WO2022041722A1 - 导诊数据获取方法、装置、计算机设备和存储介质 - Google Patents
导诊数据获取方法、装置、计算机设备和存储介质 Download PDFInfo
- Publication number
- WO2022041722A1 WO2022041722A1 PCT/CN2021/084346 CN2021084346W WO2022041722A1 WO 2022041722 A1 WO2022041722 A1 WO 2022041722A1 CN 2021084346 W CN2021084346 W CN 2021084346W WO 2022041722 A1 WO2022041722 A1 WO 2022041722A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- user
- user identity
- identity information
- personalized
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000003745 diagnosis Methods 0.000 claims abstract description 129
- 238000004088 simulation Methods 0.000 claims description 62
- 239000011159 matrix material Substances 0.000 claims description 60
- 238000013528 artificial neural network Methods 0.000 claims description 45
- 238000004590 computer program Methods 0.000 claims description 33
- 208000024891 symptom Diseases 0.000 claims description 28
- 238000000605 extraction Methods 0.000 claims description 14
- 201000010099 disease Diseases 0.000 claims description 13
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 10
- 239000000284 extract Substances 0.000 claims description 5
- 238000013480 data collection Methods 0.000 abstract 1
- 230000008569 process Effects 0.000 description 12
- 230000004044 response Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 6
- 229940079593 drug Drugs 0.000 description 5
- 239000003814 drug Substances 0.000 description 5
- 206010020751 Hypersensitivity Diseases 0.000 description 4
- 208000026935 allergic disease Diseases 0.000 description 4
- 230000007815 allergy Effects 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000011282 treatment Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000011369 optimal treatment Methods 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
- 230000001755 vocal effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
-
- 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
- the present application relates to knowledge relationship analysis in the field of data analysis, and in particular, to a method, device, computer equipment and storage medium for acquiring diagnostic guidance data.
- the inventor realizes that the traditional guidance technology is specifically responsible for collecting the most basic information of users, and then performing operations such as predicting departments and assigning doctors. These multiple rounds of fixed questions include several meaningless questions for the current user, resulting in low efficiency in collecting information about the consultation. .
- a method for obtaining diagnostic guidance data comprising:
- the guide data corresponding to the user is acquired.
- a guide data acquisition device includes:
- an information acquisition module configured to receive the main complaint information and user identity information sent by the terminal, and determine the user's intention to inquire according to the main complaint information and the user identity information;
- a personalized processing module configured to generate personalized inquiries questions according to the inquiry intention, the main complaint information of the inquiries and the user identity information, and send the personalized inquiry questions to the terminal;
- a reply receiving module configured to receive a personalized reply from the terminal according to the personalized inquiry question feedback
- a diagnosis path obtaining module configured to obtain the diagnosis path corresponding to the user according to the main complaint information, the user identity information and the personalized reply;
- the guide data acquisition module is used for obtaining the guide data corresponding to the user according to the diagnosis path.
- a computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:
- the guide data corresponding to the user is acquired.
- the guide data corresponding to the user is acquired.
- the present application can effectively improve the collection efficiency of the guide data.
- Fig. 1 is an application scenario diagram of a method for obtaining diagnostic guidance data in one embodiment
- FIG. 2 is a schematic flowchart of a method for obtaining diagnostic guidance data in one embodiment
- FIG. 3 is a schematic flowchart of a step of feeding back preset guidance problems to a terminal in one embodiment
- Fig. 4 is a sub-flow schematic diagram of step 207 in Fig. 2 in one embodiment
- FIG. 5 is a schematic flowchart of steps of constructing a knowledge graph in one embodiment
- FIG. 6 is a schematic flowchart of a user recommendation step in one embodiment
- Fig. 7 is a structural block diagram of a device for obtaining diagnostic data in one embodiment
- FIG. 8 is a diagram of the internal structure of a computer device in one embodiment.
- the method for acquiring guidance data provided by the present application can be applied to the application environment shown in FIG. 1 .
- the terminal 102 communicates with the intelligent guidance server 104 through the network.
- the intelligent medical guidance can be realized through the intelligent medical interaction platform, and the intelligent guidance server 104 equipped with the guidance data acquisition method of this solution can communicate with the medical interaction platform through the medical interaction platform.
- the user conducts simulated question-and-answer communication, so as to obtain the corresponding guidance data of the user.
- the user can log in to the medical interaction platform through the terminal 102 .
- the terminal 102 sends the main complaint information and user identity information to the intelligent guidance server 104 .
- the intelligent consultation server 104 receives the main complaint information and user identity information sent by the terminal 102, and determines the user's intention to inquire according to the main complaint information and the user's identity information; Personalize the consultation question, send the personalized consultation question to the terminal 102; receive the personalized reply from the terminal 102 according to the feedback of the personalized consultation question; obtain the diagnosis corresponding to the user according to the main complaint information, user identity information and personalized reply Path; according to the diagnosis path, obtain the guide data corresponding to the user.
- the terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices, and the server 104 can be implemented by an independent server or a server cluster composed of multiple servers.
- a method for obtaining diagnosis guide data is provided, and the method is applied to the intelligent diagnosis guide server 104 in FIG. 1 as an example for description, including the following steps:
- Step 201 Receive the main consultation complaint information and the user identity information sent by the terminal, and determine the user's consultation intention according to the main consultation complaint information and the user identity information.
- the main complaint information of the consultation refers to the information input by the user that includes the main symptoms of the disease to be consulted.
- the user identity information specifically refers to the user's name, gender, ID number, address, age and other information.
- the consultation intention refers to the main complaint information entered by the user indicating whether the user wishes to conduct a consultation.
- the user when obtaining a consultation data, the user needs to provide the corresponding consultation chief complaint information and user identity information to the intelligent consultation server 104 through the terminal 102 first. Then, the intelligent consultation server 104 can obtain the corresponding consultation data from the user according to the information, and at the same time submit the obtained user to the corresponding doctor, so as to maximize the doctor's consultation efficiency in the consultation process, and user experience. Then, after the user inputs the main complaint, the intelligent guidance server 104 needs to firstly judge the invalid main complaint, to determine whether the user's intention of the inquiry contained in the main complaint input by the user is clear.
- the user will be inquired individually and supplemented with relevant consultation information, including relevant symptoms, allergy history, examination, medication, etc., to better predict the department and diagnosis path. Specifically, when the input information of the main complaint of the consultation is "hello” or “thank you” and other meaningless information that is not related to the consultation, it is determined that the consultation intention corresponding to the main complaint of the consultation information input by the user is not Clear, and when the user inputs specific symptom information, it can be determined that the user's intention to inquire is relatively clear.
- Step 203 generating personalized consultation questions according to the consultation intention, main complaint information and user identity information, and sending the personalized consultation questions to the terminal.
- Step 205 Receive the personalized reply fed back by the terminal according to the personalized inquiry question.
- Personalized consultation questions refer to questions determined with respect to user information, and are used to obtain more detailed condition information from the user.
- the personalized consultation questions are determined based on the user and the main consultation complaint information.
- the personalized consultation questions are all pre-stored in the corresponding consultation question database.
- the corresponding personalized consultation questions are more than those of users with obvious consultation intentions, so as to obtain more Judging the information of the consultation, and personalized questions can specifically include related symptoms, allergy history, examinations, medication, etc., to better predict the department and diagnosis path.
- Step 207 Obtain a diagnosis path corresponding to the user according to the main complaint information, user identity information and personalized reply.
- the diagnosis path specifically refers to the simulated consultation questions that have been designed. Compared with the previous personalized questions, the diagnosis path is more inclined to the specific analysis of the disease, similar to simulating the consultation process of doctors in the department, so as to improve the guidance The efficiency of information acquisition in the process of acquiring diagnostic data.
- the diagnosis path corresponding to the user can be obtained based on analysis based on the main complaint information, user identity information, and personalized reply submitted by the user.
- the diagnosis path corresponding to the user can be obtained based on analysis based on the main complaint information, user identity information, and personalized reply submitted by the user.
- Step 209 Acquire diagnostic guidance data corresponding to the user according to the diagnostic path.
- the questions in the diagnostic path can be fed back to the user in turn. These questions can be fed back to the user in the form of question and answer or selection based on the pre-designed question, and the user can follow the After the user completes all answers to the questions in the diagnosis path, the user's reply information obtained by the intelligent guidance server is the guidance data.
- the above method for obtaining the consultation data is to determine the user's consultation intention according to the consultation main complaint information and the user identity information by receiving the main consultation information and the user identity information sent by the terminal; according to the consultation intention, the main consultation information and the user identity
- the information generates personalized consultation questions, and sends the personalized consultation questions to the terminal; receives the personalized responses from the terminal based on the feedback of the personalized consultation questions; obtains the corresponding diagnosis of the user according to the main complaint information, user identity information and personalized responses.
- Path according to the diagnosis path, obtain the guide data corresponding to the user.
- step 201 before step 201, it further includes:
- Step 302 Receive a consultation request sent by the terminal.
- Step 304 feeding back preset guidance questions to the terminal according to the guidance request.
- Step 201 includes: receiving the main inquiring complaint information and user identity information fed back by the terminal according to the preset guiding question.
