CN114864098A - Data mining system, method and device - Google Patents
Data mining system, method and device Download PDFInfo
- Publication number
- CN114864098A CN114864098A CN202210596907.3A CN202210596907A CN114864098A CN 114864098 A CN114864098 A CN 114864098A CN 202210596907 A CN202210596907 A CN 202210596907A CN 114864098 A CN114864098 A CN 114864098A
- Authority
- CN
- China
- Prior art keywords
- module
- training
- historical
- department
- patient
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- 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
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- 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
Abstract
The invention relates to a data mining method, a data mining system and a related device. The data mining method at least comprises the steps of obtaining historical medical data, training a memory network model and achieving establishment and updating of a department classification model. The establishment and the updating of the department classification model at least comprise the following steps; inputting the historical disease description into a memory network model for training to obtain the probability of the historical disease description corresponding to each department; evaluating the training effect of the memory network model, and judging whether to stop training according to the evaluation result; updating the parameters of the memory network model to carry out the next training when the evaluation result is invalid training; and in the case that the evaluation result is that the training is stopped, generating the department classification model by using the current memory network model.
Description
Technical Field
The invention relates to the technical field of data mining, in particular to a data mining system, method and device.
Background
In current medical services, assigning patients to the correct departments is time consuming and labor intensive, requiring specialized medical personnel as a referrer to assign the corresponding departments to the patients based on the patient's condition profile for each patient. However, most patients in treatment cannot accurately express the disease condition, the disease condition can only be described simply, and the condition that one patient determines to see the correct department after seeing a doctor in a plurality of departments often occurs, so that the treatment is delayed, and even serious patients suffer from life threatening due to wrong treatment direction.
In summary, the present invention provides a data mining system, method and device to solve the problems in the prior art.
Furthermore, on the one hand, due to the differences in understanding to the person skilled in the art; on the other hand, since the applicant has studied a great deal of literature and patents when making the present invention, but the disclosure is not limited thereto and the details and contents thereof are not listed in detail, it is by no means the present invention has these prior art features, but the present invention has all the features of the prior art, and the applicant reserves the right to increase the related prior art in the background.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a data mining method. The data mining method at least comprises the steps of obtaining historical medical data, training a memory network model and achieving establishment and updating of a department classification model. The establishment and the updating of the department classification model at least comprise the following steps: inputting the historical disease description into a memory network model for training to obtain the probability of the historical disease description corresponding to each department; evaluating the training effect of the memory network model, and judging whether to stop training according to the evaluation result; under the condition that the evaluation result is invalid training, judging that the evaluation result is retraining, and updating the parameters of the memory network model to carry out next training; and under the condition that the evaluation result is good training, stopping training and generating the department classification model by using the current memory network model.
According to a preferred embodiment, the data mining method obtains and aggregates historical medical data. The historical medical data includes historical disease descriptions and corresponding historical departments. And training a memory network model according to the historical medical data by the data mining method to obtain the department classification model.
According to a preferred embodiment, the data mining method is used for obtaining the patient condition description according to medical term expression by guiding the patient to click on preset entries.
According to a preferred embodiment, the data mining method inputs the patient condition description conforming to the medical term expression into the department classification model to obtain the corresponding department so as to carry out automatic diagnosis of the medical treatment of the patient.
According to a preferred embodiment, the department classification model establishes a word bank of disease descriptions between historical disease descriptions and corresponding historical departments by training historical medical data. The disease condition description word bank can provide lexical data support for guidance of the patient by the data mining method, so that preset entries clicked by the patient for expressing the purpose of self medical treatment conform to medical terms.
According to a preferred embodiment, a data mining method acquires a non-medical-terminology description of a patient's condition and maps the non-medical-terminology description with the medical-terminology description of the same condition. In the case where the patient is directed to click on a preset entry to describe the patient's condition, the preset entry provided to the patient for the same condition data mining method includes a non-medical terminology description and/or a medical terminology description. In the case where a patient clicks on a non-medical and/or medical glossary description, the data mining method transmits the corresponding medical glossary description to the department classification model to determine the patient visit department. Preferably, the non-medical terminology term can be readily understood by the patient in directing the patient to describe his or her condition. Preferably, in the case that the patient clicks the non-medical terminology description and/or the medical terminology description, the data mining method only transmits the corresponding medical terminology description to the department classification model, and compared with the way that both the non-medical terminology description and the medical terminology description are transmitted to the department classification model for processing, the data mining method can effectively reduce the amount of processed data, thereby improving the processing efficiency of the department classification model, and the accuracy of the classification result of the department classification model can be increased by adopting the medical terminology description.
