CN109785941B - Doctor recommendation method and device - Google Patents
Doctor recommendation method and device Download PDFInfo
- Publication number
- CN109785941B CN109785941B CN201910027953.XA CN201910027953A CN109785941B CN 109785941 B CN109785941 B CN 109785941B CN 201910027953 A CN201910027953 A CN 201910027953A CN 109785941 B CN109785941 B CN 109785941B
- Authority
- CN
- China
- Prior art keywords
- tongue
- vector
- tongue picture
- doctor
- picture
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 239000013598 vector Substances 0.000 claims abstract description 166
- 230000001815 facial effect Effects 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000003745 diagnosis Methods 0.000 claims description 5
- 238000005286 illumination Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 17
- 238000012545 processing Methods 0.000 description 17
- 238000004590 computer program Methods 0.000 description 11
- 238000004891 communication Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 238000002372 labelling Methods 0.000 description 8
- 201000010099 disease Diseases 0.000 description 6
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000009471 action Effects 0.000 description 4
- 239000011248 coating agent Substances 0.000 description 4
- 238000000576 coating method Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 239000003814 drug Substances 0.000 description 3
- 230000005236 sound signal Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001717 pathogenic effect Effects 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 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
- 238000009825 accumulation Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000006806 disease prevention Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 206010018388 glossodynia Diseases 0.000 description 1
- 230000036541 health 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
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 208000011580 syndromic disease Diseases 0.000 description 1
Images
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The embodiment of the application provides a recommendation method and a recommendation device for doctors, wherein the method comprises the following steps: firstly, acquiring a tongue picture image of a user to be diagnosed; then inputting the tongue picture image into a tongue picture recognition model to obtain a corresponding tongue picture characteristic vector; and finally, determining a recommended doctor corresponding to the user to be diagnosed according to the tongue picture characteristic vector. Therefore, the method and the device have the advantages that the tongue picture images are convenient to acquire, so that the recommended doctor is automatically determined according to the tongue picture images, the doctor recommendation efficiency is improved, in addition, the matching degree of the recommended doctor and the patient condition is improved based on the tongue picture characteristic vectors, and the doctor recommendation method accuracy is improved.
Description
Technical Field
The application relates to the field of vision and the field of tongue diagnosis in traditional Chinese medicine, in particular to a method and a device for doctor recommendation.
Background
Traditional Chinese medicine is the precious accumulation and summarization of the experience of Chinese nation in the long-term production, life and medical practice on life, health and disease prevention and treatment, and becomes an important component of Chinese nation traditional culture.
Currently, patients search for a suitable physician by: the method comprises the steps that firstly, a hospital telephone is dialed to consult medical guide staff, but the medical guide staff are usually positioned in a department and cannot be positioned to a specific doctor; in the second mode, the transmission is carried out through the mouth and the ear of relatives and friends, but the method has extremely low efficiency and low probability of meeting doctors who just deal with the disease; thirdly, searching the symptoms of the patient in a search engine, and searching hospitals and doctors good at treating the symptoms in the search results, but the reliable information and the false information in the search results returned by the current search engine are mixed and difficult to distinguish; and fourthly, searching the hospital official network which the user wishes to see a doctor, and selecting the doctor to see the doctor by checking the information of the department and the doctor to match the illness state of the patient, wherein the process of searching the matching one by one is time-consuming and labor-consuming. It can be seen that the patient is limited to the knowledge of the disease and the doctor, and the doctor is looked up in natural language with low efficiency and relatively low accuracy.
Disclosure of Invention
In view of the foregoing problems, embodiments of the present application provide a recommendation method and apparatus for a doctor.
In order to solve the above problem, an embodiment of the present application discloses a recommendation method for a doctor, including:
acquiring a tongue picture image of a user to be diagnosed;
inputting the tongue picture image into a tongue picture recognition model to obtain a corresponding tongue picture characteristic vector;
and determining a recommended doctor corresponding to the user to be diagnosed according to the tongue picture characteristic vector.
Correspondingly, the embodiment of the application also discloses a recommendation device for doctors, which comprises:
the first acquisition module is used for acquiring a tongue image of a user to be diagnosed;
the second acquisition module is used for inputting the tongue picture image into a tongue picture recognition model to obtain a corresponding tongue picture characteristic vector;
and the determining module is used for determining a recommended doctor corresponding to the user to be diagnosed according to the tongue picture characteristic vector.
The embodiment of the application also provides a device recommended by a doctor, which comprises a processor and a memory, wherein,
the processor executes the computer program codes stored in the memory to realize the doctor recommendation method.
The embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the recommendation method for a doctor described in the present application.
The embodiment of the application has the following advantages:
the method comprises the steps of firstly, acquiring a tongue picture image of a user to be diagnosed; then inputting the tongue picture image into a tongue picture recognition model to obtain a corresponding tongue picture characteristic vector; and finally, determining a recommended doctor corresponding to the user to be diagnosed according to the tongue picture characteristic vector. Therefore, the method and the device have the advantages that the tongue picture images are convenient to acquire, so that the recommended doctor is automatically determined according to the tongue picture images, the doctor recommendation efficiency is improved, in addition, the matching degree of the recommended doctor and the patient condition is improved based on the tongue picture characteristic vectors, and the doctor recommendation method accuracy is improved.
Drawings
FIG. 1 is a flow chart of steps of an embodiment of a method for physician recommendation of the present application;
FIG. 2 is a flow chart illustrating the steps of an alternative embodiment of a physician recommendation method of the present application;
FIG. 3 is a block diagram of a recommendation device of a doctor in the present application;
FIG. 4 is a block diagram of an alternative embodiment of a recommendation device for a physician of the present application;
FIG. 5 is a block diagram of an alternative embodiment of a recommendation device for a physician of the present application;
FIG. 6 is a block diagram of an alternative embodiment of a recommendation device for a physician of the present application;
FIG. 7 is a schematic hardware configuration diagram of a recommendation device for doctors according to an embodiment of the present application;
fig. 8 is a schematic hardware configuration diagram of a recommendation device for doctors according to another embodiment of the present application.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, the present application is described in further detail with reference to the accompanying drawings and the detailed description.
In the overall syndrome differentiation of traditional Chinese medicine, the tongue diagnosis is an extremely important component, and the depth of the disease location, the nature of pathogenic factors, the abundance or insufficiency of pathogenic factors and the progression of the disease condition can be objectively reflected by observing the tongue picture, so that the tongue picture becomes an important basis for clinical diagnosis and treatment.
The invention aims to solve the problem that the efficiency and the accuracy of the doctor for the patient to see a doctor are low in the prior art, and provides a doctor recommending method. Therefore, the method and the device have the advantages that the tongue picture images are convenient to acquire, so that the recommended doctor is automatically determined according to the tongue picture images, the doctor recommendation efficiency is improved, in addition, the matching degree of the recommended doctor and the patient condition is improved based on the tongue picture characteristic vectors, and the doctor recommendation method accuracy is improved.
The present invention will be described in detail with reference to specific examples.
Referring to fig. 1, a flowchart illustrating steps of an embodiment of a recommendation method for a doctor according to the present application is shown, which may specifically include the following steps:
In the embodiment of the present invention, a user to be diagnosed may log in a doctor recommendation platform on a terminal (e.g., a mobile phone, a tablet computer, a notebook computer, a palm computer, etc.), so as to receive a facial image input by the user to be diagnosed through the doctor recommendation platform, where the doctor recommendation platform may collect the facial image through an image collecting device (e.g., a camera, etc.) of the terminal, and of course, the doctor recommendation platform may also receive the facial image selected by the user to be diagnosed from an image file of the terminal, which is described above by way of example only, and the disclosure does not limit this.
Because the invention confirms and recommends the doctor through the tongue picture characteristic in the tongue picture, therefore, in this step, if include tongue picture part in the facial picture, or the tongue picture part in the facial picture does not meet and predetermine the tongue picture quality, can't carry out the follow-up step of confirming and recommending the doctor, in this way, this step can confirm whether include the tongue picture part in the facial picture, and when including the tongue picture part in the facial picture, continue confirming whether the tongue picture part meets and predetermines the tongue picture quality, if the tongue picture part meets and predetermines the tongue picture quality, confirm the tongue picture is the tongue picture; when the tongue portion is not included in the face image or the tongue portion does not satisfy the preset tongue quality, a prompt message for prompting the user to re-input the face image may be presented to the user. For example, the prompt message may be a text message displayed in a text box, the text message is "please re-input the facial image", and of course, the prompt message may also be a voice message, which is not limited in the present invention.
It should be noted that the preset tongue image quality includes that the definition of the tongue portion is greater than or equal to a preset definition, the tongue portion is a tongue surface or a tongue bottom, and the tongue portion is a tongue of the user to be diagnosed, which faces the lens in front.
