CN114566270A

CN114566270A - Intelligent medical self-service comprehensive service system

Info

Publication number: CN114566270A
Application number: CN202210245424.9A
Authority: CN
Inventors: 何晓俊; 邵冠亚
Original assignee: Beijing Rongwei Zhongbang Electronic Technology Co ltd
Current assignee: Beijing Rongwei Zhongbang Electronic Technology Co ltd
Priority date: 2022-03-14
Filing date: 2022-03-14
Publication date: 2022-05-31

Abstract

The invention relates to an intelligent medical self-service comprehensive service system. The self-service comprehensive service system at least comprises a cloud server, a patient end and a medical care end. The patient side can guide a patient to log in and/or register to the self-service comprehensive service system so as to obtain patient data including the purpose of hospitalizing of the patient, and the patient data are sent to the cloud server. The cloud server can respond to the receipt of the patient data, input the patient data into a department classification model to obtain a corresponding department, and send the medical purpose of the patient to the medical end configured by the corresponding department. Medical staff in the corresponding department establishes contact with the corresponding patient through the medical care end to conduct initial diagnosis.

Description

Intelligent medical self-service comprehensive service system

Technical Field

The invention relates to the field of medical services, in particular to an intelligent medical self-service comprehensive service system.

Background

In the current medical service, it is time-consuming and labor-consuming to introduce a patient into the correct department, and a professional medical staff is required to be used as a guide to assign the corresponding department to the patient according to the disease condition description of each patient, and the guide is required to explain the route of the patient to the corresponding department after the department is explained.

In the prior art, patients are introduced into correct departments mainly through manual triage and oral diagnosis guidance of professional medical staff, but due to the fact that the diseases are various, the professional medical staff cannot necessarily distribute the patients to the correct departments, and the cases of the departments for seeing the patients determine the self-illness after seeing the doctor in a plurality of departments often occur. Therefore, the efficiency and accuracy of the manual triage and oral referral by arranging the medical professionals are low, the energy of the medical professionals is consumed, and the waste of medical resources is caused.

In summary, the present invention provides an intelligent medical self-service integrated service system to solve the problems in the prior art.

Furthermore, on the one hand, due to the differences in understanding to those 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 an intelligent medical self-service comprehensive service system. The self-service comprehensive service system at least comprises a cloud server, a patient end and a medical care end. The patient side can guide a patient to log in and/or register to the self-service comprehensive service system so as to obtain patient data including the medical purpose of the patient, and the patient data is sent to the cloud server. The cloud server can respond to the receipt of the patient data, input the patient data into a department classification model to obtain a corresponding department, and send the medical purpose of the patient to the medical end configured by the corresponding department. Medical staff in the corresponding department establishes contact with the corresponding patient through the medical care end to conduct initial diagnosis. Preferably, the invention can guide the patient to click the preset entries through the patient end to obtain the patient hospitalizing purpose according with the medical term expression. The invention inputs the patient data including the patient hospitalizing purpose according with the medical term expression into the department classification model obtained by training a large amount of historical medical data for automatic triage, relieves professional medical care personnel from low-efficiency manual triage work, reduces the waste of medical resources, improves the accuracy of triage, and can effectively avoid the situation that the patient determines the department corresponding to the self disease after hospitalizing in a plurality of departments.

According to a preferred embodiment, the patient end at least comprises a medical purpose inquiry module for obtaining the medical purpose of the patient. The medical purpose inquiry module can classify the medical purpose of the patient into a first purpose needing the medical professional to participate and a second purpose needing no medical professional to participate according to whether the medical purpose of the patient needs the medical professional to participate. When the patient is seeking medical attention for two categories (such as registration, payment, report getting, receipt obtaining and the like), the cloud server responds to the receipt of the patient data, and can not input the patient data including the two categories into the department classification model, but call corresponding subsystems according to the two categories of the patient to achieve the purpose of the patient. Preferably, the subsystems comprise a registration subsystem, a payment subsystem, a reporting subsystem and the like. The cloud server will match the corresponding medical professional for the patient if and only if the patient's medical purpose is one that requires the medical professional to participate. The cloud server executes differentiated processing on the medical purpose of the patient, so that the energy of professional medical staff spent on non-medical affairs such as number assignment, report document printing and the like can be effectively reduced while the requirement of the patient is met, the professional medical staff can put more energy into diagnosis and treatment of the patient, and the medical resources are fully utilized.