- the user when the user selects a consultation on the medical interactive platform through the terminal 102, it can be regarded as sending a consultation request to the intelligent consultation server 104, and then the intelligent consultation server 104 can push the user to enter the main complaint information (specific symptoms). information), so as to obtain the main complaint information entered by the user, and then push the form for filling in the identity information, and the user's completed form collects the user's personal identity information.
- the user can upload the main complaint information of the consultation in the form of text, image or audio.
- text refers to the chief complaint information of the consultation directly input by the user
- image refers to the user can upload the historical medical record by taking a photo
- the image of the historical medical record is used as the chief complaint information of the consultation
- the audio refers to the information recorded by the user through the recording.
- the intelligent guidance server will convert the information of the main complaints entered by the user in various forms into text information. Using the form of question and answer to conduct anthropomorphic verbal inquiries can effectively improve the user's online experience during the consultation process and improve the efficiency of consultation data acquisition.
- step 207 includes:
- Step 401 construct a first multi-dimensional feature vector matrix according to the chief complaint information, user identity information and personalized reply, and input the first multi-dimensional feature vector matrix into a preset first deep neural network guidance model to obtain department information.
- the preset first deep neural network guide model is constructed based on historical consultation data
- the model may be a classification model specifically, and the output result of the classification is an optional department of the hospital.
- user identity information such as the user's gender and age
- features in the personalized response information such as symptoms, parts, allergy history, examination, and medication
- the deep neural network model the most suitable department for the current user is obtained from the optional departments of the hospital.
- Step 403 construct a second multi-dimensional eigenvector matrix according to the main complaint information, user identity information, personalized response and department information, input the second multi-dimensional eigenvector matrix into a preset second deep neural network guidance model, and obtain a diagnosis path.
- the diagnosis path refers to the simulated questions that have been designed. These simulated questions are also pre-stored in the corresponding database, and the corresponding simulated questions can be found in the database by presetting the second deep neural network guide model. Diagnose problems to build a complete diagnostic path.
- a department can be responsible for several diseases, and the process of obtaining the diagnosis path can be regarded as the process of further inquiring the user in the department to obtain more detailed disease information.
- the accuracy of the proposed diagnosis can be effectively improved, and the number of invalid dialogue rounds can be reduced. Improve consultation efficiency and user experience.
- step 403 includes:
- a second multi-dimensional feature vector matrix is constructed according to the main complaint information, user identity information, personalized reply and department information, and the second multi-dimensional feature vector matrix is input into the preset second deep neural network guidance model.
- the deep neural network guided diagnosis model extracts the corresponding diagnosis and simulation problems from the knowledge graph of the preset diagnosis and simulation problems, and constructs a diagnosis path according to the diagnosis and simulation problems.
- the knowledge graph is called knowledge domain visualization or knowledge domain mapping map in the library and information industry. It is a series of various graphs showing the development process and structural relationship of knowledge. Build, map and display knowledge and the interconnections between them.
- the simulated consultation questions in the diagnosis path can be associated and stored in the form of a knowledge graph, and associated with the preset second deep neural network guidance model. Then in the process of obtaining the diagnosis path, the problems in the diagnosis path can be continuously mined and determined based on the association relationship of the knowledge graph, and at the same time, the problems in the knowledge graph can be continuously expanded during the use of the model to obtain more accurate Diagnose simulation problems.
- the mining and determination of the diagnosis path can be more conveniently performed, thereby improving the efficiency of the acquisition of the guidance data.
- a second multi-dimensional feature vector matrix is constructed according to the main complaint information, user identity information, personalized response and department information, and the second multi-dimensional feature vector matrix is input into the preset No.
- the second deep neural network guide model before extracting the corresponding diagnosis simulation problem from the preset diagnosis simulation problem knowledge map through the preset second deep neural network guide model, also includes:
- Step 502 obtaining a diagnosis simulation problem.
- Step 504 perform entity name recognition operation and relation extraction operation on the diagnosis simulation problem.
- Step 506 according to the processing results of the entity name recognition operation and the relationship extraction operation, construct a knowledge graph of a preset diagnosis simulation problem.
- the diagnosis simulation problem is the foundation of the knowledge graph, and related diagnosis simulation problems can be constructed based on different diseases and symptoms.
- the diagnosis simulation problems of the same symptom are related, and the diagnosis simulation problems of the same disease are also related.
- These associations can be stored by means of a knowledge graph, and a second deep neural network guide model can also be preset to mine the diagnostic simulation problems corresponding to the information submitted by the user when constructing a diagnostic path. to build the diagnostic path.
- the operation staff at the guide data acquisition server 104 can first construct a large number of diagnosis simulation problems, and then input these diagnosis simulation problems into the guide data acquisition server 104 in the form of text.
- the guide data acquisition server 104 may perform entity name recognition and relation extraction operations on the diagnosis simulation problem based on the rules constructed by the knowledge graph, and then construct a preset diagnosis simulation problem knowledge graph based on the processing result.
- the construction of the knowledge graph of the preset diagnosis simulation problems can be effectively realized.
- step 209 it further includes:
- Step 601 extracting symptom feature labels in the guide data.
- Step 603 obtaining the recommendation degree of each doctor based on the symptom feature label and the doctor feature label, where the doctor feature label is the doctor feature label of the doctor corresponding to the department information.
- Step 605 Obtain recommended departments according to the department information, and obtain recommended doctors according to the recommendation degree.
- Step 607 feedback the recommended department and the recommended doctor to the terminal.
- the symptom feature label is used to reflect the characteristic symptoms of the user's symptoms and the symptom types corresponding to these symptoms, while the doctor feature label is determined according to the doctor's field and disease.
- feature tags can be extracted from the guide data, and then based on the feature tags, the doctor feature tags corresponding to each doctor in the determined department can be compared and searched, and based on the matching degree between the tags, each doctor can be obtained relative to the current patient recommendation. Then, the doctor is recommended to the user according to the ranking of the recommendation degree.
- the number of doctors waiting for consultation may be added as a piece of data for calculating the recommendation degree. Therefore, the doctor who does not need to wait too long is recommended to the user first, and the waiting efficiency of the user is improved.
- the user's guide data can also be fed back to the doctors in the department according to the department information.
- the guide data fed back in this step specifically includes the diagnostic path submitted to the user and the user's feedback on the diagnostic path.
- the doctor can analyze the specific situation of the user through the diagnosis path, thereby shortening the actual consultation time and improving the efficiency of the consultation.
- steps in the flowcharts of FIGS. 2-6 are shown in sequence according to the arrows, these steps are not necessarily executed in the sequence shown by the arrows. Unless explicitly stated herein, the execution of these steps is not strictly limited to the order, and these steps may be performed in other orders. Moreover, at least a part of the steps in FIGS. 2-6 may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed and completed at the same time, but may be executed at different times. These sub-steps or stages are not necessarily completed at the same time. The order of execution of the steps is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a part of sub-steps or stages of other steps.
- a device for acquiring diagnostic guidance data including:
- the information acquisition module 701 is used to receive the main complaint information and user identity information sent by the terminal, and determine the user's intention to inquire according to the main complaint information and the user identity information;
- Personalization processing module 703, configured to generate personalized consultation questions according to the consultation intention, the main complaint information of the consultation and the user identity information, and send the personalized consultation questions to the terminal;
- a reply receiving module 705, configured to receive a personalized reply from the terminal according to the personalized inquiry question feedback;
- the diagnosis path obtaining module 707 is configured to obtain the diagnosis path corresponding to the user according to the main complaint information, user identity information and personalized reply;
- the guidance data acquisition module 709 is configured to acquire the guidance data corresponding to the user according to the diagnosis path.
- it further includes a problem feedback module, configured to: receive a guidance request sent by the terminal; and feed back preset guidance questions to the terminal according to the guidance request.
- the information acquisition module 701 is specifically configured to: receive the main complaint information and user identity information fed back by the terminal according to the preset guidance questions.
- the diagnostic path obtaining module 707 is specifically configured to: construct a first multi-dimensional feature vector matrix according to the main complaint information, user identity information and personalized reply, and input the first multi-dimensional feature vector matrix into the preset first A deep neural network guide model to obtain department information; construct a second multi-dimensional eigenvector matrix according to the main complaint information, user identity information, personalized response and department information, and input the second multi-dimensional eigenvector matrix into the preset second Deep neural network guide model to obtain the diagnosis path.
- the diagnostic path obtaining module 707 is further configured to: construct a second multi-dimensional feature vector matrix according to the main complaint information, user identity information, personalized response and department information, and input the second multi-dimensional feature vector matrix into the A second deep neural network guide model is preset, and the corresponding diagnosis simulation problem is extracted from the preset diagnosis simulation problem knowledge map by the preset second deep neural network guide model; a diagnosis path is constructed according to the diagnosis simulation problem.
- a graph construction module is also included, used for: obtaining the diagnosis simulation problem; performing entity name recognition operation and relation extraction operation on the diagnosis simulation problem; Set up a knowledge graph for diagnosing simulation problems.
- a recommendation information feedback module is further included, which is used to: extract the symptom feature label in the guide data; obtain the recommendation degree of each doctor based on the symptom feature label and the doctor feature label, and the doctor feature label corresponds to the department information The doctor's feature label of the doctor; obtain the recommended department according to the department information, and obtain the recommended doctor according to the recommendation degree; feedback the recommended department and recommended doctor to the terminal.
