CN112037888A - Physiological health characteristic data monitoring method, device, equipment and storage medium - Google Patents

Physiological health characteristic data monitoring method, device, equipment and storage medium Download PDF

Info

Publication number
CN112037888A
CN112037888A CN202010884367.XA CN202010884367A CN112037888A CN 112037888 A CN112037888 A CN 112037888A CN 202010884367 A CN202010884367 A CN 202010884367A CN 112037888 A CN112037888 A CN 112037888A
Authority
CN
China
Prior art keywords
target
information
characteristic data
food
preset
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202010884367.XA
Other languages
Chinese (zh)
Other versions
CN112037888B (en
Inventor
蓝龙辉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Kangjian Information Technology Shenzhen Co Ltd
Original Assignee
Kangjian Information Technology Shenzhen Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Kangjian Information Technology Shenzhen Co Ltd filed Critical Kangjian Information Technology Shenzhen Co Ltd
Priority to CN202010884367.XA priority Critical patent/CN112037888B/en
Publication of CN112037888A publication Critical patent/CN112037888A/en
Application granted granted Critical
Publication of CN112037888B publication Critical patent/CN112037888B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/60—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to nutrition control, e.g. diets
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9536—Search customisation based on social or collaborative filtering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • 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
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Abstract

The invention relates to the technical field of artificial intelligence, and provides a method, a device, equipment and a storage medium for monitoring physiological health characteristic data, which are used for solving the problem of low accuracy of health analysis in the prior art. The monitoring method of the physiological health characteristic data comprises the following steps: calling corresponding initial physiological health characteristic data according to the user authorization information and the user mode information; calling a preset food identification model, and identifying a diet image through the food identification model to obtain target food information; according to the auxiliary information called from the health monitoring system and the food health analysis rule corresponding to the auxiliary information, food health analysis is carried out on the target food information to obtain an analysis result, wherein the auxiliary information comprises the basic information of the user and various pieces of environmental information of the area where the user is located; determining a target health influence value corresponding to the target food information according to the analysis result; and updating the initial physiological health characteristic data according to the target health influence value to obtain target physiological health characteristic data.

