extraction on the condition data to obtain multiple condition features of the condition data; perform matching in the preset medical database based on the multiple condition features , obtain candidate symptoms that match multiple disease characteristics; determine the target registration department that matches the user based on the candidate symptoms; obtain all doctors in the target registration department, and calculate all the doctors based on the disease characteristics.
  • the matching degree of the doctor, and determine the target registration object from all the doctors based on the matching degree; generate the user's registration information based on the identity information and the target registration object, and push it to the client.
  • the fourth aspect of this application provides an Internet registration device for medical treatment, wherein the Internet registration device for medical treatment includes: an acquisition module, used to receive an appointment registration request, and obtain the user's condition data and identity information according to the appointment registration request. ; Feature extraction module, used to perform feature extraction on the condition data, to obtain multiple condition features of the condition data; Matching module, used to match in the preset medical database according to multiple condition features, to obtain the A plurality of candidate symptoms that match the disease characteristics; a first determination module for determining a target registration department matching the user based on the candidate symptoms; a second determination module for obtaining the target registration department in the target registration department All doctors calculate the matching degree of all doctors according to the condition characteristics, and determine the target registration objects from all the doctors according to the matching degree; a generation module is used to register according to the identity information and the target registration Object, generate the registration information of the user and push it to the client.
  • an acquisition module used to receive an appointment registration request, and obtain the user's condition data and identity information according to the appointment registration request.
  • the user's condition data and identity information are obtained according to the appointment registration request; feature extraction is performed on the condition data to obtain multiple condition characteristics of the condition data; and multiple condition characteristics are obtained in advance based on the multiple condition characteristics.
  • matching is performed in the medical database to obtain candidate symptoms that match multiple disease characteristics; determine the target registration department that matches the user based on the candidate symptoms; obtain all doctors in the target registration department, and calculate the matching degree of all doctors based on the disease characteristics. , and determine the target registration object from all doctors based on the matching degree; based on the identity information and the target registration object, the user's registration information is generated and pushed to the client.
  • This application receives the appointment registration request and obtains the user's condition data and identity information according to the appointment registration request; further, analyzes the user's condition data, determines the registered doctor from all doctors in the target registration department, and shortens the user registration operation steps. You only need to enter the expected conditions to find the number source and register directly, which improves the efficiency of online registration for users.
  • Figure 1 is a schematic diagram of the first embodiment of the Internet registration method for medical treatment in the embodiment of the present application
  • Figure 2 is a schematic diagram of the second embodiment of the Internet registration method for medical treatment in the embodiment of the present application.
  • Figure 3 is a schematic diagram of the third embodiment of the Internet registration method for medical treatment in the embodiment of the present application.
  • Figure 4 is a schematic diagram of the fourth embodiment of the Internet registration method for medical treatment in the embodiment of the present application.
  • Figure 5 is a schematic diagram of the fifth embodiment of the Internet registration method for medical treatment in the embodiment of the present application.
  • Figure 6 is a schematic diagram of the first embodiment of the Internet registration device for medical treatment in the embodiment of the present application.
  • Figure 7 is a schematic diagram of the second embodiment of the Internet registration device for medical treatment in the embodiment of the present application.
  • Figure 8 is a schematic diagram of an embodiment of the Internet registration equipment for medical treatment in the embodiment of the present application.
  • This application provides an Internet registration method, device, equipment and storage medium for medical treatment.
  • the main purpose is to improve the efficiency of online registration for users by shortening the user's registration operation steps and only needing to enter the expected conditions to find the number source and register directly.
  • the first embodiment of the Internet registration method for medical treatment in the embodiment of the present application includes:
  • the online registration request can be understood as an appointment consultation request input by the user in the intelligent registration platform.
  • the intelligent registration platform can be an app, a small program, a public account, etc. It should be understood that after the user inputs the online registration request, the intelligent registration platform will obtain the registration information of the online registration request, where the registration information includes: user information, condition information and registration time, so
  • the user information refers to the user's basic personal data, such as name, age, gender, contact information, address, ID card, etc.
  • the condition information refers to the user's physical state description data, such as dizziness, lightheadedness, cold, chest tightness, etc.
  • the registration time refers to the user's expected treatment time, which is generated based on different user needs.
  • collecting the registration information of the online registration request includes: obtaining the request fields of the online registration request, querying the data table of the request fields from the background database, and according to the Data table to query the registration information of the online registration request.
  • the request field can be understood as the identity identifier of the online registration request, used to characterize the registration identity of the online registration request, and the background database refers to the page data generated by the above-mentioned intelligent registration platform. , which can be a relational database, such as MySQL database.
  • training data is obtained, and the training data includes the original features corresponding to each sample data; the training data is used to train the initial feature extraction model, and the parameter values of the initial feature extraction model are obtained; and the initial feature extraction model is Filter the parameter values to obtain the filtered parameter values; use the filtered parameter values to reconstruct the initial feature extraction model to obtain the reconstructed feature extraction model; input the training data into the reconstructed feature
  • the extraction model the derived features of each sample data are obtained; the reconstructed feature extraction model is retrained according to the derived features of each sample data and the original features corresponding to each sample data until the iteration is terminated and the trained features are obtained feature extraction model.
