CN109242836A - Disease forecasting method, apparatus and storage medium - Google Patents
Disease forecasting method, apparatus and storage medium Download PDFInfo
- Publication number
- CN109242836A CN109242836A CN201810981971.7A CN201810981971A CN109242836A CN 109242836 A CN109242836 A CN 109242836A CN 201810981971 A CN201810981971 A CN 201810981971A CN 109242836 A CN109242836 A CN 109242836A
- Authority
- CN
- China
- Prior art keywords
- skin
- prediction result
- user
- image
- server
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30088—Skin; Dermal
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The application provides a kind of disease forecasting method, apparatus and storage medium, wherein, this method comprises: obtaining the skin image of user, the skin image includes: the skin of user, it is analyzed according to skin characteristic of the above-mentioned skin image to user, it obtains for indicating whether the skin of user occurs the prediction result of pathologic variation, and pushes the prediction result.In the technical solution, terminal device can determine whether the skin of user has occurred pathologic and change and be pushed to user in time, so that user has found cutaneous lesions in time, the problem of causing skin disease development serious not in time due to skin disease discovery, endanger user health is avoided.
Description
Technical field
This application involves technical field of image processing more particularly to a kind of disease forecasting method, apparatus and storage mediums.
Background technique
Skin participates in the functional activity of body as first of physiology defence line of human body and maximum organ, moment, maintains
The unity of opposites of body and natural environment, the abnormal conditions of body can also be reflected in skin surface.Skin has life
Defencive function is managed, in the health of maintenance body, is played the role of highly important.The physiological function of skin is damaged, and causes
Skin disease.
In the prior art, dermopathic diagnosis mainly is carried out in such a way that naked-eye observation and instrument detection combine.Tool
Body, it is further detected when user observes by the naked eye skin, and pathologic variation occurs, then by instrument, to make a definite diagnosis out disease
Disease.
However, the pathologic variation of certain skin diseases (for example, infant jaundice) at the initial stage of a disease is smaller, generally it is not easy
Visually found, and when user's discovery, the ratio of General development is more serious, endangers the health of user.
Summary of the invention
The application provides a kind of disease forecasting method, apparatus and storage medium, to overcome existing skin disease detection method
In cause disease development serious not in time due to user's discovery, compromise the problem of the health of user.
A kind of disease forecasting method that the application first aspect provides, comprising:
The skin image of user is obtained, the skin image includes: the skin of user；
It is analyzed according to skin characteristic of the skin image to the user, obtains prediction result, the prediction knot
Fruit is for indicating whether the skin of the user occurs pathologic variation；
Push the prediction result.
Optionally, in a kind of possible implementation of first aspect, it is described according to the skin image to the user
Skin characteristic analyzed, obtain prediction result, comprising:
Image analysis processing is carried out to the skin image, obtains the skin characteristic of the user；
The skin detection model that skin characteristic input obtains in advance is detected, the prediction result is obtained.
Optionally, in the above-mentioned possible implementation of first aspect,
The skin detection model is by healthy skin feature to the various colours of skin and different syndromes in the various stages
When the pathologic delta data that occurs of skin be trained；
Or
The skin detection model is received from server.
Optionally, in the alternatively possible implementation of first aspect, it is described according to the skin image to the use
The skin characteristic at family is analyzed, and prediction result is obtained, comprising:
Skin detection request is sent to server, the skin detection request includes the skin image, the skin inspection
Request is surveyed for requesting the server to carry out analysis detection to the skin image, determines whether the skin of the user occurs
Pathologic variation；
Receive the prediction result that the server returns.
Optionally, in another possible implementation of first aspect, it is described according to the skin image to the use
The skin characteristic at family is analyzed, and prediction result is obtained, comprising:
Image analysis processing is carried out to the skin image, obtains the skin characteristic of the user；
Skin detection request is sent to server, the skin detection request includes the skin characteristic, the skin inspection
Request is surveyed for requesting the server to carry out analysis detection to the skin characteristic, determines whether the skin of the user occurs
Pathologic variation；
Receive the prediction result that the server returns.
Optionally, in another possible implementation of first aspect, the method also includes:
Obtain the accuracy of the prediction result；
According to the accuracy of the prediction result, processing is optimized to the skin detection model；
Or
The accuracy of the prediction result is fed back into the server, so that the server is according to the prediction result
Accuracy, processing is optimized to the skin detection model.
Optionally, in another possible implementation of first aspect, the push prediction result, comprising:
By augmented reality AR mode by the prediction result Overlapping display in the corresponding pictured scene of the skin image
In.
The application second aspect provides a kind of disease forecasting method, comprising:
The skin detection request that receiving terminal apparatus is sent, skin detection request include user skin image or
The skin characteristic of the user；
It is requested according to the skin detection, analysis detection is carried out to the skin image or the skin characteristic, is obtained
Prediction result, the prediction result is for indicating whether the skin of the user occurs pathologic variation；
The prediction result is returned into the terminal device.
Optionally, described to be requested according to the skin detection in a kind of possible implementation of second aspect, to described
Skin image or the skin characteristic carry out analysis detection, obtain prediction result, comprising:
Image analysis processing is carried out to the skin image, obtains the skin characteristic of the user；
The skin detection model that skin characteristic input obtains in advance is detected, the prediction result is obtained；
Or
The skin detection model that skin characteristic input obtains in advance is detected, the prediction result is obtained.
Optionally, in the above-mentioned possible implementation of second aspect, the method also includes:
The corresponding pathologic of skin becomes when by healthy skin feature to the various colours of skin and different syndromes in each stage
Change data and carry out model training, obtains the skin detection model.
Optionally, in the above-mentioned possible implementation of second aspect, the method also includes:
Receive the accuracy of the prediction result of the terminal device feedback；
According to the accuracy of the prediction result, processing is optimized to the skin detection model.
The application third aspect provides a kind of disease forecasting device, comprising: obtains module and processing module；
The acquisition module, for obtaining the skin image of user, the skin image includes: the skin of user, according to
The skin image analyzes the skin characteristic of the user, obtains prediction result, the prediction result is for indicating institute
Whether the skin for stating user occurs pathologic variation；
The processing module, for pushing the prediction result.
Optionally, in a kind of possible implementation of the third aspect, the acquisition module, for according to the skin figure
As analyzing the skin characteristic of the user, acquisition prediction result, specifically:
The acquisition module is specifically used for carrying out image analysis processing to the skin image, obtains the skin of the user
The skin detection model that skin characteristic input obtains in advance is detected, obtains the prediction result by skin feature.
Optionally, in the above-mentioned possible implementation of the third aspect,
The skin detection model is by healthy skin feature to the various colours of skin and different syndromes in the various stages
When the pathologic delta data that occurs of skin carry out model training and obtain；
Or
The skin detection model is received from server.
Optionally, in the alternatively possible implementation of the third aspect, described device further include: transceiver module；
The transceiver module, for sending skin detection request, and the institute that the reception server returns to server
Prediction result is stated, the skin detection request includes the skin image, and the skin detection request is for requesting the service
Device carries out analysis detection to the skin image, determines whether the skin of the user occurs pathologic variation.