In order to quickly determine whether the tongue image is included in the face image, an image recognition model may be trained in advance so that the tongue image is extracted from the face image when it is determined that the tongue image is included in the face image by the image recognition model. The image recognition model may be trained by: firstly, acquiring a tongue sample of a doctor in a known visit, and acquiring a part of training tongue samples from the tongue sample, for example, 5000 training tongue samples can be acquired from the tongue sample because the identification accuracy of the image identification model obtained by 5000 training tongue samples meets the requirements of users; then, respectively carrying out image annotation on the training tongue photo sample, if the tongue part in the training tongue photo sample can be selected, marking whether the tongue part of the training tongue photo sample is the tongue front side facing the lens or the tongue side facing the lens, marking whether the tongue part is the tongue surface or the tongue bottom, and also marking whether the tongue part is clear or not; finally, the image labeling result of the training tongue sample is used as a training set, so that a preset detection model is trained through the training set to obtain the image recognition model, wherein, the preset detection model can comprise a target detection model and an image quality analysis model, the invention can adopt an SSD (Single Shot Multi Box Detector) model, a Fast-R-CNN model or a YOLO (you Only Look one) model and the like as the target detection model, considering that the mobileNet is a lightweight network, and adopts a deep-wise convolution mode to replace the traditional 3D convolution, thereby reducing the redundant expression of the convolution kernel, therefore, the invention can adopt the mobileNet as an image quality analysis model, of course, the image quality analysis model may also be an xceptionNet model, a mobileNet V2 model, and the above examples are only illustrative, and the disclosure does not limit this.
And 102, inputting the tongue picture image into a tongue picture recognition model to obtain a corresponding tongue picture characteristic vector.
In the embodiment of the present invention, the tongue recognition model can be obtained by:
firstly, collecting tongue samples of known doctors for treatment;
then, acquiring a tongue picture to be labeled from the tongue picture sample, wherein the tongue picture to be labeled needs to be obtained by respectively identifying the tongue picture sample through the image identification model trained in the step 101, and the tongue picture to be labeled is a tongue picture part with facial features removed and meets the preset tongue picture quality;
and then, labeling tongue picture characteristics of the tongue picture to be labeled to obtain a tongue picture vector sample, wherein the tongue picture characteristics can comprise tongue characteristics (such as tongue color, swollen and thin tongue shape, old and tender tongue shape, tooth marks and silt points), tongue coating (such as tongue coating color, moist tongue quality, thin and thick tongue coating, greasy tongue coating, cracks and peeling), and the like, so that each tongue picture characteristic of the tongue picture to be labeled needs to be labeled. For example, when tongue color is labeled, tongue color may be divided into different tongue color grades, so that a professional determines the tongue color grade corresponding to the tongue image to be labeled.
Certainly, in order to improve the accuracy of the labeling, the method can label the same tongue picture feature by a plurality of professionals, and when the professionals with preset number give the same labeling result to the same tongue picture feature, the same tongue picture feature is determined to be labeled. For example, if the tongue color is labeled by a plurality of professionals, and the tongue color levels include "white", "pale red", "red", and "deep red", each professional labels the tongue color in turn, and when the number of labeled persons of the tongue color "pale red" first meets a preset number, the labeling result of the tongue color is determined to be "pale red". Therefore, after all tongue picture features of the tongue picture to be labeled are labeled, a tongue picture vector sample of the tongue picture to be labeled can be generated according to the labeling result, namely, each dimension of the tongue picture vector sample represents the labeling result of different tongue picture features respectively.
And finally, training a preset recognition model according to the tongue picture to be marked and the corresponding tongue picture vector sample to obtain the tongue picture recognition model, wherein the preset recognition model can be ResNet and the like. In another possible implementation, it is known empirically that: the method comprises the steps of training 100000 tongue pictures to be labeled to obtain tongue picture recognition models, meeting user requirements, selecting 100000 tongue pictures to be labeled from the tongue pictures to be labeled to label the tongue picture characteristics when labeling the tongue picture characteristics of the tongue picture to be labeled to obtain tongue picture vector samples, and obtaining the tongue picture vector samples corresponding to the other tongue pictures to be labeled except the 100000 tongue pictures to be labeled through the trained tongue picture recognition models.
The tongue picture recognition model can be obtained through the training process, so that the tongue picture characteristic vector corresponding to the tongue picture image can be quickly obtained based on the tongue picture recognition model in the step, and the processing efficiency is improved.
And 103, determining a recommended doctor corresponding to the user to be diagnosed according to the tongue picture characteristic vector.