- each module in the above-mentioned device for acquiring diagnostic guidance data may be implemented by software, hardware, or a combination thereof.
- the above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
- a computer device is provided, and the computer device may be a server, and its internal structure diagram may be as shown in FIG. 8 .
- the computer device includes a processor, memory, a network interface, and a database connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities.
- the memory of the computer device includes a non-volatile storage medium, an internal memory.
- the nonvolatile storage medium stores an operating system, a computer program, and a database.
- the internal memory provides an environment for the execution of the operating system and computer programs in the non-volatile storage medium.
- the database of the computer device is used to store the data of the guide data acquisition.
- the network interface of the computer device is used to communicate with an external terminal through a network connection.
- FIG. 8 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. Include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components.
- a computer device including a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:
- the processor executes the computer program, the following steps are further implemented: receiving a guidance request sent by a terminal; and feeding back preset guidance questions to the terminal according to the guidance request.
- the processor further implements the following steps when executing the computer program: constructing a first multi-dimensional feature vector matrix according to the main complaint information, user identity information and personalized reply, and inputting the first multi-dimensional feature vector matrix into a preset
- the first deep neural network guide model is used to obtain department information;
- a second multi-dimensional eigenvector matrix is constructed according to the chief complaint information, user identity information, personalized reply and department information, and the second multi-dimensional eigenvector matrix is input into the preset No.
- the deep neural network guide model to obtain the diagnosis path.
- the processor further implements the following steps when executing the computer program: constructing a second multi-dimensional feature vector matrix according to the main complaint information, user identity information, personalized response and department information, and converting the second multi-dimensional feature vector matrix
- the preset second deep neural network guide model is input, and the corresponding diagnosis simulation problem is extracted from the preset diagnosis simulation problem knowledge map through the preset second deep neural network guide model; the diagnosis path is constructed according to the diagnosis simulation problem.
- the processor when the processor executes the computer program, the following steps are further implemented: obtaining a diagnosis simulation problem; performing an entity name recognition operation and a relationship extraction operation on the diagnosis simulation problem; according to the processing results of the entity name recognition operation and the relationship extraction operation, constructing Preset diagnostics to simulate problem knowledge graphs.
- the processor further implements the following steps when executing the computer program: extracting symptom feature labels in the guide data; obtaining the recommendation degrees of each doctor based on the symptom feature labels and the doctor feature labels, where the doctor feature labels correspond to department information The doctor's feature label of the doctor; obtain the recommended department according to the department information, and obtain the recommended doctor according to the recommendation degree; feedback the recommended department and recommended doctor to the terminal.
- a computer storage medium is provided, the computer storage medium may be volatile or non-volatile, and a computer program is stored thereon, and the computer program implements the following steps when executed by a processor :
- the following steps are further implemented: receiving a guidance request sent by the terminal; and feeding back preset guidance questions to the terminal according to the guidance request.
- the following steps are further implemented: constructing a first multi-dimensional feature vector matrix according to the main complaint information, user identity information and personalized reply, and inputting the first multi-dimensional feature vector matrix into the pre-set Set up a first deep neural network guide model to obtain department information; build a second multi-dimensional eigenvector matrix according to the main complaint information, user identity information, personalized reply and department information, and input the second multi-dimensional eigenvector matrix into the preset
