CN111990969A - Tongue diagnosis detecting system - Google Patents
Tongue diagnosis detecting system Download PDFInfo
- Publication number
- CN111990969A CN111990969A CN202010887001.8A CN202010887001A CN111990969A CN 111990969 A CN111990969 A CN 111990969A CN 202010887001 A CN202010887001 A CN 202010887001A CN 111990969 A CN111990969 A CN 111990969A
- Authority
- CN
- China
- Prior art keywords
- tongue
- user
- image
- detected
- information
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0082—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence adapted for particular medical purposes
- A61B5/0088—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence adapted for particular medical purposes for oral or dental tissue
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0033—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/45—For evaluating or diagnosing the musculoskeletal system or teeth
- A61B5/4538—Evaluating a particular part of the muscoloskeletal system or a particular medical condition
- A61B5/4542—Evaluating the mouth, e.g. the jaw
- A61B5/4552—Evaluating soft tissue within the mouth, e.g. gums or tongue
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Heart & Thoracic Surgery (AREA)
- Public Health (AREA)
- Dentistry (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Veterinary Medicine (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Physical Education & Sports Medicine (AREA)
- Orthopedic Medicine & Surgery (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Rheumatology (AREA)
Abstract
The invention provides a tongue diagnosis detection system, comprising: the system comprises a back-end service platform and a tongue diagnosis detection platform, wherein the back-end service platform is connected with the tongue diagnosis detection platform through a communication interface; the backend service platform comprises: a data storage layer, a service support layer, and an application service layer. The tongue diagnosis detection system provided by the embodiment of the invention allows a user to autonomously perform tongue diagnosis detection, and is convenient for the user to perform tongue diagnosis in time; and the tongue diagnosis detection report can be automatically fed back to the user, so that the user can conveniently know the state of an illness. Meanwhile, the service supporting layer is deployed into a plurality of micro services, and the routing information of each micro service is managed and distributed by using the dynamic routing module, so that micro service scheduling can be realized, and load balancing is facilitated.
Description
Technical Field
The invention relates to the technical field of tongue diagnosis detection, in particular to a tongue diagnosis detection system.
Background
Tongue diagnosis is a term of diagnosis and is one of the key points of inspection. The tongue diagnosis is an effective method for assisting diagnosis and identification by observing the changes of color and form of the tongue, and the changes of tongue manifestation can objectively and accurately reflect the state of an illness and can be used as an important basis for diagnosing diseases, knowing the development and change of the state of an illness and differentiating syndromes.
Currently, tongue diagnosis is mainly performed by professional physicians, and the general public often needs to go to hospitals to obtain professional diagnosis. However, in many cases, it is often inconvenient for people to go to the hospital in time for tongue diagnosis.
Disclosure of Invention
To solve the above problems, an embodiment of the present invention provides a tongue inspection system.
The embodiment of the invention provides a tongue diagnosis detection system, which comprises: the system comprises a back-end service platform and a tongue diagnosis detection platform, wherein the back-end service platform is connected with the tongue diagnosis detection platform through a communication interface; the backend service platform comprises: the system comprises a data storage layer, a service supporting layer and an application service layer;
the data storage layer is used for storing tongue fur information, routing information, user information and main syndrome differentiation information; the service supporting layer comprises an authentication authorization module, a dynamic routing module and a file processing module which are respectively provided with independent addresses; the application service layer comprises a main identification operation module, a tongue diagnosis judging module, a report generating module and a receiving and sending module;
the dynamic routing module is used for setting routing configuration, and the routing configuration represents the target address of each type of request configured according to the routing information;
the authentication authorization module is used for authenticating a login request submitted by a first user and judging whether the first user has the authority to use the back-end service platform or not, wherein the login request comprises a first user identifier of the first user;
the main identification operation module is used for inputting user information of a first user and a tongue to be detected image of the first user; the receiving and sending module is used for sending the tongue image to be detected to the tongue diagnosis detection platform;
the tongue inspection detection platform is used for presetting a tongue inspection detection model, inputting the tongue inspection image to be detected to the tongue inspection detection model when receiving the tongue inspection image, determining a classification mark of the tongue inspection image, and feeding back the classification mark of the tongue inspection image to the back-end service platform;
the tongue diagnosis distinguishing module is used for determining main disease distinguishing description of the first user according to the classification identification of the tongue image to be detected, the tongue fur information and the main disease distinguishing information;
the report generation module is used for generating a tongue diagnosis detection report of the first user according to the main syndrome differentiation description of the first user;
the file processing module is used for storing the tongue image to be detected and/or storing the tongue inspection report of the first user.
On the basis of the foregoing embodiment, the dynamic routing module is configured to:
taking over a microservice processing module, the microservice processing module comprising the application service layer;
performing a route matching mapping process to match the routing configuration of each of the microservice processing modules;
determining routing information corresponding to each micro-service processing module according to a routing locator, and determining routing definition information according to the routing information of the micro-service processing module;
and carrying out route matching on the route configuration according to the route definition information, and executing a filter linked list in the route definition information so as to route to a corresponding micro service processing module.