  • the weight of the filtered parameter values is increased to obtain the reconstructed feature extraction model, and the weight of other parameter values in the parameter values of the initial feature extraction model is reduced, so that It facilitates the training of feature extraction models and is more sensitive to features corresponding to parameters with higher sensitivity, thereby mining more hidden features.
  • condition data is input into the feature extraction model for feature extraction to obtain the user's condition characteristics.
  • the medical database is constructed based on a medical database containing departments where symptoms should be reported.
  • the medical database containing the department where symptoms should be reported refers to the answer generated on the Internet by the user to the question of which department the patient should go to for registration.
  • the data sources of the data set include but are not limited to social networking sites, sharing sites, search sites, etc.
  • the medical database refers to the messages sent between the user's friends about the department where the symptoms should be reported; or when the network source is a sharing website, the medical database refers to the messages posted by users about the department where the symptoms should be reported.
  • Articles, videos, voices, etc.; or, when the network source is a search website the medical database refers to the web page results related to the department where the symptoms searched by the user should be linked.
  • the medical database is represented in the form of a structure tree, which includes several parent nodes and several child nodes connected to the parent nodes. Among them, at least one character is stored on each node, the characters stored on the parent node are used to represent field symptoms, and the characters stored on the child nodes are used to represent the registration department.
  • the path connecting the parent node and the child node is used to represent the confidence that the field symptom corresponds to the registration department.
  • two parent nodes connected to each other through a path are regarded as adjacent parent nodes, and the characters stored on the adjacent parent nodes are used to represent similar field symptoms.
  • the candidate symptom matching the condition feature "headache” is the field symptom "headache”
  • the confidence levels of the candidate symptoms corresponding to different registration departments are obtained from the medical knowledge graph database; based on the obtained confidence levels, the set to be pushed is generated by the registration departments corresponding to the candidate symptoms. That is to say, regarding the confidence level of each registration department corresponding to the candidate symptom, only the registration department whose confidence level exceeds a certain threshold or has the highest confidence level can be added to the set to be pushed as the department that should be registered for the disease characteristics.
  • the specific threshold can be flexibly set according to the actual needs of the application scenario, and is not limited here.
  • the medical field of the medical personnel in each department is queried, and the matching degree between the characteristic condition information and the medical field is calculated; the medical personnel whose matching degree is greater than the preset matching degree are selected as the initial registration objects, and Query the medical time of the initial registration object; calculate the correlation between the registration time and the medical time, and obtain the correlation between the characteristic condition information and the medical personnel in each department.
  • the medical field refers to the scope of medical expertise of the medical personnel, that is, the types of diseases treated by the medical personnel, such as neurological medical personnel, brain medical personnel and internal medicine medical personnel.
  • the medical time refers to the unscheduled medical treatment time of the medical personnel.
  • the target user's identity information, target department, and target physician can be used to generate the target user's registration information to complete self-service registration.
  • they may register for follow-up consultation.
  • the case samples associated with the target users can be found in the case database, and based on the case samples, it can be analyzed that the target user's consultation type is follow-up consultation. Obtain the original registration information of the target user's last consultation, so as to use the original registration information to generate the registration information corresponding to this consultation.
  • the methods provided by the embodiments of this application combine the use of various high-precision technologies, such as artificial intelligence, face recognition, voice assistants, big data analysis, etc., to help the elderly and all people who are not good at using electronic products, provide a convenient Quick registration process.
  • various high-precision technologies such as artificial intelligence, face recognition, voice assistants, big data analysis, etc.
  • the user's condition data and identity information are obtained according to the appointment registration request; feature extraction is performed on the condition data to obtain multiple condition characteristics of the condition data; and the preset medical treatment is performed based on the multiple condition features.
  • Match in the database to obtain candidate symptoms that match multiple disease characteristics; determine the target registration department matching the user based on the candidate symptoms; obtain all doctors in the target registration department, calculate the matching degree of all doctors according to the disease characteristics, and Determine the target registration target from all doctors based on the matching degree; generate the user's registration information based on the identity information and the target registration target, and push it to the client.
  • This application receives the appointment registration request and obtains the user's condition data and identity information according to the appointment registration request; further, analyzes the user's condition data, determines the registered doctor from all doctors in the target registration department, and shortens the user registration operation steps. You only need to enter the expected conditions to find the number source and register directly, which improves the efficiency of online registration for users.
  • the second embodiment of the Internet registration method for medical treatment in the embodiment of this application includes:
  • the registration terminal can be pre-set with different speech skills, and the self-service registration terminal can be used to ask the target user's discomfort symptoms through voice, and obtain the voice symptom information verbally described by the target user.
  • the self-service registration terminal obtains the voice symptom information of the target user, , it can be converted into text symptom information first, and through a series of data cleaning and semantic recognition, the symptom feature information of the target user can be further obtained.
  • the self-service registration terminal can send out a voice inquiry message, such as "Excuse me, where do you feel uncomfortable?" If the target user answers "Eye discomfort," then the symptom characteristic information of the target user can be obtained as eye discomfort.