In this step, the vector distance between the tongue picture feature vector and each tongue picture vector sample can be calculated respectively; the tongue picture vector sample is preset with a corresponding doctor; acquiring target tongue picture vector samples from all tongue picture vector samples according to the vector distance; and determining the recommended doctor from the doctors corresponding to the target tongue picture vector samples.
In summary, in the embodiment of the present application, a tongue image of a user to be diagnosed is obtained; then inputting the tongue picture image into a tongue picture recognition model to obtain a corresponding tongue picture characteristic vector; and finally, determining a recommended doctor corresponding to the user to be diagnosed according to the tongue picture characteristic vector. Therefore, the method and the device have the advantages that the tongue picture images are convenient to acquire, so that the recommended doctor is automatically determined according to the tongue picture images, the doctor recommendation efficiency is improved, in addition, the matching degree of the recommended doctor and the patient condition is improved based on the tongue picture characteristic vectors, and the doctor recommendation method accuracy is improved.
Referring to fig. 2, a flowchart illustrating steps of an alternative embodiment of a recommendation method for a doctor according to the present application is shown, which may specifically include the following steps:
in step 201, a facial image input by a user to be diagnosed is received.
In a possible implementation manner, after the user to be diagnosed inputs the complete facial image on the doctor recommendation platform, a trigger completion operation may be performed, so that the doctor recommendation platform in the present invention continues to perform subsequent steps after detecting the trigger completion operation, and the trigger completion operation may be a click completion button, etc., which is not limited by the present disclosure.
In step 202, it is determined whether a tongue image is included in the face image.
Whether the face image includes the tongue image can be determined by the image recognition model in step 101, which is not described again.
When the tongue image is included in the face image, steps 203 and 205 are performed;
when the tongue image is not included in the face image, executing step 204;
The tongue image can be obtained by the image recognition model in the step.
Wherein the prompt message is for prompting the user to re-enter the facial image.
For details, refer to step 102, which is not described again.
The tongue vector sample is a vector corresponding to a tongue image sample of a known doctor, so that the corresponding doctor can be preset in the tongue vector sample.
In the embodiment of the present invention, if the vector distance is closer, the more similar the tongue manifestation feature vector and the tongue manifestation vector sample are, i.e. the more similar the disease conditions of the patients corresponding to the two are; conversely, the farther the vector distance is, the greater the difference between the tongue image feature vector and the tongue image vector sample, i.e. the more different the disease condition of the corresponding patients. In a possible implementation manner, the vector distance may be determined by a cosine distance algorithm or a euclidean distance algorithm, and the above example is only an example, and the disclosure does not limit this.
It should be noted that, because there are many data of the tongue vector samples and there are many dimensions of the tongue vector samples, when calculating the vector distance, in order to reduce the calculation workload, the present invention may be established to calculate the vector distance on the k-d tree, thereby improving the calculation efficiency.
In this step, all tongue vector samples may be sorted in order from small to large according to the vector distance, and if the preset number is M, the first M tongue vector samples are selected according to the sorting result.
The vector distance between the target tongue picture vector sample and the tongue picture characteristic vector is smaller than or equal to a preset distance, so that whether the vector distance corresponding to each tongue picture vector sample to be determined is smaller than or equal to the preset distance or not can be determined in sequence, and tongue picture vector samples with longer vector distances from the tongue picture characteristic vector can be deleted.
It should be noted that, the manner of determining the target tongue vector sample through the steps 207 and 208 is only an example, and the present invention is not limited to this, and of course, the present invention may use the tongue vector sample to be determined in the step 207 as the target tongue vector sample.
Since the doctors corresponding to part of the target tongue image vector samples may be the same doctor, the method may count the doctors corresponding to all the target tongue image vector samples to obtain different doctors to be determined.
Illustratively, if the target tongue vector includes
And
and is
And
the doctor who visits the doctor is D1，
And
the doctor who visits the doctor is D2Then the doctor to be determined is D1And D2。
And step 210, calculating the visit matching value of each doctor to be determined respectively.
In this step, the visit matching value of each doctor to be determined can be calculated by the following formula:
wherein r isjRepresenting the corresponding clinic matching value of the jth doctor to be determined; s is the whole target tongue vectorIn the sample, the doctor is the vector quantity of the jth doctor to be determined; m is a preset number;
is a characteristic vector of tongue picture
And the vector distance between the ith target tongue picture vector sample; t is a preset distance.
Illustratively, continuing with the example in step 209, if the target tongue vector includes
And
and is
And
the doctor who visits the doctor is D1，
And
the doctor who visits the doctor is D2The doctor to be determined is D1And D2Then D is1The calculation formula of the visit matching value can be expressed as:
D2the calculation formula of the visit matching value can be expressed as:
the foregoing examples are illustrative only, and the disclosure is not limited thereto.