On the basis of the above embodiment, the tongue inspection platform is used for:
constructing a plurality of picture data related to tongue diagnosis main differentiation symptoms, labeling the picture data, determining a classification identifier of each picture data, and constructing a sample set according to the plurality of picture data and the corresponding classification identifiers;
performing data enhancement on the picture data to generate new picture data, and adding the new picture data to the sample set;
training a preset tongue diagnosis detection model according to the sample set, and further determining the trained tongue diagnosis detection model;
receiving wait to examine when examining the tongue image, will wait to examine the tongue image input to training after the tongue inspection detection model confirms wait to examine the classification mark of tongue image, and will wait to examine the classification mark feedback of tongue image extremely rear end service platform.
On the basis of the embodiment, after the back-end service platform receives the classification identifier of the tongue image to be detected, if the back-end service platform obtains a reclassification request, determining a new classification identifier of the tongue image to be detected according to the reclassification request, and sending the new classification identifier of the tongue image to be detected to the tongue diagnosis detection platform;
and after receiving the new classification identification of the tongue image to be detected, the tongue inspection detection platform takes the tongue image to be detected as input and correspondingly takes the new classification identification as output, and trains the tongue inspection detection model again to update the trained tongue inspection detection model.
On the basis of the above embodiment, the main syndrome differentiation information includes a corresponding relationship between a classification identifier and a plurality of main syndrome differentiation descriptions, and each of the main syndrome differentiation descriptions corresponds to a tongue image;
the tongue diagnosis distinguishing module determines the main disease distinguishing description of the first user according to the classification identification of the to-be-detected tongue image, the tongue fur information and the main disease distinguishing information, and the method comprises the following steps:
determining the tongue coating name of the tongue image to be detected according to the classification identification of the tongue image to be detected and the tongue coating information;
determining a plurality of effective tongue images corresponding to the tongue image to be detected according to the classification identification of the tongue image to be detected and the main disease identification information, wherein the effective tongue images are a plurality of tongue images corresponding to main disease identification description which has a corresponding relation with the classification identification of the tongue image to be detected;
determining a designated threshold in advance according to the quantity of the image data in the sample set, and respectively calculating the similarity between the image to be detected and the effective tongue image, wherein the designated threshold and the quantity of the image data are in positive correlation;
and generating the main syndrome differentiation description of the first user according to the main syndrome differentiation information corresponding to the effective tongue image with the similarity larger than the specified threshold.
On the basis of the foregoing embodiment, the main-discerning operation module is further configured to:
modifying and/or deleting the user information of the first user and the tongue to be detected image of the first user;
and when the query request is acquired, querying corresponding user information and/or tongue diagnosis detection reports according to the keywords in the query request.
On the basis of the above embodiment, the authentication and authorization module is further configured to:
and authenticating a management request submitted by a second user, and allowing the second user to manage the back-end service platform when a second user identifier in the management request is legal.
On the basis of the above embodiment, the backend service platform further includes: a base layer;
the base layer is used for providing software support and hardware support for the operation of the back-end service platform.
On the basis of the embodiment, the system also comprises a tongue diagnosis front end which is in communication connection with the back end service platform;
the tongue diagnosis front end is used for responding to input operation, determining user information of a first user and a tongue image to be detected of the first user, and sending the user information of the first user and the tongue image to be detected to the back end service platform.
On the basis of the above embodiment, the tongue diagnosis front end is further configured to receive a tongue diagnosis detection report of the first user sent by the back end service platform, and display the tongue diagnosis detection report of the first user.
In the scheme provided by the embodiment of the invention, when tongue diagnosis detection is required, a user can conveniently send the tongue image to be detected to a back-end service platform through a front end of tongue diagnosis such as a smart phone, the back-end service platform uniformly forwards the tongue image to be detected to the tongue diagnosis detection platform to determine a corresponding classification identifier, and then a corresponding tongue diagnosis detection report can be generated based on the classification identifier and is provided for the user to check. The tongue diagnosis detection system allows the user to autonomously perform tongue diagnosis detection, and facilitates the user to perform tongue diagnosis in time; and the tongue diagnosis detection report can be automatically fed back to the user, so that the user can conveniently know the state of an illness. Meanwhile, the service supporting layer is deployed into a plurality of micro services, and the routing information of each micro service is managed and distributed by using the dynamic routing module, so that micro service scheduling can be realized, and load balancing is facilitated.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a first structural schematic diagram of a tongue inspection system according to an embodiment of the present invention;
fig. 2 is a schematic diagram illustrating a second structure of the tongue inspection system according to the embodiment of the invention.