- the second deep neural network guide model is used to obtain the diagnosis path.
- the following steps are further implemented: constructing a second multi-dimensional feature vector matrix according to the chief complaint information, user identity information, personalized reply and department information, and converting the second multi-dimensional feature vector
- the matrix input presets the second deep neural network guide model, and extracts the corresponding diagnosis simulation problem from the preset diagnosis simulation problem knowledge map through the preset second deep neural network guide model; constructs a diagnosis path according to the diagnosis simulation problem.
- the following steps are further implemented: obtaining a diagnosis simulation problem; performing an entity name recognition operation and a relationship extraction operation on the diagnosis simulation problem; according to the processing results of the entity name recognition operation and the relationship extraction operation, Build a knowledge graph of preset diagnostic simulation problems.
- the following steps are further implemented: extracting the symptom feature labels in the guide data; obtaining the recommendation degree of each doctor based on the symptom feature labels and the doctor feature labels, and the doctor feature labels are department information Corresponds to the doctor's feature label of the doctor; obtains the recommended department according to the department information, and obtains the recommended doctor according to the recommendation degree; feedbacks the recommended department and recommended doctor to the terminal.
- all the above-mentioned data can also be stored in a node of a blockchain.
- a node of a blockchain For example, the chief complaint information and user identity information, etc., these data can be stored in the blockchain nodes.
- Blockchain essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information to verify its Validity of information (anti-counterfeiting) and generation of the next block.
- the blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.
- Nonvolatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory.
- Volatile memory may include random access memory (RAM) or external cache memory.
- RAM is available in various forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Road (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM) and so on.
- SRAM static RAM
- DRAM dynamic RAM
- SDRAM synchronous DRAM
- DDRSDRAM double data rate SDRAM
- ESDRAM enhanced SDRAM
- SLDRAM synchronous chain Road (Synchlink) DRAM
- SLDRAM synchronous chain Road (Synchlink) DRAM
- Rambus direct RAM
- DRAM direct memory bus dynamic RAM
- RDRAM memory bus dynamic RAM
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Business, Economics & Management (AREA)
- Public Health (AREA)
- General Engineering & Computer Science (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Pathology (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- Animal Behavior & Ethology (AREA)
- Databases & Information Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
一种导诊数据获取方法、装置、计算机设备和存储介质。所述方法通过接收终端发送的问诊主诉信息以及用户身份信息,根据问诊主诉信息以及用户身份信息,确定用户的问诊意图;并生成个性化问诊问题,发送个性化问诊问题至终端;接收终端根据个性化问诊问题反馈的个性化回复;根据问诊主诉信息、用户身份信息以及个性化回复,获取用户对应的诊断路径;根据诊断路径获取用户对应的导诊数据。本申请通过先确定用户的问诊意图、问诊主诉以及身份信息,而后基于问诊意图、问诊主诉以及身份信息来构建用户相应的诊断路径,基于诊断路径来获得导诊数据,可以有效减少问诊过程中无效的对话轮数,可以有效提高导诊数据的收集效率。
Description
本申请要求于2020年8月28日提交中国专利局、申请号为CN2020108866830 ,发明名称为“导诊数据获取方法、装置、计算机设备和存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
本申请涉及数据分析领域的知识关系分析,特别是涉及一种导诊数据获取方法、装置、计算机设备和存储介质。
用户对病症信息不了解是“看病难”原因之一,大多数用户是知症不知病、知病不知科,往往就会出现挂错号和找错医生的情况。面对“一号难求”的挂号局面,这种情况的发生无疑是雪上加霜,一方面导致不能对疾病进行及时的诊治,甚至可能错过最佳治疗时间;另一方面也是一种资源的浪费,用户的病情与专家所擅长的领域并不匹配;更重要的是,在这个过程中大大增加了用户及家属的心理负担和经济压力。所以,可以通过导诊技术来对用户进行引导。导诊即人们常说的导医。其工作涉及指导用户就医、护送用户做各种化验、检查、交费、取药、办理入院手续并护送用户到相应科室等一系列细致的内容。
发明人意识到传统导诊技术在使用时具体负责收集用户最基本的信息,而后进行预测科室以及分配医生等操作,然而在导诊的过程中,现有技术需要通过预设的多轮固定问话来明确用户的问诊意图、问诊主诉以及身份信息,而这多轮固定问话包含若干对于当前用户而言无意义的问话,从而导致导诊信息收集的效率较低。。
一种导诊数据获取方法,所述方法包括:
接收终端发送的问诊主诉信息以及用户身份信息,根据所述问诊主诉信息以及所述用户身份信息,确定用户的问诊意图;
根据所述问诊意图、所述问诊主诉信息以及所述用户身份信息生成个性化问诊问题,发送个性化问诊问题至所述终端;
接收所述终端根据所述个性化问诊问题反馈的个性化回复;
根据所述问诊主诉信息、所述用户身份信息以及所述个性化回复,获取用户对应的诊断路径;
根据所述诊断路径获取用户对应的导诊数据。
一种导诊数据获取装置,所述装置包括:
信息获取模块,用于接收终端发送的问诊主诉信息以及用户身份信息,根据所述问诊主诉信息以及所述用户身份信息,确定用户的问诊意图;
个性化处理模块,用于根据所述问诊意图、所述问诊主诉信息以及所述用户身份信息生成个性化问诊问题,发送个性化问诊问题至所述终端;
回复接收模块,用于接收所述终端根据所述个性化问诊问题反馈的个性化回复;
诊断路径获取模块,用于根据所述问诊主诉信息、所述用户身份信息以及所述个性化回复,获取用户对应的诊断路径;
导诊数据获取模块,用于根据所述诊断路径获取用户对应的导诊数据。
一种计算机设备,包括存储器和处理器,所述存储器存储有计算机程序,所述处理器执行所述计算机程序时实现以下步骤:
接收终端发送的问诊主诉信息以及用户身份信息,根据所述问诊主诉信息以及所述用户身份信息,确定用户的问诊意图;
根据所述问诊意图、所述问诊主诉信息以及所述用户身份信息生成个性化问诊问题,发送个性化问诊问题至所述终端;
接收所述终端根据所述个性化问诊问题反馈的个性化回复;