  • a voice inquiry message such as "Excuse me, where do you feel uncomfortable?"
  • the target user answers "Eye discomfort” then the symptom characteristic information of the target user can be obtained as eye discomfort.
  • follow-up inquiry information can also be further formed based on the voice symptom information answered by the target user.
  • the target user's answer of "eye discomfort” you can further ask “are the eyes dry, painful, vision loss or other symptoms” to generate detailed symptom characteristics of the target user after further obtaining the target user's reply information. information. If the target user's answer is "eye pain”, you can further ask the target user about the pain level and so on.
  • the interaction content between the registration terminal and the target user can be simultaneously displayed on the screen of the registration terminal.
  • symptom options can be provided on the registration terminal for the target user to perform. Selection, for example, provide corresponding options (such as “dry eyes”, “eye pain”, “vision loss” and other symptom options) for the "eyes are dry, painful, vision loss or other symptoms” mentioned above, target users
  • the screen can be triggered to select one or more of the symptoms, and then combined with the target user's selection of symptoms, the symptom characteristic information of the target user can be obtained.
  • the process of semantic recognition at the registration terminal can be executed at the registration terminal or uploaded to the cloud for recognition.
  • a pre-set semantic recognition system can be used.
  • the semantic recognition system in addition to semantic recognition of common Mandarin, can also realize dialect recognition.
  • different language recognition systems can be established for the registration terminal according to the location attributes of the hospital where the registration terminal is deployed, so as to achieve accurate recognition of the user's voice and improve the user experience of the registration terminal.
  • a variety of recognition algorithms can be used, such as algorithms based on dynamic time warping (Dynamic Time Warping), algorithms based on deep learning neural networks, convolutional neural networks, etc.
  • the first convolutional neural network preset in the semantic recognition model is used to obtain the text vector of the text to be recognized.
  • Obtain the text to be recognized preprocess the obtained text to be recognized, obtain the initialized text vector, and input the initialized text vector into the first convolutional neural network preset by the semantic recognition model to generate a text vector used to characterize the text to be recognized.
  • Text vector can be specifically set according to the actual application scenario.
  • the preprocessing can be set to word segmentation processing, that is, the text to be recognized is segmented and marked in units of words; or the preprocessing can be set to word filtering processing, that is, in word segmentation processing.
  • the specific word segmentation processing of the text to be recognized is to use the SBME notation method to mark the words in the text to be recognized, that is, the single word is marked as S, and the first part of the word is marked as B.
  • the middle part of the word is marked as M, the end of the word is marked as E, and an initialized text vector is generated based on the marked text to be recognized.
  • the semantic recognition model of this application is constructed, and a training sample set used to train the semantic recognition model is obtained, that is, the training sample set can be used to train the initialized first convolutional neural network, second Convolutional neural network and the third convolutional neural network to obtain the semantic recognition model.
  • the preset second convolutional neural network is used to identify named entities contained in the text to be recognized, and the output result of the preset first convolutional neural network is used as the input of the preset second convolutional neural network, and the preset input
  • the output result of the second convolutional neural network is the named entity contained in the text to be recognized.
  • the preset third convolutional neural network is used to identify entity relationships contained in the text to be recognized, and the output results of the preset first convolutional neural network and the preset output results of the second convolutional neural network are used as the preset
  • the input of the third convolutional neural network is input to the preset third convolutional neural network, and the output result is the entity relationship between the named entities contained in the text to be recognized.
  • Steps 204-208 in this embodiment are similar to steps 102-106 in the first embodiment, and will not be described again here.
  • the user's condition data and identity information are obtained according to the appointment registration request; feature extraction is performed on the condition data to obtain multiple condition characteristics of the condition data; and the preset medical treatment is performed based on the multiple condition features.
  • Match in the database to obtain candidate symptoms that match multiple disease characteristics; determine the target registration department matching the user based on the candidate symptoms; obtain all doctors in the target registration department, calculate the matching degree of all doctors according to the disease characteristics, and Determine the target registration target from all doctors based on the matching degree; generate the user's registration information based on the identity information and the target registration target, and push it to the client.
  • This application receives the appointment registration request and obtains the user's condition data and identity information according to the appointment registration request; further, analyzes the user's condition data, determines the registered doctor from all doctors in the target registration department, and shortens the user registration operation steps. You only need to enter the expected conditions to find the number source and register directly, which improves the efficiency of online registration for users.
  • the third embodiment of the Internet registration method for medical treatment in the embodiment of this application includes:
  • stop words refer to words without meaning in the condition information, such as modal particles, adverbs, prepositions, connectives, etc.
  • the weight can be understood as the weight of the condition word vector in the condition information. accounting for the importance.
  • the deletion of the stop words can be achieved by matching the stop words in the stop word list;
  • the word segmentation can be achieved by a word segmentation algorithm, such as the stuttering word segmentation algorithm, the dictionary word segmentation algorithm, and Marco Word segmentation algorithm, etc.
  • the conversion of the disease word vector can be realized by word vector conversion algorithm, such as Word2vec algorithm;
  • the weight of the disease word vector can be realized by information concentration algorithm, such as factor analysis algorithm, principal component analysis algorithm, etc.
