CN109785941A - A kind of recommended method and device of doctor - Google Patents
A kind of recommended method and device of doctor Download PDFInfo
- Publication number
- CN109785941A CN109785941A CN201910027953.XA CN201910027953A CN109785941A CN 109785941 A CN109785941 A CN 109785941A CN 201910027953 A CN201910027953 A CN 201910027953A CN 109785941 A CN109785941 A CN 109785941A
- Authority
- CN
- China
- Prior art keywords
- tongue
- tongue picture
- doctor
- vector
- image
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000012549 training Methods 0.000 claims description 14
- 230000003760 hair shine Effects 0.000 claims description 7
- 210000002105 tongue Anatomy 0.000 description 240
- 230000015654 memory Effects 0.000 description 17
- 238000012545 processing Methods 0.000 description 17
- 238000010586 diagram Methods 0.000 description 15
- 238000004891 communication Methods 0.000 description 10
- 238000004590 computer program Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000001514 detection method Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 239000003814 drug Substances 0.000 description 3
- 230000005236 sound signal Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000000712 assembly Effects 0.000 description 2
- 238000000429 assembly Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 230000001815 facial effect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- MCSXGCZMEPXKIW-UHFFFAOYSA-N 3-hydroxy-4-[(4-methyl-2-nitrophenyl)diazenyl]-N-(3-nitrophenyl)naphthalene-2-carboxamide Chemical compound Cc1ccc(N=Nc2c(O)c(cc3ccccc23)C(=O)Nc2cccc(c2)[N+]([O-])=O)c(c1)[N+]([O-])=O MCSXGCZMEPXKIW-UHFFFAOYSA-N 0.000 description 1
- 206010037549 Purpura Diseases 0.000 description 1
- 208000037656 Respiratory Sounds Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000007373 indentation Methods 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 206010034754 petechiae Diseases 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 208000011580 syndromic disease Diseases 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The embodiment of the present application provides the recommended method and device of a kind of doctor, which comprises obtains the tongue picture image of user to be diagnosed first；Then the tongue picture image is input in tongue image recognition model and obtains corresponding tongue picture feature vector；The corresponding recommendation doctor of the user to be diagnosed finally is determined according to the tongue picture feature vector.In this way, recommending doctor so that automatically determining according to tongue picture image since acquisition tongue picture image is convenient, improve the efficiency of doctor's recommendation, in addition, the matching degree for recommending doctor and conditions of patients is improved the present invention is based on tongue picture feature vector, to improve the accuracy of doctor's recommended method.
Description
Technical field
This application involves visual field and TCM tongue diagnosis field, the method and apparatus recommended more particularly to a kind of doctor.
Background technique
Traditional Chinese medicine be the Chinese nation in long-term production, life and medical practice to the warp of life, health, disease preventing and treating
The valuable accumulation and summary tested, become the important component of Chinese traditional culture.
Patient searches suitably medical doctor in the following manner at present: mode one is led by dialing Telephone in Hospital consulting
Staff is cured, but guiding doctor staff usually navigates to department, specifically medical doctor can not be navigated to；Mode two passes through
Relatives and friends teach orally, and still, this method efficiency is extremely low, and the probability for encountering the doctor to suit the medicine to the illness just is lower；Mode three,
In the symptom of search engine search patient, and hospital and the doctor for being good at treating such symptom are searched in search result, still,
Authentic communication and deceptive information mix in the lookup result that present search engine returns, it is difficult to distinguish；Mode four, to search for oneself uncommon
Medical hospital official website is hoped, and by the data information of the department and doctor of checking the inside to match the state of an illness of patient, to select
Medical doctor is selected, still, is relatively taken time and effort by searching matched process one by one.As it can be seen that patient is confined to disease and doctor
Raw understanding, the efficiency for searching medical doctor by natural language is lower, and accuracy rate is relatively low.
Summary of the invention
In view of the above problems, the embodiment of the present application provides the recommended method and device of a kind of doctor.
To solve the above-mentioned problems, the embodiment of the present application discloses the recommended method of doctor a kind of, comprising:
Obtain the tongue picture image of user to be diagnosed；
The tongue picture image is input in tongue image recognition model and obtains corresponding tongue picture feature vector；
The corresponding recommendation doctor of the user to be diagnosed is determined according to the tongue picture feature vector.
Correspondingly, the embodiment of the present application also discloses the recommendation apparatus of doctor a kind of, comprising:
First obtains module, for obtaining the tongue picture image of user to be diagnosed；
Second obtains module, obtains corresponding tongue picture feature for the tongue picture image to be input in tongue image recognition model
Vector；
Determining module, for determining the corresponding recommendation doctor of the user to be diagnosed according to the tongue picture feature vector.
The embodiment of the present application also provides a kind of device that doctor recommends, including processor and memory, wherein
The processor executes the computer program code that the memory is stored, to realize doctor described herein
Recommended method.
The embodiment of the present application also provides a kind of computer readable storage medium, deposited on the computer readable storage medium
Computer program is stored up, the computer program realizes the step of the recommended method of doctor described herein when being executed by processor
Suddenly.
The embodiment of the present application includes the following advantages:
The embodiment of the present application passes through the tongue picture image for obtaining user to be diagnosed first；Then the tongue picture image is input to
Corresponding tongue picture feature vector is obtained in tongue image recognition model；The use to be diagnosed finally is determined according to the tongue picture feature vector
The corresponding recommendation doctor in family.In this way, recommend doctor so that automatically determining according to tongue picture image since acquisition tongue picture image is convenient,
The efficiency of doctor's recommendation is improved, in addition, improving for recommending doctor and conditions of patients the present invention is based on tongue picture feature vector
With degree, to improve the accuracy of doctor's recommended method.