According to a preferred embodiment, the data mining method classifies the patient's medical objectives into a category of objectives requiring professional medical personnel to participate and a category of objectives not requiring professional medical personnel to participate based on whether the patient's medical objectives are achieved by requiring professional medical personnel to participate. Under the condition that the medical purpose of the patient is a class purpose, the data mining method obtains the disease description of the patient by guiding the patient to click a preset entry, and inputs the disease description of the patient into a department classification model to obtain a corresponding department.
The invention also provides a data mining device. The data mining device at least comprises: the device comprises a training module, an evaluation module, an adjustment module, a generation module, a storage module and a transmission module. And the training module is used for inputting the historical disease description into a memory network model for training to obtain the probability of the historical disease description corresponding to each department. And the evaluation module is used for evaluating the training effect of the training module and judging whether to stop training according to the evaluation result. And the adjusting module is used for updating the parameters of the memory network model to perform the next training under the condition that the evaluation module judges that the result is retraining. And the generating module is used for generating a department classification model from the current memory network model under the condition that the evaluation module judges that the training is stopped. The storage module is used for storing historical medical data. And the transmission module is used for sending the disease description of the patient to the department classification model and returning the classification result of the department classification model.
The invention also provides a data mining system. The system at least comprises a user terminal, a medical terminal and a server. The client can acquire the disease description of the patient and upload the disease description to the server. The medical end can upload historical medical data to the server. Preferably, the historical medical data includes historical disease descriptions and corresponding historical departments. The server establishes a department classification model based on the historical medical data and inputs the disease description into the department classification model to determine a corresponding department. The server includes at least: the device comprises a training module, an evaluation module, an adjustment module, a generation module, a storage module and a transmission module. The training module is used for inputting the historical disease description into the memory network model to obtain the probability of the historical disease description corresponding to each department. And the evaluation module is used for evaluating the training effect of the training module and judging whether to stop training according to the evaluation result. And the adjusting module is used for updating the parameters of the memory network model to perform the next training when the evaluation result of the evaluation module is invalid training. And the generating module is used for generating the department classification model from the current memory network model under the condition that the evaluation module judges that the training is stopped. The storage module is used for storing the historical medical data uploaded by the medical end. And the transmission module is used for sending the disease description of the patient to the department classification model and returning the classification result of the department classification model to the user side.
Preferably, the department classification model is established by retrieving historical medical data stored in the storage module and inputting historical disease descriptions in the historical medical data into the memory network model for training to obtain the probability that the historical disease descriptions correspond to each department. Preferably, the evaluation module evaluates the training results of the training module based on a historian corresponding to a historical disease description. Preferably, the evaluation module determines whether to stop training according to the evaluation result. Preferably, the evaluation result of the evaluation module comprises good training, effective training and ineffective training, and the corresponding judgment result is stopping training, continuing training and retraining. And in the case that the evaluation module judges that the training is stopped, the generation module generates the department classification model by using the current memory network model. And under the condition that the evaluation module judges that the training is stopped, the adjusting module updates the parameters of the memory network model to carry out the next training, the steps are repeated until the evaluation module judges that the training is stopped, and the generating module generates the determined memory network model into the department classification model.
Preferably, the evaluation module arranges the departments in the training result in descending order according to the probability value. Preferably, when the department with the highest probability in the training results is the same as the historical department corresponding to the historical disease description, the evaluation result of the evaluation module is passed, and the judgment result is that the training is stopped. Preferably, when the probability of the historical department corresponding to the historical disease description in the training result is not the highest, but is three before the probability values of the departments are sorted in a descending order, the sum of the three probabilities is not lower than half of the total probability, the probability values are sorted in a descending order, the ratio of the probability values of the last item to the probability value of the last item is not lower than three quarters, the evaluation result of the evaluation module is retraining, and the judgment result is continuous training. Preferably, when the training result does not satisfy the two aforementioned conditions, the evaluation result of the evaluation module is invalid training, and the determination result is retraining. Preferably, when the evaluation result of the evaluation module is retraining and the determination result is continuing training, the training module continues training without changing the parameters of the memory network model until the evaluation module determines that the training is stopped, and the generation module generates the determined memory network model into the department classification model.
According to a preferred embodiment, the user terminal may be a kiosk provided in a hospital. Preferably, the user side may include an interaction module, a processing module, a database module, and a communication module. Preferably, the interaction module is capable of guiding a patient to log in and/or register to the user terminal to obtain patient data including patient hospitalization purposes and to send the patient data to the server. Preferably, the interaction module is capable of describing the condition of the patient by a preset entry clicked by the patient. Preferably, medical staff, scientific research institutions and the like collect the non-medical terminology description of the patient on the disease condition, and store the non-medical terminology description of the same disease condition and the medical terminology description in the database module after establishing a mapping relationship. Preferably, the department classification model establishes a disease description word bank by training historical medical data and historical disease descriptions and corresponding historical departments. The disease condition description word bank can provide lexical data support for guidance of the patient by the data mining method, so that preset entries clicked by the patient for expressing the purpose of self medical treatment conform to medical terms.