Optionally, in another possible implementation of the third aspect, the acquisition module, for according to the skin
Image analyzes the skin characteristic of the user, obtains prediction result, specifically:
The acquisition module is specifically used for carrying out image analysis processing to the skin image, obtains the skin of the user
Skin feature；
Described device further include: transceiver module；
The transceiver module, for sending skin detection request, and the institute that the reception server returns to server
Prediction result is stated, the skin detection request includes the skin characteristic, and the skin detection request is for requesting the service
Device carries out analysis detection to the skin characteristic, determines whether the skin of the user occurs pathologic variation.
Optionally, in another possible implementation of the third aspect, the acquisition module is also used to obtain described pre-
Survey the accuracy of result；
The processing module is also used to the accuracy according to the prediction result, carries out to the skin detection model excellent
Change processing；
Or
The transceiver module is also used to the accuracy of the prediction result feeding back to the server, so that the clothes
Device be engaged according to the accuracy of the prediction result, processing is optimized to the skin detection model.
Optionally, in another possible implementation of the third aspect, the processing module, for pushing the prediction
As a result, specifically:
The processing module is used for the prediction result Overlapping display through augmented reality AR mode in the skin figure
As in corresponding pictured scene.
The application fourth aspect provides a kind of disease forecasting device, comprising: includes: transceiver module and processing module；
The transceiver module, for the skin detection request that receiving terminal apparatus is sent, the skin detection request includes
The skin image of user or the skin characteristic of the user；
The processing module, for being requested according to the skin detection, to the skin image or the skin characteristic
Analysis detection is carried out, obtains prediction result, the prediction result is for indicating whether the skin of the user occurs pathologic change
Change；
The transceiver module is also used to the prediction result returning to the terminal device.
Optionally, in a kind of possible implementation of fourth aspect, the processing module, for being examined according to the skin
Request is surveyed, analysis detection is carried out to the skin image or the skin characteristic, obtains prediction result, specifically:
The processing module is specifically used for carrying out image analysis processing to the skin image, obtains the skin of the user
The skin detection model that skin characteristic input obtains in advance is detected, obtains the prediction result by skin feature；
Or
The processing module is examined specifically for the skin detection model for obtaining skin characteristic input in advance
It surveys, obtains the prediction result.
Optionally, in a kind of possible implementation of fourth aspect, the processing module is also used to by various skins
The healthy skin feature and different syndromes of color in each stage when the corresponding pathologic delta data of skin carry out model training, obtain
To the skin detection model.
Optionally, in the above-mentioned possible implementation of fourth aspect, the transceiver module is also used to receive the terminal
The accuracy of the prediction result of equipment feedback；
The processing module is also used to the accuracy according to the prediction result, carries out to the skin detection model excellent
Change processing.
The aspect of the application the 5th provides a kind of disease forecasting device, including processor, memory and is stored in the storage
On device and the computer program that can run on a processor, the processor realize such as above-mentioned first aspect when executing described program
And method or such as above-mentioned second aspect and second aspect described in any one of various possible implementations of first aspect
Method described in any one of various possibility implementations.
The 6th aspect of the application provides a kind of storage medium, instruction is stored in the storage medium, when it is in computer
When upper operation, so that computer is executed as described in any one of above-mentioned first aspect and the various possible implementations of first aspect
Method or the method as described in any one of above-mentioned second aspect and the various possible implementations of second aspect.
Disease forecasting method, apparatus provided by the embodiments of the present application and storage medium, by the skin for obtaining user's skin
Skin image, and analysis is carried out according to skin characteristic of the skin image to user and is obtained for indicating whether the skin of user occurs
The prediction result of pathologic variation, pushes the prediction result.In the technical solution, terminal device can determine in time user's
Whether skin has occurred pathologic variation, and is pushed to user, so that user has found cutaneous lesions in time, avoids due to skin
The problem of disease discovery causes skin disease development serious not in time, endangers user health.
Detailed description of the invention
Fig. 1 is the flow diagram of disease forecasting embodiment of the method one provided by the embodiments of the present application；
Fig. 2 is the flow diagram of disease forecasting embodiment of the method two provided by the embodiments of the present application；
Fig. 3 is the interaction schematic diagram of disease forecasting embodiment of the method three provided by the embodiments of the present application；
Fig. 4 is the interaction schematic diagram of disease forecasting embodiment of the method four provided by the embodiments of the present application；
Fig. 5 is the flow diagram of disease forecasting embodiment of the method five provided by the embodiments of the present application；
Fig. 6 is the interaction schematic diagram of disease forecasting embodiment of the method six provided by the embodiments of the present application；
Fig. 7 is the structural schematic diagram of disease forecasting Installation practice one provided by the embodiments of the present application；
Fig. 8 is the structural schematic diagram of disease forecasting Installation practice two provided by the embodiments of the present application；
Fig. 9 is the structural schematic diagram of disease forecasting Installation practice three provided by the embodiments of the present application.
Specific embodiment
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
In attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is
Some embodiments of the present application, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall in the protection scope of this application.
In order to judge whether user has suffered from skin disease, in the prior art, phase is usually detected by naked-eye observation and instrument
In conjunction with mode carry out dermopathic diagnosis.But in practical applications, the pathologic due to certain skin diseases at the initial stage of a disease
Change smaller, be generally not easy visually to be found, so that the prior art exists since skin disease discovery leads to skin disease not in time
The problem of ratio of development is more serious, endangers user health.
In view of the above-mentioned problems, the embodiment of the present application provides a kind of disease forecasting method, the skin based on the user got
Skin image is analyzed by the skin characteristic to user, is obtained for indicating whether the skin of user occurs pathologic variation
Prediction result, and be pushed to user in time, avoid skin disease discovery causes skin disease development serious not in time, endangers user
The problem of health.
Optionally, the executing subject of the disease forecasting method provided by the embodiments of the present application can be independently complete by terminal device
At can also be completed by terminal device and server collaboration.In the following, being carried out by technical solution of the specific embodiment to the application
It is described in detail.
It should be noted that these specific embodiments can be combined with each other below, for the same or similar concept
Or process may repeat no more in certain embodiments.
Fig. 1 is the flow diagram of disease forecasting embodiment of the method one provided by the embodiments of the present application.Optionally, the disease
Prediction technique can be applied to terminal device, which can be smart phone, smartwatch, camera etc. and have camera shooting function
The smart machine of energy, is also possible to the other equipment for having camera function.The embodiment of the present application is not to the specific table of terminal device
Existing form is defined.
Specifically, as shown in Figure 1, disease forecasting method provided by the embodiments of the present application may include steps of:
Step 11: obtaining the skin image of user, which includes: the skin of user.
It optionally,, should when user wants determination oneself or whether other people suffer from skin disease in embodiments herein
The camera that user can use terminal device shoots the skin of user, to obtain the skin image of user.It can manage
Solution, need in the skin image include user skin, such terminal device or server just can be to the skin images
In user skin handle and obtain skin whether occur pathologic variation prediction result.