Detailed description of the invention
Fig. 1 is a kind of step flow chart of the recommended method embodiment of doctor of the application；
Fig. 2 is a kind of step flow chart of the recommended method alternative embodiment of doctor of the application；
Fig. 3 is a kind of structural block diagram of the recommendation apparatus embodiment of doctor of the application；
Fig. 4 is a kind of structural block diagram of the recommendation apparatus alternative embodiment of doctor of the application；
Fig. 5 is a kind of structural block diagram of the recommendation apparatus alternative embodiment of doctor of the application；
Fig. 6 is a kind of structural block diagram of the recommendation apparatus alternative embodiment of doctor of the application；
Fig. 7 is the hardware structural diagram of the recommendation apparatus for the doctor that the embodiment of the application provides；
Fig. 8 is the hardware structural diagram of the recommendation apparatus for the doctor that another embodiment of the application provides.
Specific embodiment
In order to make the above objects, features, and advantages of the present application more apparent, with reference to the accompanying drawing and it is specific real
Applying mode, the present application will be further described in detail.
In the integral syndrome differentiation of Chinese medicine, lingual diagnosis is extremely important component part, can more objectively by observation tongue picture
Reflect the depth, the property of disease and evil, the advance and retreat of evil positive prosperity and decline and patient's condition of sick position, therefore, tongue picture image, which becomes, clinically debates
The important evidence that card opinion is controlled.
The present invention is in order to solve the problems, such as that patient determines that the efficiency of medical doctor and accuracy rate are lower in the prior art, proposition
A kind of recommended method of doctor, can be by obtaining the tongue picture image of patient, and determines based on tongue picture image the tongue picture of patient
Feature vector, to determine the corresponding recommendation doctor of patient according to tongue picture feature vector.In this way, due to acquiring tongue picture image side
Just, recommend doctor so that automatically determining according to tongue picture image, the efficiency of doctor's recommendation is improved, in addition, the present invention is based on tongue pictures
Feature vector improves the matching degree for recommending doctor and conditions of patients, to improve the accuracy of doctor's recommended method.
Below in conjunction with specific embodiment, the present invention is described in detail.
Referring to Fig.1, a kind of step flow chart of the recommended method embodiment of doctor of the application is shown, specifically can wrap
Include following steps:
Step 101, the tongue picture image of user to be diagnosed is obtained.
In embodiments of the present invention, user to be diagnosed can be with registration terminal (such as mobile phone, tablet computer, laptop, the palm
Upper computer etc.) on doctor recommend platform, to recommend platform to receive the facial figure of user diagnose input by the doctor
Picture, wherein the doctor recommends platform that can acquire the face-image by the image capture device (such as camera) of terminal, when
So, which recommends platform that can also receive the face-image that user to be diagnosed selects from the image file of the terminal, above-mentioned
Example is merely illustrative, and the disclosure does not limit this.
Since the present invention is to determine to recommend doctor by the tongue picture feature in tongue picture image, in this step, if should
Do not include that tongue picture part in tongue picture part or the face-image is unsatisfactory for default tongue picture quality in face-image, then can not
Subsequent determining the step of recommending doctor is executed, in this way, whether it includes tongue picture part that this step can determine in the face-image, and
When including the tongue picture part in the face-image, continue to determine whether the tongue picture part meets default tongue picture quality, if the tongue
As part meets default tongue picture quality, it is determined that the tongue picture part is the tongue picture image；It does not include tongue picture in the face-image
When part or the tongue picture part are unsatisfactory for default tongue picture quality, it can show that prompting message, the prompting message are used for user
Prompt user re-enters face-image.Illustratively, which can be the text information shown in text box, this article
This information is " woulding you please re-enter face-image ", and certainly, which can also be speech message, and the present invention does not do this
It limits.
It is preset clearly it should be noted that the clarity that the default tongue picture quality includes the tongue part is more than or equal to
Degree, and the tongue part is lingual surface or tongue bottom, and the tongue part is the tongue of user to be diagnosed just facing to camera lens.
In order to whether can quickly determine in the face-image including the tongue picture image, mould can be identified by training image in advance
Type, to be mentioned from the face-image when including the tongue picture image in determining the face-image by the image recognition model
Take the tongue picture image.The following procedure training image recognition model can be passed through: firstly, the tongue of the known medical doctor of acquisition is in the same old way
This, and obtain in this in the same old way from tongue a part training tongue in the same old way this, for example, due to originally being obtained by 5000 trained tongues in the same old way
The recognition accuracy of the image recognition model meets user demand, therefore, 5000 trained tongues can be obtained from tongue in the same old way this
In the same old way originally；Then, to the training tongue in the same old way this carry out image labeling respectively, such as can be by the tongue portion in the training tongue in the same old way this
Frame is divided to elect, and marking the tongue part of the training tongue in the same old way originally is tongue just facing to camera lens or tongue side facing to mirror
Head, and marking tongue part is lingual surface or tongue bottom, and whether can also mark tongue part clear etc.；Finally, by the instruction
Practice the image labeling result of tongue in the same old way originally as training set, to be trained this to default detection model by training set
Image recognition model, wherein the default detection model may include target detection model and image quality analysis model, the present invention
SSD (Single Shot Multibox Detector) model, Fast-R-CNN model or YOLO (You can be used
Only Look Once) model etc. is used as target detection model, it is contemplated that and mobileNet is a lightweight network, and is used
The convolution mode of deep-wise substitutes traditional 3D convolution, thus reduce the redundant representation of convolution kernel, therefore, the present invention
Can be using mobileNet as image quality analysis model, certainly, which can also be
The models such as xceptionNet, mobileNet V2, above-mentioned example are merely illustrative, and the disclosure does not limit this.