According to the formula, the obtained s is larger when the tongue picture of the user to be diagnosed is common, so that the doctor who treats the similar patient with the largest number of tongue pictures can be determined as the recommended doctor; the tongue picture of the user to be diagnosed is rare, and the obtained s is less, so that the doctor who treats the tongue picture of the most similar patient can be determined as the recommended doctor.
And step 211, determining the recommended doctor from the doctors to be determined according to the visit matching value.
In this step, the doctor to be determined corresponding to the maximum visit matching value may be determined as the recommended doctor.
To sum up, the embodiment of the present application first obtains a tongue image of a user to be diagnosed; then inputting the tongue picture image into a tongue picture recognition model to obtain a corresponding tongue picture characteristic vector; and finally, determining a recommended doctor corresponding to the user to be diagnosed according to the tongue picture characteristic vector. Therefore, the method and the device have the advantages that the tongue picture images are convenient to acquire, so that the recommended doctor is automatically determined according to the tongue picture images, the doctor recommendation efficiency is improved, in addition, the matching degree of the recommended doctor and the patient condition is improved based on the tongue picture characteristic vectors, and the doctor recommendation method accuracy is improved.
It is noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the embodiments are not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the embodiments. Further, those skilled in the art will also appreciate that the embodiments described in the specification are presently preferred and that no particular act is required of the embodiments of the application.
Referring to fig. 3, a block diagram of an embodiment of a recommendation apparatus for a doctor according to the present application is shown, and specifically, the recommendation apparatus may include the following modules:
the first acquisition module 301 is configured to acquire a tongue image of a user to be diagnosed;
a second obtaining module 302, configured to input the tongue image into a tongue recognition model to obtain a corresponding tongue feature vector;
the first determining module 303 is configured to determine, according to the tongue image feature vector, a recommended doctor corresponding to the user to be diagnosed.
Referring to fig. 4, in an alternative embodiment of the present application, the first determining module 303 includes:
a calculating submodule 3031, configured to calculate a vector distance between the tongue feature vector and each tongue vector sample; the tongue picture vector sample is preset with a corresponding doctor;
an obtaining sub-module 3032, configured to obtain target tongue vector samples from all tongue vector samples according to the vector distance;
a determining submodule 3033, configured to determine the recommended doctor from the physicians corresponding to the target tongue image vector samples.
In an optional embodiment of the present application, the obtaining sub-module 3032 is configured to obtain, according to the vector distance, a preset number of tongue vector samples to be determined that are closest to the tongue feature vector from all tongue vector samples; obtaining the target tongue picture vector sample from the tongue picture vector sample to be determined; the vector distance between the target tongue picture vector sample and the tongue picture characteristic vector is smaller than or equal to a preset distance.
In an optional embodiment of the present application, the determining sub-module 3033 is configured to determine that the referring doctor corresponding to the target tongue vector sample is the doctor to be determined; respectively calculating the diagnosis matching value of each doctor to be determined; and determining the recommended doctor from the doctors to be determined according to the visit matching value.
Referring to fig. 5, in an alternative embodiment of the present application, further includes:
an acquisition module 304 for acquiring tongue illumination samples of known attending physicians;
a third obtaining module 305, configured to obtain a tongue picture to be annotated from the tongue picture sample;
a fourth obtaining module 306, configured to label tongue features of the tongue illumination to be labeled to obtain a tongue vector sample;
a fifth obtaining module 307, configured to train a preset recognition model according to the tongue to be labeled and the corresponding tongue vector sample to obtain the tongue recognition model.
Referring to fig. 6, in an alternative embodiment of the present application, further includes:
a receiving module 308, configured to receive a facial image input by the user to be diagnosed;
a second determination module 309 for determining whether the tongue image is included in the face image;
the first obtaining module 301 is configured to obtain a tongue image of the user to be diagnosed when the tongue image is included in the facial image.
To sum up, the embodiment of the present application first obtains a tongue image of a user to be diagnosed; then inputting the tongue picture image into a tongue picture recognition model to obtain a corresponding tongue picture characteristic vector; and finally, determining a recommended doctor corresponding to the user to be diagnosed according to the tongue picture characteristic vector. Therefore, the method and the device have the advantages that the tongue picture images are convenient to acquire, so that the recommended doctor is automatically determined according to the tongue picture images, the doctor recommendation efficiency is improved, in addition, the matching degree of the recommended doctor and the patient condition is improved based on the tongue picture characteristic vectors, and the doctor recommendation method accuracy is improved.