According to a preferred embodiment, the cloud server inputs patient data including a category into the department classification model to obtain a corresponding department. The department classification model is established in such a way that the cloud server acquires and summarizes historical medical data. The historical medical data includes historical disease descriptions and corresponding historical departments. And the cloud server trains a memory network model according to the historical medical data to obtain the department classification model. Preferably, the historical medical data comprising the historical disease description and the corresponding historical department is used as the training materials, so that the professional accuracy of the training result can be improved by fully utilizing the historical disease description written by professional medical staff by using terms.

According to a preferred embodiment, the cloud server is provided with a department classification model establishing module. The department classification model establishing module trains a memory network model by acquiring historical medical data to realize establishment and update of the department classification model. The department classification model establishing module can establish the department classification model with high professional accuracy by acquiring historical medical data and can realize continuous learning along with the continuous increase of the historical medical data, thereby realizing the continuous expansion of case and disease condition data.

According to a preferred embodiment, the department classification model building module specifically includes: the device comprises a training execution unit, a training evaluation unit, a training adjustment unit and a model generation unit. And the training execution unit is used for inputting 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 the training evaluation unit is used for evaluating the training effect of the training execution unit and judging whether to stop training according to the evaluation result. Preferably, when the department with the highest probability obtained by the training execution unit is the same as the historical department corresponding to the historical disease description, the evaluation result is passed, and the training is stopped as the judgment result. Training the evaluation result of the evaluation unit further comprises retraining. And when the probability obtained by the historical department corresponding to the historical disease description after training is not the highest, but is three before the probability descending order of each department, and the sum of the three probabilities is not lower than 90%, and in addition, after the three descending order, the ratio of the probability value of the next item to the probability value of the previous item is not lower than 0.8, the evaluation result is retraining, and the judgment result is continuous training. And when the evaluation result of the training evaluation unit is retraining, the training execution unit continues to execute the training without adjusting the parameters of the memory network model until the evaluation result is passed. And when the probability obtained after the training is executed by the historical department corresponding to the historical disease description does not meet the passed evaluation condition or the retraining evaluation condition, the evaluation result is invalid training, and the judgment result is retraining. And the training adjusting unit is used for updating the parameters of the memory network model to carry out the next training when the evaluation result of the training evaluation unit is invalid training. And the model generation unit is used for generating the department classification model from the current memory network model when the training evaluation unit judges that the training is stopped. Preferably, the department classification model building module strictly trains historical medical data to enable historical illness descriptions and corresponding historical departments to build an illness description word bank. Preferably, the department classification model generated by the department classification model building module can be used for obtaining a department matched with the medical purpose of the patient by analyzing the received patient data. Preferably, the disease description lexicon established by the department classification model establishing module in the training process can provide lexical data support for the patient's guidance, so that the preset entries clicked by the patient for expressing the purpose of self medical care conform to the medical terms.

According to a preferred embodiment, the medical staff can set address data including at least one location through the medical end according to the initial diagnosis result and transmit the address data to the cloud server and/or the patient end to generate a patient travel route. Preferably, in a case that the cloud server sends the purpose of seeking medical services of the patient to the medical care end configured in the corresponding department, the medical staff in the corresponding department can establish contact with the corresponding patient through the medical care end to perform remote initial diagnosis and/or consultation. Preferably, after the initial diagnosis is finished, for a patient needing a face diagnosis, the medical staff transmits the face diagnosis address data to the cloud server or the patient end through the medical end to generate a patient traveling route so as to guide the patient to go to a corresponding department for diagnosis.

