CN114596593B - Health-preserving data recommendation method and system based on image processing - Google Patents
Health-preserving data recommendation method and system based on image processing Download PDFInfo
- Publication number
- CN114596593B CN114596593B CN202210500147.1A CN202210500147A CN114596593B CN 114596593 B CN114596593 B CN 114596593B CN 202210500147 A CN202210500147 A CN 202210500147A CN 114596593 B CN114596593 B CN 114596593B
- Authority
- CN
- China
- Prior art keywords
- image
- standard
- health
- data
- standard 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
Abstract
The invention discloses a health preserving data recommendation method and system based on image processing, and relates to the field related to image processing, wherein the method comprises the following steps: building a health-care data recommendation platform; obtaining an initial training image set based on the image acquisition layer, and uploading the initial training image set to an image processing layer; generating a standard image set and a defect image set by performing reference classification on the input information; comparing the standard image set, performing parameter calibration on the image data in the defect image set, and adding the obtained calibration parameter set as a first constraint condition to an image processing layer; uploading a first collected image of a first user to the health-preserving data recommendation platform, matching the disease relation of the first collected image based on the image-disease mapping relation, and recommending the health-preserving data to the first user according to the matching result. The technical effects of improving the effectiveness of recommended data and multi-environment adaptability based on image intelligent processing and realizing high-quality health preservation are achieved.
Description
Technical Field
The invention relates to the field related to image processing, in particular to a health-preserving data recommendation method and system based on image processing.
Background
At the present stage, people gradually increase attention on physical health, know health care knowledge, implement a health care mode, and keep a better mental state is a main means for keeping health at present, and traditional Chinese medicine health care is used as a main basis of people and plays a role in guidance and reference.
At present, the technical problems that health care data recommendation modes are not intelligent enough, image processing modes are not flexible enough and are easily influenced by multiple environmental factors, accuracy is poor, and health care recommendation quality is influenced exist in the prior art.
Disclosure of Invention
Aiming at the defects in the prior art, the method and the system for recommending health-preserving data based on image processing solve the technical problems that in the prior art, the health-preserving data recommendation mode is not intelligent enough, the image processing mode is not flexible enough and is easily influenced by multiple environmental factors, so that the accuracy is poor, and the health-preserving recommendation quality is influenced, and achieve the technical effects of improving the accuracy of image acquisition by processing images through an intelligent image processing technology, improving the effectiveness of recommended data and multiple environmental adaptability based on a high-accuracy matching mapping mode, and further realizing high-quality health preservation.
In one aspect, the present application provides a health preserving data recommendation method based on image processing, including: building a health data recommendation platform, wherein the health data recommendation platform comprises an image acquisition layer, an image processing layer and a data matching layer, and an image-disease mapping relation is embedded in the data matching layer; based on the image acquisition layer, acquiring images of key parts of a target user set, and taking the acquired images as an initial training image set; uploading the initial training image set serving as input information to the image processing layer, and performing reference classification on the input information based on preset standard image parameters to generate a standard image set and a defect image set; performing parameter calibration on the image data in the defect image set by contrasting the standard image set to generate a calibration parameter set; taking the set of calibration parameters as a first constraint and appending the first constraint to the image processing layer for performing image calibration; uploading a first collected image of a first user to the health-preserving data recommendation platform, and carrying out disease relation matching on the first collected image based on the image-disease mapping relation to obtain a first matching result; and recommending health maintenance data to the first user according to the first matching result.
On the other hand, the application also provides a health preserving data recommendation system based on image processing, and the system comprises: the health-care data recommendation system comprises a first construction unit, a second construction unit and a third construction unit, wherein the first construction unit is used for constructing a health-care data recommendation platform, the health-care data recommendation platform comprises an image acquisition layer, an image processing layer and a data matching layer, and an image-disease mapping relation is embedded in the data matching layer; the first acquisition unit is used for acquiring images of key parts of a target user set based on the image acquisition layer and taking the acquired images as an initial training image set; the first classification unit is used for uploading the initial training image set as input information to the image processing layer, performing reference classification on the input information based on preset standard image parameters, and generating a standard image set and a defect image set; the first calibration unit is used for performing parameter calibration on the image data in the defect image set by contrasting the standard image set to generate a calibration parameter set; a first operation unit for using the set of calibration parameters as a first constraint and appending the first constraint to the image processing layer for performing image calibration; a first obtaining unit, configured to upload a first acquired image of a first user to the health care data recommendation platform, and perform disease relation matching on the first acquired image based on the image-disease mapping relation to obtain a first matching result; and the first recommending unit is used for recommending health preserving data to the first user according to the first matching result.