Detailed Description
Referring to fig. 1, the tongue diagnosis detection system according to an embodiment of the present invention includes: the system comprises a back-end service platform and a tongue inspection detection platform, wherein the back-end service platform is connected with the tongue inspection detection platform through a communication interface. Wherein, back-end service platform includes: a data storage layer, a service support layer, and an application service layer. The data storage layer is used for storing tongue coating information, routing configuration information, user information and main syndrome differentiation information; the service supporting layer comprises an authentication authorization module, a dynamic routing module and a file processing module which are respectively provided with independent addresses; the application service layer comprises a main identification operation module, a tongue diagnosis judging module, a report generating module and a receiving and sending module.
In the embodiment of the invention, the dynamic routing module is used for setting routing configuration, and the routing configuration represents that the target address of each type of request is configured according to the routing information; the authentication authorization module is used for authenticating a login request submitted by a first user and judging whether the first user has the authority to use the back-end service platform or not, wherein the login request comprises a first user identifier of the first user; the main identification operation module is used for inputting user information of a first user and a tongue image to be detected of the first user; the receiving and sending module is used for sending the tongue image to be detected to the tongue diagnosis detection platform.
The tongue inspection detection platform is used for presetting a tongue inspection detection model, inputting the tongue image to be inspected to the tongue inspection detection model when receiving the tongue image to be inspected, determining the classification identification of the tongue image to be inspected, and feeding back the classification identification of the tongue image to be inspected to the back-end service platform.
The tongue diagnosis distinguishing module is used for determining main disease identification description of the first user according to the classification identification, the tongue fur information and the main disease identification information of the tongue image to be detected; the report generation module is used for generating a tongue diagnosis detection report of the first user according to the main syndrome differentiation description of the first user; the file processing module is used for storing the tongue image to be detected and storing a tongue diagnosis detection report of the first user.
Specifically, in the embodiment of the present invention, the first user is a user who needs tongue diagnosis detection, and the first user may upload user information of the first user and a captured tongue image (i.e., a tongue image to be detected) to the back-end service platform. As shown in fig. 1, the tongue inspection system optionally further comprises a tongue inspection front end, through which the first user can input and upload user information and an image of the tongue to be inspected. Specifically, the first user may input the user information and the tongue image to be examined to the tongue examination front end, and then the tongue examination front end responds to the input operation of the first user, so that the user information of the first user and the tongue image to be examined of the first user may be determined, and the user information of the first user and the tongue image to be examined are sent to the back-end service platform. After the back-end service platform receives the user information of the first user and the image of the tongue to be detected, the main identification operation module can enter the user information of the first user and the image of the tongue to be detected.
In this embodiment, since the backend service platform of the system needs to allow access to multiple tongue diagnosis front ends, that is, multiple first users can upload their own related information through their own tongue diagnosis front ends (e.g., smart phones, tablet computers, personal computers, etc.), in order to ensure that one-to-many backend service platform and tongue diagnosis front ends can work normally, the embodiment divides the service support layer into multiple micro-service processing modules, that is, at least into an authentication authorization module, a file processing module, etc., and at the same time, part or all of the functions in the application service layer can be implemented based on one micro-service processing module; and constructing a system architecture by utilizing the characteristics of independent deployment, horizontal extension, independent access and the like of the microservice. Meanwhile, a dynamic routing module is also arranged to manage and distribute the routing information of each micro-service processing module. Specifically, the dynamic routing module configures a routing configuration for each of the microservice processing modules based on routing information stored in the data store layer, and the routing configuration can represent a destination address for a corresponding type of request, which can represent a path. For example, after receiving a login request of a first user, the login request can be routed to an authentication authorization module, even a micro-service processing module such as an application service layer.
Meanwhile, the authentication and authorization module needs to authenticate and authorize the first user to determine whether the first user can use the tongue inspection function provided by the system. Specifically, the tongue diagnosis front end may request authentication in a manner of sending a login request, where the login request includes a first user identifier; or, after receiving the user information of the first user and the image to be detected, the back-end service platform may actively generate a login request of the first user identifier, where the user information includes the first user identifier; after determining the login request, the authentication authorization module authenticates the login request. Specifically, the user information stored in the data storage layer includes identity information of a legal user, and the authentication authorization module determines whether the first user identifier is a legal user by judging whether the first user identifier is matched with the legal user in the user information, and passes authentication when the first user identifier is the legal user, that is, the first user is allowed to access the back-end service platform to use the tongue diagnosis detection function. After the first user passes the authentication, the login request may be routed to the application service layer according to the routing configuration of the application service layer, so that the first user may use the function provided by the application service layer through the tongue diagnosis front end, for example, upload the tongue image to be checked, and the like. And then, the receiving and sending module can send the tongue image to be detected to the tongue diagnosis detection platform.
In the embodiment of the invention, the tongue diagnosis detection platform is used for carrying out image recognition on the tongue image to be detected and determining the corresponding classification identification. The tongue inspection detection platform comprises a tongue inspection detection model generated based on an image classification model, the tongue image to be inspected is input into the image classification model, the classification identification of the tongue image to be inspected can be determined, and the classification identification is fed back to the back-end service platform through the communication interface. The category identifier may be in the form of a series of numeric codes, a series of characters, or a combination of numbers and characters, such as "lightwhite".