Step 102, which is input in tongue image recognition model and obtains corresponding tongue picture feature vector.
In embodiments of the present invention, the tongue image recognition model can be obtained in the following manner:
Firstly, the tongue of the known medical doctor of acquisition in the same old way this；
Then, tongue to be marked is obtained from the tongue in the same old way this to shine, wherein need the figure by training completion in step 101
As identification model respectively to tongue in the same old way this identified to obtain the tongue to be marked and shone, the tongue to be marked is according to being to eliminate facial spy
The tongue picture part of sign and the tongue picture part meet default tongue picture quality；
Then, the mark for shining into row tongue picture feature to the tongue to be marked obtains tongue picture vector sample, wherein due to tongue picture spy
Sign may include tongue nature (such as tongue color, ligulate is fat or thin, and ligulate is always tender, if has indentation, if has petechiae), tongue fur (such as tongue
Tongue fur color, tongue nature are moisturized, tongue fur thin and thick, the greasy corruption of coating nature, if having crackle, if strip off) etc. features, therefore, it is necessary to treat mark
Each tongue picture feature that note tongue shines is labeled.For example, tongue color can be divided when being labeled to tongue color
For different tongue color grades, to determine the tongue to be marked according to corresponding tongue color grade by professional.
Certainly, in order to improve the accuracy of mark, the present invention can be equal to same tongue picture feature by multiple professionals
It is labeled, and when determining that the professional that there is default number provides identical annotation results to the same tongue picture feature, really
The fixed same tongue picture feature mark is completed.For example, if be labeled by multiple professionals to tongue color, and the tongue face
Colour gradation includes " white ", " light red ", " red " and " deep red ", then each professional successively marks the tongue color, in tongue face
When the mark number of color " light red " meets default number at first, determine that the annotation results of the tongue color are " light red ".In this way,
After the completion of whole tongue picture features mark that the tongue to be marked shines, can be generated according to annotation results tongue picture that the tongue to be marked shines to
Sample is measured, i.e. each dimension of the tongue picture vector sample respectively represents the annotation results of different tongue picture features.
Tongue picture knowledge is obtained finally, shining according to the tongue to be marked and presetting identification model with corresponding tongue picture vector sample training
Other model, wherein the default identification model can be ResNet etc..In alternatively possible implementation, rule of thumb may be used
Know: user demand can be met according to the tongue image recognition model being trained by 100000 tongues to be marked, therefore, right
When the mark that the tongue to be marked shines into row tongue picture feature obtains tongue picture vector sample, it can be chosen from the tongue photograph to be marked
100000 tongues to be marked shine into the mark of row tongue picture feature, and are obtained by trained tongue image recognition model, in addition to
Other tongues to be marked other than 100000 tongues to be marked shine shine corresponding tongue picture vector sample.
By the available tongue image recognition model of above-mentioned training process, so that this step can be based on tongue image recognition model
The corresponding tongue picture feature vector of the tongue picture image is quickly obtained, treatment effeciency is improved.
Step 103, it is determined according to the tongue picture feature vector and is somebody's turn to do the corresponding recommendation doctor of user to be diagnosed.
In this step, can calculate separately between the tongue picture feature vector and each tongue picture vector sample to span
From；The tongue picture vector sample is previously provided with corresponding medical doctor；According to the vector distance from all the tongue picture vector samples
Middle acquisition target tongue picture vector sample；Recommendation doctor is determined from the corresponding medical doctor of the target tongue picture vector sample.
In conclusion the embodiment of the present application passes through the tongue picture image for obtaining user to be diagnosed first；Then by the tongue picture figure
Corresponding tongue picture feature vector is obtained as being input in tongue image recognition model；The follow-up is finally determined according to the tongue picture feature vector
The disconnected corresponding recommendation doctor of user.In this way, since acquisition tongue picture image is convenient, so that automatically determining recommendation doctor according to tongue picture image
It is raw, the efficiency of doctor's recommendation is improved, recommends doctor and conditions of patients in addition, improving the present invention is based on tongue picture feature vector
Matching degree, to improve the accuracy of doctor's recommended method.
Referring to Fig. 2, a kind of step flow chart of the recommended method alternative embodiment of doctor of the application is shown, specifically may be used
To include the following steps:
Step 201, the face-image of user's input to be diagnosed is received.
In one possible implementation, when user to be diagnosed recommends input on platform to complete the face-image in doctor
Afterwards, triggering can be executed and complete operation, so that the doctor in the present invention recommends platform after detecting that operation is completed in the triggering, after
Continuous to execute subsequent step, which completes operation can be to click completing button etc., and the disclosure does not limit this.
Step 202, determine in the face-image whether include tongue picture image.
Wherein it is possible to determine in the face-image whether include tongue picture by the image recognition model described in step 101
Image repeats no more.
When including tongue picture image in the face-image, step 203 and 205 is executed；
When not including tongue picture image in the face-image, step 204 is executed；
Step 203, the tongue picture image of the user to be diagnosed is obtained.
This step again may be by the image recognition model and get the tongue picture image.
Step 204, prompting message is generated, and is back to step 201.
Wherein, the prompting message is for prompting user to re-enter face-image.
Step 205, which is input in tongue image recognition model and obtains corresponding tongue picture feature vector.
Particular content refers to step 102, repeats no more.
Step 206, the vector distance between the tongue picture feature vector and each tongue picture vector sample is calculated separately.
Wherein, due to tongue that the tongue picture vector sample is known medical doctor this corresponding vector in the same old way, the tongue picture
Vector sample can be previously provided with corresponding medical doctor.