  • the preset weight can be set to 0.6, or can be set according to actual business scenarios.
  • converting target disease words into disease word vectors includes: performing word segmentation operations on multiple field texts in the target disease words to obtain multiple field word segmentation sets; encoding multiple field word segmentation sets.
  • the word segmentation is vectorized and combined using pre-trained word vector models to obtain condition word vectors corresponding to multiple field word segmentation sets; multiple condition word vectors are determined to form the vectorized text set.
  • performing word segmentation operations on multiple field texts in the target condition words to obtain multiple field word segmentation sets includes: decoding multiple encoded texts using decoding codes corresponding to the encoding codes, and obtaining multiple encoded texts. decoded text; obtain a text corpus corresponding to the type of the decoded text set; establish a joint distribution probability of a plurality of decoded texts according to the text corpus; filter and obtain a plurality of decoded texts based on the joint distribution probability Multiple decoded word segmentation text sets; use the encoding code to encode the decoded word segmentation texts in multiple decoded word segmentation text sets to obtain multiple field word segmentation sets.
  • condition word vectors are sorted according to the weight values, and the condition word vectors whose weight values are greater than the chalcedony weight values are selected as the target condition word vectors. Further, characteristic condition information is generated according to the target condition word vector.
  • the weight of the disease word vector can be realized by information concentration algorithm, such as factor analysis algorithm, principal component analysis algorithm, etc.
  • factor analysis refers to the study of statistical techniques for extracting common factors from variable groups. It was first proposed by British psychologist C.E. Spearman. He found that there was a certain correlation between students' scores in various subjects. Students who did well in one subject often had better scores in other subjects, and thus speculated whether there were some potential common factors, or some general intellectual conditions. Affects students' academic performance. Factor analysis can find hidden representative factors among many variables. Grouping variables of the same nature into one factor can reduce the number of variables and test hypotheses about the relationship between variables.
  • Steps 301 and 305-308 in this embodiment are similar to steps 101 and 103-106 in the first embodiment, and will not be described again here.
  • the user's condition data and identity information are obtained according to the appointment registration request; feature extraction is performed on the condition data to obtain multiple condition characteristics of the condition data; and the preset medical treatment is performed based on the multiple condition features.
  • Match in the database to obtain candidate symptoms that match multiple disease characteristics; determine the target registration department matching the user based on the candidate symptoms; obtain all doctors in the target registration department, calculate the matching degree of all doctors according to the disease characteristics, and Determine the target registration target from all doctors based on the matching degree; generate the user's registration information based on the identity information and the target registration target, and push it to the client.
  • This application receives the appointment registration request and obtains the user's condition data and identity information according to the appointment registration request; further, analyzes the user's condition data, determines the registered doctor from all doctors in the target registration department, and shortens the user registration operation steps. You only need to enter the expected conditions to find the number source and register directly, which improves the efficiency of online registration for users.
  • the fourth embodiment of the Internet registration method for medical treatment in the embodiment of this application includes:
  • condition characteristics are symptoms input by the user with the help of the client, there may be more colloquial symptom descriptions. Therefore, when performing a matching search based on the condition characteristics in the medical knowledge graph, it is likely that the condition characteristics cannot be directly searched. Exact match field symptoms.
  • the field symptom is "headache” and the condition feature is “headache”
  • the condition feature is “headache”
  • it can be considered that there is a field symptom “headache” matching the condition feature "headache” in the medical knowledge graph
  • the condition feature is “headache” "
  • the matching search process essentially includes: a complete matching search process and a similarity search process. Specifically, a complete matching search process is first performed to match each field symptom in the medical knowledge graph with the disease characteristics, that is, this step is performed.
  • the calculation methods of text similarity include but are not limited to: similarity calculation based on Euclidean distance, similarity calculation based on Manhattan distance, similarity calculation based on Mining distance, similarity calculation based on Mahalanobis distance, Similarity calculation based on cosine distance, similarity calculation based on Jaccard coefficient, similarity calculation based on Pearson correlation coefficient, etc. are not limited in this embodiment.
  • the medical knowledge graph ⁇ field symptoms, registration department, confidence level ⁇ .
  • ⁇ Headache, Neurology, 0.9 ⁇ , ⁇ Headache, Neurosurgery, 0.8 ⁇ are both included in the medical knowledge graph.
  • the medical knowledge graph is represented in the form of a structural tree, which includes several parent nodes and several child nodes connected to the parent nodes. Among them, at least one character is stored on each node, the characters stored on the parent node are used to represent field symptoms, and the characters stored on the child nodes are used to represent the registration department.
  • the path connecting the parent node and the child node is used to represent the confidence that the field symptom corresponds to the registration department. Further, two parent nodes connected to each other through a path are regarded as adjacent parent nodes, and the characters stored on the adjacent parent nodes are used to represent similar field symptoms.
  • the medical knowledge graph includes the parent node "Headache” and the parent node “Headache”, as well as the child nodes "Neurology” and “Neururgery” connected to the parent node "Headache”.
  • the parent node "Headache” and the parent node “ “Headache” are adjacent parent nodes to each other.