According to a preferred embodiment, the patient end can comprise a self-service machine arranged in the hospital and an intelligent terminal carried by the patient. In the event that a patient logs in and/or registers with a self-service integrated services system through a kiosk, the kiosk generates a patient travel route and models a portion of a model corresponding to a hospital for the patient travel route. Under the condition that a patient logs in and/or registers to a self-service comprehensive service system through an intelligent terminal carried by the patient, the patient traveling route is generated by the cloud server and a corresponding local model is modeled. If and only if the patient end is a self-service machine arranged in the hospital, the medical staff can send the address data of the face diagnosis to the patient end, namely the self-service machine. When the patient end is a private device such as an intelligent terminal carried by the patient, the medical staff sends the address data of the face examination to the cloud server.

According to a preferred embodiment, the local model corresponding to the patient travel route is sent to the intelligent terminal carried by the patient in a video stream mode. The intelligent terminal can receive the video stream in a matching mode with the self-service machine. The intelligent terminal carried by the patient can display the local model at any time after receiving the video stream of the corresponding local model, thereby providing route navigation for the patient. Preferably, after the patient enters the hospital, especially in case of interference of communication signals, the patient can go to the destination by viewing the navigation video on the intelligent terminal.

According to a preferred embodiment, the cloud server can read the position information of the intelligent terminal when the patient logs in and/or registers to the self-service comprehensive service system through the intelligent terminal. In response to receipt of the location information, the self-service integrated services system performs a differencing operation for the respective patient to form a local model that matches the patient location. Preferably, when the position information of the intelligent terminal shows that the intelligent terminal is located in the hospital position range, namely, the patient is located in the hospital position range, the intelligent terminal prompts the patient to go to a self-service machine to obtain the local model, so that the video navigation can still be obtained under the condition that the intelligent terminal cannot smoothly receive the local model video stream generated by the cloud server due to the blockage of the communication signal.

According to a preferred embodiment, the cloud server can access a public map database, a local model generated and modeled by the cloud server is matched with a public map, and the intelligent terminal is switched from public map navigation to video navigation under the condition that a patient logs in and/or registers to a self-service comprehensive service system through the intelligent terminal and navigates to a hospital entrance along the public map by using the intelligent terminal.

Drawings

FIG. 1 is a simplified schematic diagram of a preferred embodiment provided by the present invention;

FIG. 2 is a schematic diagram of a communication relationship of a patient logging and/or registering with a self-service integrated services system via a smart terminal;

FIG. 3 is a schematic diagram of a communication relationship of a patient logging and/or registering with a self-service integrated services system through a kiosk.

List of reference numerals

100: a self-service integrated service system; 110: a cloud server; 120: a patient end; 121: a self-service machine; 122: an intelligent terminal; 130: a medical care end.

Detailed Description

The following detailed description is made with reference to fig. 1 to 3.

The intelligent medical self-service comprehensive service system provided by the invention can be used for guiding the patient to click the preset entries so as to obtain the purpose of seeking medical treatment of the patient according with medical term expression. The invention inputs the patient data including the medical purpose of the patient according with the medical term expression into a department classification model obtained by training a large amount of historical medical data for automatic triage.

Example 1

The invention provides an intelligent medical self-service comprehensive service system 100. Referring to fig. 1, the self-service integrated service system 100 includes at least a cloud server 110, a patient end 120, and a healthcare end 130. The patient end 120 can direct the patient to log in and/or register with the self-service integrated services system 100 to obtain patient data, including patient hospitalization purposes, and send the patient data to the cloud server 110. The cloud server 110 may, in response to receiving the patient data, input the patient data into the department classification model to obtain a corresponding department, and send the medical purpose of the patient to the medical care end 130 configured in the corresponding department. Medical staff in the corresponding department establishes contact with the corresponding patient through the medical care terminal 130 to perform a preliminary diagnosis. Preferably, the present invention can guide the patient to click on the preset entries through the patient end 120 to achieve the objective of seeking medical advice for the patient in compliance with the medical terminology expression. The invention inputs the patient data including the patient hospitalizing purpose according with the medical term expression into the department classification model obtained by training a large amount of historical medical data for automatic triage, relieves professional medical staff from low-efficiency manual triage work, improves the accuracy of triage while reducing medical resource waste, and can effectively avoid the occurrence of the condition that the patient determines the department corresponding to the self disease after hospitalizing in a plurality of departments.