Step 12: being analyzed according to skin characteristic of the above-mentioned skin image to user, obtain prediction result.
Wherein, the prediction result is for indicating whether the skin of user occurs pathologic variation.
Optionally, after terminal device gets the skin image of user, pass through the skin of user in analyzing skin image
It determines skin characteristic, then the skin characteristic is analyzed, judge whether the skin of the user has occurred pathologic variation, and
It obtains prediction result, indicates whether the skin of user occurs pathologic and change using the prediction result.
Optionally, which can be analyzed to obtain by skin characteristic of the terminal device to user, be also possible to
Skin image that terminal device will acquire or obtained skin characteristic are sent to server, by server to skin image or skin
Skin signature analysis obtains.It may refer in following Fig. 2, Fig. 3 or embodiment illustrated in fig. 4 about specific possible implementation
It records, details are not described herein again.
Step 13: pushing above-mentioned prediction result.
Optionally, when terminal device gets the prediction result whether skin for indicating user occurs pathologic variation
Later, which can be pushed to user.Optionally, the mode of push, which can be, passes through augmented reality
(augmented reality, AR) mode is shown in the pictured scene where skin image, is also possible to pass through information reminding
Mode be pushed to the user of the terminal device so that the user gets the prediction result about skin in time.
Optionally, the mode that above- mentioned information are reminded can be terminal device and make a sound prompting, be also possible to terminal device
Generating one includes that the texts such as the short message of pathologic problem are reminded, and can also be other alerting patterns.The embodiment of the present application
The push mode of the mode of the information reminding and prediction result is not defined, it can be according to the actual set of user
Mode determines.
Disease forecasting method provided by the embodiments of the present application, by obtaining the skin image of user's skin, and according to the skin
Skin image carries out analysis to the skin characteristic of user and obtains for indicating whether the skin of user occurs the prediction of pathologic variation
As a result, pushing the prediction result.In the technical solution, terminal device can determine whether the skin of user has occurred disease in time
Rationality variation, and it is pushed to user, so that user has found cutaneous lesions in time, avoid since skin disease discovery causes not in time
The problem of skin disease development is serious, endangers user health.
Optionally, in a kind of possible implementation of the embodiment of the present application, above-mentioned steps 12 can be only by terminal device
It is vertical to execute.Optionally, Fig. 2 is the flow diagram of disease forecasting embodiment of the method two provided by the embodiments of the present application.Such as Fig. 2 institute
Show, above-mentioned steps 12 (being analyzed according to skin characteristic of the above-mentioned skin image to user, obtain prediction result) may include
Following steps:
Step 21: image analysis processing being carried out to above-mentioned skin image, obtains the skin characteristic of user.
It optionally, in the present embodiment, can be to the skin when terminal device gets the skin image of the user of shooting
Skin image carries out image transformation, image compression, image enhancement and recovery, image segmentation, iamge description and image (classification)
Certain or several operations in a variety of image analysis processings such as identification, and then obtain the skin spy that the skin image correspond to user
Sign.
It is understood that the concrete operations for the image analysis processing that terminal device carries out skin image can be according to end
Itself of the ability of end equipment and the skin image feature determine that details are not described herein again.
Step 22: the skin detection model that skin characteristic input obtains in advance being detected, prediction result is obtained.
It optionally,, can be by the skin after terminal device gets the skin characteristic of user in embodiments herein
Skin feature is input on terminal device in running skin detection model, and it is pre- to execute pathologic variation by skin detection model
It surveys, and then obtains prediction result.
Optionally, which is that terminal device is got in advance, specifically can be terminal device or other
Equipment is trained by the skin characteristic data to numerous users, is also possible to server and is passed through to numerous users'
Skin characteristic data are trained.Optionally, in the present embodiment, the skin characteristic data of numerous users include user's
Healthy skin feature and different syndromes in each stage when the corresponding pathologic delta data of skin.
Specifically, as an example, skin detection model can be terminal device or other equipment and pass through to numerous use
What the skin characteristic data at family were trained, it can be construed to as follows:
The skin detection model be by healthy skin feature to the various colours of skin and different syndromes at the various stages
The pathologic delta data that skin occurs carries out what model training obtained.
In the present embodiment, terminal device or the available health to the corresponding various colours of skin of a variety of users of other equipment
Skin characteristic, also the available skin to the user pathologic that skin occurs at the various stages of different syndromes changes number
According to, thus, terminal device or other equipment can obtain above-mentioned skin detection model based on the deep learning ability of big data.
Specifically, it is that server passes through the skin to numerous users that skin detection model, which can be, as another example
What characteristic was trained, at this point, the skin detection model that terminal device is got in advance can be construed to as follows:
The skin detection model is received from server.
Optionally, server can also by healthy skin feature to the various colours of skin and different syndromes in each stage when
The corresponding pathologic delta data of skin carries out model training, obtains above-mentioned skin detection model, and the skin detection that will be obtained
Model is sent to terminal device, so that terminal device be made to get the skin detection model.
Optionally, regardless of in terminal device, still in the server, skin detection model can use convolutional Neural
Network (convolutional neural networks, CNNs) structure, the specific can be that depth convolutional neural networks.It can
Choosing, the terminal device perhaps server skin image that can will acquire or user in training skin detection model
Input of the skin characteristic as defect inspection model, using convolutional neural networks to the skin characteristic of skin image or user into
Row signature analysis or identification obtain above-mentioned prediction result.
Disease forecasting method provided by the embodiments of the present application, terminal device carry out at image analysis above-mentioned skin image
Reason, obtains the skin characteristic of user, and the skin detection model that skin characteristic input obtains in advance is detected, is predicted
As a result.The technical solution may be implemented to change the automatic detection of skin characteristic and skin disease rationality pre- using skin detection model
It surveys, can find the pathologic variation of skin in time, avoid because it is found that the development of bring disease seriously, use by harm not in time
The problem of family health.
Optionally, in the alternatively possible implementation of the embodiment of the present application, above-mentioned steps 12 can be set by terminal
Standby and server interactive operation executes.Optionally, the above-mentioned skin image that terminal device both can directly will acquire is direct
Be sent to server so that server according to the skin image execute pathologic variation (referring to following embodiment illustrated in fig. 3),
The skin characteristic obtained by image analysis processing can be sent to server so that server is executed according to the skin characteristic
Pathologic changes (referring to following embodiment illustrated in fig. 4).About the determination of concrete mode, can according to the ability of terminal device and
Actual demand determines that details are not described herein again.
As an example, Fig. 3 is the interaction schematic diagram of disease forecasting embodiment of the method three provided by the embodiments of the present application.
As shown in figure 3, above-mentioned steps 12 (being analyzed according to skin characteristic of the above-mentioned skin image to user, obtain prediction result) can
To include the following steps:
Step 31: terminal device sends skin detection request to server, and skin detection request includes above-mentioned skin figure
Picture.