  • "headache” and “headache” are regarded as field symptoms, and they are similar field symptoms to each other.
  • Neurology and “Neurosurgery” are regarded as the registration departments of the field symptom “Headache” or “Headache”, 0.9 is the confidence level that the field symptom "Headache” or “Headache” corresponds to the registration department "Neurology”, 0.8 is The field symptom "Headache” or “Headache” corresponds to the confidence level of the registered department "Neurosurgery”.
  • candidate symptoms that match the input symptoms can be searched in the medical knowledge graph. For example, assuming that the input symptom is "headache”, then, no matter which form of medical knowledge graph is based on the above, through matching search, for example, for each parent node in the medical knowledge graph, the input symptom "headache” will be matched with the parent node By matching the characters on, it can be determined that the candidate symptom matching the input symptom "headache" is the field symptom "headache”.
  • Steps 401-402 and 406-408 in this embodiment are similar to steps 101-102 and 104-106 in the first embodiment, and will not be described again here.
  • the user's condition data and identity information are obtained according to the reservation registration request; feature extraction is performed on the condition data to obtain multiple condition characteristics of the condition data; and based on the multiple condition characteristics, the user's condition data is preset Match in the medical database to obtain candidate symptoms that match multiple disease characteristics; determine the target registration department that matches the user based on the candidate symptoms; obtain all doctors in the target registration department, and calculate the matching degree of all doctors based on the disease characteristics. And determine the target registration target from all doctors based on the matching degree; based on the identity information and the target registration target, generate the user's registration information and push it to the client.
  • This application receives the appointment registration request and obtains the user's condition data and identity information according to the appointment registration request; further, analyzes the user's condition data, determines the registered doctor from all doctors in the target registration department, and shortens the user registration operation steps. You only need to enter the expected conditions to find the number source and register directly, which improves the efficiency of online registration for users.
  • the fifth embodiment of the Internet registration method for medical treatment in the embodiment of this application includes:
  • the registration information of the symptom includes: the department where the symptom should be reported, the hospital where the department should be reported, the doctor who published the medical database, the hospital where the doctor works, the department where the doctor works, and the doctor who published the medical database.
  • the doctor specializes in at least one of the symptoms of the disease.
  • the process of extracting the registration information is explained. Specifically, first, based on the hospital and registration department in the hospital department set, the department where the symptom should be reported and the hospital where the department should be reported are searched from the medical database.
  • the hospitals and registration departments in the hospital department collection all exist in the form of identification information, which is formed in advance by collecting the names of hospitals and registration departments that really exist in life.
  • the collection of hospital departments is essentially a collection of hospital names and registered department names.
  • “Shenzhen People's Hospital” in the hospital department set is used to uniquely identify the real Shenzhen People's Hospital
  • “Shenzhen Renming Hospital Neurology Department” in the hospital department set is used to uniquely identify the real Shenzhen People's Hospital. Department of Neurology, Shenzhen People's Hospital.
  • registration information for the symptom is generated based on the department where the symptom should be admitted and the hospital where the department should be admitted.
  • symptom registration information ⁇ department or hospital to be registered ⁇ .
  • the doctor who published the medical database, the doctor's rank, the hospital where the doctor is located, and the doctor who published the medical database can also be obtained from the medical database.
  • the department where the doctor belongs, the doctor's expertise in disease symptoms, etc. are used to generate symptom registration information, which is not specifically limited in this embodiment.
  • a confidence factor is calculated based on the registration information of the symptom; and a confidence factor that the symptom should be admitted to a department is calculated based on the confidence factor.
  • the confidence factor includes at least one of a department confidence factor, a hospital confidence factor where the department is located, and a doctor confidence factor. Further, based on the confidence level, the target registration department matching the user is determined.
  • the medical field refers to the scope of medical expertise of the medical personnel, that is, the types of diseases treated by the medical personnel, such as neurological medical personnel, brain medical personnel and internal medicine medical personnel.
  • the medical time refers to the unscheduled medical treatment time of the medical personnel.
  • the medical personnel whose correlation degree is greater than the preset threshold are selected as the target registration objects of the online registration request, and the target registration objects are returned to the user to realize the user's online registration. request.
  • the preset threshold can be set to 0.9, or can be set according to actual business scenarios.
  • the medical personnel whose correlation degree is greater than the preset threshold are selected as the target registration objects of the online registration request, and the target registration objects are returned to the user to realize the user's online registration. request.
  • the preset threshold can be set to 0.9, or can be set according to actual business scenarios.
  • Steps 501-503 and 509 in this embodiment are similar to steps 101-103 and 106 in the first embodiment and will not be described again here.
  • the user's condition data and identity information are obtained according to the appointment registration request; feature extraction is performed on the condition data to obtain multiple condition characteristics of the condition data; and the preset medical treatment is performed based on the multiple condition features.
  • Match in the database to obtain candidate symptoms that match multiple disease characteristics; determine the target registration department matching the user based on the candidate symptoms; obtain all doctors in the target registration department, calculate the matching degree of all doctors according to the disease characteristics, and Determine the target registration target from all doctors based on the matching degree; generate the user's registration information based on the identity information and the target registration target, and push it to the client.