Preferably, the patient end 120 includes at least a medical purpose query module for obtaining medical purposes for the patient. The medical purpose inquiry module can classify the medical purpose of the patient into a first purpose needing the medical professional to participate and a second purpose needing no medical professional to participate according to whether the medical purpose of the patient needs the medical professional to participate. When the patient is seeking medical attention for two categories (e.g., the patient registers, pays a fee, receives a report, obtains a receipt, etc.), the cloud server 110 may not input the patient data including the two categories into the department classification model in response to the receipt of the patient data, but call corresponding subsystems according to the two categories of the patient to achieve the purpose of the patient. Preferably, the subsystems comprise a registration subsystem, a payment subsystem, a reporting subsystem and the like. The cloud server 110 will match the medical professional to the patient if and only if the patient's medical purpose is of a type that requires the medical professional to participate. The cloud server 110 performs differentiated processing on the medical purpose of the patient, so that the energy of professional medical staff spent on non-medical matters such as number assignment and report document printing can be effectively reduced while the requirement of the patient is met, and the professional medical staff can put more energy into diagnosis and treatment of the patient, so that the medical resources are fully utilized.

Preferably, the cloud server 110 inputs the patient data including a category into the department classification model to obtain the corresponding department. The department classification model is built in such a way that the cloud server 110 acquires and aggregates historical medical data. The historical medical data includes historical disease descriptions and corresponding historical departments. The cloud server 110 trains the memory network model according to the historical medical data to obtain a department classification model. Preferably, the historical medical data comprising the historical disease description and the corresponding historical department is used as the training materials, so that the professional accuracy of the training result can be improved by fully utilizing the historical disease description written by professional medical staff by using terms.

Preferably, the cloud server 110 is provided with a department classification model building module. The department classification model establishing module trains the memory network model by acquiring historical medical data to realize establishment and update of the department classification model. The department classification model building module can build a department classification model with high professional accuracy by acquiring historical medical data and can realize continuous learning along with the continuous increase of the historical medical data, so that the continuous expansion of case and disease condition data is realized.

Preferably, the department classification model establishing module specifically includes: the device comprises a training execution unit, a training evaluation unit, a training adjustment unit and a model generation unit. And the training execution unit 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 training evaluation unit is used for evaluating the training effect of the training execution unit and judging whether to stop training according to the evaluation result. Preferably, when the department with the highest probability obtained by the training execution unit is the same as the historical department corresponding to the historical disease description, the evaluation result is passed, and the training is stopped as the judgment result. Training the evaluation result of the evaluation unit further comprises retraining. And when the probability obtained by the historical department corresponding to the historical disease description after training is not the highest, but is three before the probability descending order of each department, and the sum of the three probabilities is not lower than 90%, and in addition, after the three descending order, the ratio of the probability value of the next item to the probability value of the previous item is not lower than 0.8, the evaluation result is retraining, and the judgment result is continuous training. And under the condition that the evaluation result of the training evaluation unit is retraining, the training execution unit continues to execute training under the condition of not adjusting the parameters of the memory network model until the evaluation result is passed. And when the probability obtained after the training is executed by the historical department corresponding to the historical disease description does not meet the passed evaluation condition or the retraining evaluation condition, the evaluation result is invalid training, and the judgment result is retraining. And the training adjusting unit is used for updating the parameters of the memory network model to carry out the next training when the evaluation result of the training evaluation unit is invalid training. And the model generation unit is used for generating a department classification model from the current memory network model when the training evaluation unit judges that the training is stopped. Preferably, the department classification model building module strictly trains historical medical data to enable historical disease descriptions to be matched with corresponding historical departments, and a disease description word bank is built. Preferably, the department classification model generated by the department classification model building module can be used for analyzing the received patient data to obtain a department matched with the medical purpose of the patient. Preferably, the disease description lexicon established by the department classification model establishing module during the training process can provide lexical data support for the patient guidance of the patient end 120, so that the preset entries clicked by the patient for expressing the purpose of self medical care conform to the medical terms.