Wherein, skin detection request is determined and is used for requesting the server to carry out analysis detection to above-mentioned skin image
Whether the skin at family occurs pathologic variation.
Optionally, in the present embodiment, terminal device and server can have wireless communication function, thus the terminal
Equipment can be linked into server, and carry out wireless communication with the server.
Optionally, terminal device can include according to skin image generation after getting the skin image of user
Skin detection request including skin image, and then skin detection request is sent to server, to request the server pair
Skin image in skin detection request carries out analysis detection, determines whether the skin of user occurs pathologic variation.
Step 32: server is requested according to the above-mentioned skin detection received, to skin image in skin detection request
Analysis detection is carried out, prediction result is obtained.
Wherein, the prediction result is for indicating whether the skin of user occurs pathologic variation.
Optionally, after the skin detection request of generation is sent to server by terminal device, which can be connect
Receive skin detection request.Optionally, in the present embodiment, skin detection request includes the skin image of user.
Optionally, server is requested according to above-mentioned skin detection, is carried out analysis detection to the skin image and is obtained prediction knot
Fruit, the i.e. step 32 could alternatively be following steps 321 and step 322:
Step 321: server carries out image analysis processing to above-mentioned skin image, obtains the skin characteristic of user.
Optionally, server gets the skin detection request of terminal device transmission, and by being analyzed and acquired by skin inspection
It surveys after the skin image for including in request, can determine the skin of user first by the skin of user in analyzing skin image
Skin feature, and then step 322 is executed again.
Step 322: server detects the skin detection model that the input of above-mentioned skin characteristic obtains in advance, obtains pre-
Survey result.
Optionally, after server determines the skin characteristic of user, further the skin characteristic can be handled, had
Body, above-mentioned skin characteristic can be input in the skin detection model obtained in advance by server, detected and judged the user
Skin pathologic variation whether has occurred, and obtain prediction result, i.e., using the prediction result indicate user skin whether
Pathologic variation occurs.
Optionally, in the present embodiment, the skin detection model that server obtains in advance can be server and be gone through according to numerous
History skin characteristic data are trained, and are also possible to terminal device and are trained according to numerous history skin characteristic data
Server is obtained and is sent to, the mode that the embodiment of the present application does not obtain skin detection model to server is defined.
Step 33: above-mentioned prediction result is returned to terminal device by server.
It optionally, can after server carries out analysis detection acquisition prediction result to skin image in skin detection request
The prediction result is then forwarded to terminal device, so that terminal device receives the prediction result that server returns.
Optionally, due to the platform that server may be an information processing, it can receive terminal device transmission
Skin detection request, and to the skin detection request perform corresponding processing to obtain prediction result, due to terminal device need by
Indicate whether the skin of user occurs the prediction result of pathologic variation and is pushed to user, so, server needs to obtain
Prediction result feeds back to terminal device.
Disease forecasting method provided by the embodiments of the present application, terminal device send the skin including skin image to server
Detection request, skin detection request carry out analysis detection to the skin image for request server, determine the skin of user
Whether pathologic variation is occurred, and server is requested according to the above-mentioned skin detection received, to skin in skin detection request
Image carries out analysis detection, obtains prediction result, and above-mentioned prediction result is returned to terminal device.In the technical solution, eventually
The skin image that end equipment will acquire is sent to server and carries out analysis detection, reduces the processing pressure of terminal device, mentions
The high reaction speed of terminal device.
As another example, Fig. 4 is the interaction signal of disease forecasting embodiment of the method four provided by the embodiments of the present application
Figure.The difference of Fig. 4 and Fig. 3 is: carrying out image analysis processing to skin image in embodiment illustrated in fig. 4 and obtains the skin of user
The step of feature is to execute in terminal equipment side, and carry out image analysis processing to skin image in embodiment illustrated in fig. 3 and obtain
The step of skin characteristic of user, is executed in server side.
Optionally, as shown in figure 4, above-mentioned steps 12 (analyzed according to skin characteristic of the above-mentioned skin image to user,
Obtain prediction result) it may include steps of:
Step 41: terminal device carries out image analysis processing to the skin image got, obtains the skin characteristic of user.
Optionally, after terminal device gets the skin image of user, image can be carried out to the skin image first
The image analysis processings such as transformation, image segmentation and image recognition, obtain the skin characteristic that the skin image corresponds to user, then again
The skin characteristic is sent to server so that the server analyzes the skin of user to obtain prediction result, that is, executes step
Rapid 42.
Step 42: terminal device sends skin detection request to server, and skin detection request includes the skin of user
Feature.
Wherein, skin detection request carries out analysis detection to skin characteristic for request server, determines the skin of user
Whether skin occurs pathologic variation.
Optionally, in the present embodiment, terminal device and server can carry out wireless communication, thus, terminal device exists
After getting the skin characteristic of user, it can be asked according to the skin detection that the skin characteristic generates including skin characteristic
It asks, and then skin detection request is sent to server, to request the server special to the skin in skin detection request
Sign carries out analysis detection, determines whether the skin of user occurs pathologic variation.
Step 43: server detects the skin detection model that the input of above-mentioned skin characteristic obtains in advance, obtains pre-
Survey result.
Optionally, after the skin detection including skin characteristic that server receives terminal device transmission is requested,
Above-mentioned skin characteristic can be input in the skin detection model obtained in advance, detect and judge whether the skin of the user is sent out
Pathologic variation has been given birth to, and has shown whether the skin of expression user occurs the prediction result of pathologic variation.
It may refer to step 322 in above-mentioned embodiment illustrated in fig. 3 about how server obtains skin detection model in advance
In record, details are not described herein again.
Step 44: above-mentioned prediction result is returned to terminal device by server.
Optionally, the step is as the operation of step 33 in above-mentioned embodiment illustrated in fig. 3, and server is by above-mentioned skin
The skin detection model that feature input obtains in advance is detected after obtaining prediction result, needs prediction result feeding back to end
End equipment, so that terminal device pushes the prediction result.
Disease forecasting method provided by the embodiments of the present application, terminal device carry out image analysis to the skin image got
Processing obtains the skin characteristic of user, and sends skin detection request to server, and skin detection request includes user's
Skin characteristic, skin detection request carry out analysis detection to skin characteristic for request server, determine that the skin of user is
The skin detection model that the input of above-mentioned skin characteristic obtains in advance is detected, is obtained by no generation pathologic variation, server
Prediction result, and the prediction result is sent to terminal device.In the technical solution, terminal device is to the skin image got
After carrying out the skin characteristic that processing obtains user, it is then forwarded to server and carries out analysis detection, reduce the processing of terminal device
Pressure improves the reaction speed of terminal device.
Optionally, based on any of the above embodiments, Fig. 5 is that disease forecasting method provided by the embodiments of the present application is real
Apply the flow diagram of example five.As shown in figure 5, above-mentioned steps 13 (push above-mentioned prediction result) in embodiments herein
Replace with following steps realization:
Step 51: by augmented reality AR mode by above-mentioned prediction result Overlapping display in the corresponding picture of above-mentioned skin image
In the scene of face.