  • This application receives the appointment registration request and obtains the user's condition data and identity information according to the appointment registration request; further, analyzes the user's condition data, determines the registered doctor from all doctors in the target registration department, and shortens the user registration operation steps. You only need to enter the expected conditions to find the number source and register directly, which improves the efficiency of online registration for users.
  • the Internet registration method for medical treatment in the embodiment of the present application is described above.
  • the Internet registration device for medical treatment in the embodiment of the present application is described below.
  • the first embodiment of the Internet registration device for medical treatment in the embodiment of the present application include:
  • the acquisition module 601 is used to receive an appointment registration request, and obtain the user's condition data and identity information according to the appointment registration request;
  • the feature extraction module 602 is used to extract features from the condition data and obtain multiple condition features of the condition data;
  • the matching module 603 is configured to perform matching in a preset medical database according to a plurality of the condition characteristics, and obtain candidate symptoms that match a plurality of the condition characteristics;
  • the first determination module 604 is used to determine the target registration department matching the user according to the candidate symptoms
  • the second determination module 605 is used to obtain all doctors in the target registration department, calculate the matching degree of all the doctors according to the condition characteristics, and determine the target registration object from all the doctors according to the matching degree. ;
  • the generation module 606 is configured to generate the user's registration information according to the identity information and the target registration object, and push it to the client.
  • the user's condition data and identity information are obtained according to the appointment registration request; feature extraction is performed on the condition data to obtain multiple condition characteristics of the condition data; and the preset medical treatment is performed based on the multiple condition characteristics.
  • Match in the database to obtain candidate symptoms that match multiple disease characteristics; determine the target registration department matching the user based on the candidate symptoms; obtain all doctors in the target registration department, calculate the matching degree of all doctors according to the disease characteristics, and Determine the target registration target from all doctors based on the matching degree; generate the user's registration information based on the identity information and the target registration target, and push it to the client.
  • This application receives the appointment registration request and obtains the user's condition data and identity information according to the appointment registration request; further, analyzes the user's condition data, determines the registered doctor from all doctors in the target registration department, and shortens the user registration operation steps. You only need to enter the expected conditions to find the number source and register directly, which improves the efficiency of online registration for users.
  • the Internet registration device for medical treatment specifically includes:
  • the acquisition module 601 is used to receive an appointment registration request, and obtain the user's condition data and identity information according to the appointment registration request;
  • the feature extraction module 602 is used to extract features from the condition data and obtain multiple condition features of the condition data;
  • Matching module 603 is used to perform matching in a preset medical database according to a plurality of the condition characteristics, and obtain candidate symptoms that match a plurality of the condition characteristics;
  • the first determination module 604 is used to determine the target registration department matching the user according to the candidate symptoms
  • the second determination module 605 is used to obtain all doctors in the target registration department, calculate the matching degree of all the doctors according to the condition characteristics, and determine the target registration object from all the doctors according to the matching degree. ;
  • the generation module 606 is configured to generate the user's registration information according to the identity information and the target registration object, and push it to the client.
  • the acquisition module 601 is specifically used to:
  • Receive an appointment registration request parse the appointment registration request, and obtain the voice symptom data carried in the appointment registration request; perform format conversion on the voice symptom data to obtain text symptom data in text format;
  • Semantic recognition is performed on the text symptom information to obtain the user's condition data and identity information.
  • the feature extraction module 602 is specifically used to:
  • the matching module 603 includes:
  • the calculation unit 6031 is configured to obtain a medical knowledge graph corresponding to a plurality of the condition characteristics from a preset medical database, and calculate the relationship between each disease field in the medical knowledge graph and a plurality of the condition characteristics. suitability;
  • Matching unit 6032 configured to match multiple of the disease characteristics in the medical knowledge graph when the matching degree between each disease field and the plurality of disease characteristics is less than a preset threshold.
  • the most similar field symptom use the field symptom as a candidate symptom that matches multiple disease characteristics.
  • the matching unit 6032 is specifically used to:
  • target field symptoms whose similarity to the disease characteristics exceeds a preset threshold are obtained from the field symptoms.
  • the first determination module 604 is specifically used to:
  • the target registration department matching the user is determined.
  • the second determination module 605 is specifically used to:
  • the user's condition data and identity information are obtained according to the appointment registration request; feature extraction is performed on the condition data to obtain multiple condition characteristics of the condition data; and the preset medical treatment is performed based on the multiple condition features.
  • Match in the database to obtain candidate symptoms that match multiple disease characteristics; determine the target registration department matching the user based on the candidate symptoms; obtain all doctors in the target registration department, calculate the matching degree of all doctors according to the disease characteristics, and Determine the target registration target from all doctors based on the matching degree; generate the user's registration information based on the identity information and the target registration target, and push it to the client.
  • This application receives the appointment registration request and obtains the user's condition data and identity information according to the appointment registration request; further, analyzes the user's condition data, determines the registered doctor from all doctors in the target registration department, and shortens the user registration operation steps. You only need to enter the expected conditions to find the number source and register directly, which improves the efficiency of online registration for users.