Preferably, the medical staff can set address data including at least one location through the medical care end 130 according to the initial diagnosis result and transmit the address data to the cloud server 110 and/or the patient end 120 to generate the patient travel route. Preferably, in the case that the cloud server 110 transmits the purpose of the patient to the medical care end 130 configured in the corresponding department, the medical staff in the corresponding department can establish contact with the corresponding patient through the medical care end 130 to perform remote preliminary diagnosis and/or consultation. Preferably, after the initial diagnosis is finished, for the patient to be subjected to the face-diagnosis, the medical staff transmits the face-diagnosis address data to the cloud server 110 or the patient end 120 through the medical care end 130 to generate a patient traveling route so as to guide the patient to go to a corresponding department for a diagnosis.

Preferably, the patient end 120 may include a kiosk 121 disposed inside the hospital and an intelligent terminal 122 that the patient personally carries with him. Preferably, the smart terminal 122 may include a smart phone, a smart band, a tablet computer, and the like. In the event that a patient logs in and/or registers with the self-service integrated services system 100 through the kiosk 121, the kiosk 121 generates a patient travel route and models the part of the model corresponding to the hospital for the patient travel route. In the case where a patient logs in and/or registers with the self-service integrated services system 100 through the personal, portable, smart terminal 122, the patient travel route is generated and modeled by the cloud server 110 as a corresponding local model. If and only if the patient side 120 is a kiosk 121 located inside the hospital, the medical staff member will send the address data for the interview to the patient side 120, i.e., the kiosk 121. When the patient end 120 is a private device such as an intelligent terminal 122 carried by the patient, the medical staff sends the address data of the patient to the cloud server 110.

Preferably, the local model corresponding to the patient's travel route is sent in a video stream to the intelligent terminal 122 that the patient person carries with him. The intelligent terminal 122 can receive the video stream by pairing with the kiosk 121. After receiving the video stream of the corresponding local model, the intelligent terminal 122 carried by the patient can display the local model at any time so as to provide route navigation for the patient. Preferably, after the patient enters the hospital, especially in case the communication signal is disturbed, the patient can go to the destination by looking at the navigation video on the smart terminal 122.

Preferably, in the case that the patient logs in and/or registers to the self-service integrated service system 100 through the smart terminal 122, the cloud server 110 can read the location information of the smart terminal 122. In response to receipt of the location information, the self-service integrated services system 100 performs a differencing operation for the respective patient to form a local model that matches the patient location. Preferably, when the position information of the intelligent terminal 122 shows that the intelligent terminal 122 is located in the hospital position range, that is, when the patient is located in the hospital position range, the intelligent terminal 122 prompts the patient to go to the self-service machine 121 to obtain the local model, so that the patient can still obtain video navigation in the case that the intelligent terminal 122 cannot smoothly receive the local model video stream generated by the cloud server 110 due to the blocked communication signal.

Preferably, the cloud server 110 has access to a common map database. The local model generated and modeled by cloud server 110 may be matched to a public map, and in the event that a patient logs in and/or registers with self-service integrated services system 100 through intelligent terminal 122 and navigates to a hospital portal along the public map using intelligent terminal 122, intelligent terminal 122 switches from public map navigation to video navigation.