Optionally, in embodiments herein, terminal device, which gets prediction result, (can be terminal device to skin
Image carries out what analysis detection obtained, is also possible to server and obtains to skin image or skin characteristic progress analysis detection, and
Feed back to terminal device) after, it, can be by the side AR in order to allow user to find that pathologic variation has occurred in skin in time
Formula is by the prediction result Overlapping display in the corresponding pictured scene of skin image.
For example, the prediction result can by way of character introduction, animation or video Overlapping display in above-mentioned skin figure
As corresponding pictured scene (optional, which can be by showing that screen is shown), so that the user obtains in time
Get the prediction result about skin.
Optionally, AR technology is a kind of by " seamless " the integrated new technology of real-world information and virtual world information, is
Script is difficult experience in the certain time spatial dimension of real world entity information (visual information, sound, taste,
Tactile etc.) pass through the science and technology such as computer, it is superimposed again after analog simulation, by virtual Information application to real world, by the mankind
Sense organ is perceived, to reach the sensory experience of exceeding reality.True environment and virtual object have been added to together in real time
One picture or space exist simultaneously.
In the present embodiment, by AR mode by prediction result Overlapping display in the corresponding pictured scene of skin image,
It is amplified the prediction result of the skin characteristic of user and is superimposed upon the corresponding picture of the above-mentioned skin image of shooting
In the scene of face, such user can be shortened user and be found that the pathologic changes with the open-and-shut timely learning prediction result
Time, improve detection efficiency.
Optionally, on the basis of the above embodiments, Fig. 6 is disease forecasting embodiment of the method provided by the embodiments of the present application
Six interaction schematic diagram.As shown in fig. 6, the disease forecasting method can also include the following steps:
Step 61: terminal device obtains the accuracy of above-mentioned prediction result.
Optionally, after terminal device obtains above-mentioned prediction result and is pushed to user or medical staff, user or doctor
Shield personnel can be detected by means of skin of the special instrument to the user again, to determine the prediction result of terminal device push
Accuracy, and by it by the screen feedback of terminal device to terminal device, thus the available above-mentioned prediction of terminal device
As a result accuracy.
Optionally, in the embodiment of the application, if it is determined that whether the skin of user occurs the skin of pathologic variation
When detection model is disposed on the terminal device, terminal device can directly execute following steps:
Step 62: terminal device optimizes processing to skin detection model according to the accuracy of the prediction result.
Optionally, the prediction result obtained using skin detection model when terminal device and the reality obtained by special instrument
When border testing result is less than prediction threshold value, terminal device can directly be tied above-mentioned skin image or skin characteristic and prediction
Fruit, actually detected result etc. are input in above-mentioned skin detection model to optimize above-mentioned skin detection model, improve skin inspection
Survey the prediction accuracy of model.
Optionally, in another embodiment of the application, if it is determined that whether the skin of user occurs the skin of pathologic variation
When skin detection model is disposed on the server, after above-mentioned steps 61, terminal device and server can be executed by cooperation
Following steps 63 and step 64:
Step 63: the accuracy of above-mentioned prediction result is fed back to server by terminal device.
Step 64: server carries out above-mentioned skin detection model according to the accuracy of the above-mentioned prediction result received
Optimization processing.
Optionally, in the present embodiment, after terminal device gets the accuracy of above-mentioned prediction result, if prediction result
Accuracy be less than preset threshold, and prediction result is that terminal device is got from server, then, terminal device can
The accuracy of the prediction result is fed back into server again so that server according to above-mentioned skin image or skin characteristic and its
Corresponding prediction result, actually detected result etc. are input in above-mentioned skin detection model to optimize above-mentioned skin detection mould
Type improves the prediction accuracy of skin detection model in server.
Disease forecasting method provided by the embodiments of the present application, after terminal device obtains the accuracy of above-mentioned prediction result,
Terminal device can optimize processing to skin detection model, end can be improved in this way according to the accuracy of the prediction result
The prediction accuracy of skin detection model in end equipment；Alternatively, the accuracy of above-mentioned prediction result is fed back to clothes by terminal device
Business device, so that accuracy of the server according to the above-mentioned prediction result received, optimizes place to above-mentioned skin detection model
Reason improves the prediction accuracy of skin detection model in server.
Following is the application Installation practice, can be used for executing the application embodiment of the method.It is real for the application device
Undisclosed details in example is applied, the application embodiment of the method is please referred to.
Fig. 7 is the structural schematic diagram of disease forecasting Installation practice one provided by the embodiments of the present application.In the present embodiment,
The disease forecasting device can integrate in terminal device, or a terminal device.Optionally, as shown in fig. 7, the application
The disease forecasting device that embodiment provides may include: to obtain module 71 and processing module 72.
Wherein, the acquisition module 71, for obtaining the skin image of user, which includes: the skin of user, root
It is analyzed according to skin characteristic of the skin image to user, obtains prediction result, the prediction result is for indicating the use
Whether the skin at family occurs pathologic variation.
The processing module 72, for pushing the prediction result.
Optionally, in a kind of possible implementation of the present embodiment, above-mentioned acquisition module 71, for according to the skin
Image analyzes the skin characteristic of the user, obtains prediction result, specifically:
Above-mentioned acquisition module 71 is specifically used for carrying out image analysis processing to the skin image, obtains the user's
The skin detection model that skin characteristic input obtains in advance is detected, obtains the prediction result by skin characteristic.
Optionally, above-mentioned skin detection model is by healthy skin feature to the various colours of skin and different syndromes each
What the pathologic delta data that skin occurs when the kind stage was trained；
Or
Above-mentioned skin detection model is received from server.
Optionally, in the alternatively possible implementation of the present embodiment, as shown in fig. 7, the disease forecasting device also wraps
It includes: transceiver module 73.
The transceiver module 73, for sending skin detection request, and the institute that the reception server returns to server
Prediction result is stated, the skin detection request includes the skin image, and the skin detection request is for requesting the service
Device carries out analysis detection to the skin image, determines whether the skin of the user occurs pathologic variation.
Optionally, in the alternatively possible implementation of the present embodiment, above-mentioned acquisition module 71, for according to the skin
Skin image analyzes the skin characteristic of the user, obtains prediction result, specifically:
Above-mentioned acquisition module 71 is specifically used for carrying out image analysis processing to the skin image, obtains the user's
Skin characteristic；
Correspondingly, above-mentioned transceiver module 73, for sending skin detection request, and the reception server to server
The prediction result returned, the skin detection request includes the skin characteristic, and the skin detection request is for requesting
The server carries out analysis detection to the skin characteristic, determines whether the skin of the user occurs pathologic variation.
Optionally, in the above-mentioned possible implementation of the present embodiment, above-mentioned acquisition module 71 is also used to obtain described pre-
Survey the accuracy of result.
Above-mentioned processing module 72, is also used to the accuracy according to the prediction result, carries out to the skin detection model
Optimization processing.