In the embodiment of the invention, the tongue coat information stored in the data storage layer comprises the name of the tongue coat and corresponding classification identification; wherein, the name of the tongue coating is a name which is convenient for users to understand. For example, the category is labeled "lightwhite", and the corresponding tongue coating name is "white coating"; the main syndrome differentiation information is used for representing the corresponding relation between the classification identification and the main syndrome differentiation description. In this embodiment, after determining the classification identifier of the tongue image to be detected, the tongue diagnosis determination module may determine the corresponding tongue coating name based on the tongue coating information, and may determine the main syndrome differentiation description corresponding to the classification identifier, that is, the description related to the characteristics or features of the main syndrome differentiation, based on the main syndrome differentiation information.
Then, the report generating module may generate a tongue examination report of the first user, where the tongue examination includes a main diagnosis description of the first user, and may further include a tongue fur name and corresponding user information, for example, the user information may include a name, a gender, an age, a number of photos taken, and the like of the first user, and may further include an outpatient number, an inpatient number, and the like if the first user is an inpatient. Then, the back-end service platform can send the tongue diagnosis detection report to the tongue diagnosis front end; after the tongue diagnosis front end receives the tongue diagnosis detection report of the first user sent by the back end service platform, the tongue diagnosis detection report of the first user can be displayed, so that the first user can check the tongue diagnosis detection report through the tongue diagnosis front end.
According to the tongue diagnosis detection system provided by the embodiment of the invention, when tongue diagnosis detection is required, a user can conveniently send a tongue image to be detected to a back-end service platform through a front end of tongue diagnosis such as a smart phone, the back-end service platform uniformly forwards the tongue image to be detected to the tongue diagnosis detection platform to determine a corresponding classification identifier, and then a corresponding tongue diagnosis detection report can be generated based on the classification identifier and can be viewed by the user. The tongue diagnosis detection system allows the user to autonomously perform tongue diagnosis detection, and facilitates the user to perform tongue diagnosis in time; and the tongue diagnosis detection report can be automatically fed back to the user, so that the user can conveniently know the state of an illness. Meanwhile, the service supporting layer is deployed into a plurality of micro services, and the routing information of each micro service is managed and distributed by using the dynamic routing module, so that micro service scheduling can be realized, and load balancing is facilitated.
On the basis of the embodiment, in order to ensure high reliability and high availability in an actual production environment, the system is prevented from restarting as much as possible; in the conventional routing gateway system, when the system is started, the routing configuration and rules are loaded into the memory, and the configuration and rules of the corresponding routing can not be dynamically added, modified or deleted without restarting the gateway. In this embodiment, a dynamic route is also required to be determined, and in order to avoid the need for restarting, the background request route analyzed by the dynamic route loading tongue diagnosis is used in this embodiment. The route loading sequence of the dynamic routing module is specifically as follows:
step A1: and taking over the micro-service processing module, wherein the micro-service processing module comprises an application service layer.
Step A2: a route matching mapping process is performed to match the route configuration of each microservice processing module.
Step A3: and determining the routing information corresponding to each micro-service processing module according to the routing locator, and determining routing definition information according to the routing information of the micro-service processing modules.
Step A4: and carrying out route matching on the route configuration according to the route definition information, and executing a filter linked list in the route definition information so as to route to the corresponding micro service processing module.
In the embodiment of the present invention, the dynamic routing module may specifically be a gateway device, and takes over each micro service processing module based on a forwarding processor; and then, performing route matching mapping processing to match the route configuration of each micro service processing module, such as matching the route configuration of an application service layer. In addition, the route locator is an interface for acquiring the route, and the route locator can directly acquire the route information based on the route, so as to determine corresponding route definition information; the route definition information is a configuration information of the route, and includes a route ID, a route assertion definition list, a filter linked list definition list, a URI (Uniform Resource Identifier) forwarding address, a priority, and the like. After a certain request (such as a login request) is acquired, routing matching can be performed, and a filter is called to execute a filter linked list, and finally routing is performed to a corresponding micro service processing module. The dynamic routing mode does not need to restart the system, and the dynamic configuration is conveniently realized.
On the basis of the above embodiment, the tongue inspection platform is specifically configured to perform the following steps:
step B1: constructing a plurality of picture data related to the tongue diagnosis main differentiation disease, labeling the picture data, determining the classification identification of each picture data, and constructing a sample set according to the plurality of picture data and the corresponding classification identification.
Step B2: and performing data enhancement on the picture data to generate new picture data, and adding the new picture data to the sample set.
In the embodiment of the present invention, a plurality of image data related to the tongue diagnosis main syndrome can be obtained in advance, the image data is also a tongue image in nature, and each image data may include a front image of a tongue photograph, a left image of the tongue photograph, and a right image of the tongue photograph. Meanwhile, each picture data is subjected to a labeling process, and the picture data has corresponding classification identification. And constructing a sample set for training the model by the plurality of picture data and the corresponding classification identifications. And the more the number of samples in the sample set is, the higher the model precision obtained by final training is. The number of samples of the current tongue image is small, which is not beneficial to model training, and the embodiment generates new picture data in a data enhancement mode to increase the number of samples of the sample set, thereby improving the precision of model training.