Example 2

This embodiment is a further improvement of embodiment 1, and repeated details are not repeated. Preferably, the user can enter the self-service integrated service system through the intelligent terminal 122 for medical treatment. Referring to fig. 2, a user may establish data communication with cloud server 110 through intelligent terminal 122, and cloud server 110 may establish data communication with medical care end 130 disposed in a hospital department in addition to data communication with intelligent terminal 122. Preferably, when the intelligent terminal 122 is stable in communication and located outside the hospital, the patient can log in and/or register to the self-service integrated service system 100 through the intelligent terminal 122. Preferably, the smart terminal 122 directs the patient to operate the patient end 120 to specify the purpose of the patient's doctor based on data communication with the cloud server 110. When the purpose of the patient's medical treatment belongs to a class of purposes requiring the participation of medical professionals, the cloud server 110 matches the corresponding medical professional for the patient by establishing data communication with the medical care terminal 130 provided in the corresponding department of the hospital. Medical professionals are associated with the patient operating the intelligent terminal 122 through the medical care terminal 130 to realize telemedicine. Preferably, in case that the patient needs to go to the corresponding department of the hospital after the remote diagnosis, the doctor uploads the address of the patient needing to arrive at the department to the cloud server 110 through the medical care end 130. In response to receipt of the department address, cloud server 110 designs a navigation route for the patient to reach the corresponding department from the location of the patient based on the location information of smart terminal 122 and the public map data. Preferably, the navigation route includes a public route from the intelligent terminal 122 to an entrance of the hospital, and a personal route from the entrance of the hospital to a corresponding department. Preferably, a common route from the intelligent terminal 122 to the entrance of the hospital can be designed by a common navigation application. Preferably, a personal route from the entrance of the hospital to the corresponding department is designed and generated by the cloud server 110, and a local model corresponding to the hospital is transmitted to the smart terminal 122 in the form of a video stream. Preferably, the patient can navigate to the hospital entrance along the public map using the intelligent terminal 122, and in the case where the patient arrives at the hospital entrance, the intelligent terminal 122 switches from the public map navigation to the video navigation. Preferably, when video navigation is performed, the patient can view the local model at any time, and can perform all-around observation on the model by adjusting the visual direction of the virtual character, so that the architectural features in the virtual environment and the architectural features in the actual environment are compared to determine the travel route.

Preferably, in case that the doctor confirms the diagnosis of the patient's disease through the telemedicine, the doctor orders and uploads the medicine-taking department address to the cloud server 110. Preferably, the cloud server 110 designs a navigation route for the patient to reach the drug taking department from the position of the patient based on the position information of the intelligent terminal 122 and public map data. Preferably, the navigation route includes a public route from the intelligent terminal 122 to the entrance of the hospital, and a personal route from the entrance of the hospital to the department of the drug taking department. Preferably, a common route from the intelligent terminal 122 to the entrance of the hospital can be designed by a common navigation application. Preferably, a personal route from the entrance of the hospital to the department of the drug taking department is designed and generated by the cloud server 110 and a local model corresponding to the hospital is then sent to the intelligent terminal 122 of the patient. Preferably, the local model generated by cloud server 110 may be combined with a public navigation map and transmitted to smart terminal 122. The patient can move to the hospital entrance through public navigation first and then reach the drug-taking department through a video navigation mode under the condition that the intelligent terminal 122 receives the navigation route.

Preferably, the cloud server 110 obtains the starting point position and the viewing direction of the patient by reading the position information of the intelligent terminal 122, and navigates the patient to the hospital entrance according to the starting point position and the viewing direction of the patient in combination with the public map data. Preferably, routes from hospital entrances to respective departments generate respective local models by cloud server 110. Preferably, cloud server 110 generates the local model in the following manner. Preferably, the cloud server 110 may take a hospital entrance where a patient arrives as a patient starting position and a direction of entry into the hospital as a patient viewing direction, while retrieving planar and stereoscopic data associated with respective patient target departments and starting positions to complete the modeling. Preferably, the cloud server 110 can generate an avatar in the virtual model, which is the same as the starting position and the viewing direction of the patient, when the virtual model is modeled.

When a patient arrives at a hospital entrance according to a navigation route and starts video navigation, the starting point position and the visual direction of the patient are matched with the corresponding local model, and the patient can determine a feature reference object on a 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 mobile robot moves in a hospital, a patient can check the local model at any time, and can carry out all-around observation on the model by adjusting the visual direction of the virtual character, so that the building characteristics in the virtual environment and the building characteristics in the actual environment are compared to determine the traveling route, and the carry-on navigation is realized. In the process of navigating through the intelligent terminal 122 by the patient, the intelligent terminal 122 can only receive the navigation video of the virtual model generated by the cloud server 110, so that the internal building structure data of the hospital and the like can be prevented from being remained on the intelligent terminal 122 of the patient.