In embodiments of the present invention, if the vector distance is closer, which gets over the tongue picture vector sample
Similar, i.e. the state of an illness of the corresponding patient of the two is more close；On the contrary, if the vector distance is remoter, the tongue picture feature vector with should
The difference of tongue picture vector sample is bigger, i.e. the state of an illness of the corresponding patient of the two is more different.In one possible implementation, should
Vector distance can determine that above-mentioned example is merely illustrative by the modes such as COS distance algorithm or Euclidean distance algorithm,
The disclosure does not limit this.
It should be noted that since the data of the tongue picture vector sample are more, and the dimension of the tongue picture vector sample is more
A, therefore, when calculating vector distance, in order to reduce the workload of calculating, the present invention be can establish in the enterprising row vector of k-d tree
The calculating of distance, to improve computational efficiency, detailed process refers to the prior art, repeats no more.
Step 207, it is obtained and the tongue picture feature vector distance from all tongue picture vector samples according to the vector distance
The tongue picture vector sample to be determined of nearest preset quantity.
In this step, sequentially successively all tongue picture vector samples can be carried out from small to large according to the vector distance
Sequence, if the preset quantity is M, M tongue picture vector sample before being chosen according to ranking results.
Step 208, target tongue picture vector sample is obtained from the tongue picture vector sample to be determined.
Wherein, the vector distance between the target tongue picture vector sample and the tongue picture feature vector is less than or equal to default
Distance, in this way, can successively determine whether the corresponding vector distance of each tongue picture vector sample to be determined is less than or equal to this
Pre-determined distance, so as to delete and the farther away tongue picture vector sample of the vector distance of the tongue picture feature vector.
It should be noted that the mode for determining the target tongue picture vector sample by step 207 and step 208 mode is
For example, which is not limited by the present invention, certainly, the present invention can make the tongue picture vector sample to be determined in step 207
For the target tongue picture vector sample.
Step 209, determine that the corresponding medical doctor of the target tongue picture vector sample is doctor to be determined.
Wherein, since the corresponding medical doctor of partial target tongue picture vector sample may be same doctor, this step
The corresponding medical doctor of the target complete tongue picture vector sample can be counted to obtain different doctors to be determined.
Illustratively, if the target tongue picture vector includesWithAndWithIt is corresponding just
Examining doctor is D1,WithCorresponding medical doctor is D2, then the doctor to be determined is D1And D2。
Step 210, the medical matching value of each doctor to be determined is calculated separately.
In this step, the medical matching value of each doctor to be determined can be calculated by the following formula:
Wherein, rjIndicate the corresponding medical matching value of j-th of doctor to be determined；S is whole target tongue picture vector samples
In, the vector quantity that doctor is j-th of doctor to be determined of going to a doctor；M is preset quantity；For tongue picture feature vectorVector distance between i-th of target tongue picture vector sample；T is pre-determined distance.
Illustratively, continue to be illustrated by taking the example in step 209 as an example, if the target tongue picture vector includesWithAndWithCorresponding medical doctor is D1,WithCorresponding medical doctor is
D2, which is D1And D2, then D1The calculation formula of medical matching value can indicate are as follows:D2The calculation formula of medical matching value can indicate are as follows:Above-mentioned example is merely illustrative, and the disclosure does not limit this.
By the above formula, relatively conventional for the tongue picture of user to be diagnosed, then the s obtained is larger, in this way, can be with
Determine that the most doctor of the quantity for treating similar patients' tongue picture is recommendation doctor；It is more rare for the tongue picture of user to be diagnosed
See, then the s obtained is less, in this way, can determine that the doctor for treating most like patient's tongue picture is recommendation doctor.
Step 211, recommendation doctor is determined from the doctor to be determined according to the matching value of going to a doctor.
In this step, it can determine that the maximum medical corresponding doctor to be determined of matching value is recommendation doctor.
In conclusion the embodiment of the present application obtains the tongue picture image of user to be diagnosed first；Then the tongue picture image is defeated
Enter into tongue image recognition model to obtain corresponding tongue picture feature vector；Finally being determined according to the tongue picture feature vector should use be diagnosed
The corresponding recommendation doctor in family.In this way, recommend doctor so that automatically determining according to tongue picture image since acquisition tongue picture image is convenient,
The efficiency of doctor's recommendation is improved, in addition, improving for recommending doctor and conditions of patients the present invention is based on tongue picture feature vector
With degree, to improve the accuracy of doctor's recommended method.
It is noted that for simple description, therefore, it is stated as a series of action groups for embodiment of the method
It closes, but those skilled in the art should understand that, the embodiment of the present application is not limited by the described action sequence, because according to
According to the embodiment of the present application, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art also should
Know, the embodiments described in the specification are all preferred embodiments, and related movement not necessarily the application is implemented
Necessary to example.
Referring to Fig. 3, a kind of structural block diagram of the recommendation apparatus embodiment of doctor of the application is shown, can specifically include
Following module:
First obtains module 301, for obtaining the tongue picture image of user to be diagnosed；
Second obtains module 302, obtains corresponding tongue picture spy for the tongue picture image to be input in tongue image recognition model
Levy vector；
First determining module 303 is somebody's turn to do the corresponding recommendation doctor of user to be diagnosed for determining according to the tongue picture feature vector.
Referring to Fig. 4, in the alternative embodiment of the application, which includes:
Computational submodule 3031, for calculating separately the vector between the tongue picture feature vector and each tongue picture vector sample
Distance；The tongue picture vector sample is previously provided with corresponding medical doctor；
Acquisition submodule 3032, for according to the vector distance from all obtain in the tongue picture vector samples target tongue picture to
Measure sample；
Submodule 3033 is determined, for determining recommendation doctor from the corresponding medical doctor of the target tongue picture vector sample
It is raw.