根据所述问诊主诉信息、所述用户身份信息以及所述个性化回复,获取用户对应的诊断路径;
根据所述诊断路径获取用户对应的导诊数据。
一种计算机存储介质,其上存储有计算机程序,所述计算机程序被处理器执行时实现以下步骤:
接收终端发送的问诊主诉信息以及用户身份信息,根据所述问诊主诉信息以及所述用户身份信息,确定用户的问诊意图;
根据所述问诊意图、所述问诊主诉信息以及所述用户身份信息生成个性化问诊问题,发送个性化问诊问题至所述终端;
接收所述终端根据所述个性化问诊问题反馈的个性化回复;
根据所述问诊主诉信息、所述用户身份信息以及所述个性化回复,获取用户对应的诊断路径;
根据所述诊断路径获取用户对应的导诊数据。
本申请可以有效提高导诊数据的收集效率。
图1为一个实施例中导诊数据获取方法的应用场景图;
图2为一个实施例中导诊数据获取方法的流程示意图;
图3为一个实施例中向终端反馈预设导诊问题步骤的流程示意图;
图4为一个实施例中图2中步骤207的子流程示意图;
图5为一个实施例中构建知识图谱步骤的流程示意图;
图6为一个实施例中进行用户推荐步骤的流程示意图;
图7为一个实施例中导诊数据获取装置的结构框图;
图8为一个实施例中计算机设备的内部结构图。
为了使本申请的目的、技术方案及优点更加清楚明白,以下结合附图及实施例,对本申请进行进一步详细说明。应当理解,此处描述的具体实施例仅仅用以解释本申请,并不用于限定本申请。
本申请提供的导诊数据获取方法,可以应用于如图1所示的应用环境中。其中,终端102通过网络与智能导诊服务器104通过网络进行通信。当用户前往医院就医前,或者在处于医院前台时,可以通过智能化的医疗交互平台来实现智能导诊,而搭载本方案的导诊数据获取方法的智能导诊服务器104可以通过医疗交互平台与用户进行模拟问答交流,从而获得用户相应的导诊数据。具体地,用户可以通过终端102来登录医疗交互平台。首先,终端102发送问诊主诉信息以及用户身份信息至智能导诊服务器104。智能导诊服务器104接收终端102发送的问诊主诉信息以及用户身份信息,根据问诊主诉信息以及用户身份信息,确定用户的问诊意图;根据问诊意图、问诊主诉信息以及用户身份信息生成个性化问诊问题,发送个性化问诊问题至终端102;接收终端102根据个性化问诊问题反馈的个性化回复;根据问诊主诉信息、用户身份信息以及个性化回复,获取用户对应的诊断路径;根据诊断路径获取用户对应的导诊数据。其中,终端102可以但不限于是各种个人计算机、笔记本电脑、智能手机、平板电脑和便携式可穿戴设备,服务器104可以用独立的服务器或者是多个服务器组成的服务器集群来实现。
在一个实施例中,如图2所示,提供了一种导诊数据获取方法,以该方法应用于图1中的智能导诊服务器104为例进行说明,包括以下步骤:
步骤201,接收终端发送的问诊主诉信息以及用户身份信息,根据问诊主诉信息以及用户身份信息,确定用户的问诊意图。
其中,问诊主诉信息是指用户输入的包含所要问诊疾病的主要症状的信息。而用户身份信息则具体是指用户的姓名、性别、身份证号、住址以及年龄等信息。而问诊意图是指用户输入的问诊主诉信息表明用户是否希望进行问诊。
具体地,在进行一次导诊数据获取时,用户需要先通过终端102向智能导诊服务器104提供相应的问诊主诉信息以及用户身份信息。而后智能导诊服务器104可以根据这些信息从用户获取相应的导诊数据,同时还会将得到的用户提交给到对应的医生,从而最终最大限度的提高问诊过程中医生的问诊效率,及用户体验。而后用户输入主诉后,智能导诊服务器104需要首先进行无效主诉判断,确定用户是否用户输入的主诉内包含的问诊意图是否明确,当明确时即可直接确定问诊主诉信息,而如果非问诊或问诊意图不明显,对用户进行个性化问询,补充相关问诊信息,包括相关症状、过敏史、检查、用药等,用于更好的预测科室和诊断路径。具体的,当用输入的问诊主诉信息为“你好”或者“谢谢”之类的与问诊并无关联的无意义信息时,则确定用户输入的问诊主诉信息对应的问诊意图不明确,而当用户输入的为具体的症状信息时,则可以判断用户的问诊意图较为明确。
步骤203,根据问诊意图、问诊主诉信息以及用户身份信息生成个性化问诊问题,发送个性化问诊问题至终端。
步骤205,接收终端根据个性化问诊问题反馈的个性化回复。
个性化问诊问题是指针对用户信息所确定的问题,用于从用户方获取更详细的病情信息。
具体地,个性化问诊问题基于用户以及问诊主诉信息确定。个性化问诊问题都预存于相应的问诊问题数据库内。基于用户主诉信息以及用户身份信息查找获取,一般的对于问诊意图不明显的用户,其对应的个性化问诊问题相较于问诊意图明显的用户问题更多,从而获得更多的用于判断问诊的信息,而个性化问题则具体可以包括相关症状、过敏史、检查、用药等,用于更好的预测科室和诊断路径。通过对用户主诉进行无效主诉,而后通过个性化问诊问题来进行问诊意图的判断及补全,可收集更多对于用户诊断路径判别的信息,使得诊断路径的判断更准确。
步骤207,根据问诊主诉信息、用户身份信息以及个性化回复,获取用户对应的诊断路径。
其中,诊断路径具体是指已经设计好的模拟问诊问题,相较于前面的个性化问题,诊断路径更倾向于对病症的具体分析,类似于模拟科室内医生的问诊过程,从而提高导诊数据获取过程的信息获取效率。
具体的,在得到用户反馈的个性化回复后,可以基于用户提交的问诊主诉信息、用户身份信息以及个性化回复等进行分析,得到用户对应的诊断路径。通过对用户主诉进行无效主诉及问诊意图的判断及补全,可收集更多对于用户拟诊路径判别的信息,使得预判更准确。
步骤209,根据诊断路径获取用户对应的导诊数据。
具体的,当得到用于模拟问诊的诊断路径后,可以依次向用户反馈诊断路径中的问题,这些问题可以基于预先的问题设计,以问答或者选择的形式向用户反馈过去,而用户可以依序对诊断路径的问题进行回复,当用户完成诊断路径内问题的全部答复后,智能导诊服务器所获得的用户答复信息即为导诊数据。
上述导诊数据获取方法,通过接收终端发送的问诊主诉信息以及用户身份信息,根据问诊主诉信息以及用户身份信息,确定用户的问诊意图;根据问诊意图、问诊主诉信息以及用户身份信息生成个性化问诊问题,发送个性化问诊问题至终端;接收终端根据个性化问诊问题反馈的个性化回复;根据问诊主诉信息、用户身份信息以及个性化回复,获取用户对应的诊断路径;根据诊断路径获取用户对应的导诊数据。本申请通过先确定用户的问诊意图、问诊主诉以及身份信息,而后基于问诊意图、问诊主诉以及身份信息来构建用户相应的诊断路径,基于诊断路径来获得导诊数据,可以有效减少问诊过程中无效的对话轮数,可以有效提高导诊数据的收集效率。
在其中一个实施例中,如图3所示,步骤201之前,还包括:
步骤302,接收终端发送的导诊请求。
步骤304,根据导诊请求向终端反馈预设导诊问题。
步骤201包括:接收终端根据预设导诊问题反馈的问诊主诉信息以及用户身份信息。
具体地,当用户通过终端102在医疗交互平台上选择导诊后,即可视为向智能导诊服务器104发送导诊请求,而后智能导诊服务器104可以向用户推送请输入主诉信息(具体症状信息)的预设导诊问题,从而获取用户输入的问诊主诉信息,而后推送用于填写身份信息的表格,由用户填写完成的表格来收集用户的个人身份信息。用户具体可以以文字、图像或者音频的方式来上传问诊主诉信息。其中,文字是指由用户打字直接输入的问诊主诉信息,而图像是指用户可以以拍照的方式上传历史病历,将历史病历的图像作为问诊主诉信息,而音频是指由用户通过录音的方式上传语音的方式来上传问诊主诉信息。而智能导诊服务器则会将用户以各种形式输入的问诊主诉信息都转化成文字信息。通过问答的形式拉进行拟人化方式的话术问询,可以有效提高用户在导诊过程中的在线体验,并提升导诊数据获取的效率。
在其中一个实施例中,如图4所示,步骤207包括:
步骤401,根据问诊主诉信息、用户身份信息以及个性化回复构建第一多维特征向量矩阵,将第一多维特征向量矩阵输入预设第一深度神经网络导诊模型,获取科室信息。
其中,预设第一深度神经网络导诊模型基于历史的问诊数据构建,该模型具体可以为分类模型,分类的输出结果为医院的可选科室。具体地,通过提取收集到的问诊主诉信息,用户的性别以及年龄等用户身份信息,还有症状、部位、过敏史、检查以及用药等个性化回复信息中的特征,而后构建相应的多维特征向量矩阵,并通过将深度神经网络模型对多维特征向量矩阵对应的分类结果进行预测,从医院的可选科室中得到当前用户最合适的科室。
步骤403,根据问诊主诉信息、用户身份信息、个性化回复以及科室信息构建第二多维特征向量矩阵,将第二多维特征向量矩阵输入预设第二深度神经网络导诊模型,获取诊断路径。
具体地,诊断路径是指已经设计好的模拟问诊问题,这些模拟问题也被预先存储在相应的数据库内,可以通过预设第二深度神经网络导诊模型从数据库内查找到相应的模拟问诊问题,从而构建完整的诊断路径。一般一个科室可以负责若干的病症,而获取诊断路径的过程即可以视为在科室内对用户进行进一步问诊,以获得更详细的病症信息的过程。可以通过预测得到的科室信息,及收集到的问诊主诉信息,用户的性别以及年龄等用户身份信息,还有症状、部位、过敏史、检查以及用药等个性化回复信息中的特征,而后构建相应的第二多维特征向量矩阵,并通过第二深度神经网络导诊模型,得到当前用户最合适的诊断路径。而后就可以通过诊断路径来对用户进行模拟问诊,来获取相应的导诊数据。本实施例中,通过使用多维信息构建相应的多维向量矩阵,利用深度神经网络预测科室,并找到最合适的拟诊判决路径,可有效提高拟诊的准确率,并减少无效的对话轮数,提升问诊效率及用户体验。
在其中一个实施例中,步骤403包括:
根据问诊主诉信息、用户身份信息、个性化回复以及科室信息构建第二多维特征向量矩阵,将第二多维特征向量矩阵输入预设第二深度神经网络导诊模型,通过预设第二深度神经网络导诊模型从预设诊断模拟问题知识图谱中抽取相应的诊断模拟问题;根据诊断模拟问题构建诊断路径。
其中,知识图谱在图书情报界称为知识域可视化或知识领域映射地图,是显示知识发展进程与结构关系的一系列各种不同的图形,用可视化技术描述知识资源及其载体,挖掘、分析、构建、绘制和显示知识及它们之间的相互联系。
具体的,在本实施例中,可以以知识图谱的方式来将诊断路径中的模拟问诊问题进行关联存储,并将其与预设第二深度神经网络导诊模型相关联。而后在获取诊断路径的过程中,就可以基于知识图谱的关联关系来不断挖掘确定诊断路径中的问题,同时还可以在模型的使用过程中不断对知识图谱内的问题进行拓展,以得到更加精确地问诊模拟问题。在本实施例中,通过将知识图谱与诊断路径的获取相关联,可以更方便地进行诊断路径的挖掘确定工作,从而提高导诊数据获取的效率。
在其中一个实施例中,如图5所示,根据问诊主诉信息、用户身份信息、个性化回复以及科室信息构建第二多维特征向量矩阵,将第二多维特征向量矩阵输入预设第二深度神经网络导诊模型,通过预设第二深度神经网络导诊模型从预设诊断模拟问题知识图谱中抽取相应的诊断模拟问题之前,还包括:
步骤502,获取诊断模拟问题。
步骤504,对诊断模拟问题进行实体命名识别操作和关系抽取操作。
步骤506,根据实体命名识别操作和关系抽取操作的处理结果,构建预设诊断模拟问题知识图谱。
其中,诊断模拟问题是构成知识图谱的基础,可以基于不同病症以及症状来构建相关的诊断模拟问题,相同症状的诊断模拟问题存在关联关系,相同疾病的诊断模拟问题也存在关联关系。通过知识图谱的方式可以将这些关联关系进行存储,同时在构建诊断路径也可以通过预设第二深度神经网络导诊模型来挖掘用户所提交信息相应的诊断模拟问题。来构建诊断路径。