Example 3

This embodiment is a further improvement of embodiment 1 and embodiment 2, and repeated details are not repeated. The existence of a large crowded crowd in the range of hospital locations means that a large number of personal intelligent terminals 122 exist, which causes the burden of local communication base stations to be increased so that the communication quality of the intelligent terminals 122 is reduced; in addition, the intelligent terminal 122 carried by the patient after entering the hospital building is very vulnerable to the degradation of communication quality due to the interference of the building. If the local model video stream generated by the cloud server 110 is still transmitted to the intelligent terminal 122 when the patient enters the hospital location range, the integrity and stability of the video stream transmission cannot be ensured. Preferably, the patient may be navigated by using the kiosk 121 while the patient is within the hospital location.

Preferably, the patient can register and/or log in the self-service integrated service system by matching the intelligent terminal 122 with the self-service machine 121, and then perform business transaction by operating the self-service machine 121. After the medical staff upload the address of the department to which the patient needs to arrive to the cloud server 110 through the medical care end 130, the cloud server 110 transmits the address of the department to the self-service machine 121 operated by the patient. The kiosk 121, in response to receipt of the department address, generates a corresponding virtual model and sends it to the intelligent terminal 122 worn by the patient.

Preferably, the self-service machine 121 is capable of generating a visit path for the corresponding patient according to the target location (corresponding department address), the starting point location and the viewing direction of the corresponding patient in response to receipt of the department address. The visit path of the corresponding patient is formed in such a manner that the business kiosk 121 generates an initial visit path according to the target location, the starting point position, and the viewing direction of the corresponding patient in combination with the hospital configuration data called from the cloud server 110 by the kiosk 121. In response to the generation of the initial diagnosis path, the self-service machine 121 connects to the hospital cloud server 110 to obtain the road conditions of each node on the initial diagnosis path, and corrects the error on the initial diagnosis path to generate a final diagnosis path. In the case where the hospital temporarily closes a certain area on the initial visit path, the self-service machine 121 will re-plan the path through the closed path to preferentially guide the patient to the temporarily opened passage of the hospital administration.

Preferably, the kiosk 121 may acquire the self-location data through a configured positioning unit, and then obtain the starting point location and the viewing direction of the corresponding patient by mirroring the self-location data. The starting position and the viewing direction of the corresponding patient are determined in such a way that the self-service machine 121 performs position detection by using a positioning unit so as to determine the current position and the orientation of the self-service machine 121, determines the viewing direction and the positioning of the current patient of the self-service machine 121 after mirroring the current position and the orientation of the self-service machine along the display side, and determines the starting position and the viewing direction of the patient in the corresponding local model according to the viewing direction and the positioning of the current patient and the hospital structure data.

Preferably, kiosk 121 may generate an avatar in the generated virtual model. Preferably, the starting position and the viewing direction of the virtual character are determined by the kiosk 121 determining the viewing direction and the location of the current patient of the kiosk 121 according to the current position and orientation of the kiosk 121 and providing the viewing direction and the location to the business kiosk 121 and determining the starting position and the viewing direction of the corresponding virtual character by the kiosk 121, so that the starting position and the viewing direction of the corresponding virtual character are the same as the current position and the viewing direction of the patient of the kiosk 121 and the patient can substitute the model into reality.