Or
Above-mentioned transceiver module 73 is also used to the accuracy of the prediction result feeding back to the server, so that described
Server optimizes processing to the skin detection model according to the accuracy of the prediction result.
Optionally, in the possible implementation of any one of the above of the present embodiment, above-mentioned processing module 72, for pushing
The prediction result, specifically:
Above-mentioned processing module 72 is used for the prediction result Overlapping display through augmented reality AR mode in the skin
In the corresponding pictured scene of image.
The disease forecasting device of the present embodiment can be used for executing the reality of terminal device in embodiment of the method shown in Fig. 1 to Fig. 6
Existing scheme, specific implementation is similar with technical effect, and which is not described herein again.
Fig. 8 is the structural schematic diagram of disease forecasting Installation practice two provided by the embodiments of the present application.In the present embodiment,
The disease forecasting device can integrate in the server, or a server.Optionally, as shown in figure 8, the application is implemented
The disease forecasting device that example provides may include: transceiver module 81 and processing module 82.
Wherein, the transceiver module 81, for the skin detection request that receiving terminal apparatus is sent, the skin detection request
The skin characteristic of skin image or the user including user.
The processing module 82, for being requested according to the skin detection, to the skin image or the skin characteristic
Analysis detection is carried out, obtains prediction result, the prediction result is for indicating whether the skin of the user occurs pathologic change
Change.
The transceiver module 81 is also used to the prediction result returning to the terminal device.
Optionally, in a kind of possible implementation of the embodiment of the present application, above-mentioned processing module 82, for according to
Skin detection request carries out analysis detection to the skin image or the skin characteristic, obtains prediction result, specifically:
The processing module 82 is specifically used for carrying out image analysis processing to the skin image, obtains the skin of the user
The skin detection model that skin characteristic input obtains in advance is detected, obtains the prediction result by skin feature.
Or
The processing module 82 is examined specifically for the skin detection model for obtaining skin characteristic input in advance
It surveys, obtains the prediction result.
Optionally, in the above-mentioned possible implementation of the embodiment of the present application, above-mentioned processing module 82 is also used to by right
The healthy skin feature and different syndromes of the various colours of skin in each stage when the corresponding pathologic delta data of skin carry out model
Training, obtains the skin detection model.
Optionally, in a kind of possible implementation of the embodiment of the present application, above-mentioned transceiver module 81 is also used to receive institute
State the accuracy of the prediction result of terminal device feedback.
Above-mentioned processing module 82, is also used to the accuracy according to the prediction result, carries out to the skin detection model
Optimization processing.
The disease forecasting device of the present embodiment can be used for executing the realization of server in embodiment of the method shown in Fig. 1 to Fig. 6
Scheme, specific implementation is similar with technical effect, and which is not described herein again.
It should be noted that it should be understood that the modules of apparatus above division be only a kind of logic function division,
It can completely or partially be integrated on a physical entity in actual implementation, it can also be physically separate.And these modules can be with
All realized by way of processing element calls with software；It can also all realize in the form of hardware；It can also part mould
Block realizes that part of module passes through formal implementation of hardware by way of processing element calls software.For example, determining module can be with
For the processing element individually set up, it also can integrate and realized in some chip of above-mentioned apparatus, in addition it is also possible to program
The form of code is stored in the memory of above-mentioned apparatus, is called by some processing element of above-mentioned apparatus and is executed above true
The function of cover half block.The realization of other modules is similar therewith.Furthermore these modules completely or partially can integrate together, can also
With independent realization.Processing element described here can be a kind of integrated circuit, the processing capacity with signal.In the process of realization
In, each step of the above method or the above modules can by the integrated logic circuit of the hardware in processor elements or
The instruction of software form is completed.
For example, the above module can be arranged to implement one or more integrated circuits of above method, such as:
One or more specific integrated circuits (application specific integrated circuit, ASIC), or, one
Or multi-microprocessor (digital signal processor, DSP), or, one or more field programmable gate array
(field programmable gate array, FPGA) etc..For another example, when some above module dispatches journey by processing element
When the form of sequence code is realized, which can be general processor, such as central processing unit (central
Processing unit, CPU) or it is other can be with the processor of caller code.For another example, these modules can integrate one
It rises, is realized in the form of system on chip (system-on-a-chip, SOC).
In the above-described embodiments, can come wholly or partly by software, hardware, firmware or any combination thereof real
It is existing.When implemented in software, it can entirely or partly realize in the form of a computer program product.The computer program
Product includes one or more computer instructions.When loading on computers and executing the computer program instructions, all or
It partly generates according to process or function described in the embodiment of the present application.The computer can be general purpose computer, dedicated meter
Calculation machine, computer network or other programmable devices.The computer instruction can store in computer readable storage medium
In, or from a computer readable storage medium to the transmission of another computer readable storage medium, for example, the computer
Instruction can pass through wired (such as coaxial cable, optical fiber, number from a web-site, computer, server or data center
User's line (DSL)) or wireless (such as infrared, wireless, microwave etc.) mode to another web-site, computer, server or
Data center is transmitted.The computer readable storage medium can be any usable medium that computer can access or
It is comprising data storage devices such as one or more usable mediums integrated server, data centers.The usable medium can be with
It is magnetic medium, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid state hard disk
Solid state disk (SSD)) etc..
Fig. 9 is the structural schematic diagram of disease forecasting Installation practice three provided by the embodiments of the present application.As shown in figure 9, should
Disease forecasting device may include: processor 91 and memory 92 and be stored on the memory 92 and can be in the processing
The computer program run on device 91, the processor 91 realize that the method as shown in above-mentioned Fig. 1 to Fig. 6 is real when executing described program
Apply the realization side of the implementation of terminal device or realization server in the embodiment of the method as shown in above-mentioned Fig. 1 to Fig. 6 in example
Case.
Optionally, which can also include transceiver 93, which can be by standalone feature
Transmitters and receivers are realized, both can realize that the embodiment of the present application does not limit it by forms such as antennas.Accordingly
, processor 91 and transceiver 93 execute terminal device or server and are as above applied to for running computer executed instructions
Each step in disease forecasting method.
Optionally, the processor 91 in the acquisition module 71 in above-mentioned Fig. 7 and the corresponding the embodiment of the present application of processing module 72,
The transceiver 93 etc. in the corresponding the embodiment of the present application of transceiver module 73 in above-mentioned Fig. 7.
Alternatively, the processing module 82 in above-mentioned Fig. 8 corresponds to the processor 91 in the embodiment of the present application, the receipts in above-mentioned Fig. 8
Send out the transceiver 93 etc. in the corresponding the embodiment of the present application of module 81.
Optionally, the embodiment of the present application also provides a kind of storage medium, and instruction is stored in the storage medium, when its
When being run on computer, so that computer executes the implementation of terminal device in the embodiment of the method as shown in above-mentioned Fig. 1 to Fig. 6
Or realize the implementation of server in the embodiment of the method as shown in above-mentioned Fig. 1 to Fig. 6.