In the alternative embodiment of the application, the acquisition submodule 3032, for according to the vector distance from whole
In the tongue picture vector sample, obtain and to be determined tongue picture vector sample of the tongue picture feature vector apart from nearest preset quantity；
And the target tongue picture vector sample is obtained from the tongue picture vector sample to be determined；The target tongue picture vector sample and the tongue picture are special
The vector distance levied between vector is less than or equal to pre-determined distance.
In the alternative embodiment of the application, the determination submodule 3033, for determining the target tongue picture vector sample
This corresponding medical doctor is doctor to be determined；Calculate separately the medical matching value of each doctor to be determined；It is medical according to this
Matching value determines recommendation doctor from the doctor to be determined.
Referring to Fig. 5, in the alternative embodiment of the application, further includes:
Acquisition module 304, for acquire the tongue of known medical doctor in the same old way this；
Third obtains module 305, shines for obtaining tongue to be marked from the tongue in the same old way this；
4th obtains module 306, and the mark for shining into row tongue picture feature to the tongue to be marked obtains tongue picture vector sample；
5th obtains module 307, for being shone and the default identification of corresponding tongue picture vector sample training according to the tongue to be marked
Model obtains the tongue image recognition model.
Referring to Fig. 6, in the alternative embodiment of the application, further includes:
Receiving module 308, for receiving the face-image of user's input to be diagnosed；
Second determining module 309, for whether determining in the face-image including the tongue picture image；
The first acquisition module 301, when for including the tongue picture image in the face-image, obtaining should user be diagnosed
Tongue picture image.
In conclusion the embodiment of the present application obtains the tongue picture image of user to be diagnosed first；Then the tongue picture image is defeated
Enter into tongue image recognition model to obtain corresponding tongue picture feature vector；Finally being determined according to the tongue picture feature vector should use be diagnosed
The corresponding recommendation doctor in family.In this way, recommend doctor so that automatically determining according to tongue picture image since acquisition tongue picture image is convenient,
The efficiency of doctor's recommendation is improved, in addition, improving for recommending doctor and conditions of patients the present invention is based on tongue picture feature vector
With degree, to improve the accuracy of doctor's recommended method.
The embodiment of the present application also provides a kind of non-volatile readable storage medium, be stored in the storage medium one or
Multiple modules (programs) when the one or more module is used in terminal device, can make the terminal device execute
The instruction (instructions) of various method steps in the embodiment of the present application.
Fig. 7 is the hardware structural diagram of the recommendation apparatus for the doctor that one embodiment of the application provides.As shown in fig. 7, should
The recommendation apparatus of doctor may include that input equipment 70, processor 71, output equipment 72, memory 73 and at least one communication are total
Line 74.Communication bus 74 is for realizing the communication connection between element.Memory 73 may include high speed RAM memory, can also
It can further include non-volatile memories NVM, a for example, at least magnetic disk storage can store various programs in memory 73, use
In the method and step for completing various processing functions and realization the present embodiment.
Optionally, above-mentioned processor 71 can be for example central processing unit (Central Processing Unit, abbreviation
CPU), application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing appts (DSPD), programmable
Logical device (PLD), field programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic components are real
Existing, which is coupled to above-mentioned input equipment 70 and output equipment 72 by wired or wireless connection.
Optionally, above-mentioned input equipment 70 may include a variety of input equipments, such as may include user oriented user
At least one of interface, device oriented equipment interface, the programmable interface of software, camera, sensor.Optionally, the face
It can be wireline interface for carrying out data transmission between equipment and equipment to the equipment interface of equipment, can also be for setting
Standby hardware insertion interface (such as USB interface, serial ports etc.) carried out data transmission between equipment；Optionally, the user oriented
User interface for example can be user oriented control button, for receive voice input voice-input device and user
Receive the touch awareness apparatus (such as touch screen, Trackpad with touch sensing function etc.) of user's touch input；Optionally,
The programmable interface of above-mentioned software for example can be the entrance for editing or modifying program for user, such as the input pin of chip
Interface or input interface etc.；Optionally, above-mentioned transceiver can be rf chip with communication function, at base band
Manage chip and dual-mode antenna etc..The audio input device such as microphone can receive voice data.Output equipment 72 may include
The output equipments such as display, sound equipment.
In the present embodiment, the processor of the recommendation apparatus of the doctor includes for executing each mould in the setting device of background
The function of block, concrete function and technical effect are referring to above-described embodiment, and details are not described herein again.
Fig. 8 is the hardware structural diagram of the recommendation apparatus for the doctor that another embodiment of the application provides.Fig. 8 is to Fig. 7
Specific embodiment during realization.As shown in figure 8, the recommendation apparatus of the doctor of the present embodiment includes processor 81
And memory 82.
Processor 81 executes the computer program code that memory 82 is stored, and realizes Fig. 1 and Fig. 2 in above-described embodiment
The recommended method of doctor.
Memory 82 is configured as storing various types of data to support the operation in the recommended method of doctor.These numbers
According to example include any application or method for being operated on the recommendation apparatus of doctor instruction, such as message, figure
Piece, video etc..Memory 82 may include random access memory (random access memory, abbreviation RAM), it is also possible to
It further include nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.
Optionally, processor 81 is arranged in processing component 80.The recommendation apparatus of the doctor can also include: communication component
83, power supply module 84, multimedia component 85, audio component 86, input/output interface 87 and/or sensor module 88.Doctor's
Component that recommendation apparatus is specifically included etc. is set according to actual demand, and the present embodiment does not limit this.
The integrated operation of the usually recommendation apparatus of control doctor of processing component 80.Processing component 80 may include one or more
A processor 81 executes instruction, to complete all or part of the steps of above-mentioned Fig. 1 to Fig. 5 method.In addition, processing component 80 can
To include one or more modules, convenient for the interaction between processing component 80 and other assemblies.For example, processing component 80 can wrap
Multi-media module is included, to facilitate the interaction between multimedia component 85 and processing component 80.