The self-service machine 121 can prompt the corresponding patient to select his or her personalized avatar in a manner of providing voice prompt to the patient logged in the self-service integrated service system 100, and determine the current position and orientation of the patient through the positioning function of the intelligent device 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 path generated by operating the self-service machine 121 and the doctor path of at least another patient intersect, the virtual character corresponding to the current patient appears in the navigation video which is generated by operating the self-service machine 121 and is sent to the intelligent device to determine the starting position and the viewing direction of the patient, so that the real people flow condition of the corresponding region is reflected in the local 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

1. An intelligent medical self-service comprehensive service system is characterized by at least comprising a cloud server (110), a patient end (120) and a medical care end (130);

the patient side (120) can guide a patient to log in and/or register to a self-service comprehensive service system so as to acquire patient data including the medical purpose of the patient and send the patient data to the cloud server (110);

the cloud server (110) can respond to the receipt of the patient data, input the patient data into a department classification model to obtain a corresponding department, and send the medical purpose of the patient to the medical care end (130) configured by the corresponding department;

medical staff in the corresponding department establishes contact with the corresponding patient through the medical care terminal (130) to perform initial diagnosis.

2. The intelligent medical self-help comprehensive service system according to claim 1, wherein the patient end (120) at least comprises a medical purpose inquiry module for acquiring medical purpose of the patient; the medical purpose inquiry module can classify the medical purpose of the patient into a first purpose requiring the participation of the professional medical staff and a second purpose requiring no the participation of the professional medical staff according to the medical purpose of the patient.

3. The intelligent medical self-service integrated service system according to claim 2, wherein the cloud server (110) inputs patient data including a category into a department classification model to obtain a corresponding department;

the department classification model is established in such a way that the cloud server (110) acquires and summarizes historical medical data, wherein the historical medical data comprises historical illness state description and corresponding historical departments; and training a memory network model according to the historical medical data to obtain the department classification model.

4. The intelligent medical self-service comprehensive service system according to claim 3, wherein the cloud server (110) is provided with a department classification model building module; the department classification model establishing module is used for training the memory network model by acquiring historical medical data to realize establishment and updating of the department classification model.

5. The intelligent medical self-service comprehensive service system according to claim 4, wherein the department classification model establishing module specifically comprises:

the training execution unit 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 training evaluation unit is used for evaluating the training effect of the training execution unit and judging whether to stop training according to the evaluation result;

the training adjusting unit is used for updating the parameters of the memory network model to perform the next training when the evaluation result of the training evaluation unit is invalid training;

and the model generating unit is used for generating the department classification model from the current memory network model under the condition that the training evaluation unit judges that the training is stopped.

6. The intelligent medical self-service integrated service system according to claim 5, wherein the medical staff can set address data including at least one location through the healthcare terminal (130) according to the result of the initial diagnosis and transmit the address data to the cloud server (110) or the patient terminal (120) to generate a patient travel route.

7. The intelligent medical self-help comprehensive service system according to claim 6, wherein the patient terminal (120) at least comprises a self-help machine (121) arranged inside a hospital and an intelligent terminal (122) carried by a patient;

in the event that a patient logs in and/or registers with a self-service integrated services system through a kiosk (121), the kiosk (121) generates a patient travel route and models a part of a model corresponding to a hospital for the patient travel route;

in the case of a patient logging in and/or registering to a self-service integrated services system via a personal, hand-held smart terminal (122), the patient travel route is generated and modeled by the cloud server (110) into a corresponding local model.

8. The intelligent medical self-service comprehensive service system according to claim 7, wherein the local model corresponding to the patient travel route is sent to the intelligent terminal (122) carried by the patient in a video stream mode, wherein the intelligent terminal (122) can receive the video stream in a mode of pairing with the self-service machine (121).

9. The intelligent medical self-service integrated service system according to claim 8, wherein in case of a patient logging in and/or registering to a self-service integrated service system through the intelligent terminal (122), the cloud server (110) is capable of reading location information of the intelligent terminal (122), in response to receipt of the location information, the self-service integrated service system performs a differentiated operation for the respective patient to form a local model matching the patient location.

10. The intelligent medical self-service integrated service system according to claim 9, wherein the cloud server (110) has access to a common map database; and the local model generated and modeled by the cloud server (110) can be matched with a public map, and the intelligent terminal (122) is switched from public map navigation to video navigation under the condition that a patient logs in and/or registers to a self-service integrated service system through the intelligent terminal (122) and navigates to a hospital entrance along the public map by using the intelligent terminal (122).