The present application further provides a non-volatile readable storage medium, where one or more modules (programs) are stored in the storage medium, and when the one or more modules are applied to a terminal device, the one or more modules may cause the terminal device to execute instructions (instructions) of method steps in the present application.
Fig. 7 is a schematic hardware structure diagram of a recommendation device for doctors according to an embodiment of the present application. As shown in FIG. 7, the physician's recommendation apparatus may include an input device 70, a processor 71, an output device 72, a memory 73, and at least one communication bus 74. The communication bus 74 is used to enable communication connections between the elements. The memory 73 may comprise a high speed RAM memory, and may also include a non-volatile memory NVM, such as at least one disk memory, in which various programs may be stored for performing various processing functions and implementing the method steps of the present embodiment.
Alternatively, the processor 71 may be implemented by, for example, a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a controller, a microcontroller, a microprocessor, or other electronic components, and the processor 71 is coupled to the input device 70 and the output device 72 through a wired or wireless connection.
Alternatively, the input device 70 may include a variety of input devices, such as at least one of a user-oriented user interface, a device-oriented device interface, a software-programmable interface, a camera, and a sensor. Optionally, the device interface facing the device may be a wired interface for data transmission between devices, or may be a hardware plug-in interface (e.g., a USB interface, a serial port, etc.) for data transmission between devices; optionally, the user-facing user interface may be, for example, a user-facing control key, a voice input device for receiving voice input, and a touch sensing device (e.g., a touch screen with a touch sensing function, a touch pad, etc.) for receiving user touch input; optionally, the programmable interface of the software may be, for example, an entry for a user to edit or modify a program, such as an input pin interface or an input interface of a chip; optionally, the transceiver may be a radio frequency transceiver chip with a communication function, a baseband processing chip, a transceiver antenna, and the like. An audio input device such as a microphone may receive voice data. The output device 72 may include a display, a sound, or other output device.
In this embodiment, the processor of the recommendation device for doctors includes a function for executing each module in the setting device for the background, and specific functions and technical effects may refer to the above embodiments, which are not described herein again.
Fig. 8 is a schematic hardware structure diagram of a recommendation device for doctors according to another embodiment of the present application. FIG. 8 is a specific embodiment of FIG. 7 in an implementation. As shown in fig. 8, the recommendation apparatus for a doctor of the present embodiment includes a processor 81 and a memory 82.
The processor 81 executes the computer program code stored in the memory 82 to implement the recommendation method of the doctor of fig. 1 and 2 in the above embodiment.
The memory 82 is configured to store various types of data to support the operation of the recommendation method at the doctor. Examples of such data include instructions for any application or method operating on the recommendation device of the physician, such as messages, pictures, videos, and the like. The memory 82 may include a Random Access Memory (RAM) and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.
Optionally, the processor 81 is provided in the processing assembly 80. The doctor's recommendation apparatus may further include: a communication component 83, a power component 84, a multimedia component 85, an audio component 86, an input/output interface 87 and/or a sensor component 88. The components and the like specifically included in the recommendation device of the doctor are set according to actual requirements, which is not limited in this embodiment.
The processing assembly 80 generally controls the overall operation of the recommendation device of the physician. The processing component 80 may include one or more processors 81 to execute instructions to perform all or part of the steps of the methods of fig. 1-5 described above. Further, the processing component 80 may include one or more modules that facilitate interaction between the processing component 80 and other components. For example, the processing component 80 may include a multimedia module to facilitate interaction between the multimedia component 85 and the processing component 80.
The power supply component 84 provides power to the various components of the recommendation device of the physician. The power components 84 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the recommendation device of the physician.
The multimedia component 85 includes a display screen that provides an output interface between the recommendation device of the physician and the user. In some embodiments, the display screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the display screen includes a touch panel, the display screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.
The audio component 86 is configured to output and/or input audio signals. For example, the audio component 86 includes a Microphone (MIC). The received audio signal may further be stored in the memory 82 or transmitted via the communication component 83. In some embodiments, audio assembly 86 also includes a speaker for outputting audio signals.
The input/output interface 87 provides an interface between the processing component 80 and peripheral interface modules, which may be click wheels, buttons, etc. These buttons may include, but are not limited to: a volume button, a start button, and a lock button.