Power supply module 84 provides electric power for the various assemblies of the recommendation apparatus of doctor.Power supply module 84 may include power supply pipe
Reason system, one or more power supplys and other with the recommendation apparatus for doctor generate, manage, and distribute associated group of electric power
Part.
Multimedia component 85 includes the display screen of one output interface of offer between the recommendation apparatus and user of doctor.
In some embodiments, display screen may include liquid crystal display (LCD) and touch panel (TP).If display screen includes touching
Panel, display screen may be implemented as touch screen, to receive input signal from the user.Touch panel includes one or more
Touch sensor is to sense the gesture on touch, slide, and touch panel.The touch sensor can not only sense touch or
The boundary of sliding action, but also detect duration and pressure associated with the touch or slide operation.
Audio component 86 is configured as output and/or input audio signal.For example, audio component 86 includes a microphone
(MIC).The received audio signal can be further stored in memory 82 or send via communication component 83.In some realities
It applies in example, audio component 86 further includes a loudspeaker, is used for output audio signal.
Input/output interface 87 provides interface, above-mentioned peripheral interface mould between processing component 80 and peripheral interface module
Block can be click wheel, button etc..These buttons may include, but are not limited to: volume button, start button and locking press button.
Sensor module 88 includes one or more sensors, provides the shape of various aspects for the recommendation apparatus for doctor
State assessment.For example, sensor module 88 can detecte the state that opens/closes of the recommendation apparatus of doctor, component it is relatively fixed
Position, the existence or non-existence that user contacts with the recommendation apparatus of doctor.Sensor module 88 may include proximity sensor, be matched
It sets for detecting the presence of nearby objects without any physical contact.In some embodiments, the sensor module 88
It can also be including camera etc..
Communication component 83 is configured to facilitate the logical of wired or wireless way between the recommendation apparatus of doctor and other equipment
Letter.The recommendation apparatus of doctor can access the wireless network based on communication standard, such as WiFi, 2G or 3G or their combination.
From the foregoing, it will be observed that communication component 83, audio component 86 involved in Fig. 8 embodiment and input/output interface
87, sensor module 88 can be used as the implementation of the input equipment in Fig. 7 embodiment.
For device embodiment, since it is basically similar to the method embodiment, related so being described relatively simple
Place illustrates referring to the part of embodiment of the method.
All the embodiments in this specification are described in a progressive manner, the highlights of each of the examples are with
The difference of other embodiments, the same or similar parts between the embodiments can be referred to each other.
It should be understood by those skilled in the art that, the embodiments of the present application may be provided as method, apparatus or calculating
Machine program product.Therefore, the embodiment of the present application can be used complete hardware embodiment, complete software embodiment or combine software and
The form of the embodiment of hardware aspect.Moreover, the embodiment of the present application can be used one or more wherein include computer can
With in the computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) of program code
The form of the computer program product of implementation.
The embodiment of the present application is referring to according to the method for the embodiment of the present application, terminal device (system) and computer program
The flowchart and/or the block diagram of product describes.It should be understood that flowchart and/or the block diagram can be realized by computer program instructions
In each flow and/or block and flowchart and/or the block diagram in process and/or box combination.It can provide these
Computer program instructions are set to general purpose computer, special purpose computer, Embedded Processor or other programmable data processing terminals
Standby processor is to generate a machine, so that being held by the processor of computer or other programmable data processing terminal devices
Capable instruction generates for realizing in one or more flows of the flowchart and/or one or more blocks of the block diagram
The device of specified function.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing terminal devices
In computer-readable memory operate in a specific manner, so that instruction stored in the computer readable memory generates packet
The manufacture of command device is included, which realizes in one side of one or more flows of the flowchart and/or block diagram
The function of being specified in frame or multiple boxes.
These computer program instructions can also be loaded into computer or other programmable data processing terminal devices, so that
Series of operation steps are executed on computer or other programmable terminal equipments to generate computer implemented processing, thus
The instruction executed on computer or other programmable terminal equipments is provided for realizing in one or more flows of the flowchart
And/or in one or more blocks of the block diagram specify function the step of.
Although preferred embodiments of the embodiments of the present application have been described, once a person skilled in the art knows bases
This creative concept, then additional changes and modifications can be made to these embodiments.So the following claims are intended to be interpreted as
Including preferred embodiment and all change and modification within the scope of the embodiments of the present application.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that process, method, article or terminal device including a series of elements not only wrap
Those elements are included, but also including other elements that are not explicitly listed, or further includes for this process, method, article
Or the element that terminal device is intrinsic.In the absence of more restrictions, being wanted by what sentence "including a ..." limited
Element, it is not excluded that there is also other identical elements in process, method, article or the terminal device for including the element.
Above to the recommended method and device of a kind of doctor provided herein, it is described in detail, answers herein
With specific case, the principle and implementation of this application are described, and the explanation of above example is only intended to help to manage
Solve the present processes and its core concept；At the same time, for those skilled in the art, according to the thought of the application,
There will be changes in specific embodiment and application range, in conclusion the content of the present specification should not be construed as to this Shen
Limitation please.
Claims (12)
1. a kind of recommended method of doctor, which is characterized in that the described method includes:
Obtain the tongue picture image of user to be diagnosed；
The tongue picture image is input in tongue image recognition model and obtains corresponding tongue picture feature vector；
The corresponding recommendation doctor of the user to be diagnosed is determined according to the tongue picture feature vector.