Step B3: and training a preset tongue diagnosis detection model according to the sample set, and further determining the trained tongue diagnosis detection model.
Step B4: and when the tongue image to be detected is received, inputting the tongue image to be detected into the trained tongue inspection detection model, determining the classification identification of the tongue image to be detected, and feeding back the classification identification of the tongue image to be detected to the back-end service platform.
In the embodiment of the present invention, the tongue diagnosis detection model is a classification model based on image recognition, and specifically may be a convolutional neural network model, such as Yolov3 convolutional neural network model. After the model training is finished, the received tongue image to be detected can be input into the tongue inspection detection model, and the output result is the classification identification of the tongue image to be detected; and then the tongue diagnosis detection platform can feed the classification identification back to the back-end service platform. In this embodiment, set up tongue diagnosis testing platform independently, can separate out tongue diagnosis testing function, and also make the tongue diagnosis front end of different hospitals all can insert same tongue diagnosis testing platform, guarantee the unity of testing result.
Optionally, after the back-end service platform receives the classification identifier of the tongue image to be detected, if the back-end service platform obtains a re-classification request, determining a new classification identifier of the tongue image to be detected according to the re-classification request, and sending the new classification identifier of the tongue image to be detected to the tongue diagnosis detection platform. And after the tongue inspection detection platform receives the new classification identification of the tongue image to be inspected, the tongue image to be inspected is used as input, the corresponding new classification identification is used as output, the tongue inspection detection model is trained again, and the trained tongue inspection detection model is updated.
In the embodiment of the invention, after the back-end service platform receives the classification identifier of the image to be detected, the classification identifier can be further judged in other ways, for example, an experienced doctor can review the classification identifier, and if the classification identifier is wrong, a reclassification request can be submitted to provide a new classification identifier; and then the back-end service platform sends the new classification identification to the tongue diagnosis detection platform. And then, the tongue inspection platform takes the image of the tongue to be inspected as input and the corresponding new classification identification as output, trains the tongue inspection model again to correct the coefficient of the tongue inspection model and further improves the identification accuracy of the tongue inspection model. Experiments prove that the average accuracy rate of the tongue inspection model can reach 96%.
Optionally, the main syndrome information stored in the data storage layer includes: and the classification identification corresponds to a plurality of main syndrome differentiation descriptions, and each main syndrome differentiation description corresponds to a tongue image.
Specifically, the tongue diagnosis distinguishing module determines the main disease distinguishing description of the first user according to the classification identification, the tongue fur information and the main disease distinguishing information of the tongue image to be detected, and comprises the following steps:
step C1: and determining the tongue coating name of the tongue image to be detected according to the classification identification and the tongue coating information of the tongue image to be detected.
Step C2: and determining a plurality of effective tongue images corresponding to the tongue image to be detected according to the classification identification of the tongue image to be detected and the main disease identification information, wherein the effective tongue images are a plurality of tongue images corresponding to the main disease identification description which has a corresponding relation with the classification identification of the tongue image to be detected.
Step C3: and predetermining a designated threshold according to the quantity of the image data in the sample set, and respectively calculating the similarity between the image to be detected and the effective tongue image, wherein the designated threshold and the quantity of the image data are in positive correlation.
Step C4: and generating the main syndrome differentiation description of the first user according to the main syndrome differentiation information corresponding to the effective tongue image with the similarity larger than the specified threshold.
In the embodiment of the invention, the data storage layer stores tongue coating information and main syndrome differentiation information, wherein the tongue coating information comprises a tongue coating name and a corresponding classification identifier, the main syndrome differentiation information comprises a corresponding relation between the classification identifier and a main syndrome differentiation description, and the main syndrome differentiation description is description information related to main syndrome differentiation. After the classification identification of the tongue image to be detected is determined, the corresponding tongue coating name can be determined based on the tongue coating information, so that the classification identification is converted into the tongue coating name which is convenient for a user to check, and the user can understand the tongue coating name conveniently. Meanwhile, the corresponding main syndrome differentiation description can be determined based on the main syndrome differentiation information.
The main disease identification information is generated in advance, and for a certain classification identifier, tongue images of different patients are not completely the same, and their respective main disease identification descriptions are also not completely the same, so that in this embodiment, the main disease identification information corresponding to the classification identifier is established based on a plurality of tongue images, that is, in the main disease identification information, one main disease identification description corresponds to a plurality of tongue images. In this embodiment, after determining the main syndrome differentiation description having a corresponding relationship with the classification identifier of the tongue image to be detected, a plurality of tongue images corresponding to the main syndrome differentiation description, that is, effective tongue images, may be further determined. For example, the main syndrome description a corresponding to white coating is generated based on the tongue images a1, a2, and a3, and if the classification of the tongue image to be examined is white coating, the corresponding effective tongue images are the tongue images a1, a2, and a 3. The main syndrome description a may be generated by synthesizing three main syndrome descriptions of tongue images a1, a2, a3, or may directly include three main syndrome descriptions of tongue images a1, a2, a 3.