The sensor assembly 88 includes one or more sensors for providing various aspects of status assessment to the recommendation device of the physician. For example, the sensor assembly 88 may detect the open/closed status of the physician's recommendation device, the relative positioning of the assemblies, the presence or absence of user contact with the physician's recommendation device. The sensor assembly 88 may include a proximity sensor configured to detect the presence of a nearby object in the absence of any physical contact. In some embodiments, the sensor assembly 88 may also include a camera or the like.
The communication component 83 is configured to facilitate wired or wireless communication between the recommendation device of the physician and other devices. The recommendation device of the doctor may have access to a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof.
From the above, the communication component 83, the audio component 86, the input/output interface 87 and the sensor component 88 referred to in the embodiment of fig. 8 can be implemented as the input device in the embodiment of fig. 7.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As will be appreciated by one of skill in the art, embodiments of the present application may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present application have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the true scope of the embodiments of the application.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
The method and the device for recommending a doctor provided by the application are introduced in detail, specific examples are applied in the method to explain the principle and the implementation manner of the application, and the description of the embodiments is only used for helping to understand the method and the core idea of the application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (8)
1. A method of recommendation for a doctor, the method comprising:
acquiring a tongue picture image of a user to be diagnosed;
inputting the tongue picture image into a tongue picture recognition model to obtain a corresponding tongue picture characteristic vector;
determining a recommended doctor corresponding to the user to be diagnosed according to the tongue picture characteristic vector;
wherein, the determining the recommended doctor corresponding to the user to be diagnosed according to the tongue picture feature vector comprises:
respectively calculating the vector distance between the tongue picture characteristic vector and each tongue picture vector sample; the tongue picture vector sample is preset with a corresponding doctor;
acquiring target tongue picture vector samples from all tongue picture vector samples according to the vector distance;
determining the recommended doctor from the doctors corresponding to the target tongue picture vector samples;
the determining the recommended doctor from the doctors corresponding to the target tongue picture vector sample comprises:
determining the doctor who visits the doctor corresponding to the target tongue picture vector sample as a doctor to be determined;
respectively calculating the diagnosis matching value of each doctor to be determined;
determining the recommended doctor from the doctors to be determined according to the visit matching value;
the calculation formula of the doctor visit matching value to be determined is as follows:
wherein r isjRepresenting the corresponding clinic matching value of the jth doctor to be determined; s is the vector quantity of the jth doctor to be determined in all the target tongue picture vector samples; m is a preset number;
is a characteristic vector of tongue picture
And the vector distance between the ith target tongue picture vector sample; t is a preset distance.
2. The method of claim 1, wherein obtaining a target tongue vector sample from all tongue vector samples according to the vector distance comprises:
acquiring a preset number of tongue picture vector samples to be determined, which are closest to the tongue picture characteristic vector, from all tongue picture vector samples according to the vector distance;
acquiring the target tongue picture vector sample from the tongue picture vector sample to be determined; and the vector distance between the target tongue picture vector sample and the tongue picture characteristic vector is smaller than or equal to a preset distance.
3. The method according to claim 1, before said inputting said tongue image into a tongue recognition model to obtain a corresponding tongue feature vector, further comprising:
collecting tongue-looking samples of known doctors;
acquiring a tongue picture to be marked from the tongue picture sample;
marking tongue picture characteristics of the tongue picture to be marked to obtain a tongue picture vector sample;
and training a preset recognition model according to the tongue picture to be marked and the corresponding tongue picture vector sample to obtain the tongue picture recognition model.
4. The method according to claim 1, further comprising, before said acquiring the tongue image of the user to be diagnosed:
receiving a face image input by the user to be diagnosed;
determining whether the tongue image is included in the face image;
the acquiring of the tongue picture image of the user to be diagnosed comprises:
and when the facial image comprises the tongue image, acquiring the tongue image of the user to be diagnosed.
5. A recommendation device for a doctor, characterized in that it comprises:
the first acquisition module is used for acquiring a tongue image of a user to be diagnosed;
the second acquisition module is used for inputting the tongue picture image into a tongue picture recognition model to obtain a corresponding tongue picture characteristic vector;
the first determination module is used for determining a recommended doctor corresponding to the user to be diagnosed according to the tongue picture characteristic vector;
wherein the first determining module comprises:
the calculation submodule is used for calculating the vector distance between the tongue picture characteristic vector and each tongue picture vector sample respectively; the tongue picture vector sample is preset with a corresponding doctor;
the acquisition submodule is used for acquiring target tongue picture vector samples from all tongue picture vector samples according to the vector distance;
the determining submodule is used for determining the recommended doctor from the doctors corresponding to the target tongue picture vector samples;
the determining submodule is used for determining the doctor who visits the doctor corresponding to the target tongue picture vector sample as the doctor to be determined; respectively calculating the diagnosis matching value of each doctor to be determined; determining the recommended doctor from the doctors to be determined according to the visit matching value;
the calculation formula of the doctor visit matching value to be determined is as follows:
wherein r isjRepresenting the corresponding clinic matching value of the jth doctor to be determined; s is the whole target tongue pictureIn the vector sample, the doctor is the vector quantity of the jth doctor to be determined; m is a preset number;
is a characteristic vector of tongue picture
And the vector distance between the ith target tongue picture vector sample; t is a preset distance.