具体地,在构建预设诊断模拟问题知识图谱时,导诊数据获取服务器104端的运营工作人员可以先构建海量诊断模拟问题,而后将这些诊断模拟问题以文本形式输入到导诊数据获取服务器104内,导诊数据获取服务器104可以基于知识图谱构建的规则,对诊断模拟问题进行实体命名识别操作和关系抽取操作,而后基于处理结果来构建预设诊断模拟问题知识图谱。本实施例中,通过预先获取诊断模拟问题,而后基于这些问题来构建知识图谱,可以有效实现预设诊断模拟问题知识图谱的构建。
在其中一个实施例中,如图6所示,步骤209之后,还包括:
步骤601,提取导诊数据中的症状特征标签。
步骤603,基于症状特征标签与医生特征标签,获取各个医生的推荐度,医生特征标签为科室信息对应医生的医生特征标签。
步骤605,根据科室信息获取推荐科室,根据推荐度获取推荐医生。
步骤607,向终端反馈推荐科室以及推荐医生。
其中,症状特征标签用于体现用户病症的特征症状,以及这些症状所对应的病症类型,而医生特征标签则是根据医生所擅长的领域以及病症来进行确定的。
具体地,可以通过在导诊数据中提取出特征标签,而后基于特征标签来比对查找所确定的科室内各个医生对应的医生特征标签,基于标签之间的匹配度来获取各个医生相对于当前患者的推荐度。而后根据推荐度的排名来向用户推荐医生,在其中一个实施例中,还可以将医生的候诊人数作为一项计算推荐度的数据加入。从而优先向用户推荐不需要等待过久的医生,提高用户的候诊效率。此外,在获取导诊数据之后,还可以根据科室信息向科室内的医生反馈用户的导诊数据,这一步骤反馈的导诊数据具体包含了提交给用户的诊断路径以及用户对诊断路径的反馈,此时医生可以通过诊断路径来对用户的具体情况进行分析,从而缩短实际的问诊时间,提高问诊效率。
应该理解的是,虽然图2-6的流程图中的各个步骤按照箭头的指示依次显示,但是这些步骤并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明,这些步骤的执行并没有严格的顺序限制,这些步骤可以以其它的顺序执行。而且,图2-6中的至少一部分步骤可以包括多个子步骤或者多个阶段,这些子步骤或者阶段并不必然是在同一时刻执行完成,而是可以在不同的时刻执行,这些子步骤或者阶段的执行顺序也不必然是依次进行,而是可以与其它步骤或者其它步骤的子步骤或者阶段的至少一部分轮流或者交替地执行。
在一个实施例中,如图7所示,提供了一种导诊数据获取装置,包括:
信息获取模块701,用于接收终端发送的问诊主诉信息以及用户身份信息,根据问诊主诉信息以及用户身份信息,确定用户的问诊意图;
个性化处理模块703,用于根据问诊意图、问诊主诉信息以及用户身份信息生成个性化问诊问题,发送个性化问诊问题至终端;
回复接收模块705,用于接收终端根据个性化问诊问题反馈的个性化回复;
诊断路径获取模块707,用于根据问诊主诉信息、用户身份信息以及个性化回复,获取用户对应的诊断路径;
导诊数据获取模块709,用于根据诊断路径获取用户对应的导诊数据。
在其中一个实施例中,还包括,问题反馈模块,用于:接收终端发送的导诊请求;根据导诊请求向终端反馈预设导诊问题。信息获取模块701具体用于:接收终端根据预设导诊问题反馈的问诊主诉信息以及用户身份信息。
在其中一个实施例中,诊断路径获取模块707具体用于:根据问诊主诉信息、用户身份信息以及个性化回复构建第一多维特征向量矩阵,将第一多维特征向量矩阵输入预设第一深度神经网络导诊模型,获取科室信息;根据问诊主诉信息、用户身份信息、个性化回复以及科室信息构建第二多维特征向量矩阵,将第二多维特征向量矩阵输入预设第二深度神经网络导诊模型,获取诊断路径。
在其中一个实施例中,诊断路径获取模块707还用于:根据问诊主诉信息、用户身份信息、个性化回复以及科室信息构建第二多维特征向量矩阵,将第二多维特征向量矩阵输入预设第二深度神经网络导诊模型,通过预设第二深度神经网络导诊模型从预设诊断模拟问题知识图谱中抽取相应的诊断模拟问题;根据诊断模拟问题构建诊断路径。
在其中一个实施例中,还包括图谱构建模块,用于:获取诊断模拟问题;对诊断模拟问题进行实体命名识别操作和关系抽取操作;根据实体命名识别操作和关系抽取操作的处理结果,构建预设诊断模拟问题知识图谱。
在其中一个实施例中,还包括推荐信息反馈模块,用于:提取导诊数据中的症状特征标签;基于症状特征标签与医生特征标签,获取各个医生的推荐度,医生特征标签为科室信息对应医生的医生特征标签;根据科室信息获取推荐科室,根据推荐度获取推荐医生;向终端反馈推荐科室以及推荐医生。
关于导诊数据获取装置的具体限定可以参见上文中对于导诊数据获取方法的限定,在此不再赘述。上述导诊数据获取装置中的各个模块可全部或部分通过软件、硬件及其组合来实现。上述各模块可以硬件形式内嵌于或独立于计算机设备中的处理器中,也可以以软件形式存储于计算机设备中的存储器中,以便于处理器调用执行以上各个模块对应的操作。
在一个实施例中,提供了一种计算机设备,该计算机设备可以是服务器,其内部结构图可以如图8所示。该计算机设备包括通过系统总线连接的处理器、存储器、网络接口和数据库。其中,该计算机设备的处理器用于提供计算和控制能力。该计算机设备的存储器包括非易失性存储介质、内存储器。该非易失性存储介质存储有操作系统、计算机程序和数据库。该内存储器为非易失性存储介质中的操作系统和计算机程序的运行提供环境。该计算机设备的数据库用于存储导诊数据获取数据。该计算机设备的网络接口用于与外部的终端通过网络连接通信。该计算机程序被处理器执行时以实现一种导诊数据获取方法。
本领域技术人员可以理解,图8中示出的结构,仅仅是与本申请方案相关的部分结构的框图,并不构成对本申请方案所应用于其上的计算机设备的限定,具体的计算机设备可以包括比图中所示更多或更少的部件,或者组合某些部件,或者具有不同的部件布置。
在一个实施例中,提供了一种计算机设备,包括存储器和处理器,该存储器存储有计算机程序,该处理器执行计算机程序时实现以下步骤:
接收终端发送的问诊主诉信息以及用户身份信息,根据问诊主诉信息以及用户身份信息,确定用户的问诊意图;
根据问诊意图、问诊主诉信息以及用户身份信息生成个性化问诊问题,发送个性化问诊问题至终端;
接收终端根据个性化问诊问题反馈的个性化回复;
根据问诊主诉信息、用户身份信息以及个性化回复,获取用户对应的诊断路径;
根据诊断路径获取用户对应的导诊数据。
在一个实施例中,处理器执行计算机程序时还实现以下步骤:接收终端发送的导诊请求;根据所述导诊请求向所述终端反馈预设导诊问题。
在一个实施例中,处理器执行计算机程序时还实现以下步骤:根据问诊主诉信息、用户身份信息以及个性化回复构建第一多维特征向量矩阵,将第一多维特征向量矩阵输入预设第一深度神经网络导诊模型,获取科室信息;根据问诊主诉信息、用户身份信息、个性化回复以及科室信息构建第二多维特征向量矩阵,将第二多维特征向量矩阵输入预设第二深度神经网络导诊模型,获取诊断路径。
在一个实施例中,处理器执行计算机程序时还实现以下步骤:根据问诊主诉信息、用户身份信息、个性化回复以及科室信息构建第二多维特征向量矩阵,将第二多维特征向量矩阵输入预设第二深度神经网络导诊模型,通过预设第二深度神经网络导诊模型从预设诊断模拟问题知识图谱中抽取相应的诊断模拟问题;根据诊断模拟问题构建诊断路径。
在一个实施例中,处理器执行计算机程序时还实现以下步骤:获取诊断模拟问题;对诊断模拟问题进行实体命名识别操作和关系抽取操作;根据实体命名识别操作和关系抽取操作的处理结果,构建预设诊断模拟问题知识图谱。
在一个实施例中,处理器执行计算机程序时还实现以下步骤:提取导诊数据中的症状特征标签;基于症状特征标签与医生特征标签,获取各个医生的推荐度,医生特征标签为科室信息对应医生的医生特征标签;根据科室信息获取推荐科室,根据推荐度获取推荐医生;向终端反馈推荐科室以及推荐医生。
在一个实施例中,提供了一种计算机存储介质,该计算机存储介质可以是易失性的,也可以是非易失性的,其上存储有计算机程序,计算机程序被处理器执行时实现以下步骤:
接收终端发送的问诊主诉信息以及用户身份信息,根据问诊主诉信息以及用户身份信息,确定用户的问诊意图;
根据问诊意图、问诊主诉信息以及用户身份信息生成个性化问诊问题,发送个性化问诊问题至终端;
接收终端根据个性化问诊问题反馈的个性化回复;
根据问诊主诉信息、用户身份信息以及个性化回复,获取用户对应的诊断路径;
根据诊断路径获取用户对应的导诊数据。
在一个实施例中,计算机程序被处理器执行时还实现以下步骤:接收终端发送的导诊请求;根据所述导诊请求向所述终端反馈预设导诊问题。
在一个实施例中,计算机程序被处理器执行时还实现以下步骤:根据问诊主诉信息、用户身份信息以及个性化回复构建第一多维特征向量矩阵,将第一多维特征向量矩阵输入预设第一深度神经网络导诊模型,获取科室信息;根据问诊主诉信息、用户身份信息、个性化回复以及科室信息构建第二多维特征向量矩阵,将第二多维特征向量矩阵输入预设第二深度神经网络导诊模型,获取诊断路径。
在一个实施例中,计算机程序被处理器执行时还实现以下步骤:根据问诊主诉信息、用户身份信息、个性化回复以及科室信息构建第二多维特征向量矩阵,将第二多维特征向量矩阵输入预设第二深度神经网络导诊模型,通过预设第二深度神经网络导诊模型从预设诊断模拟问题知识图谱中抽取相应的诊断模拟问题;根据诊断模拟问题构建诊断路径。
在一个实施例中,计算机程序被处理器执行时还实现以下步骤:获取诊断模拟问题;对诊断模拟问题进行实体命名识别操作和关系抽取操作;根据实体命名识别操作和关系抽取操作的处理结果,构建预设诊断模拟问题知识图谱。
在一个实施例中,计算机程序被处理器执行时还实现以下步骤:提取导诊数据中的症状特征标签;基于症状特征标签与医生特征标签,获取各个医生的推荐度,医生特征标签为科室信息对应医生的医生特征标签;根据科室信息获取推荐科室,根据推荐度获取推荐医生;向终端反馈推荐科室以及推荐医生。
在另一个实施例中,本申请所提供的导诊数据获取方法,为进一步保证上述所有出现的数据的私密和安全性,上述所有数据还可以存储于一区块链的节点中。例如问诊主诉信息以及用户身份信息等,这些数据均可存储在区块链节点中。
需要说明的是,本申请所指区块链是分布式数据存储、点对点传输、共识机制、加密算法等计算机技术的新型应用模式。区块链(Blockchain),本质上是一个去中心化的数据库,是一串使用密码学方法相关联产生的数据块,每一个数据块中包含了一批次网络交易的信息,用于验证其信息的有效性(防伪)和生成下一个区块。区块链可以包括区块链底层平台、平台产品服务层以及应用服务层等。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程,是可以通过计算机程序来指令相关的硬件来完成,的计算机程序可存储于一非易失性计算机可读取存储介质中,该计算机程序在执行时,可包括如上述各方法的实施例的流程。其中,本申请所提供的各实施例中所使用的对存储器、存储、数据库或其它介质的任何引用,均可包括非易失性和/或易失性存储器。非易失性存储器可包括只读存储器(ROM)、可编程ROM(PROM)、电可编程ROM(EPROM)、电可擦除可编程ROM(EEPROM)或闪存。易失性存储器可包括随机存取存储器(RAM)或者外部高速缓冲存储器。作为说明而非局限,RAM以多种形式可得,诸如静态RAM(SRAM)、动态RAM(DRAM)、同步DRAM(SDRAM)、双数据率SDRAM(DDRSDRAM)、增强型SDRAM(ESDRAM)、同步链路(Synchlink) DRAM(SLDRAM)、存储器总线(Rambus)直接RAM(RDRAM)、直接存储器总线动态RAM(DRDRAM)、以及存储器总线动态RAM(RDRAM)等。