In the embodiment of the invention, the specified threshold is determined in advance according to the quantity of the image data in the sample set, and the specified threshold and the quantity of the image data are in positive correlation, namely the more the quantity of the image data is, the higher the accuracy of the finally obtained tongue diagnosis detection model is, and the more easily and accurately matched the effective tongue image; at this time, the larger the designated threshold is set, the more appropriate tongue image can be selected from the plurality of effective tongue images. In this embodiment, a more suitable tongue image is selected according to the similarity between tongue images, that is, an effective tongue image with a similarity greater than the specified threshold is a more suitable tongue image, and then the primary syndrome description of the first user is generated based on the selected tongue image. In the embodiment, the similarity is used as a judgment reference, and the main syndrome description of the first user is generated based on the effective tongue image with the similarity larger than the specified threshold, so that the generated main syndrome description is more accurate.
On the basis of the above embodiment, the main-recognition operation module is further configured to: and modifying and/or deleting the user information of the first user and the tongue to be detected image of the first user. And when the query request is acquired, querying corresponding user information and/or tongue diagnosis detection reports according to the keywords in the query request.
In the embodiment of the invention, if the user information or the tongue image to be detected uploaded by the first user is wrong, the main identification operation module can also provide a modification or deletion function, so that the first user can delete the wrong or useless user information or tongue image to be detected. Meanwhile, the main identification operation module also allows the user to initiate an inquiry request so as to inquire the required user information and/or tongue diagnosis detection report.
Optionally, the authentication and authorization module is further configured to: and authenticating the management request submitted by the second user, and allowing the second user to manage the back-end service platform when the second user identifier in the management request is legal. In the embodiment of the invention, the back-end service platform can allow various users to log in or use, such as patients, doctors and the like, the patients can be used as first users to upload own tongue images to be examined, and the doctors can also be used as first users to upload the tongue images to be examined of the patients. In addition, part of doctors or other administrators can manage the back-end service platform; specifically, the second user may be used as the second user to input the management request, and then the authentication and authorization module authenticates the management request, and when the second user passes the authentication, the second user is allowed to manage the backend service platform. For example, if the second user is an expert physician, when the classification identifier of the tongue image to be detected is incorrect, the second user may initiate a reclassification request and submit a new classification identifier.
Optionally, referring to fig. 2, the backend service platform further includes: a base layer; the base layer is used for providing software support and hardware support for the operation of the back-end service platform. The infrastructure may specifically include platform infrastructure (server hosting, storage, network), operating system (Linux), database (MySQL), and basic services, among others. Optionally, the application service layer further comprises a report printing module, or the tongue diagnosis front end has a report printing module, so as to facilitate the user to print the tongue diagnosis detection report.
According to the tongue diagnosis detection system provided by the embodiment of the invention, when tongue diagnosis detection is required, a user can conveniently send a tongue image to be detected to a back-end service platform through a front end of tongue diagnosis such as a smart phone, the back-end service platform uniformly forwards the tongue image to be detected to the tongue diagnosis detection platform to determine a corresponding classification identifier, and then a corresponding tongue diagnosis detection report can be generated based on the classification identifier and can be viewed by the user. The tongue diagnosis detection system allows the user to autonomously perform tongue diagnosis detection, and facilitates the user to perform tongue diagnosis in time; and the tongue diagnosis detection report can be automatically fed back to the user, so that the user can conveniently know the state of an illness. Meanwhile, the service supporting layer is deployed into a plurality of micro services, and the routing information of each micro service is managed and distributed by using the dynamic routing module, so that micro service scheduling can be realized, and load balancing is facilitated. The dynamic routing mode adopted by the method does not need to restart the system, and the dynamic configuration is conveniently realized. Through data enhancement, reclassification of tongue images to be detected and the like, the number of samples can be increased, and the tongue diagnosis detection model can be corrected through reclassification, so that the accuracy of the tongue diagnosis detection model can be improved. And by taking the similarity as a judgment standard, generating the main syndrome description of the first user based on the effective tongue image with the similarity larger than a specified threshold, wherein the generated main syndrome description is more accurate.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A tongue inspection system, comprising: the system comprises a back-end service platform and a tongue diagnosis detection platform, wherein the back-end service platform is connected with the tongue diagnosis detection platform through a communication interface; the backend service platform comprises: the system comprises a data storage layer, a service supporting layer and an application service layer;
the data storage layer is used for storing tongue fur information, routing information, user information and main syndrome differentiation information; the service supporting layer comprises an authentication authorization module, a dynamic routing module and a file processing module which are respectively provided with independent addresses; the application service layer comprises a main identification operation module, a tongue diagnosis judging module, a report generating module and a receiving and sending module;
the dynamic routing module is used for setting routing configuration, and the routing configuration represents the target address of each type of request configured according to the routing information;
the authentication authorization module is used for authenticating a login request submitted by a first user and judging whether the first user has the authority to use the back-end service platform or not, wherein the login request comprises a first user identifier of the first user;
the main identification operation module is used for inputting user information of a first user and a tongue to be detected image of the first user; the receiving and sending module is used for sending the tongue image to be detected to the tongue diagnosis detection platform;
the tongue inspection detection platform is used for presetting a tongue inspection detection model, inputting the tongue inspection image to be detected to the tongue inspection detection model when receiving the tongue inspection image, determining a classification mark of the tongue inspection image, and feeding back the classification mark of the tongue inspection image to the back-end service platform;
the tongue diagnosis distinguishing module is used for determining main disease distinguishing description of the first user according to the classification identification of the tongue image to be detected, the tongue fur information and the main disease distinguishing information;
the report generation module is used for generating a tongue diagnosis detection report of the first user according to the main syndrome differentiation description of the first user;
the file processing module is used for storing the tongue image to be detected and/or storing the tongue inspection report of the first user.