6. The apparatus according to claim 5, wherein the obtaining sub-module is configured to obtain, from all tongue vector samples according to the vector distance, a preset number of tongue vector samples to be determined that are closest to the tongue feature vector; acquiring the target tongue picture vector sample from the tongue picture vector sample to be determined; and the vector distance between the target tongue picture vector sample and the tongue picture characteristic vector is smaller than or equal to a preset distance.
7. The apparatus of claim 5, further comprising:
the acquisition module is used for acquiring tongue illumination samples of known doctors;
the third acquisition module is used for acquiring the tongue picture to be marked from the tongue picture sample;
the fourth acquisition module is used for marking tongue picture characteristics of the tongue to be marked to obtain a tongue picture vector sample;
and the fifth acquisition module is used for training a preset recognition model according to the tongue picture to be marked and the corresponding tongue picture vector sample to obtain the tongue picture recognition model.
8. The apparatus of claim 5, further comprising:
the receiving module is used for receiving the facial image input by the user to be diagnosed;
a second determination module for determining whether the tongue image is included in the face image;
the first obtaining module is configured to obtain a tongue image of the user to be diagnosed when the facial image includes the tongue image.
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 CN109785941A (en) | 2019-05-21 |
| CN109785941B true 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) |
Families Citing this family (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 |
| 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 |
Citations (6)
| 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 |
| 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 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106510636A (en) * | 2016-11-29 | 2017-03-22 | 深圳市易特科信息技术有限公司 | Automatic detection system and method for tongue image in traditional Chinese medicine technology |
-
2019
- 2019-01-11 CN CN201910027953.XA patent/CN109785941B/en active Active
Patent Citations (6)
| 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 |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109785941A (en) | 2019-05-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107680684B (en) | Method and device for acquiring information | |
| CN107278138A (en) | It is capable of the electronic installation and the body composition measuring method of electronic installation of automatic identification body part to be measured | |
| JP2017507386A (en) | Medical device tracking | |
| CN103886284B (en) | Character attribute information identifying method, device and electronic equipment | |
| Jaworek-Korjakowska et al. | Eskin: study on the smartphone application for early detection of malignant melanoma | |
| WO2018120447A1 (en) | Method, device and equipment for processing medical record information | |
| CN109785941B (en) | Doctor recommendation method and device | |
| JP2023522952A (en) | Systems and methods for remote dermatological diagnosis | |
| CN112331298A (en) | Method and device for issuing prescription, electronic equipment and storage medium | |
| US20230097391A1 (en) | Image processing method and apparatus, electronic device, computer-readable storage medium, and computer program product | |
| WO2018233520A1 (en) | Method and device for generating predicted image | |
| CN109003662A (en) | Providing method, device, equipment and the storage medium of clinician information | |
| CN113192639A (en) | Training method, device and equipment of information prediction model and storage medium | |
| CN107357782B (en) | Method and terminal for identifying gender of user | |
| KR102595904B1 (en) | Method and system for recommending medical consultant based medical consultation contents | |
| JP2015228202A (en) | Determination system, determination method, and determination program | |
| CN112800758A (en) | Method, system, equipment and medium for distinguishing similar meaning words in text | |
| US10758159B2 (en) | Measuring somatic response to stimulus utilizing a mobile computing device | |
| JP2012011109A (en) | Medical image processor and program | |
| CN111462910A (en) | Item matching method and device, electronic equipment and storage medium | |
| CN115482899A (en) | Prescription recommendation method and device, electronic equipment and storage medium | |
| CN109119131B (en) | Physical examination method and system based on medical examination expert intelligence library platform | |
| CN111063406A (en) | Claims reference information generation method and device | |
| CN115691793A (en) | Method and device for processing tongue picture data and related equipment | |
| CN116130088A (en) | Multi-mode face diagnosis method, device and related equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| 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 |