2. the method according to claim 1, wherein described determine the follow-up according to the tongue picture feature vector
The disconnected corresponding recommendation doctor of user includes:
Calculate separately the vector distance between the tongue picture feature vector and each tongue picture vector sample；The tongue picture vector sample
It is previously provided with corresponding medical doctor；
Target tongue picture vector sample is obtained from all tongue picture vector samples according to the vector distance；
The recommendation doctor is determined from the corresponding medical doctor of the target tongue picture vector sample.
3. according to the method described in claim 2, it is characterized in that, according to the vector distance from all tongue picture vector samples
Target tongue picture vector sample is obtained in this includes:
According to the vector distance from all tongue picture vector samples, obtain nearest with the tongue picture feature vector distance
The tongue picture vector sample to be determined of preset quantity；
The target tongue picture vector sample is obtained from the tongue picture vector sample to be determined；The target tongue picture vector sample with
Vector distance between the tongue picture feature vector is less than or equal to pre-determined distance.
4. according to the method described in claim 2, it is characterized in that, described corresponding medical from the target tongue picture vector sample
Determine that the recommendation doctor includes: in doctor
Determine that the corresponding medical doctor of the target tongue picture vector sample is doctor to be determined；
Calculate separately the medical matching value of each doctor to be determined；
The recommendation doctor is determined from the doctor to be determined according to the medical matching value.
5. according to the method described in claim 2, it is characterized in that, the tongue picture image is input to tongue image recognition mould described
Before obtaining corresponding tongue picture feature vector in type, further includes:
The tongue of the known medical doctor of acquisition in the same old way this；
Tongue to be marked is obtained from the tongue in the same old way this to shine；
The tongue picture vector sample is obtained to the mark that the tongue to be marked shines into row tongue picture feature；
It is shone according to the tongue to be marked and corresponding tongue picture vector sample training presets identification model and obtains the tongue image recognition model.
6. the method according to claim 1, wherein being gone back before the tongue picture image for obtaining user to be diagnosed
Include:
Receive the face-image of user's input to be diagnosed；
Determine in the face-image whether include the tongue picture image；
The tongue picture image for obtaining user to be diagnosed includes:
When including the tongue picture image in the face-image, the tongue picture image of the user to be diagnosed is obtained.
7. a kind of recommendation apparatus of doctor, which is characterized in that described device includes:
First obtains module, for obtaining the tongue picture image of user to be diagnosed；
Second obtain module, for the tongue picture image is input in tongue image recognition model obtain corresponding tongue picture feature to
Amount；
First determining module, for determining the corresponding recommendation doctor of the user to be diagnosed according to the tongue picture feature vector.
8. device according to claim 7, which is characterized in that first determining module includes:
Computational submodule, for calculating separately the vector distance between the tongue picture feature vector and each tongue picture vector sample；
The tongue picture vector sample is previously provided with corresponding medical doctor；
Acquisition submodule, for obtaining target tongue picture vector sample from all tongue picture vector samples according to the vector distance
This；
Submodule is determined, for determining the recommendation doctor from the corresponding medical doctor of the target tongue picture vector sample.
9. device according to claim 8, which is characterized in that the acquisition submodule, for according to the vector distance
From all tongue picture vector samples, obtain and to be determined tongue picture of the tongue picture feature vector apart from nearest preset quantity
Vector sample；And the target tongue picture vector sample is obtained from the tongue picture vector sample to be determined；The target tongue picture to
The vector distance measured between sample and the tongue picture feature vector is less than or equal to pre-determined distance.
10. device according to claim 8, which is characterized in that the determining submodule, for determining the target tongue picture
The corresponding medical doctor of vector sample is doctor to be determined；Calculate separately the medical matching value of each doctor to be determined；Root
The recommendation doctor is determined from the doctor to be determined according to the medical matching value.
11. device according to claim 8, which is characterized in that described device further include:
Acquisition module, for acquire the tongue of known medical doctor in the same old way this；
Third obtains module, shines for obtaining tongue to be marked from the tongue in the same old way this；
4th obtains module, and the mark for shining into row tongue picture feature to the tongue to be marked obtains tongue picture vector sample；
5th obtains module, obtains for being shone according to the tongue to be marked with the default identification model of corresponding tongue picture vector sample training
To the tongue image recognition model.