2. The tongue inspection system of claim 1, wherein the dynamic routing module is configured to:
taking over a microservice processing module, the microservice processing module comprising the application service layer;
performing a route matching mapping process to match the routing configuration of each of the microservice processing modules;
determining routing information corresponding to each micro-service processing module according to a routing locator, and determining routing definition information according to the routing information of the micro-service processing module;
and carrying out route matching on the route configuration according to the route definition information, and executing a filter linked list in the route definition information so as to route to a corresponding micro service processing module.
3. The tongue examination system of claim 1, wherein the tongue examination platform is configured to:
constructing a plurality of picture data related to tongue diagnosis main differentiation symptoms, labeling the picture data, determining a classification identifier of each picture data, and constructing a sample set according to the plurality of picture data and the corresponding classification identifiers;
performing data enhancement on the picture data to generate new picture data, and adding the new picture data to the sample set;
training a preset tongue diagnosis detection model according to the sample set, and further determining the trained tongue diagnosis detection model;
receiving wait to examine when examining the tongue image, will wait to examine the tongue image input to training after the tongue inspection detection model confirms wait to examine the classification mark of tongue image, and will wait to examine the classification mark feedback of tongue image extremely rear end service platform.
4. The tongue diagnosis detection system according to claim 3, wherein after the back-end service platform receives the classification identifier of the tongue image to be detected, if the back-end service platform obtains a re-classification request, determining a new classification identifier of the tongue image to be detected according to the re-classification request, and sending the new classification identifier of the tongue image to be detected to the tongue diagnosis detection platform;
and after receiving the new classification identification of the tongue image to be detected, the tongue inspection detection platform takes the tongue image to be detected as input and correspondingly takes the new classification identification as output, and trains the tongue inspection detection model again to update the trained tongue inspection detection model.
5. The tongue diagnosis detection system according to claim 3, wherein the main syndrome differentiation information comprises a corresponding relationship between a classification identifier and a plurality of main syndrome differentiation descriptions, and each of the main syndrome differentiation descriptions corresponds to a tongue image;
the tongue diagnosis distinguishing module determines the main disease distinguishing description of the first user according to the classification identification of the to-be-detected tongue image, the tongue fur information and the main disease distinguishing information, and the method comprises the following steps:
determining the tongue coating name of the tongue image to be detected according to the classification identification of the tongue image to be detected and the tongue coating information;
determining a plurality of effective tongue images corresponding to the tongue image to be detected according to the classification identification of the tongue image to be detected and the main disease identification information, wherein the effective tongue images are a plurality of tongue images corresponding to main disease identification description which has a corresponding relation with the classification identification of the tongue image to be detected;
determining a designated threshold in advance according to the quantity of the image data in the sample set, and respectively calculating the similarity between the image to be detected and the effective tongue image, wherein the designated threshold and the quantity of the image data are in positive correlation;
and generating the main syndrome differentiation description of the first user according to the main syndrome differentiation information corresponding to the effective tongue image with the similarity larger than the specified threshold.
6. The tongue inspection system of claim 1, wherein the main identification module is further configured to:
modifying and/or deleting the user information of the first user and the tongue to be detected image of the first user;
and when the query request is acquired, querying corresponding user information and/or tongue diagnosis detection reports according to the keywords in the query request.
7. The tongue inspection system of claim 1, wherein the authentication and authorization module is further configured to:
and authenticating a management request submitted by a second user, and allowing the second user to manage the back-end service platform when a second user identifier in the management request is legal.
8. The tongue examination system of claim 1, wherein the back end service platform further comprises: a base layer;
the base layer is used for providing software support and hardware support for the operation of the back-end service platform.
9. The tongue examination system of any one of claims 1-8, further comprising a tongue examination front end, wherein the tongue examination front end is communicatively connected to the back end service platform;
the tongue diagnosis front end is used for responding to input operation, determining user information of a first user and a tongue image to be detected of the first user, and sending the user information of the first user and the tongue image to be detected to the back end service platform.