  • FIGs 6 and 7 above describe in detail the Internet registration device for medical treatment in the embodiment of the present application from the perspective of modular functional entities.
  • the following describes the Internet registration device for medical treatment in the embodiment of the present application in detail from the perspective of hardware processing.
  • FIG. 8 is a schematic structural diagram of an Internet registration device for medical treatment provided by an embodiment of the present application.
  • the Internet registration device for medical treatment 800 may vary greatly due to different configurations or performance, and may include one or more central processing units. , CPU) 810 (eg, one or more processors) and memory 820, one or more storage media 830 (eg, one or more mass storage devices) that stores application programs 833 or data 832.
  • the memory 820 and the storage medium 830 may be short-term storage or persistent storage.
  • the program stored in the storage medium 830 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the Internet registration device 800 for medical treatment.
  • the processor 810 can be configured to communicate with the storage medium 830 and execute a series of instruction operations in the storage medium 830 on the Internet medical registration device 800 to implement the Internet medical registration method provided by the above method embodiments. step.
  • the Internet registration device 800 for medical treatment may also include one or more power supplies 840, one or more wired or wireless network interfaces 850, one or more input and output interfaces 860, and/or one or more operating systems 831, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD and more.
  • operating systems 831 such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD and more.
  • the computer-readable storage medium can be a non-volatile computer-readable storage medium.
  • the computer-readable storage medium can also be a volatile computer-readable storage medium.
  • Instructions are stored in the computer-readable storage medium. When the instructions are run on the computer, they cause the computer to perform the following steps: receive an appointment registration request, obtain the user's condition data and identity information according to the appointment registration request; Feature extraction is performed on the data to obtain multiple condition characteristics of the condition data; matching is performed in a preset medical database based on the multiple condition characteristics to obtain candidate symptoms that match the multiple condition characteristics; based on the candidate symptoms The symptom determines the target registration department that matches the user; obtains all doctors in the target registration department, calculates the matching degree of all the doctors according to the condition characteristics, and selects the matching degree from all the doctors according to the matching degree. Determine the target registration object; generate the user's registration information according to the identity information and the target registration object, and push it to the client.
  • the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, at least one application program required for a function, etc.; the storage data area may store information based on the blockchain node. Use the created data, etc.
  • Blockchain is a new application model of computer technology such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm.
  • Blockchain is essentially a decentralized database. It is a series of data blocks generated using cryptographic methods. Each data block contains a batch of network transaction information and is used to verify its Validity of information (anti-counterfeiting) and generation of the next block.
  • Blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.
  • the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium.
  • the technical solution of the present application is essentially or contributes to the existing technology, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk and other media that can store program code. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Medical Informatics (AREA)
  • Business, Economics & Management (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • General Physics & Mathematics (AREA)
  • Epidemiology (AREA)
  • Computing Systems (AREA)
  • Public Health (AREA)
  • Primary Health Care (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Economics (AREA)
  • Development Economics (AREA)
  • Multimedia (AREA)
  • Acoustics & Sound (AREA)
  • General Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Human Computer Interaction (AREA)
  • General Engineering & Computer Science (AREA)
  • Tourism & Hospitality (AREA)
  • Pathology (AREA)
  • Operations Research (AREA)
  • Marketing (AREA)
  • Databases & Information Systems (AREA)
  • Bioethics (AREA)
  • Accounting & Taxation (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Quality & Reliability (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

La présente invention se rapporte au champ technique des mégadonnées, et concerne un procédé, un appareil et un dispositif d'inscription par internet destinés à demander un conseil médical, et un support d'informations. Le procédé consiste : à recevoir une requête d'inscription à un rendez-vous, et à obtenir des données d'état de maladie et d'informations d'identité d'un utilisateur en fonction de la requête d'inscription à un rendez-vous ; à procéder à l'extraction d'attributs sur les données d'état de maladie pour obtenir une pluralité d'attributs d'état de maladie des données d'état de maladie ; à apparier dans une base de données médicales prédéfinie en fonction de la pluralité d'attributs d'état de maladie pour obtenir des symptômes candidats appariés à la pluralité d'attributs d'état de maladie ; à déterminer, en fonction des symptômes candidats, un département inscrit cible apparié à l'utilisateur ; à obtenir tous les médecins dans le département inscrit cible, à calculer respectivement le degré d'appariement de tous les médecins en fonction des caractéristiques d'état de maladie, et à déterminer un objet inscrit cible à partir de tous les médecins en fonction du degré d'appariement ; et à générer des informations d'inscription de l'utilisateur en fonction des informations d'identité et de l'objet inscrit cible, et à envoyer les informations d'inscription à un client. Selon la présente invention, les étapes d'opération d'inscription de l'utilisateur sont raccourcies, l'utilisateur n'a besoin que d'entrer la condition prévue pour contrôler le numéro source pour l'inscription directe, de sorte que l'efficacité d'inscription en ligne pour l'utilisateur est améliorée.