Preferably, in the case of directing the patient to click on a preset entry to describe the patient condition, the preset entry provided by the interaction module to the patient for the same condition comprises a non-medical glossary description and/or a medical glossary description. In case the patient clicks on the non-medical and/or medical glossary description, the processing module transmits the corresponding medical glossary description to the server through the communication module to determine the patient visit department. Preferably, the transmission module of the server transmits the corresponding medical terminology description to the department classification model to obtain a classification result, and returns the classification result of the department classification model to the user terminal.
Preferably, the non-medical terminology term can be readily understood by the patient in directing the patient to describe his or her condition. Preferably, in the case that the patient clicks the non-medical terminology description and/or the medical terminology description, the user terminal only transmits the corresponding medical terminology description to the department classification model, and compared with the way that both the non-medical terminology description and the medical terminology description are transmitted to the department classification model for processing, the data processing amount can be effectively reduced, so that the processing efficiency of the department classification model is improved, and the accuracy of the classification result of the department classification model can be increased by using the medical terminology description.
Preferably, in response to the receiving of the classification result, the user terminal generates a visit navigation video by combining the classification result and pre-stored structural data of the hospital. Preferably, the communication module establishes a data transmission channel with the transmission module, so as to transmit data between the user side and the server. Preferably, the classification result of the department classification model at least comprises one target department. In response to receipt of the classification result, the processing module generates a patient travel route and models a portion of a model corresponding to the hospital for the patient travel route in conjunction with pre-stored structural data of the hospital in a database module. Preferably, the local model modeled by the processing module can be sent to an intelligent terminal carried by the patient in a video streaming way. The intelligent terminal can receive the video stream in a mode of pairing with a user side.
Preferably, the data mining system provided by the invention can also update the department classification model. The updating of the department classification model is carried out in a way that medical staff, scientific research institutions and the like upload medical data as new historical medical data to a server through a medical end, so that the historical medical data in the storage module are updated. The training module calls the medical data of the new history stored in the storage module and inputs the historical disease description in the medical data of the new history into the memory network model for training to obtain the probability that the historical disease description corresponds to each department. The evaluation module evaluates the training results of the training module based on a historian corresponding to the historical condition description. And under the condition that the evaluation module judges that the training is stopped, the generation module generates the department classification model by using the current memory network model so as to finish the updating of the department classification model.
Drawings
FIG. 1 is a simplified schematic diagram of a data mining system in accordance with a preferred embodiment of the present invention;
FIG. 2 is a simplified schematic diagram of a server in accordance with a preferred embodiment of the present invention;
fig. 3 is a simplified schematic diagram of a user terminal according to a preferred embodiment of the present invention;
fig. 4 is a conceptual diagram of a user side (kiosk) according to a preferred embodiment of the present invention.
List of reference numerals
100: a data mining system; 110: a user side; 111: an interaction module; 112: a processing module; 113: a database module; 114: a communication module; 120: a medical end; 130: a server; 131: a training module; 132: an evaluation module; 133: an adjustment module; 134: a generation module; 135: a storage module; 136: and a transmission module.
Detailed Description
The following detailed description is made with reference to fig. 1 to 3. The invention provides a data mining method, a data mining system and a related device. The invention generates a department classification model based on a large amount of historical medical data. The invention converts the non-medical term disease description of the patient into the disease description conforming to the medical term when the patient visits, and processes the disease description of the patient through the department classification model to determine the visiting department, thereby realizing automatic triage.
According to the invention, through data mining on historical medical data, the non-medical-term disease description of the patient is converted into the disease description conforming to medical terms, so that the problem of wrong treatment departments and treatment directions caused by wrong description of the disease is avoided.
Example 1
The present invention also provides a data mining system 100. Referring to fig. 1, the data mining system 100 preferably includes at least a user terminal 110, a medical terminal 120, and a server 130. The client 110 can obtain the patient's disease description and upload it to the server 130. The medical tip 120 can upload historical medical data to the server 130. Preferably, the historical medical data includes historical disease descriptions and corresponding historical departments. Server 130 builds a department classification model based on the historical medical data and inputs the disease description into the department classification model to determine the corresponding department.