In a third aspect, the present application provides a health care data recommendation system based on image processing, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of the first aspect when executing the program.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
1. the health-care data recommendation platform is established, and logical relation connection and logical function endowment are respectively carried out on an image acquisition layer, an image processing layer and a data matching layer in the platform, so that the functional structure design of the health-care data recommendation platform is completed. Furthermore, a calibration parameter set is generated by calibrating the influence parameters of the standard image on the defect image set, the calibration parameter set is used as a calibration constraint condition in the image processing layer to execute a logic function, after the image processing layer is processed, the image acquired by the first user in real time is uploaded to the health maintenance data recommendation platform, the disease relation matching is carried out on the first acquired image based on the image-disease mapping relation, and health maintenance data recommendation is carried out according to the matching result, so that the purposes of improving the accuracy of the acquired image by processing the image through an intelligent image processing technology, improving the validity degree of recommended data and multi-environment adaptability based on a high-accuracy matching mapping mode, and further realizing the technical effect of high-quality health maintenance are achieved.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
fig. 1 is a schematic flowchart of a health preserving data recommendation method based on image processing according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a defect image parameter calibration of a health care data recommendation method based on image processing according to an embodiment of the present application;
fig. 3 is a schematic flow chart illustrating disease relation matching of a health data recommendation method based on image processing according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a health care data recommendation system based on image processing according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.
Description of reference numerals: the system comprises a first building unit 11, a first acquisition unit 12, a first classification unit 13, a first calibration unit 14, a first operation unit 15, a first obtaining unit 16, a first recommendation unit 17, a bus 300, a receiver 301, a processor 302, a transmitter 303, a memory 304 and a bus interface 305.
Detailed Description
The embodiment of the application provides a health preserving data recommendation method and system based on image processing, and solves the technical problems that in the prior art, a health preserving data recommendation mode is not intelligent enough, an image processing mode is not flexible enough and is easily influenced by multiple environmental factors, so that the accuracy is poor, and the health preserving recommendation quality is influenced.
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are merely some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein.
According to the technical scheme, the data acquisition, storage, use, processing and the like meet relevant regulations of national laws and regulations.
At present, health maintenance analysis is carried out in a mode of carrying out information recording and network diagnosis on people, or health maintenance analysis guidance is carried out in a mode of carrying out inquiry based on a home electronic assistant, convenience is low, intelligence degree is low, and health maintenance continuity analysis is low along with change of multiple environments, so that the health maintenance analysis is influenced by multiple environment factors, adaptability is low, accuracy is poor, and health maintenance recommendation quality is influenced.
In view of the above technical problems, the technical solution provided by the present application has the following general idea:
the health data recommendation platform is built, and logical relation connection and logical function endowment are respectively carried out on an image acquisition layer, an image processing layer and a data matching layer in the platform, so that the functional structure design of the health data recommendation platform is completed. Furthermore, a calibration parameter set is generated by calibrating the influence parameters of the standard image on the defect image set, the calibration parameter set is used as a calibration constraint condition in the image processing layer to execute a logic function, after the image processing layer is processed, the image acquired by the first user in real time is uploaded to the health maintenance data recommendation platform, the disease relation matching is carried out on the first acquired image based on the image-disease mapping relation, and health maintenance data recommendation is carried out according to the matching result, so that the purposes of improving the accuracy of the acquired image by processing the image through an intelligent image processing technology, improving the validity degree of recommended data and multi-environment adaptability based on a high-accuracy matching mapping mode, and further realizing the technical effect of high-quality health maintenance are achieved.
For better understanding of the above technical solutions, the following detailed descriptions will be provided in conjunction with the drawings and the detailed description of the embodiments.
Example one
As shown in fig. 1, an embodiment of the present application provides a health preserving data recommendation method based on image processing, where the method includes:
step S100: building a health data recommendation platform, wherein the health data recommendation platform comprises an image acquisition layer, an image processing layer and a data matching layer, and an image-disease mapping relation is embedded in the data matching layer;
specifically, at the present stage, health-care health analysis is performed in a way of recording information of people, performing network diagnosis and the like, or health-care analysis guidance is performed in a way of querying based on a home electronic assistant, so that the convenience is low, the intelligence degree is low, and the health-care continuity analysis is low along with the change of multiple environments, so that the health-care health analysis is easily influenced by multiple environmental factors. In order to solve the problem, a health preserving data recommendation method based on image processing is provided, and intelligent recommendation is realized by combining a system platform with complex operation of a computer.
Further, firstly, a health preserving data recommendation platform is built, and the data in the health preserving engineer protective equipment recommendation platform is subjected to flow and logical function processing, so that the system is completed, specifically, the health preserving data recommendation platform comprises three functional layers of an image acquisition layer, an image processing layer and a data matching layer, and the image acquisition layer, the image processing layer and the data matching layer are connected in a presentation layer mode, wherein the image acquisition layer is used for acquiring data according to an acquisition target, the output data is used for being input into the image processing layer to be subjected to corresponding logical processing so as to meet the image reference requirement, the processed image data is input into the data matching layer and used for executing the mapping matching function given by the network layer, and the data output by the data matching layer is output as the output data of the health preserving data recommendation platform, the effects of perfecting the platform process and the function are achieved.
For example, for the tongue diagnosis in traditional Chinese medicine health maintenance, the image of the image-symptom mapping relationship is the image acquisition result of the tongue, and the symptom mapping is output based on the symptom corresponding to the tongue image information, that is, the construction of a mapping library of big data is realized through a medical database, a digital medical record library and the like, so that the data matching layer has higher reliability.