Optionally, the embodiment of the present application also provides a kind of chip of operating instruction, and the chip is for executing such as above-mentioned Fig. 1
Into embodiment of the method shown in Fig. 6, the implementation of terminal device or realization are in the embodiment of the method as shown in above-mentioned Fig. 1 to Fig. 6
The implementation of server.
The embodiment of the present application also provides a kind of program product, and described program product includes computer program, the computer
Program is stored in a storage medium, at least one processor can read the computer program from the storage medium, described
At least one processor can realize terminal device in embodiment of the method shown in above-mentioned Fig. 1 to Fig. 6 when executing the computer program
Implementation or realize the embodiment of the method as shown in above-mentioned Fig. 1 to Fig. 6 in server implementation.
Term " multiple " herein refers to two or more.The terms "and/or", only a kind of description
The incidence relation of affiliated partner indicates may exist three kinds of relationships, for example, A and/or B, can indicate: individualism A, simultaneously
There are A and B, these three situations of individualism B.In addition, character "/" herein, it is a kind of for typicallying represent forward-backward correlation object
The relationship of "or"；In formula, character "/" indicates that forward-backward correlation object is the relationship of a kind of " being divided by ".
It is understood that the area that the various digital numbers involved in embodiments herein only carry out for convenience of description
Point, it is not intended to limit the range of embodiments herein.
It is understood that magnitude of the sequence numbers of the above procedures are not meant to execute in embodiments herein
Sequence it is successive, the execution of each process sequence should be determined by its function and internal logic, without coping with embodiments herein
Implementation process constitutes any restriction.
Finally, it should be noted that the above various embodiments is only to illustrate the technical solution of the application, rather than its limitations；To the greatest extent
Pipe is described in detail the application referring to foregoing embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement；And these are modified or replaceed, each embodiment technology of the application that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (24)
1. a kind of disease forecasting method characterized by comprising
The skin image of user is obtained, the skin image includes: the skin of user；
It is analyzed according to skin characteristic of the skin image to the user, obtains prediction result, the prediction result is used
Pathologic variation whether occurs in the skin of the expression user；
Push the prediction result.
2. the method according to claim 1, wherein it is described according to the skin image to the skin of the user
Feature is analyzed, and prediction result is obtained, comprising:
Image analysis processing is carried out to the skin image, obtains the skin characteristic of the user；
The skin detection model that skin characteristic input obtains in advance is detected, the prediction result is obtained.
3. according to the method described in claim 2, it is characterized in that,
The skin detection model be by healthy skin feature to the various colours of skin and different syndromes at the various stages skin
What the pathologic delta data that skin occurs was trained；
Or
The skin detection model is received from server.
4. the method according to claim 1, wherein it is described according to the skin image to the skin of the user
Feature is analyzed, and prediction result is obtained, comprising:
Skin detection request is sent to server, the skin detection request includes the skin image, and the skin detection is asked
It asks for requesting the server to carry out analysis detection to the skin image, determines whether the skin of the user occurs pathology
Property variation；
Receive the prediction result that the server returns.
5. the method according to claim 1, wherein it is described according to the skin image to the skin of the user
Feature is analyzed, and prediction result is obtained, comprising:
Image analysis processing is carried out to the skin image, obtains the skin characteristic of the user；
Skin detection request is sent to server, the skin detection request includes the skin characteristic, and the skin detection is asked
It asks for requesting the server to carry out analysis detection to the skin characteristic, determines whether the skin of the user occurs pathology
Property variation；
Receive the prediction result that the server returns.
6. method according to claim 4 or 5, which is characterized in that the method also includes:
Obtain the accuracy of the prediction result；
According to the accuracy of the prediction result, processing is optimized to the skin detection model；
Or
The accuracy of the prediction result is fed back into the server, so that standard of the server according to the prediction result
Exactness optimizes processing to the skin detection model.
7. method according to claim 1-5, which is characterized in that the push prediction result, comprising:
By augmented reality AR mode by the prediction result Overlapping display in the corresponding pictured scene of the skin image.
8. a kind of disease forecasting method characterized by comprising
The skin detection request that receiving terminal apparatus is sent, the skin detection request include the skin image or described of user
The skin characteristic of user；
It is requested according to the skin detection, analysis detection is carried out to the skin image or the skin characteristic, obtains prediction
As a result, the prediction result is for indicating whether the skin of the user occurs pathologic variation；
The prediction result is returned into the terminal device.
9. according to the method described in claim 8, it is characterized in that, described request according to the skin detection, to the skin
Image or the skin characteristic carry out analysis detection, obtain prediction result, comprising:
Image analysis processing is carried out to the skin image, obtains the skin characteristic of the user；
The skin detection model that skin characteristic input obtains in advance is detected, the prediction result is obtained；
Or
The skin detection model that skin characteristic input obtains in advance is detected, the prediction result is obtained.
10. according to the method described in claim 9, it is characterized in that, the method also includes:
The corresponding pathologic of skin changes number when by healthy skin feature to the various colours of skin and different syndromes in each stage
According to model training is carried out, the skin detection model is obtained.
11. according to the method described in claim 10, it is characterized in that, the method also includes:
Receive the accuracy of the prediction result of the terminal device feedback；
According to the accuracy of the prediction result, processing is optimized to the skin detection model.
12. a kind of disease forecasting device characterized by comprising obtain module and processing module；
The acquisition module, for obtaining the skin image of user, the skin image includes: the skin of user, according to described
Skin image analyzes the skin characteristic of the user, obtains prediction result, the prediction result is for indicating the use
Whether the skin at family occurs pathologic variation；
The processing module, for pushing the prediction result.
13. device according to claim 12, which is characterized in that the acquisition module, for according to the skin image
The skin characteristic of the user is analyzed, prediction result is obtained, specifically:
The acquisition module is specifically used for carrying out image analysis processing to the skin image, and the skin for obtaining the user is special
The skin detection model that skin characteristic input obtains in advance is detected, obtains the prediction result by sign.
14. device according to claim 13, which is characterized in that
The skin detection model be by healthy skin feature to the various colours of skin and different syndromes at the various stages skin
The pathologic delta data that skin occurs carries out what model training obtained；
Or
The skin detection model is received from server.
15. device according to claim 12, which is characterized in that described device further include: transceiver module；
The transceiver module is requested for sending skin detection to server, and receives the described pre- of the server return
It surveys as a result, skin detection request includes the skin image, the skin detection request is for requesting the server pair
The skin image carries out analysis detection, determines whether the skin of the user occurs pathologic variation.
16. device according to claim 12, which is characterized in that the acquisition module, for according to the skin image
The skin characteristic of the user is analyzed, prediction result is obtained, specifically:
The acquisition module is specifically used for carrying out image analysis processing to the skin image, and the skin for obtaining the user is special
Sign；
Described device further include: transceiver module；
The transceiver module is requested for sending skin detection to server, and receives the described pre- of the server return
It surveys as a result, skin detection request includes the skin characteristic, the skin detection request is for requesting the server pair
The skin characteristic carries out analysis detection, determines whether the skin of the user occurs pathologic variation.