Referring to fig. 2, the server 130 includes at least: training module 131, evaluation module 132, adjustment module 133, generation module 134, storage module 135, and transmission module 136. The training module 131 is configured to input the historical disease description into the memory network model, so as to obtain the probability that the historical disease description corresponds to each department. And an evaluation module 132 for evaluating the training effect of the training module 131 and determining whether to stop training according to the evaluation result. And an adjusting module 133, configured to update the parameters of the memory network model to perform the next training when the evaluation result of the evaluating module 132 is invalid training. And a generating module 134, configured to generate a department classification model from the current memory network model if the evaluating module 132 determines that the training is stopped. The storage module 135 is used for storing the historical medical data uploaded by the medical terminal 120. The transmission module 136 sends the disease description of the patient to the department classification model, and returns the classification result of the department classification model to the user terminal 110.
Preferably, the department classification model is established by retrieving historical medical data stored in the storage module 135 and inputting historical disease descriptions in the historical medical data into the memory network model for training, so as to obtain the probability that the historical disease descriptions correspond to each department. Preferably, the evaluation module 132 evaluates the training results of the training module 131 based on the historian corresponding to the historical disease description. Preferably, the evaluation module 132 determines whether to stop training according to the evaluation result. Preferably, the evaluation results of the evaluation module 132 include good training, valid training, and invalid training, and the corresponding determination results are stop training, continuation training, and retraining. In the case where the evaluation module 132 determines that the training is stopped, the generation module 134 generates a department classification model from the current memory network model. In the case that the evaluation module 132 determines that the training is to be stopped, the adjusting module 133 updates the parameters of the memory network model for the next training, repeats the above steps until the evaluation module 132 determines that the training is to be stopped, and the generating module 134 generates the determined memory network model into the department classification model.
Preferably, the evaluation module 132 ranks the departments in the training result in descending order of the probability value. Preferably, when the department with the highest probability in the training result is the same as the historical department corresponding to the historical disease description, the evaluation result of the evaluation module 132 is passed, and the training is stopped as the determination result. Preferably, when the probability of the historical department corresponding to the historical disease description in the training result is not the highest, but is three before the descending order of the probability values of the departments, the sum of the three probabilities is not lower than half of the total probability, the probability values are three before the descending order, and the ratio of the probability value of the latter item to the probability value of the former item is not lower than three fourths, the evaluation result of the evaluation module 132 is retraining, and the determination result is continuous training. Preferably, when the training result does not satisfy the two situations, the evaluation result of the evaluation module 132 is invalid training, and the determination result is retraining. Preferably, when the evaluation result of the evaluation module 132 is retraining and the determination result is continuing training, the training module 131 continues training without changing the parameters of the memory network model until the evaluation module 132 determines that the training is stopped, and the generation module 134 generates the determined memory network model into the department classification model.
Preferably, the user terminal 110 may be a kiosk provided in a hospital. Referring to fig. 3, the user terminal 110 may preferably include an interaction module 111, a processing module 112, a database module 113, and a communication module 114. Preferably, the interaction module 111 is capable of guiding the patient to log in and/or register to the user terminal 110 to obtain patient data including the purpose of the patient's hospitalization and to send the patient data to the server 130. Preferably, the interaction module 111 is capable of describing the patient condition by a preset entry clicked by the patient. Preferably, medical personnel, scientific research institutions, etc. collect non-medical terminology descriptions of patients for medical conditions and store the non-medical terminology descriptions of the same medical conditions in the database module 113 after mapping the non-medical terminology descriptions to the medical terminology descriptions. Preferably, the department classification model establishes a word bank of disease descriptions between historical disease descriptions and corresponding historical departments by training historical medical data. The disease condition description word bank can provide lexical data support for guidance of a patient by a data mining method, so that preset entries clicked by the patient for expressing the purpose of self medical treatment conform to medical terms.
Preferably, in the case of directing the patient to click on a preset entry to describe the patient condition, the preset entry provided by the interaction module 111 to the patient for the same condition includes a non-medical terminology description and/or a medical terminology description. In the event that the patient clicks on a non-medical and/or medical terminology description, the processing module 112 transmits the corresponding medical terminology description to the server 130 through the communication module 114 to determine the patient visit department. Preferably, the transmission module 136 of the server 130 transmits the corresponding medical terminology description to the department classification model to obtain a classification result, and returns the classification result of the department classification model to the user terminal 110.
Preferably, the non-medical terminology term can be readily understood by the patient in directing the patient to describe his or her condition. Preferably, in the case that the patient clicks the non-medical terminology description and/or the medical terminology description, the user terminal 110 only transmits the corresponding medical terminology description to the department classification model, and compared with the way that both the non-medical terminology description and the medical terminology description are transmitted to the department classification model for processing, the data amount for processing can be effectively reduced, so that the processing efficiency of the department classification model is improved, and the accuracy of the classification result of the department classification model can be increased by using the medical terminology description.