Step S200: based on the image acquisition layer, acquiring images of key parts of a target user set, and taking the acquired images as an initial training image set;
step S300: uploading the initial training image set serving as input information to the image processing layer, and performing reference classification on the input information based on preset standard image parameters to generate a standard image set and a defect image set;
specifically, the image acquisition layer is a first functional layer of the health maintenance data recommendation platform; the target user set is a user set of a user population based on the characteristic information of the user, such as the age, sex, weight and the like of the login user; the image processing layer is used for receiving and processing the data output by the image acquisition layer, and in detail, the execution process is as follows:
and performing image acquisition on key parts of a target user set according to the image acquisition layer, wherein the key parts are parts with obvious changes based on health-preserving diagnosis and treatment characteristics, such as facial states, tongue states and the like, so that acquired key part data are used as an initial training image set for health-preserving analysis, the acquired initial training image set is used as input information and is uploaded to a next processing layer, namely the image processing layer, and the input image information is classified according to preset standard image parameters stored in the image processing layer in advance to complete corresponding classification results, wherein the preset standard image parameters are preset image parameters such as preset color reduction degree and preset image brightness.
The reference classification in the image processing layer is to use the parameters in the preset standard image as reference, to perform reference conforming to the standard on the input image information, and to use the image conforming to the preset standard image parameters in the input image information as the standard image set; and taking the image which does not accord with the preset standard image parameter in the input image information as the defect image set, so that the image of the target user group can be taken as training data, the classification is carried out by taking a preset standard image parameter as a reference, the next step of thinning processing is completed, and the quality processing of the initial training image set is further completed.
Step S400: performing parameter calibration on the image data in the defect image set by contrasting the standard image set to generate a calibration parameter set;
step S500: taking the set of calibration parameters as a first constraint and appending the first constraint to the image processing layer for performing image calibration;
specifically, after the image processing layer outputs the standard image set and the defect image set after reference classification, parameter calibration is performed on image data in the defect image set according to the standard image set, wherein calibration parameters include but are not limited to light calibration, angle calibration, contrast calibration, color calibration and the like, so that the image data in the defect image set is subjected to defect location, further standardized calibration is performed based on defect parameters, and the calibration parameter set is output, so that the technical effect of improving the image standard property and quality of the initial training image as a training set is achieved.
Because the calibration parameter set is an image calibration parameter based on standardization, the calibration parameter set is used as a constraint condition and fed back to a front logic relationship of the image processing layer, namely, an image processing relationship of before image calibration and after image processing, in other words, the calibration parameter set is used as a first constraint condition and added to the image processing layer, an image calibration function is executed, namely, platform module enrichment and logic function refinement can be carried out on the health-preserving data recommendation platform in a mode of reprocessing after image calibration, and the accuracy of further image processing is improved.
Step S600: uploading a first collected image of a first user to the health-preserving data recommendation platform, and carrying out disease relation matching on the first collected image based on the image-disease mapping relation to obtain a first matching result;
step S700: and recommending health maintenance data to the first user according to the first matching result.
Further, as shown in fig. 3, in the step S700 of performing disease relation matching on the first captured image, the method further includes:
step S710: acquiring disease symptoms and health-preserving data of the key parts based on big data, matching the disease symptoms and the health-preserving data one by one, and building a health-preserving data matching database;
step S720: obtaining a calibrated image of the first captured image based on the image processing layer;
step S730: obtaining a disease set of the first user by performing target region segmentation and disease characteristic sign extraction on the calibrated image;
step S740: and inputting the disease set into the health-preserving data matching database for matching to obtain the first matching result.
Specifically, a first collected image of a first user is obtained, wherein the first user is a login user or a binding user who uses the system in real time, and the first collected image of the first user is further collected, wherein the first collected image is an image collected by the first user in real time, such as a tongue image, an eye image, a nose image or a face image, and the first collected image of the first user is uploaded to the health maintenance data recommendation platform, and disease relation matching is performed according to an image-disease mapping relation embedded in the data matching layer in the health maintenance data recommendation platform, so that the first matching result is obtained.
And performing a disease relation matching process on the first acquired image according to the image-disease mapping relation, further generating a health-preserving data matching database, and storing the health-preserving data matching database in the data matching layer for auxiliary mapping. When the calibrated image of the first acquired image is obtained, further performing target area segmentation and symptom characteristic sign extraction, including target areas such as tongue, eye, face and nose, and further acquiring corresponding symptoms, for example, taking the tongue image as an example image, wherein the color change of the tongue image corresponds to different recommendation results, for example, the tongue color is pale white, the prompt content of the tongue image may be deficiency of both qi and blood or anemia, qi-tonifying and blood-nourishing nutrition conditioning is required, and the recommendation of corresponding health maintenance data is performed according to the health maintenance data matching database; the tongue tip is reddish, the fact that spleen and stomach fire is large is prompted, heat is required to be cleared away, vegetables are eaten more, corresponding health-care data are recommended according to the health-care data matching database, health-care data are recommended, the purpose that the accuracy of collected images is improved by processing the images through an intelligent image processing technology is achieved, effectiveness of the recommended data and multi-environment adaptability are improved based on a high-accuracy matching mapping mode, and the technical effect of high-quality health care is achieved.
Further, the step S300 of classifying the input information by reference further includes:
step S310: performing feature extraction on the preset standard image parameters to obtain a preset standard image feature set;
step S320: obtaining a first standard image feature in the preset standard image feature set;
step S330: classifying the initial training image set according to the first standard image characteristic to obtain a first standard image set and a first substandard image set;
step S340: traversing each feature in the preset standard image feature set based on the classification logic of the first standard image feature to generate a second standard image set and a second substandard image set corresponding to the second standard image feature until an nth standard image set and an nth substandard image set corresponding to the nth standard image feature.