Description

Physiological health characteristic data monitoring method, device, equipment and storage medium
Technical Field
The invention relates to the field of machine learning of artificial intelligence, in particular to a method, a device, equipment and a storage medium for monitoring physiological health characteristic data.
Background
With the rapid development of society, people gradually have sub-health status under the fast pace of life, busy work and irregular daily activities, and also have strengthened the attention on the health along with the sub-health status. The health condition analysis of various data of the body is one of the ways for people to pay attention to the health.
At present, the health analysis mode generally acquires diet data of various types of people through an offline questionnaire mode, and analyzes diet problems, diet cautionary matters and influences caused by diet habits of various types of people on line according to the diet data, so as to generate corresponding health analysis data.
However, the health analysis method described above is a method of performing a general classification process on collected food data, and has a drawback that it is impossible to detect, recognize, and collect information from food images in food, and it is impossible to accurately acquire health analysis data of a user.
Disclosure of Invention
The invention mainly aims to solve the problem that the health data analysis accuracy is low in the prior art.
The invention provides a method for monitoring physiological health characteristic data in a first aspect, which comprises the following steps:
acquiring user authorization information and user mode information, and calling corresponding initial physiological health characteristic data in a preset health monitoring system according to the user authorization information and the user mode information;
acquiring a diet image, calling a preset food identification model, carrying out image identification and feature extraction on the diet image through the food identification model to obtain target features, and carrying out similarity calculation and food information determination through the target features and a plurality of preset food image templates to obtain target food information;
calling auxiliary information and a food health analysis rule corresponding to the auxiliary information from the health monitoring system, and performing statistical analysis on food health data of the target food information according to the auxiliary information and the food health analysis rule to obtain an analysis result, wherein the auxiliary information comprises basic information of a user and various pieces of environmental information of the area;
determining a target health influence value corresponding to the target food information according to the analysis result;
and updating the initial physiological health characteristic data according to the target health influence value to obtain target physiological health characteristic data, and updating the initial physiological health characteristic data in the health monitoring system into the target physiological health characteristic data.
Optionally, in a first implementation manner of the first aspect of the present invention, after the updating the initial physiological health characteristic data according to the target health influence value to obtain target physiological health characteristic data, and updating the initial physiological health characteristic data in the health monitoring system to the target physiological health characteristic data, the method further includes:
acquiring user history data, and performing recommendation analysis on the user history data and the target food information through a preset recommendation algorithm to obtain target recommendation information;
judging whether the target physiological health characteristic data meets a preset early warning condition or not;
if the target physiological health characteristic data accords with a preset early warning condition, matching a corresponding target diet recommendation scheme from a preset database according to the target physiological health characteristic data and the auxiliary information;
if the target physiological health characteristic data does not accord with preset early warning conditions, calling a preset prediction model, and sequentially performing index value prediction and early warning type prediction at preset time on the target physiological health characteristic data through the prediction model, the target food information and the auxiliary information to obtain prediction information.
Optionally, in a second implementation manner of the first aspect of the present invention, the obtaining user history data and performing recommendation analysis on the user history data and the target food information through a preset recommendation algorithm to obtain target recommendation information includes:
acquiring user historical data, and performing cluster analysis on group interest information on the user historical data through a preset collaborative filtering recommendation algorithm and a density-based clustering algorithm to obtain first recommendation information;
performing cluster analysis on the commonality and the characteristic of the target food information through a preset content recommendation algorithm and a preset similarity recommendation algorithm to obtain second recommendation information;
and determining the first recommendation information and the second recommendation information as target recommendation information.
Optionally, in a third implementation manner of the first aspect of the present invention, if the target physiological health characteristic data meets a preset early warning condition, matching a corresponding target diet recommendation scheme from a preset database according to the target physiological health characteristic data and the auxiliary information includes:
if the target physiological health characteristic data accords with a preset early warning condition, calculating a weight average value of the target physiological health characteristic data;
retrieving a recommendation scheme tree set stored in a preset database to obtain a target recommendation scheme tree corresponding to the weight mean value;
and traversing the target recommendation scheme tree according to the auxiliary information to obtain a corresponding target diet recommendation scheme.
Optionally, in a fourth implementation manner of the first aspect of the present invention, if the target physiological health characteristic data does not meet a preset early warning condition, a preset prediction model is called, and index value prediction and early warning category prediction at a preset time are sequentially performed on the target physiological health characteristic data through the prediction model, the target food information, and the auxiliary information, so as to obtain prediction information, where the prediction information includes:
if the target physiological health characteristic data does not accord with preset early warning conditions, calling a preset naive Bayes model, and performing characteristic extraction on the target food information and the auxiliary information through the naive Bayes model to obtain target characteristics;
establishing a characteristic vector of the target characteristic, and respectively calculating a health index value and a hazard index value at a preset moment according to the characteristic vector;
calculating the weighted values of the health index value and the hazard index value to obtain a prediction index value;
and matching the prediction index value with a preset early warning category to obtain a corresponding prediction early warning category, and determining the prediction index value and the prediction early warning category as prediction information.
Optionally, in a fifth implementation manner of the first aspect of the present invention, the acquiring a diet image, invoking a preset food recognition model, performing image recognition and feature extraction on the diet image through the food recognition model to obtain a target feature, and performing similarity calculation and food information determination through the target feature and a plurality of preset food image templates to obtain target food information includes:
acquiring a diet image, calling a preset food identification model, and sequentially performing target detection, target frame labeling and image feature extraction on the diet image through the food identification model to obtain a target frame diagram and target features corresponding to the target frame diagram, wherein the target frame diagram comprises a target frame and images in the target frame;
according to the target characteristics, calculating the similarity between the target block diagram and a plurality of preset food image templates to obtain a plurality of similarity values, wherein the label content on each food image template comprises preset food information;
sequencing the food image templates according to the sequence of the similarity values from large to small;
and determining the preset food information corresponding to the food image template sequenced as the first food information as the target food information.
Optionally, in a sixth implementation manner of the first aspect of the present invention, before the obtaining user authorization information and user mode information, and invoking corresponding initial physiological health characteristic data in a preset health monitoring system according to the user authorization information and the user mode information, the method further includes:
acquiring basic information and physical examination data of a user, calling a preset three-dimensional living body simulation model, and generating physiological health characteristic data to be processed corresponding to the user through the three-dimensional living body simulation model, the basic information and the physical examination data;
sending the physiological health characteristic data to be processed to a preset terminal, and receiving correction data based on the physiological health characteristic data to be processed, which is sent by the preset terminal;
and updating the physiological health characteristic data to be processed according to the correction data to obtain final initial physiological health characteristic data, and storing the initial physiological health characteristic data to a preset health monitoring system.
The invention provides a physiological health characteristic data monitoring device in a second aspect, which comprises:
the calling module is used for acquiring user authorization information and user mode information and calling corresponding initial physiological health characteristic data in a preset health monitoring system according to the user authorization information and the user mode information;
the identification module is used for acquiring a diet image, calling a preset food identification model, carrying out image identification and feature extraction on the diet image through the food identification model to obtain target features, and carrying out similarity calculation and food information determination through the target features and a plurality of preset food image templates to obtain target food information;
the analysis module is used for calling auxiliary information and a food health analysis rule corresponding to the auxiliary information from the health monitoring system, and performing statistical analysis on food health data of the target food information according to the auxiliary information and the food health analysis rule to obtain an analysis result, wherein the auxiliary information comprises basic information of a user and various pieces of environmental information of the area where the user is located;
the determining module is used for determining a target health influence value corresponding to the target food information according to the analysis result;
and the first updating module is used for updating the initial physiological health characteristic data according to the target health influence value to obtain target physiological health characteristic data, and updating the initial physiological health characteristic data in the health monitoring system into the target physiological health characteristic data.
Optionally, in a first implementation manner of the second aspect of the present invention, the monitoring apparatus for physiological health characteristic data further includes:
the recommendation analysis module is used for acquiring user historical data, and performing recommendation analysis on the user historical data and the target food information through a preset recommendation algorithm to obtain target recommendation information;
the judging module is used for judging whether the target physiological health characteristic data meets a preset early warning condition or not;
the matching module is used for matching a corresponding target diet recommendation scheme from a preset database according to the target physiological health characteristic data and the auxiliary information if the target physiological health characteristic data meets a preset early warning condition;
and the prediction module is used for calling a preset prediction model if the target physiological health characteristic data does not accord with a preset early warning condition, and sequentially carrying out index value prediction and early warning type prediction at a preset moment on the target physiological health characteristic data through the prediction model, the target food information and the auxiliary information to obtain prediction information.
Optionally, in a second implementation manner of the second aspect of the present invention, the recommendation analysis module is specifically configured to:
acquiring user historical data, and performing cluster analysis on group interest information on the user historical data through a preset collaborative filtering recommendation algorithm and a density-based clustering algorithm to obtain first recommendation information;
performing cluster analysis on the commonality and the characteristic of the target food information through a preset content recommendation algorithm and a preset similarity recommendation algorithm to obtain second recommendation information;
and determining the first recommendation information and the second recommendation information as target recommendation information.
Optionally, in a third implementation manner of the second aspect of the present invention, the matching module is specifically configured to:
if the target physiological health characteristic data accords with a preset early warning condition, calculating a weight average value of the target physiological health characteristic data;
retrieving a recommendation scheme tree set stored in a preset database to obtain a target recommendation scheme tree corresponding to the weight mean value;
and traversing the target recommendation scheme tree according to the auxiliary information to obtain a corresponding target diet recommendation scheme.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the prediction module is specifically configured to:
if the target physiological health characteristic data does not accord with preset early warning conditions, calling a preset naive Bayes model, and performing characteristic extraction on the target food information and the auxiliary information through the naive Bayes model to obtain target characteristics;
establishing a characteristic vector of the target characteristic, and respectively calculating a health index value and a hazard index value at a preset moment according to the characteristic vector;
calculating the weighted values of the health index value and the hazard index value to obtain a prediction index value;
and matching the prediction index value with a preset early warning category to obtain a corresponding prediction early warning category, and determining the prediction index value and the prediction early warning category as prediction information.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the identification module is specifically configured to:
acquiring a diet image, calling a preset food identification model, and sequentially performing target detection, target frame labeling and image feature extraction on the diet image through the food identification model to obtain a target frame diagram and target features corresponding to the target frame diagram, wherein the target frame diagram comprises a target frame and images in the target frame;
according to the target characteristics, calculating the similarity between the target block diagram and a plurality of preset food image templates to obtain a plurality of similarity values, wherein the label content on each food image template comprises preset food information;
sequencing the food image templates according to the sequence of the similarity values from large to small;
and determining the preset food information corresponding to the food image template sequenced as the first food information as the target food information.
Optionally, in a sixth implementation manner of the second aspect of the present invention, the monitoring apparatus for physiological health characteristic data further includes:
the generating module is used for acquiring basic information and physical examination data of a user, calling a preset three-dimensional living body simulation model, and generating physiological health characteristic data to be processed corresponding to the user through the three-dimensional living body simulation model, the basic information and the physical examination data;
the sending and receiving module is used for sending the physiological health characteristic data to be processed to a preset terminal and receiving correction data which is sent by the preset terminal and is based on the physiological health characteristic data to be processed;
and the second updating module is used for updating the physiological health characteristic data to be processed according to the correction data to obtain final initial physiological health characteristic data, and storing the initial physiological health characteristic data to a preset health monitoring system.
In a third aspect, the present invention provides a physiological health characteristic data monitoring device, including: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the monitoring device of the physiological health characteristic data to perform the above-mentioned monitoring method of the physiological health characteristic data.
A fourth aspect of the present invention provides a computer-readable storage medium having stored therein instructions, which when run on a computer, cause the computer to execute the above-mentioned method for monitoring physiological health characteristic data.
According to the technical scheme provided by the invention, user authorization information and user mode information are obtained, and corresponding initial physiological health characteristic data in a preset health monitoring system is called according to the user authorization information and the user mode information; acquiring a diet image, calling a preset food identification model, carrying out image identification and feature extraction on the diet image through the food identification model to obtain target features, and carrying out similarity calculation and food information determination through the target features and a plurality of preset food image templates to obtain target food information; calling auxiliary information and a food health analysis rule corresponding to the auxiliary information from the health monitoring system, and performing statistical analysis on food health data of target food information according to the auxiliary information and the food health analysis rule to obtain an analysis result, wherein the auxiliary information comprises basic information of a user and various pieces of environmental information of the area where the user is located; determining a target health influence value corresponding to the target food information according to the analysis result; and updating the initial physiological health characteristic data according to the target health influence value to obtain target physiological health characteristic data, and updating the initial physiological health characteristic data in the health monitoring system into the target physiological health characteristic data. According to the method and the device, the diet image is subjected to image recognition, feature extraction, similarity calculation and food information determination, and the statistical analysis of the food health data is performed by combining the target food information, the food health analysis rule and the auxiliary information, so that the health analysis accuracy of the diet data corresponding to the diet image is improved, the basic data of the health data analysis and the statistical analysis angle of the food health data are enriched, and the health data analysis accuracy is improved.
Drawings
FIG. 1 is a schematic diagram of an embodiment of a method for monitoring physiological health characteristic data according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of another embodiment of a method for monitoring physiological health characteristic data according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an embodiment of a physiological health characteristic data monitoring device in an embodiment of the present invention;
FIG. 4 is a schematic diagram of another embodiment of a physiological health characteristic data monitoring device in an embodiment of the present invention;
fig. 5 is a schematic diagram of an embodiment of a physiological health characteristic data monitoring device in an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a method, a device, equipment and a storage medium for monitoring physiological health characteristic data, which improve the accuracy of health data analysis.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For understanding, a detailed flow of an embodiment of the present invention is described below, and referring to fig. 1, an embodiment of a method for monitoring physiological health characteristic data according to an embodiment of the present invention includes:
101. and acquiring user authorization information and user mode information, and calling corresponding initial physiological health characteristic data in a preset health monitoring system according to the user authorization information and the user mode information.
It is to be understood that the executing subject of the present invention may be a monitoring device for physiological health characteristic data, and may also be a terminal or a server, which is not limited herein. The embodiment of the present invention is described by taking a server as an execution subject.
Wherein the user mode information includes a human mode or a pet mode, and the human mode includes a healthy population mode or a patient mode. The initial physiological health characteristic data is physiological characteristic data which is corresponding to a healthy three-dimensional living body simulation diagram generated when a preset health monitoring system is logged in for the first time and represents the health of a user, the healthy three-dimensional living body simulation diagram can be dynamic or static, for example, the initial physiological health characteristic data can comprise current organs of a mode, health condition data of the organs, health index values or hazard index values of the organs, heartbeat per minute, blood pressure, respiration times per minute, fat proportion calculated according to height and weight and the like.
The user authorization information includes a user identification number and an authorization token. For example: the server receives a user identification number and an authorization token sent by a user side corresponding to a user A, after the user identification number and the authorization token are identified, the user side corresponding to the user A is in a login state, after the user side corresponding to the user A enters the login state, user mode information of a healthy crowd mode is sent to the server, after the server receives the user mode information of the healthy crowd mode, a preset dynamic human body three-dimensional living body simulation diagram (a human body image generated according to initial physiological health characteristic data) corresponding to the user A in the health monitoring system is called, and names of all organs and current harm index values are marked on the dynamic human body three-dimensional living body simulation diagram.
It should be noted that, the implementation process of monitoring the physiological health characteristic data of the pet mode in the invention is similar to that of the human mode, and is not described again. The server trains the related models before obtaining the user authorization information and the user mode information and calling the corresponding initial physiological health characteristic data according to the user authorization information and the user mode information, wherein the models comprise a living body modeling model, a food recognition model or other models of the initial physiological health characteristic data. By adopting the user mode information, the matching range is narrowed and the recognition response speed is improved.
102. Acquiring a diet image, calling a preset food identification model, carrying out image identification and feature extraction on the diet image through the food identification model to obtain target features, and carrying out similarity calculation and food information determination through the target features and a plurality of preset food image templates to obtain target food information.
Wherein the target food information includes an attribute, a weight, a type, a name, a shape, and a size of the food. The preset food identification model is a neural network which connects a plurality of neurons according to a certain rule, such as: the network connection rule of a Fully Connected (FC) neural network is: comprises an input layer, an output layer and a hidden layer; there is no connection between neurons in the same layer; each neuron of the Nth layer is connected with all neurons of the N-1 th layer, and the output of the neurons of the N-1 th layer is the input of the neurons of the Nth layer; each connection has a weight. When a food identification model is constructed, the super parameters of the food identification model are trained and updated through a training mode of forward calculation and backward propagation to obtain a final food identification model, wherein the super parameters comprise a connection mode of a neural network, the number of layers of the network, the number of nodes of each layer and the like.
The diet image is an image of a variable-appearance food, such as: the food potatoes can be in the shape of blocks and mashed potatoes, and the images of the potatoes correspond to the potato blocks and the images of the mashed potatoes correspond to the diet images. The method comprises the steps of scanning food with variable appearances through a preset scanning instrument to generate a diet image, sending the diet image to a server, starting a target detection algorithm YOLOv3 in a preset food identification model after the server receives the diet image to extract multilayer features of the diet image to obtain the multilayer features, matching corresponding food images from a preset database according to the multilayer features, and performing labeling of labeling frames and food contrastive analysis in the labeling frames on the multilayer features according to the labeling frames and the food information in the labeling frames labeled by the food images to obtain target food information. The food identification model is used for identifying the diet image to obtain target food information, so that the quality of basic data of health data analysis is improved.
103. And calling the auxiliary information and the food health analysis rule corresponding to the auxiliary information from the health monitoring system, and performing statistical analysis on the food health data of the target food information according to the auxiliary information and the food health analysis rule to obtain an analysis result, wherein the auxiliary information comprises the basic information of the user and various pieces of environmental information of the area where the user is located.
The food health analysis rule corresponding to the auxiliary information comprises an analysis scheme of the nutritional value and the hazard of each food aiming at different sexes or ages or professional groups, wherein the analysis scheme comprises whether the types of nutrients are complete or not, the quantity and the mutual proportion of the nutrients are reasonable or not, and the degree of digestion, absorption and utilization of the nutrients by a human body.
The basic information in the auxiliary information may include the sex, age, place of birth, place of residence, height, weight and occupation of the user, each item of environmental information in the auxiliary information may include regional information, weather conditions and air quality of the region where the user is located, and the statistical analysis of the food health data is performed on the target food information in combination with the auxiliary information and the food health analysis rules corresponding to the auxiliary information, so as to improve the accuracy of the health data analysis, for example: the corresponding people of each profession have specific health attention items: the programmer often does not move, the symptoms of cervical spondylosis or lumbar disc herniation are obvious, and food health analysis of the programmer can emphasize the types of cervical spondylosis or lumbar discs; the chef inhales too much oil smoke, and the chronic pneumonia or the sphagitis can be emphasized in food health analysis; the diet difference in various regions is large-southern rice, the food health analysis can correspond to rice and northern wheat bread, and the food health analysis can correspond to wheat bread; weather conditions-heavy long-term rain and humidity or long-term drought, food health analysis can emphasize dispelling dampness and removing dryness; the air quality-air quality PM2.5 can affect the throat and lung functions of people, food health analysis can emphasize wetting the throat and moistening the lung, the risk of pharyngolaryngitis or chronic pneumonia can exist in places with poor air quality after long-term life, and the food health analysis can emphasize the pharyngolaryngitis or chronic pneumonia.
104. And determining a target health influence value corresponding to the target food information according to the analysis result.
The target health influence value may be an influence degree value of the food corresponding to the target food information on the health, the target health influence value may be a health influence value corresponding to each food in the diet image, or may be a comprehensive health influence value of all foods in the diet image, for example: the server carries out food health analysis on target food information (including food A, food B and food C) according to preset food health analysis rules and auxiliary information, after an analysis result is obtained, if the analysis result is a comprehensive analysis result of the food A, the food B and the food C, a hash value of the analysis result is generated, a preset health influence value hash table is searched according to the hash value, a health influence value which is the same as the analysis result or has the similarity with the analysis result within a preset range is obtained from the health influence value hash table, and a target health influence value is obtained;
if the analysis result is the analysis result 1, the analysis result 2 and the analysis result 3 respectively corresponding to the food A, the food B and the food C, the hash value 1 of the analysis result 1, the hash value 2 of the analysis result 2 and the hash value 3 of the analysis result 3 are generated, a preset health influence value hash table is searched according to the hash value 1, the hash value 2 and the hash value 3, the health influence value 1, the health influence value 2 and the health influence value 3 which are the same as the analysis result or have the similarity with the analysis result within a preset range are obtained from the health influence value hash table, the health influence value 1, the health influence value 2 and the health influence value 3 are target health influence values, or the sum value or weighted value of the health influence value 1, the health influence value 2 and the health influence value 3 is the target health influence value.
105. And updating the initial physiological health characteristic data according to the target health influence value to obtain target physiological health characteristic data, and updating the initial physiological health characteristic data in the health monitoring system into the target physiological health characteristic data.
Wherein, the server correspondingly changes the health influence value in the initial physiological health characteristic data into a target health influence value to obtain target physiological health characteristic data, for example: and if the hazard index value of the lung in the physiological health characteristic data is 20 points and the health index value is 85 points, and the target health influence value is 10 points, updating the hazard index value of the lung in the physiological health characteristic data to 20- (-10) to 30 points, and updating the health index value to 85+ (-10) to 75 points, thereby obtaining the target physiological health characteristic data. After the server obtains the target physiological health characteristic data, the initial physiological health characteristic data in the health monitoring system is updated to the target physiological health characteristic data, so that the health of the user corresponding to the health monitoring system is monitored.
Specifically, the server updates the initial physiological health characteristic data according to the target health influence value, and renders the target physiological health characteristic data on a preset page after obtaining the target physiological health characteristic data.
After obtaining the target physiological health characteristic data, the server renders the target physiological health characteristic data on a display page corresponding to the server, or sends the target physiological health characteristic data to a preset terminal, renders the target physiological health characteristic data on the display page of the preset terminal through the preset terminal, and displays a dynamic human body image or a dynamic pet image corresponding to the target physiological health characteristic data on the display page, so that a user can clearly and clearly learn the influence condition of daily diet on the health of a human body or a pet in real time, vividly display the target physiological health characteristic data, and improve the readability of the target physiological health characteristic data.
After the server renders the target physiological health characteristic data on a preset display page, the server can also perform recommendation analysis on the analysis result and the target physiological health characteristic data through a preset recommendation algorithm to obtain a diet-adjusted health plan scheme, a business service scheme and a diet scheme, an analysis report is generated according to the analysis result, the target physiological health characteristic data, the diet-adjusted health plan scheme and the diet scheme, and the analysis report is sent to a preset terminal, wherein the business service scheme is as follows: information of health insurance, relevant information of corresponding internet hospitals, information of access interfaces and corresponding non-formula medicines, and the like.
After the server renders the target physiological health characteristic data on a preset display page, after a preset time period, the target physiological health characteristic data and the analysis result of the daily diet in the preset time period are analyzed to generate a corresponding questionnaire, the questionnaire is sent to a preset terminal, and return visit information of the user is obtained through the preset terminal.
In the embodiment of the invention, the diet image is subjected to image recognition, feature extraction, similarity calculation and food information determination, and the statistical analysis of the food health data is carried out by combining the target food information, the food health analysis rule and the auxiliary information, so that the health analysis accuracy of the diet data corresponding to the diet image is improved, the basic data of the health data analysis and the statistical analysis angle of the food health data are enriched, and the health data analysis accuracy is improved.
Referring to fig. 2, another embodiment of the method for monitoring physiological health characteristic data according to the embodiment of the present invention includes:
201. and acquiring user authorization information and user mode information, and calling corresponding initial physiological health characteristic data in a preset health monitoring system according to the user authorization information and the user mode information.
The execution process of step 201 is similar to the execution process of step 101, and is not described herein again.
Specifically, the server acquires user authorization information and user mode information, acquires basic information and physical examination data of a user before calling corresponding initial physiological health characteristic data in a preset health monitoring system according to the user authorization information and the user mode information, calls a preset three-dimensional living body simulation model, and generates physiological health characteristic data to be processed corresponding to the user through the three-dimensional living body simulation model, the basic information and the physical examination data; sending the physiological health characteristic data to be processed to a preset terminal, and receiving correction data based on the physiological health characteristic data to be processed, which is sent by the preset terminal; and updating the physiological health characteristic data to be processed according to the correction data to obtain final initial physiological health characteristic data, and storing the initial physiological health characteristic data to a preset health monitoring system.
For example: the server obtains basic information and physical examination data of a user, calls a preset three-dimensional living body simulation model, extracts human body characteristic information of the basic information and the physical examination data through the three-dimensional living body simulation model, generates physiological health characteristic data to be processed corresponding to the user according to the human body characteristic information through the three-dimensional living body simulation model, sends the physiological health characteristic data to be processed to a preset terminal, displays the physiological health characteristic data to be processed on a display page of the preset terminal, modifies organ states in the physiological health characteristic data to be processed through the display page of the preset terminal by the user, generates corresponding correction data through the preset terminal, sends the generated correction data to the server, replaces the physiological health characteristic data to be processed with the correction data through the server to obtain final initial physiological health characteristic data, and storing the initial physiological health characteristic data to a preset health monitoring system.
Wherein the basic information of the user comprises the age, sex, height and weight of the user. The correction data may include modified data of the modified part, and may also include modified data of the modified part and unmodified physiological health characteristic data to be processed, such as: the physiological health characteristic data to be processed is the condition information and health index value of the lung and the stomach, and the condition information of the stomach is modified, so that the correction data can be the modified data obtained by modifying the condition information of the stomach, and can also be the modified data obtained by modifying the condition information of the stomach, the condition information of the lung and the health index value.
202. Acquiring a diet image, calling a preset food identification model, carrying out image identification and feature extraction on the diet image through the food identification model to obtain target features, and carrying out similarity calculation and food information determination through the target features and a plurality of preset food image templates to obtain target food information.
Specifically, the server acquires a diet image, calls a preset food identification model, and sequentially performs target detection, target frame labeling and image feature extraction on the diet image through the food identification model to obtain a target frame diagram and target features corresponding to the target frame diagram, wherein the target frame diagram comprises a target frame and images in the target frame; according to the target characteristics, calculating the similarity between the target block diagram and a plurality of preset food image templates to obtain a plurality of similarity values, wherein the label content on each food image template comprises preset food information; sequencing the food image templates according to the sequence of the similarity values from large to small; and determining the preset food information corresponding to the food image template sequenced as the first food information as the target food information.
For example: the target features may include color features, shape features, and texture features of images in the target frame, each food image template may be labeled with food information of attribute, weight, type, name, shape, and size of food corresponding to each food image template, the preset plurality of food image templates are an image template B, an image template C, and an image template D, respectively, and similarity values between the target frame and the image template B, the image template C, and the image template D are calculated by calculating a similarity between the target feature of the target frame and the feature of each food image template, so as to obtain a plurality of similarity values, respectively: 0.9 (corresponding to the image template B), 0.6 (corresponding to the image template C), and 0.8 (corresponding to the image template D), so that the image template B, the image template C, and the image template D are sorted into the image template B, the image template D, and the image template C, and the food information corresponding to the image template B is the target food information.
203. And calling the auxiliary information and the food health analysis rule corresponding to the auxiliary information from the health monitoring system, and performing statistical analysis on the food health data of the target food information according to the auxiliary information and the food health analysis rule to obtain an analysis result, wherein the auxiliary information comprises the basic information of the user and various pieces of environmental information of the area where the user is located.
204. And determining a target health influence value corresponding to the target food information according to the analysis result.
205. And updating the initial physiological health characteristic data according to the target health influence value to obtain target physiological health characteristic data, and updating the initial physiological health characteristic data in the health monitoring system into the target physiological health characteristic data.
The execution process of step 203-.
206. Obtaining user history data, and performing recommendation analysis on the user history data and the target food information through a preset recommendation algorithm to obtain target recommendation information.
Specifically, the server acquires user historical data, and performs cluster analysis on group interest information on the user historical data through a preset collaborative filtering recommendation algorithm and a density-based clustering algorithm to obtain first recommendation information; performing cluster analysis on the commonality and the characteristic of the target food information through a preset content recommendation algorithm and a preset similarity recommendation algorithm to obtain second recommendation information; and determining the first recommendation information and the second recommendation information as target recommendation information.
For example: when the current user and other users use the preset health analysis system, the health analysis system generates corresponding user history data, which may include historical diet record data, health plan record data, follow-up data, health analysis data, artificial intelligent food identification data and drug identification data, etc., the server extracts the user history data of the current user and other users from the preset database, performs cluster analysis of group interest information on the user history data through a preset collaborative filtering recommendation algorithm and a density-based clustering algorithm (DBSCAN) to obtain first recommendation information, which may include business service information, diet schemes, health plans, drugs based on user similarity and confidence degree, etc. that the current user and other users are interested in, the method comprises the steps of performing cluster analysis on the commonality and the characteristics of target food information through a preset content recommendation algorithm and a preset similarity recommendation algorithm to obtain a recommended package (namely second recommendation information) similar to the performance, the attribute, the ratio and the like of the target food information, and performing recommendation analysis on user historical data and the target food information through an association rule recommendation algorithm to obtain associated business service information, so that the target recommendation information is obtained.
207. And judging whether the target physiological health characteristic data meets a preset early warning condition.
The preset early warning condition is that the health index value of each organ in the target physiological health characteristic data is smaller than a first preset threshold, or the hazard index value of each organ is larger than a second preset threshold, for example: fatty liver is a liver health index value that is less than a first preset threshold value of 35 points, which 35 points are for illustration only and do not concern the authenticity and accuracy of the data of the actual operation.
208. And if the target physiological health characteristic data accords with the preset early warning condition, matching a corresponding target diet recommendation scheme from a preset database according to the target physiological health characteristic data and the auxiliary information.
Specifically, if the target physiological health characteristic data meets a preset early warning condition, the server calculates a weight average value of the target physiological health characteristic data; retrieving a recommendation scheme tree set stored in a preset database to obtain a target recommendation scheme tree corresponding to the weight mean value; and traversing the target recommendation scheme tree according to the auxiliary information to obtain a corresponding target diet recommendation scheme.
For example, the target physiological health characteristic data is a stomach health index value of 83 points, a throat health index value of 80 points, and a lung health index value of 79 points, the professional type of the user is a chef, the corresponding weights are 40% of the lung, 30% of the throat, and other 20%, when the server obtains a coincidence judgment result, the server calculates a weight mean value of 83 + 20% +80 + 30% +79 + 40% — 43 points to obtain a target value of 43 points, an index of a corresponding score range of the target physiological health characteristic data is added to a root node of each recommendation scheme tree in the recommendation scheme tree sets stored in the preset database, that is, the score of the recommendation scheme tree 1 is 10-25 points, the score of the recommendation scheme tree 2 is 26-41 points, the score of the recommendation scheme tree 3 is 42-57 points, the target recommendation scheme tree is obtained as the recommendation scheme tree 3 through index retrieval, and randomly walking the recommendation scheme tree 3 to obtain a plurality of sequence data, calculating similarity values between the auxiliary information and the sequence data respectively, and taking the sequence data corresponding to the maximum similarity value as the target diet recommendation scheme.
209. If the target physiological health characteristic data does not accord with the preset early warning condition, calling a preset prediction model, and sequentially performing index value prediction and early warning type prediction at preset time on the target physiological health characteristic data through the prediction model, the target food information and the auxiliary information to obtain prediction information.
Specifically, if the target physiological health characteristic data does not accord with the preset early warning condition, the server calls a preset naive Bayes model, and characteristic extraction is carried out on target food information and auxiliary information through the naive Bayes model to obtain target characteristics; establishing a feature vector of the target feature, and respectively calculating a health index value and a hazard index value at a preset moment according to the feature vector; calculating the weighted values of the health index value and the hazard index value to obtain a prediction index value; and matching the prediction index value with a preset early warning category to obtain a corresponding prediction early warning category, and determining the prediction index value and the prediction early warning category as prediction information.
For example, the early warning category is a disease corresponding to a prediction index value adjacent to a threshold value of a certain disease or a prediction index value within a range value of the certain disease, that is, if the prediction index value is 40 points, the user is extremely suffered from sphagitis, and the early warning category is the sphagitis; when the server obtains the non-conforming judgment result, calling a preset naive Bayes model, sequentially carrying out feature extraction and feature vector conversion on current organs, health condition data of the organs, health index values or hazard index values of the organs, beats per minute, blood pressure, respiratory frequency per minute, fat proportion calculated according to height and weight and the like through the naive Bayes model to obtain feature vectors, calculating a health index value and a hazard index value at a preset moment according to a preset calculation strategy and a feature vector, wherein the preset calculation strategy is a calculation scheme for the health index value and the hazard index value aiming at living body simulation features, the preset calculation strategy also comprises a weight ratio of the health index value and the hazard index value, and the weighted value of the health index value and the hazard index value is calculated to obtain a prediction index value; and generating a hash value of the prediction index value, and retrieving a preset early warning type hash table (comprising various early warning types) according to the hash value to obtain a corresponding prediction early warning type.
According to the embodiment of the invention, the accuracy of health data analysis is improved, more angle information is displayed for the user by acquiring the target recommendation information and the prediction information, the user can conveniently master various types of data after the health data analysis is carried out on the diet image in multiple directions, the convenience is improved, the experience feeling of the user is enhanced, and the versatility of the health data analysis system is enhanced.
With reference to fig. 3, the method for monitoring physiological health characteristic data in the embodiment of the present invention is described above, and a monitoring device for physiological health characteristic data in the embodiment of the present invention is described below, where an embodiment of the monitoring device for physiological health characteristic data in the embodiment of the present invention includes:
the calling module 301 is configured to obtain user authorization information and user mode information, and call corresponding initial physiological health characteristic data in a preset health monitoring system according to the user authorization information and the user mode information;
the identification module 302 is configured to acquire a diet image, call a preset food identification model, perform image identification and feature extraction on the diet image through the food identification model to obtain target features, and perform similarity calculation and food information determination through the target features and a plurality of preset food image templates to obtain target food information;
the analysis module 303 is configured to retrieve the auxiliary information and the food health analysis rule corresponding to the auxiliary information from the health monitoring system, perform statistical analysis on the food health data of the target food information according to the auxiliary information and the food health analysis rule, and obtain an analysis result, where the auxiliary information includes the basic information of the user and various pieces of environmental information of the area where the user is located;
a determining module 304, configured to determine a target health influence value corresponding to the target food information according to the analysis result;
a first updating module 305, configured to update the initial physiological health characteristic data according to the target health influence value, obtain the target physiological health characteristic data, and update the initial physiological health characteristic data in the health monitoring system to the target physiological health characteristic data.
The function implementation of each module in the monitoring device for physiological health characteristic data corresponds to each step in the monitoring method embodiment for physiological health characteristic data, and the function and implementation process thereof are not described in detail herein.
In the embodiment of the invention, the dietary image is subjected to image recognition, feature extraction, similarity calculation and food information determination, and the statistical analysis of the food health data is carried out by combining the target food information, the food health analysis rule and the auxiliary information, so that the accuracy of the health data analysis of the dietary data corresponding to the dietary image is improved, the basic data of the health data analysis and the statistical analysis of the food health data are enriched, and the accuracy of the health data analysis is improved.
Referring to fig. 4, another embodiment of the monitoring device for physiological health characteristic data according to the embodiment of the present invention includes:
the calling module 301 is configured to obtain user authorization information and user mode information, and call corresponding initial physiological health characteristic data in a preset health monitoring system according to the user authorization information and the user mode information;
the identification module 302 is configured to acquire a diet image, call a preset food identification model, perform image identification and feature extraction on the diet image through the food identification model to obtain target features, and perform similarity calculation and food information determination through the target features and a plurality of preset food image templates to obtain target food information;
the analysis module 303 is configured to retrieve the auxiliary information and the food health analysis rule corresponding to the auxiliary information from the health monitoring system, perform statistical analysis on the food health data of the target food information according to the auxiliary information and the food health analysis rule, and obtain an analysis result, where the auxiliary information includes the basic information of the user and various pieces of environmental information of the area where the user is located;
a determining module 304, configured to determine a target health influence value corresponding to the target food information according to the analysis result;
a first updating module 305, configured to update the initial physiological health characteristic data according to the target health influence value, obtain target physiological health characteristic data, and update the initial physiological health characteristic data in the health monitoring system to the target physiological health characteristic data;
the recommendation analysis module 306 is configured to acquire user history data, and perform recommendation analysis on the user history data and the target food information through a preset recommendation algorithm to obtain target recommendation information;
the judging module 307 is configured to judge whether the target physiological health characteristic data meets a preset early warning condition;
the matching module 308 is configured to match a corresponding target diet recommendation scheme from a preset database according to the target physiological health characteristic data and the auxiliary information if the target physiological health characteristic data meets a preset early warning condition;
the prediction module 309 is configured to, if the target physiological health characteristic data does not meet a preset early warning condition, call a preset prediction model, and sequentially perform index value prediction and early warning category prediction at a preset time on the target physiological health characteristic data through the prediction model, the target food information and the auxiliary information to obtain prediction information.
Optionally, the recommendation analysis module 306 may be further specifically configured to:
acquiring user historical data, and performing cluster analysis on group interest information on the user historical data through a preset collaborative filtering recommendation algorithm and a density-based clustering algorithm to obtain first recommendation information;
performing cluster analysis on the commonality and the characteristic of the target food information through a preset content recommendation algorithm and a preset similarity recommendation algorithm to obtain second recommendation information;
and determining the first recommendation information and the second recommendation information as target recommendation information.
Optionally, the matching module 308 may be further specifically configured to:
if the target physiological health characteristic data accords with a preset early warning condition, calculating a weight average value of the target physiological health characteristic data;
retrieving a recommendation scheme tree set stored in a preset database to obtain a target recommendation scheme tree corresponding to the weight mean value;
and traversing the target recommendation scheme tree according to the auxiliary information to obtain a corresponding target diet recommendation scheme.
Optionally, the prediction module 309 may be further specifically configured to:
if the target physiological health characteristic data do not accord with the preset early warning condition, calling a preset naive Bayes model, and performing characteristic extraction on the target food information and the auxiliary information through the naive Bayes model to obtain target characteristics;
establishing a feature vector of the target feature, and respectively calculating a health index value and a hazard index value at a preset moment according to the feature vector;
calculating the weighted values of the health index value and the hazard index value to obtain a prediction index value;
and matching the prediction index value with a preset early warning category to obtain a corresponding prediction early warning category, and determining the prediction index value and the prediction early warning category as prediction information.
Optionally, the identifying module 302 may be further specifically configured to:
acquiring a diet image, calling a preset food identification model, and sequentially carrying out target detection, target frame labeling and image feature extraction on the diet image through the food identification model to obtain a target frame diagram and target features corresponding to the target frame diagram, wherein the target frame diagram comprises a target frame and images in the target frame;
according to the target characteristics, calculating the similarity between the target block diagram and a plurality of preset food image templates to obtain a plurality of similarity values, wherein the label content on each food image template comprises preset food information;
sequencing the food image templates according to the sequence of the similarity values from large to small;
and determining the preset food information corresponding to the food image template sequenced as the first food information as the target food information.
Optionally, the physiological health characteristic data monitoring apparatus further includes:
the generating module 310 is configured to acquire basic information and physical examination data of a user, call a preset three-dimensional living body simulation model, and generate to-be-processed physiological health characteristic data corresponding to the user through the three-dimensional living body simulation model, the basic information and the physical examination data;
the sending and receiving module 311 is configured to send the physiological health characteristic data to be processed to a preset terminal, and receive correction data sent by the preset terminal and based on the physiological health characteristic data to be processed;
the second updating module 312 is configured to update the physiological health characteristic data to be processed according to the correction data to obtain final initial physiological health characteristic data, and store the initial physiological health characteristic data in a preset health monitoring system.
The function implementation of each module and each unit in the monitoring device of the physiological health characteristic data corresponds to each step in the monitoring method embodiment of the physiological health characteristic data, and the function and implementation process thereof are not described in detail herein.
According to the embodiment of the invention, the accuracy of health data analysis is improved, more angle information is displayed for the user by acquiring the target recommendation information and the prediction information, the user can conveniently master various types of data after the health data analysis is carried out on the diet image in multiple directions, the convenience is improved, the experience feeling of the user is enhanced, and the versatility of the health data analysis system is enhanced.
Fig. 3 and 4 describe the physiological health characteristic data monitoring apparatus in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the physiological health characteristic data monitoring apparatus in the embodiment of the present invention is described in detail from the perspective of hardware processing.
Fig. 5 is a schematic structural diagram of a monitoring device for physiological health characteristic data, according to an embodiment of the present invention, the monitoring device 500 for physiological health characteristic data may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 510 (e.g., one or more processors) and a memory 520, and one or more storage media 530 (e.g., one or more mass storage devices) storing applications 533 or data 532. Memory 520 and storage media 530 may be, among other things, transient or persistent storage. The program stored on the storage medium 530 may include one or more modules (not shown), each of which may include a series of instruction operations in the monitoring device 500 for physiological health characteristic data. Still further, the processor 510 may be configured to communicate with the storage medium 530 to execute a series of instruction operations in the storage medium 530 on the monitoring device 500 for physiological health characteristic data.
The physiological health characteristic data monitoring device 500 may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input-output interfaces 560, and/or one or more operating systems 531, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will appreciate that the configuration of the physiological health characteristic data monitoring device illustrated in fig. 5 does not constitute a limitation of the physiological health characteristic data monitoring device and may include more or fewer components than illustrated, or some components in combination, or a different arrangement of components.
The invention further provides a monitoring device of physiological health characteristic data, which comprises a memory and a processor, wherein the memory stores instructions, and the instructions, when executed by the processor, cause the processor to execute the steps of the monitoring method of physiological health characteristic data in the above embodiments.
The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, and which may also be a volatile computer-readable storage medium, having stored therein instructions, which, when run on a computer, cause the computer to perform the steps of the method for monitoring physiological health characteristic data.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (10)

1. A method for monitoring physiological health characteristic data is characterized by comprising the following steps:
acquiring user authorization information and user mode information, and calling corresponding initial physiological health characteristic data in a preset health monitoring system according to the user authorization information and the user mode information;
acquiring a diet image, calling a preset food identification model, carrying out image identification and feature extraction on the diet image through the food identification model to obtain target features, and carrying out similarity calculation and food information determination through the target features and a plurality of preset food image templates to obtain target food information;
calling auxiliary information and a food health analysis rule corresponding to the auxiliary information from the health monitoring system, and performing statistical analysis on food health data of the target food information according to the auxiliary information and the food health analysis rule to obtain an analysis result, wherein the auxiliary information comprises basic information of a user and various pieces of environmental information of the area;
determining a target health influence value corresponding to the target food information according to the analysis result;
and updating the initial physiological health characteristic data according to the target health influence value to obtain target physiological health characteristic data, and updating the initial physiological health characteristic data in the health monitoring system into the target physiological health characteristic data.
2. The method for monitoring physiological health characteristic data according to claim 1, wherein after updating the initial physiological health characteristic data according to the target health influence value to obtain target physiological health characteristic data and updating the initial physiological health characteristic data in the health monitoring system to the target physiological health characteristic data, the method further comprises:
acquiring user history data, and performing recommendation analysis on the user history data and the target food information through a preset recommendation algorithm to obtain target recommendation information;
judging whether the target physiological health characteristic data meets a preset early warning condition or not;
if the target physiological health characteristic data accords with a preset early warning condition, matching a corresponding target diet recommendation scheme from a preset database according to the target physiological health characteristic data and the auxiliary information;
if the target physiological health characteristic data does not accord with preset early warning conditions, calling a preset prediction model, and sequentially performing index value prediction and early warning type prediction at preset time on the target physiological health characteristic data through the prediction model, the target food information and the auxiliary information to obtain prediction information.
3. The method for monitoring physiological health characteristic data according to claim 2, wherein the obtaining of user history data and the recommendation analysis of the user history data and the target food information by a preset recommendation algorithm to obtain target recommendation information comprises:
acquiring user historical data, and performing cluster analysis on group interest information on the user historical data through a preset collaborative filtering recommendation algorithm and a density-based clustering algorithm to obtain first recommendation information;
performing cluster analysis on the commonality and the characteristic of the target food information through a preset content recommendation algorithm and a preset similarity recommendation algorithm to obtain second recommendation information;
and determining the first recommendation information and the second recommendation information as target recommendation information.
4. The method for monitoring physiological health characteristic data according to claim 2, wherein if the target physiological health characteristic data meets a preset early warning condition, matching a corresponding target diet recommendation scheme from a preset database according to the target physiological health characteristic data and the auxiliary information comprises:
if the target physiological health characteristic data accords with a preset early warning condition, calculating a weight average value of the target physiological health characteristic data;
retrieving a recommendation scheme tree set stored in a preset database to obtain a target recommendation scheme tree corresponding to the weight mean value;
and traversing the target recommendation scheme tree according to the auxiliary information to obtain a corresponding target diet recommendation scheme.
5. The method for monitoring physiological health characteristic data according to claim 2, wherein if the target physiological health characteristic data does not meet a preset early warning condition, calling a preset prediction model, and sequentially performing index value prediction and early warning type prediction at a preset time on the target physiological health characteristic data through the prediction model, the target food information and the auxiliary information to obtain prediction information, the method comprising:
if the target physiological health characteristic data does not accord with preset early warning conditions, calling a preset naive Bayes model, and performing characteristic extraction on the target food information and the auxiliary information through the naive Bayes model to obtain target characteristics;
establishing a characteristic vector of the target characteristic, and respectively calculating a health index value and a hazard index value at a preset moment according to the characteristic vector;
calculating the weighted values of the health index value and the hazard index value to obtain a prediction index value;
and matching the prediction index value with a preset early warning category to obtain a corresponding prediction early warning category, and determining the prediction index value and the prediction early warning category as prediction information.
6. The method for monitoring physiological health characteristic data according to claim 1, wherein the acquiring of diet images, calling a preset food recognition model, performing image recognition and feature extraction on the diet images through the food recognition model to obtain target features, and performing similarity calculation and food information determination through the target features and a plurality of preset food image templates to obtain target food information comprises:
acquiring a diet image, calling a preset food identification model, and sequentially performing target detection, target frame labeling and image feature extraction on the diet image through the food identification model to obtain a target frame diagram and target features corresponding to the target frame diagram, wherein the target frame diagram comprises a target frame and images in the target frame;
according to the target characteristics, calculating the similarity between the target block diagram and a plurality of preset food image templates to obtain a plurality of similarity values, wherein the label content on each food image template comprises preset food information;
sequencing the food image templates according to the sequence of the similarity values from large to small;
and determining the preset food information corresponding to the food image template sequenced as the first food information as the target food information.
7. The method for monitoring physiological health characteristic data according to any one of claims 1 to 6, wherein before acquiring the user authorization information and the user mode information and invoking the corresponding initial physiological health characteristic data in the preset health monitoring system according to the user authorization information and the user mode information, the method further comprises:
acquiring basic information and physical examination data of a user, calling a preset three-dimensional living body simulation model, and generating physiological health characteristic data to be processed corresponding to the user through the three-dimensional living body simulation model, the basic information and the physical examination data;
sending the physiological health characteristic data to be processed to a preset terminal, and receiving correction data based on the physiological health characteristic data to be processed, which is sent by the preset terminal;
and updating the physiological health characteristic data to be processed according to the correction data to obtain final initial physiological health characteristic data, and storing the initial physiological health characteristic data to a preset health monitoring system.
8. A device for monitoring physiological health characteristic data, the device comprising:
the calling module is used for acquiring user authorization information and user mode information and calling corresponding initial physiological health characteristic data in a preset health monitoring system according to the user authorization information and the user mode information;
the identification module is used for acquiring a diet image, calling a preset food identification model, carrying out image identification and feature extraction on the diet image through the food identification model to obtain target features, and carrying out similarity calculation and food information determination through the target features and a plurality of preset food image templates to obtain target food information;
the analysis module is used for calling auxiliary information and a food health analysis rule corresponding to the auxiliary information from the health monitoring system, and performing statistical analysis on food health data of the target food information according to the auxiliary information and the food health analysis rule to obtain an analysis result, wherein the auxiliary information comprises basic information of a user and various pieces of environmental information of the area where the user is located;
the determining module is used for determining a target health influence value corresponding to the target food information according to the analysis result;
and the first updating module is used for updating the initial physiological health characteristic data according to the target health influence value to obtain target physiological health characteristic data, and updating the initial physiological health characteristic data in the health monitoring system into the target physiological health characteristic data.
9. A physiological health characteristic data monitoring device, comprising: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invokes the instructions in the memory to cause the physiological health characteristic data monitoring device to perform the physiological health characteristic data monitoring method of any one of claims 1-7.
10. A computer-readable storage medium having instructions stored thereon, wherein the instructions, when executed by a processor, implement a method for monitoring physiological health characteristic data according to any one of claims 1-7.
CN202010884367.XA 2020-08-28 2020-08-28 Physiological health characteristic data monitoring method, device, equipment and storage medium Active CN112037888B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010884367.XA CN112037888B (en) 2020-08-28 2020-08-28 Physiological health characteristic data monitoring method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010884367.XA CN112037888B (en) 2020-08-28 2020-08-28 Physiological health characteristic data monitoring method, device, equipment and storage medium

Publications (2)

Publication Number Publication Date
CN112037888A true CN112037888A (en) 2020-12-04
CN112037888B CN112037888B (en) 2022-03-25

Family

ID=73586132

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010884367.XA Active CN112037888B (en) 2020-08-28 2020-08-28 Physiological health characteristic data monitoring method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN112037888B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112735562A (en) * 2021-01-25 2021-04-30 珠海格力电器股份有限公司 Diet recommendation method and device, electronic equipment and storage medium
CN112802579A (en) * 2021-02-05 2021-05-14 上海中医药大学附属曙光医院 Body fat health interaction method and system

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7024369B1 (en) * 2000-05-31 2006-04-04 International Business Machines Corporation Balancing the comprehensive health of a user
CN108257656A (en) * 2016-12-27 2018-07-06 佛山市幻云科技有限公司 Health control method, device and terminal
US20180344215A1 (en) * 2015-11-24 2018-12-06 Dacadoo Ag Automated health data acquisition, processing and communication system and method
CN110400623A (en) * 2019-08-30 2019-11-01 董云鹏 One kind carrying out health-preserving management system and its method based on interior can balance
CN110600093A (en) * 2019-08-16 2019-12-20 东莞市康助医疗科技有限公司 Health management method, system, terminal equipment and storage medium
CN110689946A (en) * 2019-10-12 2020-01-14 南京市卫生信息中心 Healthy diet intervention system and intervention method for determining diet structure of user based on image recognition technology
US20200082169A1 (en) * 2018-09-07 2020-03-12 International Business Machines Corporation Health trends identification
WO2020069500A1 (en) * 2018-09-30 2020-04-02 Yibing Hu Smart health expert and manager

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7024369B1 (en) * 2000-05-31 2006-04-04 International Business Machines Corporation Balancing the comprehensive health of a user
US20180344215A1 (en) * 2015-11-24 2018-12-06 Dacadoo Ag Automated health data acquisition, processing and communication system and method
CN108257656A (en) * 2016-12-27 2018-07-06 佛山市幻云科技有限公司 Health control method, device and terminal
US20200082169A1 (en) * 2018-09-07 2020-03-12 International Business Machines Corporation Health trends identification
WO2020069500A1 (en) * 2018-09-30 2020-04-02 Yibing Hu Smart health expert and manager
CN110600093A (en) * 2019-08-16 2019-12-20 东莞市康助医疗科技有限公司 Health management method, system, terminal equipment and storage medium
CN110400623A (en) * 2019-08-30 2019-11-01 董云鹏 One kind carrying out health-preserving management system and its method based on interior can balance
CN110689946A (en) * 2019-10-12 2020-01-14 南京市卫生信息中心 Healthy diet intervention system and intervention method for determining diet structure of user based on image recognition technology

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112735562A (en) * 2021-01-25 2021-04-30 珠海格力电器股份有限公司 Diet recommendation method and device, electronic equipment and storage medium
CN112802579A (en) * 2021-02-05 2021-05-14 上海中医药大学附属曙光医院 Body fat health interaction method and system

Also Published As

Publication number Publication date
CN112037888B (en) 2022-03-25

Similar Documents

Publication Publication Date Title
Plötz et al. Activity recognition and healthier food preparation
Li et al. Identifying informative risk factors and predicting bone disease progression via deep belief networks
CN112890816A (en) Health index scoring method and device for individual user
CN112037888B (en) Physiological health characteristic data monitoring method, device, equipment and storage medium
US11775053B2 (en) Methods and systems for using artificial intelligence to analyze user activity data
AS et al. Estimating the surveillance of liver disorder using classification algorithms
CN106529110A (en) Classification method and equipment of user data
CN113643813A (en) Chronic disease follow-up supervision method and device based on artificial intelligence and computer equipment
CN114416967A (en) Method, device and equipment for intelligently recommending doctors and storage medium
Swarupa et al. Disease prediction: smart disease prediction system using random forest algorithm
CN108922621A (en) A kind of appraisal procedure and device of the grade that disables
Poply et al. Refined image segmentation for calorie estimation of multiple-dish food items
CN115376648A (en) Intelligent prescription generating device and intelligent prescription generating system
CN114943629A (en) Health management and health care service system and health management method thereof
CN114420279A (en) Medical resource recommendation method, device, equipment and storage medium
CN114783580A (en) Medical data quality evaluation method and system
CN111161842A (en) Postoperative rehabilitation nutrition suggestion method based on artificial intelligence technology
Mansouri et al. Predicting hospital length of stay of neonates admitted to the NICU using data mining techniques
Yang et al. 10-year CVD risk prediction and minimization via InverseClassification
CN109285594A (en) Human body 3D scanning projection technology
CN115985518A (en) Method and system for patient health intervention and accelerated rehabilitation based on artificial intelligence
Thomas et al. Heart stroke prediction using machine learning: A comparative analysis and implementation
Zope et al. Hybrid Ensemble and Features Selection for Heart Disease Prediction Using Machine Learning
CN111403042A (en) AI-based virtual standard patient simulation system
Goh et al. Development of an effective clustering algorithm for older fallers

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