Preferably, in response to the receiving of the classification result, the user terminal 110 generates a visit navigation video by combining the classification result with the pre-stored structural data of the hospital. Preferably, the communication module 114 establishes a data transmission channel with the transmission module 136, so as to transmit data between the user terminal 110 and the server 130. Preferably, the classification result of the department classification model comprises at least one target department. In response to receipt of the classification results, the processing module 112, in conjunction with pre-stored structural data of the hospital in the database module 113, generates a patient travel route and models a portion of a model corresponding to the hospital for the patient travel route. Preferably, the local model modeled by the processing module 112 can be sent in a video stream to a smart terminal carried by the patient person. The intelligent terminal can receive the video stream by pairing with the user terminal 110.
Preferably, the user terminal 110 is capable of generating a visit route for the corresponding patient according to the target location (corresponding department address), the starting location (where the user terminal 110 is located), and the viewing direction of the corresponding patient in response to the receipt by the destination department. The treatment routes for the respective patients are formed in such a way that the processing module 112 generates an initial treatment route from the target location, starting position and viewing direction of the respective patient in combination with the hospital structure data stored by the database module 113. In response to the generation of the initial visiting route, the user terminal 110 connects to the hospital monitoring network to acquire the road conditions of each node on the initial visiting route, and corrects the error on the initial visiting route to generate a final visiting route. In the case where the hospital temporarily closes an area on the initial visit route, the user terminal 110 will perform a re-planning process through the closed route to preferentially guide the patient to the temporarily opened channel of the hospital administration.
Preferably, the user end 110 can obtain the self-position data through the configured positioning unit, and then obtain the starting point position and the viewing direction of the corresponding patient by mirroring the self-position data. The starting position and the viewing direction of the corresponding patient are determined in such a way that the user terminal 110 performs position detection by using the positioning unit to determine the current position and the orientation of the user terminal, the viewing direction and the positioning of the current patient of the user terminal 110 are determined after the current position and the orientation of the user terminal are mirrored along the display side, and the starting position and the viewing direction of the patient in the corresponding local model are determined according to the viewing direction and the positioning of the current patient and the hospital structure data.
Preferably, the user terminal 110 can generate an virtual character in the generated virtual model. Preferably, the starting position and the viewing direction of the avatar are determined by the user end 110 determining the viewing direction and the location of the current patient of the user end 110 according to the current position and orientation of the user end 110 and providing the viewing direction and the location to the user end 110 and determining the starting position and the viewing direction of the corresponding avatar by the user end 110, so that the starting position and the viewing direction of the corresponding avatar are the same as the actual position and the viewing direction of the current patient of the user end 110 and the patient can substitute the model into reality.
The user terminal 110 can prompt the corresponding patient to select his or her personalized avatar by providing voice prompt to the patient using the user terminal 110 through the interactive module 111, and determine the current position and orientation of the patient through the positioning function of the intelligent terminal and thus determine the starting position and viewing direction of the avatar selected by the patient, thereby ensuring that the position and viewing direction of the avatar selected by the patient are consistent with the actual position and viewing direction of the patient.
When the corresponding local model for determining the starting point position and the visual direction of the patient is displayed to the patient in a video mode, the patient can determine the characteristic reference object on the navigation path in the navigation model by adjusting the visual angle of the corresponding virtual character image based on the movement of the virtual character corresponding to the actual position and the visual direction of the patient in the virtual model. When the patient sees the doctor route through operation user terminal 110 and the doctor route of at least another patient and intersects, the virtual character image corresponding to the current patient will appear in the navigation video which is generated by another patient through operation user terminal 110 and is sent to the intelligent terminal for determining the starting position and viewing direction of the patient, so that the real people flow condition of the corresponding region is reflected in the local model.
Preferably, the data mining system 100 provided by the present invention is also capable of updating the department classification model. The updating of the department classification model is performed by uploading medical data as new historical medical data to the server 130 through the medical terminal 120 by medical staff, scientific research institutions and the like, so as to update the historical medical data in the storage module 135. The training module 131 retrieves the medical data of the new history stored in the storage module 135, and inputs the historical disease description in the medical data of the new history into the memory network model for training, so as to obtain the probability that the historical disease description corresponds to each department. The evaluation module 132 evaluates the training results of the training module 131 based on the historian corresponding to the historical disease description. In the case that the evaluation module 132 determines that the training is stopped, the generation module 134 generates the department classification model from the current memory network model, thereby completing the updating of the department classification model.
Example 2
This embodiment is a further improvement of embodiment 1, and repeated contents are not described again.