Further, step S340 in the embodiment of the present application further includes:
step S341: generating the standard image set by carrying out image fusion on the first standard image set, the second standard image set and the nth standard image set;
step S342: and performing image fusion on the first substandard image set, the second substandard image set and the nth substandard image set to generate the defect image set.
Specifically, the process of performing reference classification according to the image processing layer of the health maintenance data platform mainly includes performing feature extraction on preset standard image parameters, such as preset brightness, preset light sensation, preset contrast, preset color and the like, so as to obtain a preset standard image feature set.
After obtaining the features of the preset standard image parameters, generating the preset standard image feature set, so as to perform feature class division according to the preset standard image feature set, taking the standard features of the images as a comparison basis, for example, when a tongue image class is adopted, the tongue color of the tongue image class is the standard feature, and then performing reference classification on the output initial training image set according to the first standard image feature to judge whether the images reach the standard, taking the images reaching the standard as the first standard image set, and taking the images failing to reach the standard as the first non-standard image set.
By analogy, traversal is performed according to the characteristics of the preset brightness, the preset light sensation, the preset contrast, the preset color and the like, so that each characteristic can be classified according to the reference, and a second standard image set, a third standard image set … till an nth standard image set, a second unqualified image set … till an nth unqualified image set, which correspond to each characteristic, are obtained.
Then, performing image fusion on the obtained first standard-reaching image set, the obtained second standard-reaching image set, the obtained third standard-reaching image set … to the nth standard-reaching image set to generate the standard image set; and carrying out image fusion on the first substandard image set, the second substandard image set and the nth substandard image set to generate the defect image set. Each set from 1 to n represents a corresponding feature, so that the defect image sets are respectively output from the standardized image sets after image feature fusion is carried out on each standard feature, the images are processed through an intelligent image processing technology to improve the accuracy of the acquired images, and the technical effect of logical intelligent classification is achieved.
Further, as shown in fig. 2, in the step S400 of performing parameter calibration on the image data in the defect image set, the method further includes:
step S410: performing element extraction on the illumination angles in the standard image set to obtain a standard illumination angle set;
step S420: performing element extraction on the illumination angles in the defect image set to obtain a non-standard illumination angle set;
step S430: performing visualization processing on the standard illumination angle set and the non-standard illumination angle set to obtain visual illumination angle distribution;
step S440: traversing and analyzing the visual illumination angle distribution, and determining the illumination angle critical values of the standard illumination angle set and the non-standard illumination angle set;
step S450: and according to the illumination angle critical value, performing parameter calibration on the image data in the defect image set.
Specifically, after the image processing layer in the health data recommendation platform performs reference identification, according to the standard image set and the defect image set classified by the reference, in order to ensure better image quality output by the input image processing layer, image calibration needs to be performed on the defect image set according to the standard image set, and the calibration process is as follows:
firstly, obtaining illumination angle elements in the standard image set, obtaining the standard illumination angle set according to different requirements on light angles of different identification parts, further, extracting the elements of the illumination angles in the defect image set, performing visualization processing on the illumination angles in the defect image set by taking the illumination angle set in the standard image set as a reference so as to output visual illumination angle distribution, and performing parameter calibration on the image set with defects according to the visual illumination angle distribution.
Furthermore, the color restoration degree and the identification matching accuracy can be ensured by comparing the light between the defect image and the standard image, and then a more accurate space angle, namely a space light angle, can be formed by performing visual illumination distribution processing on the standard image through a visual processing means, so that according to the target characteristics, for example, when the defect of the eye data set is identified, the identification range is determined under the condition that the eye light is clear, and then the illumination angle critical value is generated, wherein the illumination angle critical value is a threshold value which is met under the condition that the eye illumination is clear, namely the successful correction point of the image data in the defect image set, and further the analysis and calibration of the space light angle are realized based on the visual illumination distribution mode, the intellectualization and the accuracy of the calibration are improved, and the mode based on high-accuracy matching mapping is achieved, the effectiveness of recommended data and multi-environment adaptability are improved.
Further, step S410 in the embodiment of the present application further includes:
step S411: obtaining a definition value set of each standard angle image corresponding to the standard illumination angle set;
step S412: performing logic traversal on the standard illumination angle set and the standard angle image definition value sets to determine an angle-definition value logic relationship;
step S413: screening the definition value sets of the images at all the standard angles to obtain an optimal definition value;
step S414: and determining an optimal shooting angle based on the angle-definition value logical relationship and the optimal definition value.
Specifically, based on the standard illumination angle set obtained from the standard image set, sharpness analysis is performed on each illumination angle, and since the sharpness of light rays produced by a user at different angles is different, in order to ensure the calibration accuracy and meet the definition of calibration, the sharpness value of the image in each standard angle image is analyzed, and the optimal shooting angle is determined according to the sharpness value. Furthermore, the change relation between the illumination angle and the image definition can be visually presented by establishing an angle-definition value logical relation, so that each standard angle image definition value set is screened through the established angle-definition value logical relation, wherein the angles and the definition values in the angle-definition value logical relation are in one-to-one correspondence, the corresponding shooting angle is determined according to the optimal definition value optimizing target, and the determined shooting angle is used as the optimal shooting angle. The method achieves the aim of further optimizing the shooting angle by adding a newly-added calibration element of the illumination definition and aims to improve the corrected image quality.