10. The tongue examination system of claim 9, wherein the tongue examination front-end is further configured to receive the tongue examination report of the first user sent by the back-end service platform and display the tongue examination report of the first user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010887001.8A CN111990969A (en) | 2020-08-28 | 2020-08-28 | Tongue diagnosis detecting system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010887001.8A CN111990969A (en) | 2020-08-28 | 2020-08-28 | Tongue diagnosis detecting system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111990969A true CN111990969A (en) | 2020-11-27 |
Family
ID=73466258
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010887001.8A Pending CN111990969A (en) | 2020-08-28 | 2020-08-28 | Tongue diagnosis detecting system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111990969A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113080866A (en) * | 2021-04-09 | 2021-07-09 | 上海中医药大学附属曙光医院 | Tongue picture acquisition device and method for experimental animals |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1830380A (en) * | 2006-04-20 | 2006-09-13 | 上海交通大学 | Tongue picture anulgis and diagnosis system of traditional Chinese medicine |
| CN104298983A (en) * | 2013-07-15 | 2015-01-21 | 清华大学 | Tongue fur image acquisition and analysis system with distributed user terminals |
| CN106491099A (en) * | 2016-12-30 | 2017-03-15 | 天津森宇科技发展有限公司 | Application cloud computing technology automatically analyzes the intelligence system of human body tongue picture |
| CN109461154A (en) * | 2018-11-16 | 2019-03-12 | 京东方科技集团股份有限公司 | A kind of tongue picture detection method, device, client, server and system |
-
2020
- 2020-08-28 CN CN202010887001.8A patent/CN111990969A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1830380A (en) * | 2006-04-20 | 2006-09-13 | 上海交通大学 | Tongue picture anulgis and diagnosis system of traditional Chinese medicine |
| CN104298983A (en) * | 2013-07-15 | 2015-01-21 | 清华大学 | Tongue fur image acquisition and analysis system with distributed user terminals |
| CN106491099A (en) * | 2016-12-30 | 2017-03-15 | 天津森宇科技发展有限公司 | Application cloud computing technology automatically analyzes the intelligence system of human body tongue picture |
| CN109461154A (en) * | 2018-11-16 | 2019-03-12 | 京东方科技集团股份有限公司 | A kind of tongue picture detection method, device, client, server and system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113080866A (en) * | 2021-04-09 | 2021-07-09 | 上海中医药大学附属曙光医院 | Tongue picture acquisition device and method for experimental animals |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP2021529394A (en) | Time and attendance systems, methods and electronics | |
| US20100023510A1 (en) | Terminal device and system for searching personal information | |
| JP2013114304A (en) | Authentication program, authentication device and authentication method | |
| CN112820366A (en) | Data processing method, device, system, equipment and storage medium | |
| CN112562820A (en) | Processing method and device for detecting record, electronic equipment and storage medium | |
| JP2021099839A (en) | Dialog device, control device, dialog system, dialog method, control method, and program | |
| CN111990969A (en) | Tongue diagnosis detecting system | |
| CN110362700B (en) | Data processing method, device, computer equipment and storage medium | |
| JP7221961B2 (en) | Devices, systems and methods for optimizing pathology workflow | |
| US20150134376A1 (en) | Information management apparatus, terminal, and information management system | |
| WO2020082803A1 (en) | Information processing method and device, server, and medium | |
| CN116226196A (en) | Medical information data query method based on Internet | |
| CN109727142B (en) | Insurance application method, system, equipment and storage medium | |
| CN115841674A (en) | Automatic recording method and device for CRF, electronic equipment and storage medium | |
| WO2021104310A1 (en) | Health management method, device and system, and data acquisition device | |
| CN112906051B (en) | Intelligent medical data processing method and system and data center | |
| JP2009266076A (en) | Electronic medical chart management server and electronic medical chart management system | |
| CN108351346A (en) | Command center | |
| KR102471120B1 (en) | Data transmission system for transmitting and receiving medical information data and a data transmission method thereof | |
| CN113140293A (en) | Medical item auditing method and related device | |
| CN110827996A (en) | Medical auxiliary system based on artificial intelligence and use method thereof | |
| JP6850527B2 (en) | Recruitment support equipment, recruitment support methods, and programs | |
| US20180013816A1 (en) | Method and Apparatus for On Demand Mobile Data Transfer | |
| JP7116444B1 (en) | Application support system, user terminal device, application support device, and program | |
| US20240104173A1 (en) | Generating a token data feed with privacy-preserving logins |
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 | ||
| CB02 | Change of applicant information |
Address after: 050051 Room 102, unit 3, building 91, North Berlin district, Xinhua District, Shijiazhuang City, Hebei Province Applicant after: Shijiazhuang Renkang Technology Co.,Ltd. Address before: 050051 Room 102, unit 3, building 91, North Berlin district, Xinhua District, Shijiazhuang City, Hebei Province Applicant before: Shijiazhuang Yunjun Technology Co.,Ltd. |
|
| CB02 | Change of applicant information |