17. device according to claim 15 or 16, which is characterized in that
The acquisition module, is also used to obtain the accuracy of the prediction result；
The processing module is also used to the accuracy according to the prediction result, optimizes place to the skin detection model
Reason；
Or
The transceiver module is also used to the accuracy of the prediction result feeding back to the server, so that the server
According to the accuracy of the prediction result, processing is optimized to the skin detection model.
18. the described in any item devices of 2-16 according to claim 1, which is characterized in that the processing module, it is described for pushing
Prediction result, specifically:
The processing module is used for the prediction result Overlapping display through augmented reality AR mode in the skin image pair
In the pictured scene answered.
19. a kind of disease forecasting device characterized by comprising include: transceiver module and processing module；
The transceiver module, for the skin detection request that receiving terminal apparatus is sent, the skin detection request includes user
Skin image or the user skin characteristic；
The processing module carries out the skin image or the skin characteristic for being requested according to the skin detection
Analysis detection obtains prediction result, and the prediction result is for indicating whether the skin of the user occurs pathologic variation；
The transceiver module is also used to the prediction result returning to the terminal device.
20. device according to claim 19, which is characterized in that the processing module, for according to the skin detection
Request carries out analysis detection to the skin image or the skin characteristic, obtains prediction result, specifically:
The processing module is specifically used for carrying out image analysis processing to the skin image, and the skin for obtaining the user is special
The skin detection model that skin characteristic input obtains in advance is detected, obtains the prediction result by sign；
Or
The processing module is detected specifically for the skin detection model for obtaining skin characteristic input in advance, is obtained
To the prediction result.
21. device according to claim 20, which is characterized in that
The processing module is also used to through healthy skin feature to the various colours of skin and different syndromes skin when in each stage
Corresponding pathologic delta data carries out model training, obtains the skin detection model.
22. device according to claim 21, which is characterized in that
The transceiver module is also used to receive the accuracy of the prediction result of the terminal device feedback；
The processing module is also used to the accuracy according to the prediction result, optimizes place to the skin detection model
Reason.
23. a kind of disease forecasting device, including processor, memory and it is stored on the memory and can transports on a processor
Capable computer program, which is characterized in that the processor is realized when executing described program such as any one of the claims 1-7
The method or such as described in any item methods of the claims 8-11.
24. a kind of storage medium, which is characterized in that instruction is stored in the storage medium, when run on a computer,
So that computer executes the method according to claim 1 to 7 or the described in any item sides of the claims 8-11
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810981971.7A CN109242836A (en) | 2018-08-27 | 2018-08-27 | Disease forecasting method, apparatus and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810981971.7A CN109242836A (en) | 2018-08-27 | 2018-08-27 | Disease forecasting method, apparatus and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109242836A true CN109242836A (en) | 2019-01-18 |
Family
ID=65069539
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810981971.7A Pending CN109242836A (en) | 2018-08-27 | 2018-08-27 | Disease forecasting method, apparatus and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109242836A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109840932A (en) * | 2019-01-23 | 2019-06-04 | 平安科技（深圳）有限公司 | Cardiovascular and cerebrovascular disease methods of exhibiting, device, equipment and storage medium |
| CN111243702A (en) * | 2020-01-15 | 2020-06-05 | 广州都兰生物科技有限公司 | Method for automatically exporting skin detection report |
| CN112767334A (en) * | 2021-01-08 | 2021-05-07 | 南京中兴力维软件有限公司 | Skin problem detection method, device, equipment and medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104537592A (en) * | 2014-09-26 | 2015-04-22 | 尉子旺 | Self-diagnosis and preventive care guide system |
| CN107910061A (en) * | 2017-12-01 | 2018-04-13 | 中南大学 | A kind of medical data processing method and system |
-
2018
- 2018-08-27 CN CN201810981971.7A patent/CN109242836A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104537592A (en) * | 2014-09-26 | 2015-04-22 | 尉子旺 | Self-diagnosis and preventive care guide system |
| CN107910061A (en) * | 2017-12-01 | 2018-04-13 | 中南大学 | A kind of medical data processing method and system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109840932A (en) * | 2019-01-23 | 2019-06-04 | 平安科技（深圳）有限公司 | Cardiovascular and cerebrovascular disease methods of exhibiting, device, equipment and storage medium |
| CN111243702A (en) * | 2020-01-15 | 2020-06-05 | 广州都兰生物科技有限公司 | Method for automatically exporting skin detection report |
| CN112767334A (en) * | 2021-01-08 | 2021-05-07 | 南京中兴力维软件有限公司 | Skin problem detection method, device, equipment and medium |
| CN112767334B (en) * | 2021-01-08 | 2024-04-09 | 南京中兴力维软件有限公司 | Skin problem detection method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210397746A1 (en) | Systems and methods for processing electronic images across regions | |
| CN109508681B (en) | Method and device for generating human body key point detection model | |
| CN107680684B (en) | Method and device for acquiring information | |
| TWI773797B (en) | System, method and computer program product for tracking multi-joint subjects in an area of real space | |
| CN110348543B (en) | Fundus image recognition method and device, computer equipment and storage medium | |
| JP6447108B2 (en) | Usability calculation device, availability calculation method, and availability calculation program | |
| CN110504029A (en) | A kind of medical image processing method, medical image recognition method and device | |
| EP3234885A1 (en) | Pipeline generation for data stream actuated control | |
| CN110021404A (en) | For handling the electronic equipment and method of information relevant to food | |
| CN109242836A (en) | Disease forecasting method, apparatus and storage medium | |
| CN110110787A (en) | Location acquiring method, device, computer equipment and the storage medium of target | |
| CN110443794A (en) | A kind of image state based on pathological image determines method, apparatus and system | |
| US9921795B2 (en) | Mobile device, system and method for medical image displaying using multiple mobile devices | |
| JP2014095967A (en) | Information processing apparatus, information processing method and program | |
| JP2015219892A (en) | Visual line analysis system and visual line analysis device | |
| KR101518804B1 (en) | Method and apparatus for managing medical data | |
| JP2024502516A (en) | Data annotation methods, apparatus, systems, devices and storage media | |
| CN110517771A (en) | A kind of medical image processing method, medical image recognition method and device | |
| CN114079801A (en) | On-demand overlaying of metadata onto video streams for intelligent video analytics | |
| Lampreave et al. | Towards assisted electrocardiogram interpretation using an AI-enabled Augmented Reality headset | |
| KR20190046531A (en) | Method and apparatus for analyzing images of capsule endoscopic based on knowledge model of gastrointestinal tract diseases | |
| CA3147017C (en) | System and method for classifying dermatological images using machine learning | |
| CN115376198A (en) | Gaze direction estimation method, gaze direction estimation device, electronic apparatus, medium, and program product | |
| CN115426947A (en) | SP02 applet: AI-assisted SP02 measurement APP | |
| CN110517239A (en) | A kind of medical image detection method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190118 |
|
| RJ01 | Rejection of invention patent application after publication |