Further, a voice interaction layer is embedded in the health data recommendation platform, and step S100 in the embodiment of the present application further includes:
step S110: performing voice interaction of a preset problem on the first user according to the voice interaction layer to obtain first interactive voice information;
step S120: carrying out symptom influence element extraction on the first interactive voice information to obtain a symptom influence element set;
step S130: optimizing the first matching result according to the set of condition affecting elements.
Specifically, in order to ensure the applicability of the health data recommendation platform to the user population, a voice interaction layer is embedded in the health data recommendation platform and used for performing voice recognition and processing on real-time voice of the user, and after the first matching result is matched with corresponding health data, the recommended health data can be further optimized by setting voice interaction of preset problems, wherein the preset problems can be further acquired according to an inquiry flow, for example, further image element extraction is performed according to recent sleep conditions, appetite, rest states, working pressure and the like, so that the first matching result is optimized according to the extracted influence element set. Further, after the voice interaction layer identifies disease influencing elements, further health-preserving data emphasis adjustment can be performed through preference of the first user for a health-preserving mode, such as food health preservation, sports health preservation, medicine health preservation and the like, so that high practicability and user laminating performance of the first matching result are achieved.
Compared with the prior art, the invention has the following beneficial effects:
1. the health-care data recommendation platform is established, and logical relation connection and logical function endowment are respectively carried out on an image acquisition layer, an image processing layer and a data matching layer in the platform, so that the functional structure design of the health-care data recommendation platform is completed. Furthermore, a calibration parameter set is generated by calibrating the influence parameters of the standard image on the defect image set, the calibration parameter set is used as a calibration constraint condition in the image processing layer to execute a logic function, after the image processing layer is processed, the image acquired by the first user in real time is uploaded to the health maintenance data recommendation platform, the disease relation matching is carried out on the first acquired image based on the image-disease mapping relation, and health maintenance data recommendation is carried out according to the matching result, so that the purposes of improving the accuracy of the acquired image by processing the image through an intelligent image processing technology, improving the validity degree of recommended data and multi-environment adaptability based on a high-accuracy matching mapping mode, and further realizing the technical effect of high-quality health maintenance are achieved.
2. Due to the adoption of the mode based on the visual illumination distribution, the analysis and calibration of the space light angle are realized, the calibration intelligence and accuracy are improved, the mode based on high-accuracy matching mapping is achieved, and the recommendation data validity and multi-environment adaptability are improved.
3. Because the established angle-definition value logical relation is adopted to screen the definition value set of each standard angle image, the corresponding optimal shooting angle is determined according to the optimal target of the optimal definition value, and the corrected image quality is improved.
Example two
Based on the same inventive concept as the image processing-based health data recommendation method in the foregoing embodiment, the present invention further provides an image processing-based health data recommendation system, as shown in fig. 4, the system includes:
the health-care data recommendation system comprises a first construction unit 11, wherein the first construction unit 11 is used for constructing a health-care data recommendation platform, the health-care data recommendation platform comprises an image acquisition layer, an image processing layer and a data matching layer, and an image-disease mapping relation is embedded in the data matching layer;
the first acquisition unit 12 is configured to acquire images of key parts of a target user set based on the image acquisition layer, and use the acquired images as an initial training image set;
a first classification unit 13, where the first classification unit 13 is configured to upload the initial training image set as input information to the image processing layer, perform reference classification on the input information based on preset standard image parameters, and generate a standard image set and a defect image set;
a first calibration unit 14, where the first calibration unit 14 is configured to perform parameter calibration on image data in the defect image set with reference to the standard image set, so as to generate a calibration parameter set;
a first operation unit 15, said first operation unit 15 being configured to take said set of calibration parameters as a first constraint and to attach said first constraint to said image processing layer for performing image calibration;
a first obtaining unit 16, where the first obtaining unit 16 is configured to upload a first acquired image of a first user to the health care data recommendation platform, and perform disease relation matching on the first acquired image based on the image-disease mapping relation to obtain a first matching result;
and the first recommending unit 17, where the first recommending unit 17 is configured to recommend health preserving data to the first user according to the first matching result.
Further, the system further comprises:
a second obtaining unit, configured to perform feature extraction on the preset standard image parameter to obtain a preset standard image feature set;
a third obtaining unit, configured to obtain a first standard image feature in the preset standard image feature set;
a fourth obtaining unit, configured to classify the initial training image set according to the first standard image feature to obtain a first standard image set and a first substandard image set;
and the first generation unit is used for traversing all the features in the preset standard image feature set based on the classification logic of the first standard image feature to generate a second standard image feature corresponding second standard image feature and a second non-standard image feature corresponding second standard image feature until an nth standard image feature corresponding nth standard image feature and an nth non-standard image feature corresponding nth standard image feature.
Further, the system further comprises:
a second generating unit, configured to generate the standard image set by performing image fusion on the first standard image set, the second standard image set, and up to the nth standard image set;
a third generating unit, configured to generate the defect image set by image fusion of the first non-compliant image set, the second non-compliant image set, and up to the nth non-compliant image set.