PCT/CN2022/121725 2022-03-23 2022-09-27 Procédé, appareil et dispositif d'inscription par internet destinés à demander un conseil médical, et support d'informations WO2023178971A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210289575.4A CN114611735A (zh) 2022-03-23 2022-03-23 就医的互联网挂号方法、装置、设备及存储介质
CN202210289575.4 2022-03-23

Publications (1)

Publication Number Publication Date
WO2023178971A1 true WO2023178971A1 (fr) 2023-09-28

Family

ID=81865177

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/121725 WO2023178971A1 (fr) 2022-03-23 2022-09-27 Procédé, appareil et dispositif d'inscription par internet destinés à demander un conseil médical, et support d'informations

Country Status (2)

Country Link
CN (1) CN114611735A (fr)
WO (1) WO2023178971A1 (fr)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114611735A (zh) * 2022-03-23 2022-06-10 康键信息技术（深圳）有限公司 就医的互联网挂号方法、装置、设备及存储介质
CN116029399A (zh) * 2023-02-27 2023-04-28 华序科技开发(深圳)有限公司 基于自然语义识别的在线预约导诊方法、电子设备、介质
CN116560880B (zh) * 2023-07-10 2023-09-22 北京梆梆安全科技有限公司 一种医疗信息管理系统
CN116631597B (zh) * 2023-07-24 2024-01-16 深圳捷工智能电气股份有限公司 一种移动端、医生端、护士端就近身份信息比对确认方法
CN117196077A (zh) * 2023-09-21 2023-12-08 深圳市环阳通信息技术有限公司 一种基于互联网的协助挂号诊断系统
CN118155817A (zh) * 2024-04-26 2024-06-07 旭辉卓越健康信息科技有限公司 一种基于gpt模型的科室和专家推荐方法及系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106469242A (zh) * 2015-08-11 2017-03-01 天津平和悦科技有限公司 一种医疗服务查询方法及装置及系统
US20170228511A1 (en) * 2016-02-05 2017-08-10 Novum Patent Holdco, LLC Medical Registration System
CN109065185A (zh) * 2018-07-24 2018-12-21 合肥同佑电子科技有限公司 一种面向患者快捷精准就医服务方法及系统
CN114611735A (zh) * 2022-03-23 2022-06-10 康键信息技术（深圳）有限公司 就医的互联网挂号方法、装置、设备及存储介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106469242A (zh) * 2015-08-11 2017-03-01 天津平和悦科技有限公司 一种医疗服务查询方法及装置及系统
US20170228511A1 (en) * 2016-02-05 2017-08-10 Novum Patent Holdco, LLC Medical Registration System
CN109065185A (zh) * 2018-07-24 2018-12-21 合肥同佑电子科技有限公司 一种面向患者快捷精准就医服务方法及系统
CN114611735A (zh) * 2022-03-23 2022-06-10 康键信息技术（深圳）有限公司 就医的互联网挂号方法、装置、设备及存储介质

Also Published As

Publication number Publication date
CN114611735A (zh) 2022-06-10

Similar Documents

Publication Publication Date Title
WO2023178971A1 (fr) Procédé, appareil et dispositif d'inscription par internet destinés à demander un conseil médical, et support d'informations
CN111414393B (zh) 一种基于医学知识图谱的语义相似病例检索方法及设备
US11049165B2 (en) System for clustering and aggregating data from multiple sources
US20190035506A1 (en) Intelligent auxiliary diagnosis method, system and machine-readable medium thereof
CN112667799B (zh) 一种基于语言模型和实体匹配的医疗问答系统构建方法
CN111785368A (zh) 基于医疗知识图谱的分诊方法、装置、设备及存储介质
CN112863630A (zh) 基于数据和知识的个性化精准医疗问答系统
CN113360671B (zh) 一种基于知识图谱的医保医疗单据审核方法及其系统
CN112650840A (zh) 一种基于知识图谱推理的医疗智能问答处理方法及系统
CN112037910B (zh) 健康信息管理方法、装置、设备及存储介质
WO2023029506A1 (fr) Procédé et appareil d'analyse d'état de maladie, dispositif électronique et support de stockage
CN111666477A (zh) 一种数据处理方法、装置、智能设备及介质
WO2022227203A1 (fr) Procédé, appareil et dispositif de triage basés sur une représentation de dialogue, et support de stockage
CN113569023A (zh) 一种基于知识图谱的中文医药问答系统及方法
CN111710429A (zh) 信息的推送方法及装置、计算机设备、存储介质
CN113764112A (zh) 一种在线医疗问答方法
WO2021174923A1 (fr) Support d'enregistrement, dispositif informatique, appareil et procédé de génération de séquence de mots conceptuels
CN111339252B (zh) 一种搜索方法、装置及存储介质
WO2023124837A1 (fr) Procédé et appareil de traitement d'enquête, dispositif, et support de stockage
CN113658712A (zh) 医患匹配方法、装置、设备及存储介质
CN116628219A (zh) 一种基于知识图谱的问答方法
CN111651579A (zh) 信息查询方法、装置、计算机设备和存储介质
CN116992002A (zh) 一种智能护理方案应答方法及系统
CN114743647A (zh) 医疗数据处理方法、装置、设备及存储介质
CN111403011B (zh) 挂号科室推送方法、装置、系统、电子设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22933023

Country of ref document: EP

Kind code of ref document: A1