以上实施例仅表达了本申请的几种实施方式,其描述较为具体和详细,但并不能因此而理解为对发明专利范围的限制。应当指出的是,对于本领域的普通技术人员来说,在不脱离本申请构思的前提下,还可以做出若干变形和改进,这些都属于本申请的保护范围。因此,本申请专利的保护范围应以所附权利要求为准。
Claims (20)
- 一种导诊数据获取方法,所述方法包括:接收终端发送的问诊主诉信息以及用户身份信息,根据所述问诊主诉信息以及所述用户身份信息,确定用户的问诊意图;根据所述问诊意图、所述问诊主诉信息以及所述用户身份信息生成个性化问诊问题,发送个性化问诊问题至所述终端;接收所述终端根据所述个性化问诊问题反馈的个性化回复;根据所述问诊主诉信息、所述用户身份信息以及所述个性化回复,获取用户对应的诊断路径;根据所述诊断路径获取用户对应的导诊数据。
- 根据权利要求1所述的方法,其中,所述接收终端发送的问诊主诉信息以及用户身份信息之前,还包括:接收终端发送的导诊请求;根据所述导诊请求向所述终端反馈预设导诊问题;所述接收终端发送的问诊主诉信息以及用户身份信息包括:接收终端根据所述预设导诊问题反馈的问诊主诉信息以及用户身份信息。
- 根据权利要求1所述的方法,其中,所述根据所述问诊主诉信息、所述用户身份信息以及所述个性化回复获取用户对应的诊断路径包括:根据所述问诊主诉信息、所述用户身份信息以及所述个性化回复构建第一多维特征向量矩阵,将所述第一多维特征向量矩阵输入预设第一深度神经网络导诊模型,获取科室信息;根据所述问诊主诉信息、所述用户身份信息、所述个性化回复以及所述科室信息构建第二多维特征向量矩阵,将所述第二多维特征向量矩阵输入预设第二深度神经网络导诊模型,获取诊断路径。
- 根据权利要求3所述的方法,其中,所述根据所述问诊主诉信息、所述用户身份信息、所述个性化回复以及所述科室信息构建第二多维特征向量矩阵,将所述第二多维特征向量矩阵输入预设第二深度神经网络导诊模型,获取诊断路径包括:根据所述问诊主诉信息、所述用户身份信息、所述个性化回复以及所述科室信息构建第二多维特征向量矩阵,将所述第二多维特征向量矩阵输入预设第二深度神经网络导诊模型,通过所述预设第二深度神经网络导诊模型从预设诊断模拟问题知识图谱中抽取相应的诊断模拟问题;根据所述诊断模拟问题构建诊断路径。
- 根据权利要求4所述的方法,其中,所述根据所述问诊主诉信息、所述用户身份信息、所述个性化回复以及所述科室信息构建第二多维特征向量矩阵,将所述第二多维特征向量矩阵输入预设第二深度神经网络导诊模型,通过所述预设第二深度神经网络导诊模型从预设诊断模拟问题知识图谱中抽取相应的诊断模拟问题之前,还包括:获取诊断模拟问题;对所述诊断模拟问题进行实体命名识别操作和关系抽取操作;根据所述实体命名识别操作和关系抽取操作的处理结果,构建预设诊断模拟问题知识图谱。
- 根据权利要求1所述的方法,其中,所述诊断路径包括科室信息,所述根据所述诊断路径获取用户对应的导诊数据之后,还包括:提取所述导诊数据中的症状特征标签;基于所述症状特征标签与医生特征标签,获取各个医生的推荐度,所述医生特征标签为所述科室信息对应医生的医生特征标签;根据所述科室信息获取推荐科室,根据所述推荐度获取推荐医生;向所述终端反馈推荐科室以及推荐医生。
- 根据权利要求1所述的方法,其中,所述问诊主诉信息包括用户输入的包含所要问诊疾病的主要症状的信息,所述用户身份信息包括用户的姓名、性别、身份证号、住址以及年龄。
- 一种导诊数据获取装置,其中,所述装置包括:信息获取模块,用于接收终端发送的问诊主诉信息以及用户身份信息,根据所述问诊主诉信息以及所述用户身份信息,确定用户的问诊意图;个性化处理模块,用于根据所述问诊意图、所述问诊主诉信息以及所述用户身份信息生成个性化问诊问题,发送个性化问诊问题至所述终端;回复接收模块,用于接收所述终端根据所述个性化问诊问题反馈的个性化回复;诊断路径获取模块,用于根据所述问诊主诉信息、所述用户身份信息以及所述个性化回复,获取用户对应的诊断路径;导诊数据获取模块,用于根据所述诊断路径获取用户对应的导诊数据。
- 一种计算机设备,包括存储器和处理器,所述存储器存储有计算机程序,其中,所述处理器执行所述计算机程序时实现如下步骤:接收终端发送的问诊主诉信息以及用户身份信息,根据所述问诊主诉信息以及所述用户身份信息,确定用户的问诊意图;根据所述问诊意图、所述问诊主诉信息以及所述用户身份信息生成个性化问诊问题,发送个性化问诊问题至所述终端;接收所述终端根据所述个性化问诊问题反馈的个性化回复;根据所述问诊主诉信息、所述用户身份信息以及所述个性化回复,获取用户对应的诊断路径;根据所述诊断路径获取用户对应的导诊数据。
- 根据权利要求9所述的计算机设备,其中,所述接收终端发送的问诊主诉信息以及用户身份信息之前,所述处理器执行所述计算机程序时还实现如下步骤:接收终端发送的导诊请求;根据所述导诊请求向所述终端反馈预设导诊问题;所述接收终端发送的问诊主诉信息以及用户身份信息包括:接收终端根据所述预设导诊问题反馈的问诊主诉信息以及用户身份信息。
- 根据权利要求9所述的计算机设备,其中,所述根据所述问诊主诉信息、所述用户身份信息以及所述个性化回复获取用户对应的诊断路径包括:根据所述问诊主诉信息、所述用户身份信息以及所述个性化回复构建第一多维特征向量矩阵,将所述第一多维特征向量矩阵输入预设第一深度神经网络导诊模型,获取科室信息;根据所述问诊主诉信息、所述用户身份信息、所述个性化回复以及所述科室信息构建第二多维特征向量矩阵,将所述第二多维特征向量矩阵输入预设第二深度神经网络导诊模型,获取诊断路径。
- 根据权利要求11所述的计算机设备,其中,所述根据所述问诊主诉信息、所述用户身份信息、所述个性化回复以及所述科室信息构建第二多维特征向量矩阵,将所述第二多维特征向量矩阵输入预设第二深度神经网络导诊模型,获取诊断路径包括:根据所述问诊主诉信息、所述用户身份信息、所述个性化回复以及所述科室信息构建第二多维特征向量矩阵,将所述第二多维特征向量矩阵输入预设第二深度神经网络导诊模型,通过所述预设第二深度神经网络导诊模型从预设诊断模拟问题知识图谱中抽取相应的诊断模拟问题;根据所述诊断模拟问题构建诊断路径。
- 根据权利要求12所述的计算机设备,其中,所述根据所述问诊主诉信息、所述用户身份信息、所述个性化回复以及所述科室信息构建第二多维特征向量矩阵,将所述第二多维特征向量矩阵输入预设第二深度神经网络导诊模型,通过所述预设第二深度神经网络导诊模型从预设诊断模拟问题知识图谱中抽取相应的诊断模拟问题之前,所述处理器执行所述计算机程序时还实现如下步骤:获取诊断模拟问题;对所述诊断模拟问题进行实体命名识别操作和关系抽取操作;根据所述实体命名识别操作和关系抽取操作的处理结果,构建预设诊断模拟问题知识图谱。
- 根据权利要求9所述的计算机设备,其中,所述诊断路径包括科室信息,所述根据所述诊断路径获取用户对应的导诊数据之后,所述处理器执行所述计算机程序时还实现如下步骤:提取所述导诊数据中的症状特征标签;基于所述症状特征标签与医生特征标签,获取各个医生的推荐度,所述医生特征标签为所述科室信息对应医生的医生特征标签;根据所述科室信息获取推荐科室,根据所述推荐度获取推荐医生;向所述终端反馈推荐科室以及推荐医生。
- 根据权利要求9所述的计算机设备,其中,所述问诊主诉信息包括用户输入的包含所要问诊疾病的主要症状的信息,所述用户身份信息包括用户的姓名、性别、身份证号、住址以及年龄。
- 一种计算机存储介质,其上存储有计算机程序,其中,所述计算机程序被处理器执行时实现如下步骤:接收终端发送的问诊主诉信息以及用户身份信息,根据所述问诊主诉信息以及所述用户身份信息,确定用户的问诊意图;根据所述问诊意图、所述问诊主诉信息以及所述用户身份信息生成个性化问诊问题,发送个性化问诊问题至所述终端;接收所述终端根据所述个性化问诊问题反馈的个性化回复;根据所述问诊主诉信息、所述用户身份信息以及所述个性化回复,获取用户对应的诊断路径;根据所述诊断路径获取用户对应的导诊数据。
- 根据权利要求16所述的计算机存储介质,其中,所述接收终端发送的问诊主诉信息以及用户身份信息之前,所述计算机程序被处理器执行时实现如下步骤:接收终端发送的导诊请求;根据所述导诊请求向所述终端反馈预设导诊问题;所述接收终端发送的问诊主诉信息以及用户身份信息包括:接收终端根据所述预设导诊问题反馈的问诊主诉信息以及用户身份信息。
- 根据权利要求16所述的计算机存储介质,其中,所述根据所述问诊主诉信息、所述用户身份信息以及所述个性化回复获取用户对应的诊断路径包括:根据所述问诊主诉信息、所述用户身份信息以及所述个性化回复构建第一多维特征向量矩阵,将所述第一多维特征向量矩阵输入预设第一深度神经网络导诊模型,获取科室信息;根据所述问诊主诉信息、所述用户身份信息、所述个性化回复以及所述科室信息构建第二多维特征向量矩阵,将所述第二多维特征向量矩阵输入预设第二深度神经网络导诊模型,获取诊断路径。
- 根据权利要求18所述的计算机存储介质,其中,所述根据所述问诊主诉信息、所述用户身份信息、所述个性化回复以及所述科室信息构建第二多维特征向量矩阵,将所述第二多维特征向量矩阵输入预设第二深度神经网络导诊模型,获取诊断路径包括:根据所述问诊主诉信息、所述用户身份信息、所述个性化回复以及所述科室信息构建第二多维特征向量矩阵,将所述第二多维特征向量矩阵输入预设第二深度神经网络导诊模型,通过所述预设第二深度神经网络导诊模型从预设诊断模拟问题知识图谱中抽取相应的诊断模拟问题;根据所述诊断模拟问题构建诊断路径。
- 根据权利要求19所述的计算机存储介质,其中,所述根据所述问诊主诉信息、所述用户身份信息、所述个性化回复以及所述科室信息构建第二多维特征向量矩阵,将所述第二多维特征向量矩阵输入预设第二深度神经网络导诊模型,通过所述预设第二深度神经网络导诊模型从预设诊断模拟问题知识图谱中抽取相应的诊断模拟问题之前,所述计算机程序被处理器执行时实现如下步骤:获取诊断模拟问题;对所述诊断模拟问题进行实体命名识别操作和关系抽取操作;根据所述实体命名识别操作和关系抽取操作的处理结果,构建预设诊断模拟问题知识图谱。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010886683.0A CN112035674B (zh) | 2020-08-28 | 2020-08-28 | 导诊数据获取方法、装置、计算机设备和存储介质 |
CN202010886683.0 | 2020-08-28 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022041722A1 true WO2022041722A1 (zh) | 2022-03-03 |
Family
ID=73587623
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2021/084346 WO2022041722A1 (zh) | 2020-08-28 | 2021-03-31 | 导诊数据获取方法、装置、计算机设备和存储介质 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN112035674B (zh) |
WO (1) | WO2022041722A1 (zh) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115274086A (zh) * | 2022-09-27 | 2022-11-01 | 无码科技(杭州)有限公司 | 一种智能导诊方法及系统 |
CN116469542A (zh) * | 2023-04-20 | 2023-07-21 | 智远汇壹(苏州)健康医疗科技有限公司 | 一种个性化医疗影像诊断路径生成系统及方法 |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112035674B (zh) * | 2020-08-28 | 2023-05-23 | 康键信息技术(深圳)有限公司 | 导诊数据获取方法、装置、计算机设备和存储介质 |
CN113760227A (zh) * | 2021-01-18 | 2021-12-07 | 北京京东拓先科技有限公司 | 分诊信息采集方法、装置、电子设备和计算机存储介质 |
CN113282761A (zh) * | 2021-05-27 | 2021-08-20 | 平安科技(深圳)有限公司 | 科室信息的推送方法、装置、设备以及存储介质 |
CN113707304B (zh) * | 2021-08-30 | 2023-08-01 | 深圳平安智慧医健科技有限公司 | 分诊数据处理方法、装置、设备及存储介质 |
CN113934346A (zh) * | 2021-09-16 | 2022-01-14 | 阿里健康科技(中国)有限公司 | 接诊方法 |
CN113963765A (zh) * | 2021-10-22 | 2022-01-21 | 浙江远图互联科技股份有限公司 | 一种智能问诊方法、装置、设备及储存介质 |
CN113851219A (zh) * | 2021-11-29 | 2021-12-28 | 山东交通学院 | 一种基于多模态知识图谱的智能导诊方法 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103164616A (zh) * | 2013-02-02 | 2013-06-19 | 杭州卓健信息科技有限公司 | 一种智能导诊系统和方法 |
CN109887587A (zh) * | 2019-01-22 | 2019-06-14 | 平安科技(深圳)有限公司 | 智能分诊方法、系统、装置及存储介质 |
US20190385739A1 (en) * | 2017-06-28 | 2019-12-19 | Boe Technology Group Co., Ltd. | Triage dialogue method, device and system |
CN110675944A (zh) * | 2019-09-20 | 2020-01-10 | 京东方科技集团股份有限公司 | 分诊方法及装置、计算机设备及介质 |
CN112035674A (zh) * | 2020-08-28 | 2020-12-04 | 康键信息技术(深圳)有限公司 | 导诊数据获取方法、装置、计算机设备和存储介质 |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108198620B (zh) * | 2018-01-12 | 2022-03-22 | 洛阳飞来石软件开发有限公司 | 一种基于深度学习的皮肤疾病智能辅助诊断系统 |
CN108877929A (zh) * | 2018-05-31 | 2018-11-23 | 平安医疗科技有限公司 | 基于神经网络的拟诊推荐处理方法、装置和计算机设备 |
CN108932974B (zh) * | 2018-05-31 | 2023-04-18 | 平安医疗科技有限公司 | 在线问诊分配医生的方法、装置、计算机设备和存储介质 |
CN108766545B (zh) * | 2018-05-31 | 2023-10-03 | 平安医疗科技有限公司 | 在线问诊科室分配方法、装置、计算机设备和存储介质 |
CN108922634A (zh) * | 2018-06-13 | 2018-11-30 | 平安医疗科技有限公司 | 基于在线问诊的问题答复处理方法、装置和计算机设备 |
CN109065172B (zh) * | 2018-07-04 | 2023-04-11 | 平安科技(深圳)有限公司 | 病症信息获取方法、装置、计算机设备和存储介质 |
CN111063429A (zh) * | 2019-10-25 | 2020-04-24 | 中国科学院自动化研究所 | 一种医疗咨询方法、装置、设备和计算机可读存储介质 |
CN110838368B (zh) * | 2019-11-19 | 2022-11-15 | 广州西思数字科技有限公司 | 一种基于中医临床知识图谱的主动问诊机器人 |
-
2020
- 2020-08-28 CN CN202010886683.0A patent/CN112035674B/zh active Active
-
2021
- 2021-03-31 WO PCT/CN2021/084346 patent/WO2022041722A1/zh active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103164616A (zh) * | 2013-02-02 | 2013-06-19 | 杭州卓健信息科技有限公司 | 一种智能导诊系统和方法 |
US20190385739A1 (en) * | 2017-06-28 | 2019-12-19 | Boe Technology Group Co., Ltd. | Triage dialogue method, device and system |
CN109887587A (zh) * | 2019-01-22 | 2019-06-14 | 平安科技(深圳)有限公司 | 智能分诊方法、系统、装置及存储介质 |
CN110675944A (zh) * | 2019-09-20 | 2020-01-10 | 京东方科技集团股份有限公司 | 分诊方法及装置、计算机设备及介质 |
CN112035674A (zh) * | 2020-08-28 | 2020-12-04 | 康键信息技术(深圳)有限公司 | 导诊数据获取方法、装置、计算机设备和存储介质 |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115274086A (zh) * | 2022-09-27 | 2022-11-01 | 无码科技(杭州)有限公司 | 一种智能导诊方法及系统 |
CN116469542A (zh) * | 2023-04-20 | 2023-07-21 | 智远汇壹(苏州)健康医疗科技有限公司 | 一种个性化医疗影像诊断路径生成系统及方法 |
CN116469542B (zh) * | 2023-04-20 | 2024-01-02 | 智远汇壹(苏州)健康医疗科技有限公司 | 一种个性化医疗影像诊断路径生成系统及方法 |
Also Published As
Publication number | Publication date |
---|---|
CN112035674B (zh) | 2023-05-23 |
CN112035674A (zh) | 2020-12-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2022041722A1 (zh) | 导诊数据获取方法、装置、计算机设备和存储介质 | |
CN108986908B (zh) | 问诊数据处理方法、装置、计算机设备和存储介质 | |
WO2020220545A1 (zh) | 基于长短期记忆模型的疾病预测方法、装置和计算机设备 | |
CN110504028A (zh) | 一种疾病问诊方法、装置、系统、计算机设备和存储介质 | |
CN109036545B (zh) | 医疗信息处理方法、装置、计算机设备和存储介质 | |
CN107766574A (zh) | 数据查询方法及装置、数据存储方法及装置 | |
WO2021159759A1 (zh) | 电子病历结构化方法、装置、计算机设备和存储介质 | |
WO2022267678A1 (zh) | 视频问诊方法、装置、设备及存储介质 | |
CN109065172B (zh) | 病症信息获取方法、装置、计算机设备和存储介质 | |
CN108766545B (zh) | 在线问诊科室分配方法、装置、计算机设备和存储介质 | |
WO2022068160A1 (zh) | 基于人工智能的重症问诊数据识别方法、装置、设备及介质 | |
CN112908473B (zh) | 基于模型的数据处理方法、装置、计算机设备和存储介质 | |
CN112016295A (zh) | 症状数据处理方法、装置、计算机设备及存储介质 | |
CN110797101A (zh) | 医学数据处理方法、装置、可读存储介质和计算机设备 | |
CN112287068A (zh) | 基于人工智能的问诊对话数据处理方法及装置 | |
CN111383754B (zh) | 医疗决策方法、医疗决策装置、电子设备及存储介质 | |
WO2023098291A1 (zh) | 一种数据处理方法及数据处理装置 | |
CN117995340B (zh) | 基于大模型的临床试验智能招募方法及装置 | |
CN116741368A (zh) | 一种医用诊疗系统完善优化系统 | |
CN112035611A (zh) | 目标用户推荐方法、装置、计算机设备和存储介质 | |
Wang et al. | TWIN-GPT: digital twins for clinical trials via large language model | |
CN113724899A (zh) | 一种基于人工智能的线上问诊方法、装置、设备及介质 | |
CN116741331A (zh) | 诊断信息生成方法、装置、存储介质及计算机设备 | |
CN111415760B (zh) | 医生推荐方法、系统、计算机设备及存储介质 | |
CN112035619A (zh) | 基于人工智能的医疗问诊单筛选方法、装置、设备和介质 |
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: 21859571 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 06.06.2023) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21859571 Country of ref document: EP Kind code of ref document: A1 |