Further, the system further comprises:
a fifth obtaining unit, configured to perform element extraction on the illumination angles in the standard image set to obtain a standard illumination angle set;
a sixth obtaining unit, configured to perform element extraction on the illumination angles in the defect image set to obtain a non-standard illumination angle set;
a seventh obtaining unit, configured to perform visualization processing on the standard illumination angle set and the non-standard illumination angle set to obtain a visualization illumination angle distribution;
a first determining unit, configured to perform traversal analysis on the visual illumination angle distribution, and determine an illumination angle critical value of the standard illumination angle set and the non-standard illumination angle set;
a second calibration unit, configured to perform threshold ratio analysis on the first gap data according to the first safety gap threshold, and output a first gap evaluation index.
Further, the system further comprises:
an eighth obtaining unit, configured to obtain each standard angle image sharpness value set corresponding to the standard illumination angle set;
a second determining unit, configured to perform logical traversal on the standard illumination angle set and the standard angle image sharpness value sets, and determine an angle-sharpness value logical relationship;
a ninth obtaining unit, configured to screen the sharpness value sets of the standard angle images to obtain an optimal sharpness value;
a third determination unit configured to determine an optimal shooting angle based on the angle-sharpness-value logical relationship and the optimal sharpness value.
Further, the system further comprises:
the second building unit is used for collecting the disease symptoms and health maintenance data of the key parts based on big data, matching the disease symptoms and the health maintenance data one by one and building a health maintenance data matching database;
a tenth obtaining unit configured to obtain a calibrated image of the first captured image based on the image processing layer;
an eleventh obtaining unit, configured to obtain a disease condition set of the first user by performing target region segmentation and disease condition feature sign extraction on the calibrated image;
the first matching unit is used for inputting the disease condition set into the health-preserving data matching database for matching to obtain the first matching result.
Further, the system further comprises:
a twelfth obtaining unit, configured to perform voice interaction with a preset problem for the first user according to the voice interaction layer, and obtain first interactive voice information;
a thirteenth obtaining unit, configured to perform influence element extraction on the first interactive voice information for a medical condition, and obtain a medical condition influence element set;
a first optimization unit for optimizing the first matching result according to the set of condition affecting elements.
Various changes and specific examples of the image processing-based health care data recommendation method in the first embodiment of fig. 1 are also applicable to the image processing-based health care data recommendation system of the present embodiment, and through the foregoing detailed description of the image processing-based health care data recommendation method, those skilled in the art can clearly know the implementation method of the image processing-based health care data recommendation system in the present embodiment, so for the brevity of the description, detailed descriptions are omitted here.
EXAMPLE III
The electronic device of the present application is described below with reference to fig. 5.
Fig. 5 illustrates a schematic structural diagram of an electronic device according to the present application.
Based on the inventive concept of the image processing-based health care data recommendation method in the foregoing embodiment, the present invention further provides an image processing-based health care data recommendation system, on which a computer program is stored, and when the program is executed by a processor, the program implements the steps of any one of the methods of the image processing-based health care data recommendation system.
Where in fig. 5 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 305 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other systems over a transmission medium. The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
The embodiment of the application provides a health preserving data recommendation method based on image processing, which comprises the following steps: building a health data recommendation platform, wherein the health data recommendation platform comprises an image acquisition layer, an image processing layer and a data matching layer, and an image-disease mapping relation is embedded in the data matching layer; based on the image acquisition layer, acquiring images of key parts of a target user set, and taking the acquired images as an initial training image set; uploading the initial training image set serving as input information to the image processing layer, and performing reference classification on the input information based on preset standard image parameters to generate a standard image set and a defect image set; performing parameter calibration on the image data in the defect image set by contrasting the standard image set to generate a calibration parameter set; taking the set of calibration parameters as a first constraint and appending the first constraint to the image processing layer for performing image calibration; uploading a first collected image of a first user to the health-preserving data recommendation platform, and carrying out disease relation matching on the first collected image based on the image-disease mapping relation to obtain a first matching result; and recommending health maintenance data to the first user according to the first matching result. The method and the device achieve the technical effects that the images are processed through an intelligent image processing technology so as to improve the accuracy of the collected images, and the effectiveness of recommended data and multi-environment adaptability are improved based on a high-accuracy matching mapping mode, so that high-quality health maintenance is realized.
Those of ordinary skill in the art will understand that: the various numbers of the first, second, etc. mentioned in this application are only used for the convenience of description and are not used to limit the scope of the embodiments of this application, nor to indicate the order of precedence. "and/or" describes the association relationship of the associated object, indicating that there may be three relationships, for example, a and/or B, which may indicate: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one" means one or more. At least two means two or more. "at least one," "any," or similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one (one ) of a, b, or c, may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or multiple.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable system. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device including one or more available media integrated servers, data centers, and the like. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
The various illustrative logical units and circuits described in this application may be implemented or operated upon by general purpose processors, digital signal processors, Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other programmable logic systems, discrete gate or transistor logic, discrete hardware components, or any combination thereof. A general-purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing systems, e.g., a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a digital signal processor core, or any other similar configuration.
Although the present application has been described in conjunction with specific features and embodiments thereof, it will be evident that various modifications and combinations can be made thereto without departing from the spirit and scope of the application. Accordingly, the specification and figures are merely exemplary of the application as defined in the appended claims and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of the application. It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the present application and its equivalent technology, it is intended that the present application include such modifications and variations.