The embodiment provides a data mining method. The data mining method at least comprises the steps of obtaining historical medical data, training a memory network model and achieving establishment and updating of a department classification model. The establishment and the updating of the department classification model at least comprise the following steps: inputting the historical disease description into a memory network model for training to obtain the probability of the historical disease description corresponding to each department; evaluating the training effect of the memory network model, and judging whether to stop training according to the evaluation result; under the condition that the evaluation result is invalid training, judging that the evaluation result is retraining, and updating the parameters of the memory network model to carry out next training; and when the evaluation result is good training, stopping training and generating a department classification model from the current memory network model.
Preferably, the data mining method obtains and aggregates historical medical data. The historical medical data includes historical disease descriptions and corresponding historical departments. The data mining method trains the memory network model according to historical medical data to obtain a department classification model.
Preferably, the data mining method obtains the patient condition description conforming to the medical term expression by guiding the patient to click on a preset entry.
Preferably, the data mining method inputs the patient condition description conforming to the medical term expression into the department classification model to obtain the corresponding department, so as to perform automatic triage of the patient for medical treatment.
Preferably, the department classification model establishes a word bank of disease descriptions between historical disease descriptions and corresponding historical departments by training historical medical data. The disease condition description word bank can provide lexical data support for guidance of a patient by a data mining method, so that preset entries clicked by the patient for expressing the purpose of self medical treatment conform to medical terms.
Preferably, the data mining method collects a non-medical-terminology description of a patient's condition and maps the non-medical-terminology description with the medical-terminology description of the same condition. In the case where the patient is directed to click on a preset entry to describe the patient's condition, the preset entry provided to the patient for the same condition data mining method includes a non-medical terminology description and/or a medical terminology description. In the case where the patient clicks on a non-medical and/or medical glossary description, the data mining method transmits the corresponding medical glossary description to the department classification model to determine the patient visit department. Preferably, the non-medical terminology term can be readily understood by the patient in directing the patient to describe his or her condition. Preferably, in the case that the patient clicks the non-medical terminology description and/or the medical terminology description, the data mining method only transmits the corresponding medical terminology description to the department classification model, and compared with the way that the non-medical terminology description and the medical terminology description are both transmitted to the department classification model for processing, the data mining method can effectively reduce the processing data amount, thereby improving the processing efficiency of the department classification model, and the accuracy of the classification result of the department classification model can be increased by adopting the medical terminology description.
Preferably, the data mining method classifies the medical purpose of the patient into a first type of purpose requiring the medical professional to participate and a second type of purpose requiring no medical professional to participate according to whether the medical purpose of the patient needs to participate. Under the condition that the medical purpose of the patient is a first-class purpose, the data mining method obtains the disease description of the patient by guiding the patient to click a preset entry, and inputs the disease description of the patient into a department classification model to obtain a corresponding department.
Example 3
This embodiment is a further improvement on embodiments 1 and 3, and repeated details are not repeated. The embodiment provides a data mining device. The data mining device at least comprises: training module 131, evaluation module 132, adjustment module 133, generation module 134, storage module 135, and transmission module 136. The training module 131 is configured to input the historical disease description into the memory network model for training, so as to obtain probabilities that the historical disease description corresponds to each department. And an evaluation module 132 for evaluating the training effect of the training module 131 and determining whether to stop training according to the evaluation result. And an adjusting module 133, configured to update the parameters of the memory network model to perform the next training when the evaluation module 132 determines that the result is the retraining. And a generating module 134, configured to generate a department classification model from the current memory network model if the evaluating module 132 determines that the training is stopped. A storage module 135 for storing historical medical data. The transmission module 136 sends the disease description of the patient to the department classification model and returns the classification result of the department classification model.
It should be noted that the above-mentioned embodiments are exemplary, and that those skilled in the art, having benefit of the present disclosure, may devise various arrangements that are within the scope of the present disclosure and that fall within the scope of the invention. It should be understood by those skilled in the art that the present specification and figures are illustrative only and are not limiting upon the claims. The scope of the invention is defined by the claims and their equivalents. Throughout this document, the features referred to as "preferably" are only an optional feature and should not be understood as necessarily requiring that such applicant reserves the right to disclaim or delete the associated preferred feature at any time. The present description contains several inventive concepts, such as "preferably", "according to a preferred embodiment" or "optionally", each indicating that the respective paragraph discloses a separate concept, the applicant reserves the right to submit divisional applications according to each inventive concept.
Claims (10)
1. A data mining system, characterized in that the system comprises at least a user terminal (110), a medical terminal (120) and a server (130);
the user terminal (110) can acquire the disease description of the patient and upload the disease description to the server (130); the medical end (120) can upload historical medical data to the server (130); the server (130) building a department classification model based on the historical medical data and inputting the condition description into the department classification model to determine a corresponding department; wherein the historical medical data includes historical disease descriptions and corresponding historical departments.