12. device according to claim 7, which is characterized in that described device further include:
Receiving module, for receiving the face-image of user's input to be diagnosed；
Second determining module, for whether determining in the face-image including the tongue picture image；
Described first obtains module, when for including the tongue picture image in the face-image, obtains the use to be diagnosed
The tongue picture image at family.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910027953.XA CN109785941B (en) | 2019-01-11 | 2019-01-11 | Doctor recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910027953.XA CN109785941B (en) | 2019-01-11 | 2019-01-11 | Doctor recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109785941A true CN109785941A (en) | 2019-05-21 |
| CN109785941B CN109785941B (en) | 2021-10-01 |
Family
ID=66500288
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910027953.XA Active CN109785941B (en) | 2019-01-11 | 2019-01-11 | Doctor recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109785941B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110766665A (en) * | 2019-09-30 | 2020-02-07 | 天聚星信息科技(深圳)有限公司 | Tongue picture data analysis method based on strong supervision algorithm and deep learning network |
| CN113362334A (en) * | 2020-03-04 | 2021-09-07 | 北京悦熙兴中科技有限公司 | Tongue picture processing method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1803087A (en) * | 2006-01-19 | 2006-07-19 | 上海交通大学 | Tongue color automatic recognition method |
| CN102426583A (en) * | 2011-10-10 | 2012-04-25 | 北京工业大学 | Chinese medicine tongue manifestation retrieval method based on image content analysis |
| CN103559637A (en) * | 2013-11-13 | 2014-02-05 | 王竞 | Method and system for recommending doctor for patient |
| CN104036445A (en) * | 2014-06-17 | 2014-09-10 | 南京邮电大学 | Intelligent medical treatment personalization recommendation system and implementation method thereof |
| CN106821324A (en) * | 2017-03-06 | 2017-06-13 | 武汉嫦娥医学抗衰机器人股份有限公司 | A kind of lingual diagnosis auxiliary medical system based on lingual surface and sublingual comprehensive analysis |
| WO2018098986A1 (en) * | 2016-11-29 | 2018-06-07 | 深圳市易特科信息技术有限公司 | Automatic detection system and method for tongue images in traditional chinese medicine |
| CN109008963A (en) * | 2018-06-27 | 2018-12-18 | 南京同仁堂乐家老铺健康科技有限公司 | Intelligent lingual diagnosis system and method based on mobile terminal |
-
2019
- 2019-01-11 CN CN201910027953.XA patent/CN109785941B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1803087A (en) * | 2006-01-19 | 2006-07-19 | 上海交通大学 | Tongue color automatic recognition method |
| CN102426583A (en) * | 2011-10-10 | 2012-04-25 | 北京工业大学 | Chinese medicine tongue manifestation retrieval method based on image content analysis |
| CN103559637A (en) * | 2013-11-13 | 2014-02-05 | 王竞 | Method and system for recommending doctor for patient |
| CN104036445A (en) * | 2014-06-17 | 2014-09-10 | 南京邮电大学 | Intelligent medical treatment personalization recommendation system and implementation method thereof |
| WO2018098986A1 (en) * | 2016-11-29 | 2018-06-07 | 深圳市易特科信息技术有限公司 | Automatic detection system and method for tongue images in traditional chinese medicine |
| CN106821324A (en) * | 2017-03-06 | 2017-06-13 | 武汉嫦娥医学抗衰机器人股份有限公司 | A kind of lingual diagnosis auxiliary medical system based on lingual surface and sublingual comprehensive analysis |
| CN109008963A (en) * | 2018-06-27 | 2018-12-18 | 南京同仁堂乐家老铺健康科技有限公司 | Intelligent lingual diagnosis system and method based on mobile terminal |
Non-Patent Citations (2)
| Title |
|---|
| 刘洞波: "《移动机器人粒子滤波定位与地图创建》", 31 December 2016 * |
| 孙健: "《从生活学中医》", 31 December 2015 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110766665A (en) * | 2019-09-30 | 2020-02-07 | 天聚星信息科技(深圳)有限公司 | Tongue picture data analysis method based on strong supervision algorithm and deep learning network |
| CN113362334A (en) * | 2020-03-04 | 2021-09-07 | 北京悦熙兴中科技有限公司 | Tongue picture processing method and device |
| CN113362334B (en) * | 2020-03-04 | 2024-05-24 | 北京悦熙兴中科技有限公司 | Tongue photo processing method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109785941B (en) | 2021-10-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10115286B2 (en) | Method for providing health service and refrigerator therefor | |
| TWI657799B (en) | Electronic apparatus and method for providing skin detection information thereof | |
| US20240169518A1 (en) | Method and apparatus for identifying body constitution in traditional chinese medicine, electronic device, storage medium and program | |
| US20150227740A1 (en) | Updating a Template for a Biometric Recognition Device | |
| CN105302294B (en) | A kind of interactive virtual reality apparatus for demonstrating | |
| CN106339695A (en) | Face similarity detection method, device and terminal | |
| CN113192639B (en) | Training method, device, equipment and storage medium of information prediction model | |
| CN109785941A (en) | A kind of recommended method and device of doctor | |
| CN115115897B (en) | Multi-modal pre-trained gastric tumor classification system | |
| CN115170629A (en) | Wound information acquisition method, device, equipment and storage medium | |
| CN112307847A (en) | Multi-scale attention pedestrian re-recognition deep learning system based on guidance | |
| KR102348160B1 (en) | System and method for visualizing electric health record | |
| CN110378304A (en) | Skin condition detection method, device, equipment and storage medium | |
| CN107408208A (en) | The method and fingerprint sensing system analyzed for the bio-measurement to user | |
| CN113744384B (en) | Three-dimensional face reconstruction method and device, electronic equipment and storage medium | |
| CN110634570A (en) | Diagnostic simulation method and related device | |
| WO2021120589A1 (en) | Method and apparatus for abnormal image filtering for use on 3d images, device, and storage medium | |
| CN112800758A (en) | Method, system, equipment and medium for distinguishing similar meaning words in text | |
| CN111281355B (en) | Method and equipment for determining pulse acquisition position | |
| Hareva et al. | Retracted: The smart device for healthcare service: Iris diagnosis application | |
| CN112768064A (en) | Disease prediction device, disease prediction apparatus, symptom information processing method, symptom information processing device, and symptom information processing apparatus | |
| CN115691793A (en) | Method and device for processing tongue picture data and related equipment | |
| CN116130088A (en) | Multi-mode face diagnosis method, device and related equipment | |
| CN115482899A (en) | Prescription recommendation method and device, electronic equipment and storage medium | |
| CN109330559A (en) | Assessment method, device, computer equipment and the computer storage medium of Determination of cortisol |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: 810699 The first, second, and third floors of Building 1, County Low rent Housing, West Side of Yangjia Road, Ping'an Street, Ping'an District, Haidong City, Qinghai Province Patentee after: Qinghai Xiaolu Traditional Chinese Medicine Internet Hospital Co.,Ltd. Country or region after: China Address before: 810600 first floor of Qinghai KangTeng Hotel, 239 Xinping Avenue, Ping'an Town, Ping'an District, Haidong City, Qinghai Province Patentee before: HAIDONG PINGAN ZHENGYANG INTERNET CHINESE MEDICINE HOSPITAL Co.,Ltd. Country or region before: China |
|
| CP03 | Change of name, title or address |