Claims (8)
1. A health preserving data recommendation method based on image processing is characterized by comprising the following steps:
building a health data recommendation platform, wherein the health data recommendation platform comprises an image acquisition layer, an image processing layer and a data matching layer, and an image-disease mapping relation is embedded in the data matching layer;
based on the image acquisition layer, acquiring images of key parts of a target user set, and taking the acquired images as an initial training image set;
uploading the initial training image set serving as input information to the image processing layer, and performing reference classification on the input information based on preset standard image parameters to generate a standard image set and a defect image set;
performing parameter calibration on the image data in the defect image set by contrasting the standard image set to generate a calibration parameter set;
taking the set of calibration parameters as a first constraint and appending the first constraint to the image processing layer for performing image calibration;
uploading a first collected image of a first user to the health-preserving data recommendation platform, and carrying out disease relation matching on the first collected image based on the image-disease mapping relation to obtain a first matching result;
according to the first matching result, recommending health-preserving data to the first user;
the reference classification of the input information includes:
performing feature extraction on the preset standard image parameters to obtain a preset standard image feature set;
obtaining a first standard image feature in the preset standard image feature set;
classifying the initial training image set according to the first standard image feature to obtain a first standard image set and a first substandard image set;
traversing each feature in the preset standard image feature set based on the classification logic of the first standard image feature to generate a second standard image set and a second substandard image set corresponding to the second standard image feature until an nth standard image set and an nth substandard image set corresponding to the nth standard image feature.
2. The method of claim 1, wherein the method comprises:
generating the standard image set by carrying out image fusion on the first standard image set, the second standard image set and the nth standard image set;
and performing image fusion on the first substandard image set, the second substandard image set and the nth substandard image set to generate the defect image set.
3. The method of claim 2, wherein the performing parameter calibration on the image data in the defect image collection comprises:
performing element extraction on the illumination angles in the standard image set to obtain a standard illumination angle set;
performing element extraction on the illumination angles in the defect image set to obtain a non-standard illumination angle set;
performing visualization processing on the standard illumination angle set and the non-standard illumination angle set to obtain visual illumination angle distribution;
traversing and analyzing the visual illumination angle distribution, and determining the illumination angle critical values of the standard illumination angle set and the non-standard illumination angle set;
and according to the illumination angle critical value, performing parameter calibration on the image data in the defect image set.
4. The method of claim 3, wherein the method comprises:
obtaining a definition value set of each standard angle image corresponding to the standard illumination angle set;
performing logic traversal on the standard illumination angle set and the standard angle image definition value sets to determine an angle-definition value logic relationship;
screening the definition value sets of the images of all the standard angles to obtain an optimal definition value;
and determining an optimal shooting angle based on the angle-definition value logical relation and the optimal definition value.
5. The method of claim 4, wherein said matching the first acquired image for a medical relationship comprises:
acquiring disease symptoms and health-preserving data of the key parts based on big data, matching the disease symptoms and the health-preserving data one by one, and building a health-preserving data matching database;
obtaining a calibrated image of the first captured image based on the image processing layer;
obtaining a disease set of the first user by performing target region segmentation and disease characteristic sign extraction on the calibrated image;
and inputting the disease set into the health-preserving data matching database for matching to obtain the first matching result.
6. The method of claim 5, wherein the health data recommendation platform is embedded with a voice interaction layer, the method comprising:
performing voice interaction of a preset problem on the first user according to the voice interaction layer to obtain first interactive voice information;
carrying out symptom influence element extraction on the first interactive voice information to obtain a symptom influence element set;
optimizing the first matching result according to the set of condition affecting elements.
7. A health care data recommendation system based on image processing, the system comprising:
the health-care data recommendation system comprises a first construction unit, a second construction unit and a third construction unit, wherein the first construction unit is used for constructing a health-care data recommendation platform, the health-care data recommendation platform comprises an image acquisition layer, an image processing layer and a data matching layer, and an image-disease mapping relation is embedded in the data matching layer;
the first acquisition unit is used for acquiring images of key parts of a target user set based on the image acquisition layer and taking the acquired images as an initial training image set;
the first classification unit is used for uploading the initial training image set as input information to the image processing layer, performing reference classification on the input information based on preset standard image parameters, and generating a standard image set and a defect image set;
the first calibration unit is used for performing parameter calibration on the image data in the defect image set by contrasting the standard image set to generate a calibration parameter set;
a first operation unit for using the set of calibration parameters as a first constraint and appending the first constraint to the image processing layer for performing image calibration;
a first obtaining unit, configured to upload a first acquired image of a first user to the health care data recommendation platform, and perform disease relation matching on the first acquired image based on the image-disease mapping relation to obtain a first matching result;
the first recommending unit is used for recommending health preserving data to the first user according to the first matching result;
a second obtaining unit, configured to perform feature extraction on the preset standard image parameter to obtain a preset standard image feature set;
a third obtaining unit, configured to obtain a first standard image feature in the preset standard image feature set;
a fourth obtaining unit, configured to classify the initial training image set according to the first standard image feature to obtain a first standard image set and a first substandard image set;
and the first generation unit is used for traversing all the features in the preset standard image feature set based on the classification logic of the first standard image feature to generate a second standard image feature corresponding second standard image feature and a second non-standard image feature corresponding second standard image feature until an nth standard image feature corresponding nth standard image feature and an nth non-standard image feature corresponding nth standard image feature.