2. The data mining system of claim 1, wherein the server (130) returns the classification results of the department classification model to the user terminal (110);
in response to receipt of the classification result, the client (110) generates a visit navigation video in combination with the classification result and pre-stored hospital structure data.
3. The data mining system of claim 1 or 2, wherein the server (130) is configured with: a storage module (135) and a transmission module (136);
the storage module (135) is used for storing the historical medical data uploaded by the medical end (120);
the transmission module (136) sends the disease description of the patient to the department classification model and returns the classification result of the department classification model to the user terminal (110).
4. A data mining system according to any one of claims 1 to 3, wherein the server (130) is further configured with: a training module (131), an evaluation module (132), and a generation module (134);
the training module (131) is used for inputting the historical disease description into the memory network model to obtain the probability of the historical disease description corresponding to each department;
the evaluation module (132) is used for evaluating the training effect of the training module (131) and judging whether to stop training according to the evaluation result;
the generating module (134) is used for generating the department classification model from the current memory network model when the evaluation module (132) judges that the training is stopped.
5. The data mining system of any one of claims 1 to 4, wherein the server (130) is further configured with: an adjustment module (133);
the adjusting module (133) is configured to update the parameters of the memory network model for the next training if the evaluating module (132) determines that the result is retraining.
6. The data mining system according to any one of claims 1 to 5, wherein the user terminal (110) comprises at least an interaction module (111); the interaction module (111) is capable of guiding a patient to log in and/or register to the user terminal (110) for obtaining patient data including patient hospitalization purposes and sending the patient data to the server (130); wherein the interaction module (111) can describe the illness condition of the patient through a preset entry clicked by the patient.
7. A data mining device is characterized in that the data mining device respectively establishes data connection with a user terminal (110) and a medical terminal (120), and is characterized in that the user terminal (110) acquires disease condition description of a patient and uploads the disease condition description to the data mining device;
the medical end (120) uploads the historical medical data to the data mining device;
the data mining device establishes a department classification model based on the historical medical data and inputs the disease description into the department classification model to determine a corresponding department; wherein the historical medical data includes historical disease descriptions and corresponding historical departments.
8. The data mining device of claim 9, wherein the data mining device comprises at least: the system comprises a training module (131), an evaluation module (132), an adjustment module (133), a generation module (134), a storage module (135) and a transmission module (136);
the training module (131) is used for inputting the historical disease description into a memory network model for training to obtain the probability of the historical disease description corresponding to each department;
the evaluation module (132) is used for evaluating the training effect of the training module (131) and judging whether to stop training according to the evaluation result;
the adjusting module (133) is configured to update the parameters of the memory network model for the next training if the evaluation module (132) determines that the result is retraining;
the generating module (134) is used for generating a department classification model from the current memory network model when the evaluation module (132) judges that the training is stopped;
the storage module (135) is used for storing historical medical data;
and the transmission module (136) is used for sending the disease description of the patient to the department classification model and returning the classification result of the department classification model.
9. A data mining method, characterized in that the data mining method at least comprises:
the client (110) acquires the disease description of the patient and uploads the disease description to the server (130);
the medical end (120) uploads the historical medical data to the server (130);
the server (130) building a department classification model based on the historical medical data and inputting the condition description into the department classification model to determine a corresponding department; wherein the historical medical data includes historical disease descriptions and corresponding historical departments.