8. A health data recommendation system based on image processing is characterized by comprising: a processor coupled to a memory, the memory for storing a program that, when executed by the processor, causes a system to perform the steps of the method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210500147.1A CN114596593B (en) | 2022-05-10 | 2022-05-10 | Health-preserving data recommendation method and system based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210500147.1A CN114596593B (en) | 2022-05-10 | 2022-05-10 | Health-preserving data recommendation method and system based on image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114596593A CN114596593A (en) | 2022-06-07 |
| CN114596593B true CN114596593B (en) | 2022-07-29 |
Family
ID=81821015
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210500147.1A Active CN114596593B (en) | 2022-05-10 | 2022-05-10 | Health-preserving data recommendation method and system based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114596593B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109659037A (en) * | 2018-12-29 | 2019-04-19 | 大连君煜信息技术有限公司 | The recommended method and device of regimen |
| CN111312358A (en) * | 2020-01-21 | 2020-06-19 | 佛山市高明曦逻科技有限公司 | Self-service medicine supermarket-based medicine purchase guiding method and system and readable storage medium |
| CN111899239A (en) * | 2020-07-27 | 2020-11-06 | 腾讯科技（深圳）有限公司 | Image processing method and device |
| CN112866656A (en) * | 2019-11-26 | 2021-05-28 | Oppo广东移动通信有限公司 | White balance correction method and device, storage medium and terminal equipment |
| CN113707305A (en) * | 2021-08-30 | 2021-11-26 | 康键信息技术（深圳）有限公司 | Health scheme recommendation method, device, equipment and medium based on deep learning |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114066828B (en) * | 2021-11-03 | 2022-09-02 | 深圳市创科自动化控制技术有限公司 | Image processing method and system based on multifunctional bottom layer algorithm |
-
2022
- 2022-05-10 CN CN202210500147.1A patent/CN114596593B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109659037A (en) * | 2018-12-29 | 2019-04-19 | 大连君煜信息技术有限公司 | The recommended method and device of regimen |
| CN112866656A (en) * | 2019-11-26 | 2021-05-28 | Oppo广东移动通信有限公司 | White balance correction method and device, storage medium and terminal equipment |
| CN111312358A (en) * | 2020-01-21 | 2020-06-19 | 佛山市高明曦逻科技有限公司 | Self-service medicine supermarket-based medicine purchase guiding method and system and readable storage medium |
| CN111899239A (en) * | 2020-07-27 | 2020-11-06 | 腾讯科技（深圳）有限公司 | Image processing method and device |
| CN113707305A (en) * | 2021-08-30 | 2021-11-26 | 康键信息技术（深圳）有限公司 | Health scheme recommendation method, device, equipment and medium based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114596593A (en) | 2022-06-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11410760B2 (en) | Medical evaluation system and method for use therewith | |
| US20200357118A1 (en) | Medical scan viewing system with enhanced training and methods for use therewith | |
| KR101977174B1 (en) | Apparatus, method and computer program for analyzing image | |
| US20200342267A1 (en) | Data processing apparatus and method, recognition apparatus, learning data storage apparatus, machine learning apparatus, and program | |
| CN107742100B (en) | A kind of examinee's auth method and terminal device | |
| US20220051771A1 (en) | Report generating system and methods for use therewith | |
| CN112507701B (en) | Identification method, device, equipment and storage medium of medical data to be corrected | |
| WO2014186838A1 (en) | A system and method for remote medical diagnosis | |
| CN111475713A (en) | Doctor information recommendation method and device, electronic equipment, system and storage medium | |
| US11462315B2 (en) | Medical scan co-registration and methods for use therewith | |
| US20070150314A1 (en) | Method for carrying out quality control of medical data records collected from different but comparable patient collectives within the bounds of a medical plan | |
| CN113366499A (en) | Associating population descriptors with trained models | |
| US20220037019A1 (en) | Medical scan artifact detection system and methods for use therewith | |
| US20230316505A1 (en) | Medical scan viewing system with roc adjustment and methods for use therewith | |
| US20220051114A1 (en) | Inference process visualization system for medical scans | |
| CN114596593B (en) | Health-preserving data recommendation method and system based on image processing | |
| Chen et al. | Application of artificial intelligence in tongue diagnosis of traditional Chinese medicine: a review | |
| CN111477289A (en) | Method and device for storing and reading detection report | |
| Sameki et al. | ICORD: Intelligent Collection of Redundant Data-A Dynamic System for Crowdsourcing Cell Segmentations Accurately and Efficiently. | |
| CN111048202A (en) | Intelligent traditional Chinese medicine diagnosis system and method thereof | |
| US20110081060A1 (en) | Pathological-Diagnosis Support Device and Pathological-Diagnosis Support System | |
| CN113903433B (en) | Image processing method and device and electronic equipment | |
| Bidaki et al. | Lesion area assessment in psoriasis patients | |
| US10839299B2 (en) | Non-leading computer aided detection of features of interest in imagery | |
| Xue et al. | Retinal blood vessel segmentation using saliency detection model and region optimization |
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 |