10. The data mining method of claim 9, wherein the establishment and updating of the department classification model comprises at least the steps of:
inputting the historical disease description into a memory network model for training to obtain the probability of the historical disease description corresponding to each department;
evaluating the training effect of the memory network model, and judging whether to stop training according to the evaluation result;
under the condition that the evaluation result is invalid training, judging that the evaluation result is retraining, and updating the parameters of the memory network model to carry out next training;
and under the condition that the evaluation result is good training, stopping training and generating the department classification model by using the current memory network model.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210249268 | 2022-03-14 | ||
| CN2022102492683 | 2022-03-14 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114864098A true CN114864098A (en) | 2022-08-05 |
Family
ID=82571277
Family Applications (6)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210511714.3A Pending CN114864062A (en) | 2022-03-14 | 2022-05-10 | Medical intelligent triage method and triage system |
| CN202210511713.9A Pending CN114898851A (en) | 2022-03-14 | 2022-05-10 | Intelligent diagnosis guiding method and system |
| CN202210547944.5A Pending CN114842952A (en) | 2022-03-14 | 2022-05-17 | Computer-aided triage method and system |
| CN202210541572.5A Pending CN114881337A (en) | 2022-03-14 | 2022-05-17 | One-stop medical self-service system |
| CN202210596907.3A Pending CN114864098A (en) | 2022-03-14 | 2022-05-24 | Data mining system, method and device |
| CN202210572870.0A Pending CN114898854A (en) | 2022-03-14 | 2022-05-24 | Diagnosis guide processing method and system based on artificial intelligence and storage medium |
Family Applications Before (4)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210511714.3A Pending CN114864062A (en) | 2022-03-14 | 2022-05-10 | Medical intelligent triage method and triage system |
| CN202210511713.9A Pending CN114898851A (en) | 2022-03-14 | 2022-05-10 | Intelligent diagnosis guiding method and system |
| CN202210547944.5A Pending CN114842952A (en) | 2022-03-14 | 2022-05-17 | Computer-aided triage method and system |
| CN202210541572.5A Pending CN114881337A (en) | 2022-03-14 | 2022-05-17 | One-stop medical self-service system |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210572870.0A Pending CN114898854A (en) | 2022-03-14 | 2022-05-24 | Diagnosis guide processing method and system based on artificial intelligence and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (6) | CN114864062A (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115762744A (en) * | 2022-12-07 | 2023-03-07 | 江苏鑫亿软件股份有限公司 | Patient integration triage regulation and control system based on medical interconnection platform |
| CN116895371B (en) * | 2023-09-08 | 2024-03-26 | 中国人民解放军空军特色医学中心 | Patient guiding method, system, terminal and storage medium based on general surgery |
| CN116895358B (en) * | 2023-09-11 | 2023-11-28 | 江苏泰德医药有限公司 | Cloud platform-based medical resource intelligent management system and method |
| CN117275692A (en) * | 2023-09-25 | 2023-12-22 | 苏州仲如悦科技有限责任公司 | Medical resource optimal configuration method and system based on big data |
-
2022
- 2022-05-10 CN CN202210511714.3A patent/CN114864062A/en active Pending
- 2022-05-10 CN CN202210511713.9A patent/CN114898851A/en active Pending
- 2022-05-17 CN CN202210547944.5A patent/CN114842952A/en active Pending
- 2022-05-17 CN CN202210541572.5A patent/CN114881337A/en active Pending
- 2022-05-24 CN CN202210596907.3A patent/CN114864098A/en active Pending
- 2022-05-24 CN CN202210572870.0A patent/CN114898854A/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| CN114842952A (en) | 2022-08-02 |
| CN114898851A (en) | 2022-08-12 |
| CN114881337A (en) | 2022-08-09 |
| CN114898854A (en) | 2022-08-12 |
| CN114864062A (en) | 2022-08-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114864098A (en) | Data mining system, method and device | |
| US8195430B2 (en) | Cognitive agent | |
| US20070136068A1 (en) | Multimodal multilingual devices and applications for enhanced goal-interpretation and translation for service providers | |
| KR102202864B1 (en) | User terminal of providing disease prediction information through bid data analysis and artificial intelligence | |
| WO2018221689A1 (en) | Medical information processing system | |
| CN112164451A (en) | Intelligent diagnosis guiding and registering method, device, equipment and storage medium | |
| KR102192953B1 (en) | A system for treating skin damage based on artificial intelligence and providing remote medical service | |
| JP2017224052A (en) | Presentation evaluation device, presentation evaluation system, presentation evaluation program and control method of presentation evaluation device | |
| KR20220025360A (en) | Evolving symptom-disease prediction system for smart healthcare decision support system | |
| KR100415372B1 (en) | System and method for determining the users having the similar registered information on a cyber space | |
| CN114446455A (en) | Diagnosis path analysis and recommendation method applied to hospital | |
| CN114334119B (en) | Intelligent self-service terminal | |
| KR102330148B1 (en) | Method and device for providing inquiry-based hospital recommendation services | |
| CN116705267A (en) | Internet hospital management system and method | |
| CN114822800A (en) | Internet medical triage method and system | |
| CN111741125B (en) | Remote service method and computer equipment based on wide area network | |
| CN114582476A (en) | Intelligent assessment triage system and method based on ANN | |
| CN114566270A (en) | Intelligent medical self-service comprehensive service system | |
| JP7328489B2 (en) | Ophthalmic image processing device and ophthalmic photographing device | |
| US11199417B2 (en) | Distributed system for dynamic sensor-based trip estimation | |
| KR20220060846A (en) | Method for providing pass including QR code and management server for the same | |
| CN116839586A (en) | Diagnosis guiding system and method | |
| CN114360700B (en) | Business self-service machine and business auxiliary method | |
| JP7172915B2 (en) | In-vehicle device, first information processing device, information processing system, and information processing method | |
| CN113380428B (en) | Order processing method, system and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |