CN107658001B - Household oil health management method and system - Google Patents
Household oil health management method and system Download PDFInfo
- Publication number
- CN107658001B CN107658001B CN201710936543.8A CN201710936543A CN107658001B CN 107658001 B CN107658001 B CN 107658001B CN 201710936543 A CN201710936543 A CN 201710936543A CN 107658001 B CN107658001 B CN 107658001B
- Authority
- CN
- China
- Prior art keywords
- health
- oil
- user
- data
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/18—File system types
- G06F16/1805—Append-only file systems, e.g. using logs or journals to store data
Abstract
The invention discloses a household oil health management method and a system, wherein the management method comprises the following steps: receiving domestic oil data in a period of time from a user terminal and storing the domestic oil data in a database, wherein the domestic oil data comprises oil log information; generating a household oil statistical result based on the household oil data, and feeding back the oil statistical result to the user terminal; performing clustering calculation by utilizing preset health model characteristics at least based on received household oil data, and clustering the families of the users to a health model corresponding to the matched health model characteristics in a pre-established health model library according to the matched health model characteristics; and generating a health decision by using a decision tree algorithm associated with the health model of the user family, and sending a health scheme to the user terminal based on the health decision.
Description
Technical Field
The invention relates to the technical field of health management, in particular to a method and a system for health management of household oil.
Background
The use of domestic edible oil is closely related to the health of people in daily life. With the development of Chinese economy, the daily edible oil intake of Chinese people reaches 62 g/person day, which is 2.48 times of the standard of healthy oil, 1.26 times of the daily edible oil intake of American, and 4.13 times of Japanese. The excessive intake of edible oil buries huge health hidden troubles, the incidence of obesity, hypertension, hyperglycemia, diabetes and other chronic diseases in China exceeds the incidence in the United states at present, and leads Japan greatly. Due to the large population base, the number of the chronic diseases exceeds 2 hundred million people in China, and huge potential negative effects are caused to the country and the society.
At present, family oil control becomes the theme of a big city, and people's daily oil control concept and oil use health knowledge are often scattered health information known through networks, magazines and the like, and lack pertinence and systematicness. At present, the mode of family's accuse oil also obtains the oil mass of oil at every turn through the oilcan that has the scale mostly, then carries out manual record through writing paper, leads to the oil consumption data to be difficult to the accurate measurement like this, and the data is not convenient for record moreover, need spend more time and user's constantly unrelaxly, has influenced user experience, and the often only a few discrete data that obtain in actual operation and be difficult to obtain long-term continuous data. In addition, the oil consumption habits of each family are different, which causes different health states of different families to a certain extent, however, the current methods for acquiring the oil consumption health information and the methods for counting the oil consumption of the families make it difficult to make a targeted scheme, achieve targeted health guidance and control the oil quantity systematically.
Therefore, how to provide a set of dynamic, systematic and targeted health management scheme based on the oil consumption condition of each family even in combination with the health condition is a technical problem to be solved at present.
Disclosure of Invention
In view of the above, the present invention is directed to a method and system for managing health of domestic oil, which solves one or more problems of the prior art.
According to an aspect of the present invention, there is provided a home oil health management method, comprising the steps of:
receiving domestic oil data in a period of time from a user terminal and storing the domestic oil data in a database, wherein the domestic oil data comprises oil log information;
receiving and storing home user information from a user terminal, wherein the home user information at least comprises home population information;
generating a household oil statistical result based on the household oil data and the household population number information, and feeding back the oil statistical result to the user terminal;
based on the household oil data and the household user information, performing clustering calculation by using preset health model characteristics, and selecting a health model corresponding to the matched health model characteristics from a plurality of pre-established health models according to the matched health model characteristics;
a health decision is generated using a decision tree associated with the selected health model and a health plan is sent to the user terminal based on the health decision.
In one embodiment, the health regimen comprises at least one of: oil plan, daily catering, recipe, cooking mode, exercise advice, health living general knowledge, online health value-added service.
In one embodiment, the family user information further comprises user characterization information and/or user health information; the step of performing cluster calculation by using preset health model characteristics based on the household oil data and the household user information comprises the following steps: performing primary clustering by using preset health model characteristics according to the household oil data and the household population number information, and performing secondary clustering by using the health model characteristics according to the updated user health auxiliary information and/or the household oil data; or performing first clustering by using the health model characteristics according to the family user information, and performing second clustering by using the health model characteristics according to the updated family oil data and/or the updated family user information.
In an embodiment, the user characterization information comprises at least one of the following information: height, weight, age, sex, job category; the user health data information comprises: history of disease, sign parameters, and/or severity of disease.
In one embodiment, in the step of performing cluster calculation by using preset health model features based on the received domestic oil data and the domestic user information, a k-nearest neighbor cluster algorithm is adopted for performing cluster calculation.
In one embodiment, the health model is optimized using a deep learning algorithm.
In an embodiment, the method further comprises: after the health model is selected, a health index calculation is performed using the health factor scores and their weights associated with the health model.
In one embodiment, the health index comprises a prevalence index calculated using the na iotave bayes probability calculation:
wherein B is a health factor, Ai is a disease category, P (A)iI B) denotes A in the case of B occurrenceiProbability of occurrence, P (B | A)i) Is shown in AiProbability of occurrence of B, P (A)i) Is represented by AiI represents the unhealthy type, n represents the number of data, i.e., the number of oil families.
In an embodiment, the method further comprises: and dynamically sending the change of the health index to the user terminal, and dynamically adjusting the health scheme sent to the user terminal. The process of dynamically adjusting the health plan includes, for example: when the oil consumption data or the input data of the user change, the user data can enter different health models according to a clustering algorithm, namely the user data are attached with different labels, and the corresponding health scheme also changes due to the change of the labels. For example, the weight of a member in original data of a family exceeds the standard, the member is clustered into a model by combining with other data items to give a health scheme, and after half a year, the weight data of the user is modified and does not exceed the standard, so that the corresponding model changes, and the given health scheme also changes. Because users cannot perceive the processes of system clustering, labeling and the like, the health index concept is introduced in the embodiment of the invention, the indexes of the user data items are used for weighting and scoring, and the scores can provide more visual experience for the users.
In an embodiment, the method further comprises: receiving GPS positioning information of the user terminal or residence information input from the user terminal to adjust a health plan transmitted to the user terminal based on the positioning information or residence information of the user terminal.
In an embodiment, the method further comprises: the user terminal receives user oil log information from the oil can, wherein the user oil log information comprises oil consumption amount and oil consumption time information.
In an embodiment, the method further comprises: transmitting the detected data to the user terminal through at least one of the following intelligent electronic devices: the intelligent weighing machine comprises an intelligent weighing machine, an intelligent sphygmomanometer, an intelligent blood glucose meter, an intelligent heart rate meter, an intelligent electrocardiograph, an intelligent bed and an intelligent bracelet, wherein the user terminal automatically uploads received data to serve as user representation information and/or user health information.
According to another aspect of the present invention, there is also provided a home oil health management system, the system comprising: a server comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method as described above when executing the program.
The system may further include the user terminal receiving user oil log information from the oiler, the user oil log information including oil usage amount and oil usage time information.
The household oil health management method and the household oil health management system can automatically collect oil consumption data of each household, perform statistical analysis, feed back oil consumption statistical results to users, and provide a targeted health scheme for oil consumption conditions of each household, so that household oil health is guaranteed and user experience is improved under the condition that the users do not need to manually input excessive data.
In addition, the embodiment of the invention can also provide a set of dynamic, systematic and targeted health management scheme based on the oil consumption condition of each family and the health condition of the user, thereby greatly improving the monitoring and management strength of the health of the user.
It will be appreciated by those skilled in the art that the objects and advantages that can be achieved with the present invention are not limited to the specific details set forth above, and that these and other objects that can be achieved with the present invention will be more clearly understood from the detailed description that follows.
Drawings
Further objects, features and advantages of the present invention will become apparent from the following description of embodiments of the invention, with reference to the accompanying drawings, in which:
FIG. 1 is a schematic diagram of a home oil health management system according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for managing the health of household oil according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating the contents of user data item data in a server-side database according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a health model relationship in an embodiment of the invention;
FIG. 5 is a diagram illustrating a server-side algorithm module according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a clustering algorithm according to an embodiment of the present invention;
FIG. 7 is a diagram of a decision tree according to an embodiment of the present invention.
Detailed Description
Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. Examples of these preferred embodiments are illustrated in the accompanying drawings. The embodiments of the present invention shown in the drawings and described according to the drawings are merely exemplary, and the technical spirit of the present invention and the main operation thereof are not limited to these embodiments.
It should be noted that, in order to avoid obscuring the present invention with unnecessary details, only the structures and/or processing steps closely related to the scheme according to the present invention are shown in the drawings, and other details not so relevant to the present invention are omitted.
Fig. 1 is a schematic diagram of a home oil health management system according to an embodiment of the present invention. As shown in fig. 1, the present invention can utilize an intelligent oil can, an intelligent terminal (or called user terminal) and a server to provide functions of accurate measurement, data recording, statistical analysis, scientific knowledge push, health oil habit guidance service, etc. for the use of the household edible oil of the user in all aspects. In fig. 1, 01, 02, and 03 respectively represent an intelligent oil can, an intelligent terminal, and a server, and processes performed by the intelligent oil can, the intelligent terminal, and the server. And a Microprocessor (MCU) of the intelligent oil can receives the data acquired by the data acquisition unit, calculates and obtains the current oil consumption data through a bottom layer algorithm, and stores the calculated oil consumption data in a local database. As an example, the data acquisition unit may be a gravity sensor disposed at the bottom of the oil can, and the MCU may calculate the amount of oil used each time based on values measured by the gravity sensor before and after the oil is poured. In the invention patent application with the name of 'liquid container for displaying flow and liquid flow detection method thereof' with the application number of 2017107808304, an intelligent oil can capable of measuring the oil consumption in real time during oil pouring is described. The present invention is hereby incorporated by reference in its entirety as if fully and clearly described herein as an example of another oilcan for use in the present invention, as set forth in application No. 2017107808304. The oil consumption data detected by the oil pot is provided with a time stamp, and oil consumption log information can be generated.
The intelligent oil can automatically transmit the household oil data containing the oil log information to the intelligent terminal of the user regularly or irregularly through Bluetooth, Wi-Fi or other wireless transmission technologies. Of course, the user can also use the oilcan with the scale to obtain the oil amount of pouring oil each time, and manually enter the oil amount into the intelligent terminal.
The intelligent terminal can transmit the oil consumption data to a server, such as a cloud server, by utilizing a wireless communication technology, and receive a statistical analysis result returned by the server and a pushed health scheme. In addition, the intelligent terminal also receives data input by the user through an information input interface of the terminal, such as the family population number of the user, the user characterization information (such as height, weight, age, sex, work category and the like) and/or the user health information (such as physical sign parameters, hypertension, severe diabetes and the like) and uploads the data to the server. Typical examples of the intelligent terminal are a mobile phone, a portable intelligent electronic device such as a Pad, and an intelligent home electronic device such as an intelligent refrigerator and an intelligent television, and the invention is not limited thereto.
In addition to the user oil consumption data from the intelligent oil can and the household user data (such as family population, user representation information and/or user health information) manually input through an interface of the intelligent terminal, the data can be uploaded through other ways to be fused with the existing data in the server, for example, the exercise amount data (such as exercise amount data including daily exercise step number, walking kilometer number and the like recorded in APP of a user mobile phone) can be automatically acquired through the intelligent terminal, or the blood pressure, blood sugar and the like can be acquired from intelligent household medical equipment through the intelligent terminal, even the data can be transmitted from another server in which the user related data are recorded to the server for performing oil consumption health management in the invention based on communication between the servers, and the transmitted data and the existing data in the server are fused. The system can form the data items and supplement the data items to the data items of each user, so that the data dimension is enriched. Meanwhile, after the system of the server acquires the data, one-level or multi-level clustering (such as two-level or three-level clustering) can be performed, so that the solution provided for the user is refined, and the solution is more targeted.
The cloud server stores, counts and analyzes the data. And the software of the cloud server transmits the oil consumption statistical analysis result to the intelligent terminal of the user through the network, so that the user can know the long-term statistical trend of the household oil consumption. The cloud server can also store a plurality of health models, deep learning algorithms, scientific catering databases, scientific oil consumption knowledge and other health schemes and other push contents which are established in advance. The server preferably gives problem early warning according to the health model, pushes health schemes such as scientific oil use knowledge to users by using a pushing algorithm (which comprises a decision algorithm), and optimizes the health model by using a deep learning algorithm. The user can also further input self information through the terminal to obtain a more detailed private customized health scheme.
The home oil health management performed by the server side will be described in detail below.
Fig. 2 is a flowchart of a home oil health management method executed by a server according to an embodiment of the present invention, where the method may be implemented by using computer software. As shown in fig. 2, the method comprises the following steps:
and step S210, the server receives the domestic oil data in a period of time from the user terminal and stores the domestic oil data in a database.
For example, the user terminal may upload the home oil data to the server once a week, month/months, quarter, or other predetermined period of time. The home oil data may include oil log information including oil usage amount and oil usage time (timestamp) information.
In step S230, the server receives the home subscriber information from the user terminal and stores the home subscriber information in the database.
The family user information at least includes family population information, such as two-family, three-family, five-family, etc.
Besides uploading family population information through the user terminal, personal information (or user data) of one or more of the family users can be input through the user terminal and uploaded to the server, and the input user data can include user characterization information and/or user health information, and can include one or more of the following information: user age, gender, weight, medical history (e.g., chronic medical history), job category, etc. The user data listed here is only an example, and may also include other information, such as daily blood pressure, blood sugar, heart rate, sleep quality, and other physical health information.
Since the user data relates to personal privacy, it is entered based on the user's wishes, i.e. the user may choose to enter one or more of these pieces of information through the user terminal, or may choose not to enter.
In another embodiment of the present invention, the user terminal may further be associated with one or more intelligent products of an intelligent weighing machine, an intelligent sphygmomanometer, an intelligent blood glucose meter, an intelligent heart rate meter, an intelligent electrocardiograph, an intelligent bed, an intelligent bracelet, or other intelligent products for detecting human body parameters, so as to automatically obtain the user data measured by the intelligent products, thereby enabling the user not to manually enter the user data such as weight, blood pressure, blood glucose, heart rate, electrocardiograph parameters, sleep parameters, and the like in the intelligent terminal.
On the server side, each family (or user) generates a piece of data (which may be referred to as user data item data), and each piece of data may contain one or more data items, such as the content diagram of the user data item data in the database shown in fig. 3. For example, the data items may include oil usage data, family population, family member vital sign information, family member health status, family member chronic disease information, and the like, but the present invention is not limited thereto. If some family or user records only a part of the contents of all data items, the data items without the contents of the data items are considered to be empty, and the data items are also considered to be missing. Thus, different categories or numbers of data items may be included in the data for different households or users. The content of each data item in the user data item may include one or more data item values respectively indicative of the content of the data item, such as the high or low level of blood pressure or the blood pressure value. In fig. 3, although the data items of each user are shown as data items 1 to n, there are differences in actual application depending on the information actually entered by the user, and therefore, the present invention is not limited to the data item example in fig. 3. In the present invention, the representation of the user data in the form of data items is merely an example, and the form of the user data in the present invention is not limited thereto.
And step S250, the server generates a household oil statistical result based on the household oil data and the household population number information, and feeds the oil statistical result back to the user terminal.
The server can carry out statistical analysis according to the domestic oil data uploaded by the user terminal, and can analyze: total amount of household daily oil; the usage amount of each time period of breakfast, lunch and dinner; according to the statistical results of the household oil, such as the usage amount and the usage amount change trend of the month, the quarter and the year period, the statistical results can be the per-person statistical results of the household population, and can also be the statistical results of the total number of the whole household. The server can feed back the statistical result of the household oil and can also feed back standard oil reference data to the user terminal.
And after receiving the household oil statistical result, the user terminal can display the statistical result in the form of a chart and the like. And standard oil reference data can be simultaneously displayed in the statistical result displayed by the chart language for a user to refer to.
And step S270, based on the household oil data and the household user information, clustering calculation is carried out by utilizing preset health model characteristics, and the household of the user is clustered to a health model which is in a health model library pre-established in the server and corresponds to the matched health model characteristics according to the matched health model characteristics.
In the embodiment of the present invention, a plurality of health models are pre-established in the server, and the number of the health models may vary from several tens to several hundreds, for example, or may be more or less health models, and these health models may be stored in a health model library. The various health models may be characterized using health model features. The health model features can be, for example, a plurality of identification features corresponding to at least a portion of the data items with oil features, user signs, user health conditions, user chronic medical history conditions, and the like, a combination of the plurality of health model features being used to identify the health model. Different health model features may be provided with different matching priorities. The health models can be in tree-type association with each other based on the health model characteristics, and can also be independent of each other. Fig. 4 is a schematic diagram of health model relationships according to an embodiment of the present invention, and in fig. 4, the numbers behind the classes are health model labels.
A solidified health sample library accumulated for many years can be established in a server, a training sample (user data item data) set corresponding to various attribute characteristics such as oil condition, blood fat, blood sugar, blood pressure, age, sex, eating habits, exercise habits, working types and the like is recorded in the health sample library, the set is a training sample set of a clustering algorithm, in the process of establishing a health model, deep learning can be carried out by utilizing the training sample set, a clustering label is marked on each data in the sample set, and the corresponding relation between each data in the sample set and the health model to which the data belongs is known. The attribute features (health model features) described herein are merely examples, and the present invention is not limited thereto.
In an embodiment of the present invention, health model feature information corresponding to at least a part of data items may be extracted from the oil consumption statistical data in the form of data items and the family user information, the extracted health model features may be matched with health model features in a health model by using a clustering algorithm, and a health model applicable to a family of the user may be determined based on a matching result. The combination relationship of the data items and the data item values corresponding to different health models is different.
Because the personal information of the user relates to the privacy of the user, the user has the right to select whether to upload or not, so that the health state of the current user needs to be calculated through the related upload data of the oil can under the condition that the user data is lost, and a health model is selected. If the user does not upload other user data through the user terminal except the family population information, after the server receives the family oil consumption data and generates an oil consumption statistical result, clustering calculation can be carried out only on the basis of the oil consumption statistical result to determine a health model applicable to the family of the user.
For example, based on data synchronized from the oilcan end, categories may be categorized according to usage and time stamp, and categories may include, for example: the oil consumption is 0.5 of the health standard, the oil consumption is 0.8 of the health standard, the oil consumption standard is 1.2 times of the health standard, the oil consumption is 1.4 times of the health standard, the oil consumption is 1.6 times of the health standard, the oil consumption is 1.8 times of the health standard, the oil consumption is 2.0 times of the health standard, the oil consumption is more than 2.0 times of the health standard, and the like, and the server can perform clustering according to the oil consumption characteristics to determine a health model suitable for a user family.
Alternatively, the server may determine the breakfast oil specific gravity, the lunch oil specific gravity, the dinner oil specific gravity, and the like based on the home oil data including the time stamp, and the server may also determine the health model from the characteristic matching of the oil usage amount for each time period and give a judgment as to whether the preliminary oil is healthy or not.
If the user subsequently provides detailed personal and family main family member physical sign health information, chronic medical history, daily habits and other family user information through the intelligent terminal in addition to the family population information, the health management system of the server can perform clustering filtering again. In an embodiment, further clustering (secondary clustering) may be performed on a previous basis based on oil data clustering (primary clustering), the categories including, for example: health, sub-health, fitness, fat reduction, pregnancy, chronic disease type, chronic disease state, human body constitution, occupation, etc., thereby corresponding to suitable health models of various levels. In the case where the user uploads the user data several times or the cloud server obtains the user data of the user from other external devices, the server may perform three or more levels of clustering. In another embodiment, the health model may be determined each time new user data is entered, based on the user data from the user terminal and the user's personal information subsequently uploaded by the user via the smart terminal.
The server may also perform first clustering based on the home user information input by the user, and then perform second clustering or more-level clustering based on the oil consumption data uploaded by the intelligent terminal and measured by the oilcan, thereby determining the health model.
As an example, clustering may be performed by a k-nearest neighbor clustering algorithm: the training sample set is recorded in a health sample library of the server, and each data in the sample set has a classification label, that is, the corresponding relation between each data in the sample set and the health model to which the data belongs is known, the collected data of the oilcan and the related information of the user terminal are unlabeled data, each feature of the new data can be compared with the corresponding feature of the data in the sample set, and then the algorithm extracts the classification label of the most similar data (nearest neighbor) of the features in the sample set. Preferably, only the first k most similar data in the data set, usually k is an integer no greater than 10, and finally, the category with the largest occurrence number of the k most similar data is selected as the new data category. As shown in the following figure, if we classify the four quadrants in the following figure into 4 health models respectively, and the new data a point falls into the first quadrant after calculation, the data a point belongs to the health model type of quadrant one according to the k-nearest neighbor algorithm, as shown in FIG. 6.
The invention can further optimize the health model through deep learning by utilizing the data in the training sample set and the newly input data. The deep learning content is mainly the hit rate of each model in the process of classifying the crowd into each health model in the health model library by a statistical clustering algorithm, and the hit rate of the health model can be improved by optimizing each data item value of the model characteristic information. A threshold value may be set for the hit rate, a health model with a low hit rate (the hit rate is below the threshold value) may be gradually eliminated, or a judgment condition (health model characteristic information) in the health model with the low hit rate may be adjusted to generate a new health model. The missing data may be re-clustered by modifying the clustering algorithm. For example, data which cannot be hit in the clustering process is counted, values of data items which cannot be clustered are marked, the closest health model is selected to be copied, and health model characteristic information is adjusted to generate a new health model. And clustering the users which cannot hit again until all the users can be classified. If the number of people which can not hit exceeds a preset threshold value within a certain range, the system can manually supplement and capture conditions which can not be classified to redesign a new health model so as to quickly reduce the number of users to be classified according to the principle of how many users can be classified.
The user data is classified into different health models through a clustering algorithm, such as the classes in fig. 4, the number of data items of the health models may be different, and it can be understood that the health models have different refinement degrees, a tree-shaped topological structure can be formed, and the more downward the data items of the health models are, the higher the precision is.
In step S290, the server generates a health decision using a decision tree associated with the health model of the user' S home, and sends a health plan to the user terminal based on the health decision.
In the embodiment of the invention, the association between the decision tree and the health model is established in advance, and the health decision can be determined according to the selected health model, so that the health scheme can be sent to the user terminal based on the health decision. Different decisions can be generated according to different user data under the same health model, and the decisions correspond to different health schemes. In the embodiment of the present invention, the algorithm representing the correspondence between the tags of the content to be pushed and the tags of the health models may be referred to as a decision algorithm, which may decide which content is pushed to which users in which health models.
FIG. 7 is a schematic diagram of a pushed decision tree associated with a health model according to an embodiment of the present invention. The scientific content stored in the database shown in fig. 7 is provided with a content tag (e.g., "class 11" or the like). And a pushing module in the server selects the health scheme needing to be pushed based on the decision of the decision tree. The algorithm for determining the push content of the push module is mainly a decision-making process, clustering of user data is equivalent to labeling of users, labeling of content input in advance in a database is also performed according to a classification rule, a rule corresponding to a user label and a content label is arranged in the decision-making algorithm, and the system can send the content to a user terminal according with the rule. The health scheme service provided by the pushing module mainly comprises two parts, wherein the first part is the mobile terminal post-it-shi library information, and the information is mainly health schemes related to diet health (such as diet improvement in fig. 5), exercise health (such as exercise recommendation in fig. 5), health physical examination, life general knowledge and the like, such as oil consumption plan, daily catering, recipes, cooking modes, exercise advice and healthy life general knowledge. The information of the tips library is massive data and is continuously updated, so that a user can continuously acquire new health knowledge conveniently. The second part is the online expert part. The contents of the post-office database and the online expert are pushed to the user terminal through the server terminal in a service pushing mode, and more humanized content service is provided for the user. If there are data for multiple users in a home, the health model may be determined and the health plan selected based on users with worse health or more fuel usage.
The oil plan in the first part of the health plan may include information such as daily oil consumption, oil consumption for breakfast, lunch and dinner, and the like. Daily catering may include: three meals a day (including food types and proportions); and/or calorie, water, protein, fat, dietary fiber, carbohydrate, trace elements, amino acids, etc. of each food material. The system can calculate the numerical values of intake calorie, moisture, protein, fat, dietary fiber, carbohydrate, trace elements and amino acid according to the principle required by user information and health standards, and selects food materials and dishes for catering by adopting a preset food material and dish library. Due to the difference of the user information, the system can realize a side dish scheme with different attributes suitable for losing weight, increasing muscle, lowering blood pressure, lowering blood sugar and increasing weight. In an embodiment of the present invention, the server may further receive GPS location information of the user terminal from the user terminal to select a meal that conforms to the local eating habits based on the location information of the user terminal. The health life common knowledge can comprise contents such as oil consumption common sense, health concept, scientific health preserving articles or videos from local storage or network sources and the like.
The online expert part mainly aims at sub-health people and health high-risk people and provides online health value-added services for the people, such as online expert recommendation services, online medical inquiry services (such as expert diagnosis service, paying diagnosis service and the like) or online expert registration services and the like.
Further, in the embodiment of the present invention, in order to more intuitively reflect the health condition of the customer, the oil health management method of the present invention further includes the steps of: after the health model is determined (selected), a health index calculation is performed using preset health scoring factors and their weights associated with the health model. The health index calculation is mainly to score according to various corresponding health standards (health scoring factors) such as user physical sign information, health conditions, edible oil intake and the like, and calculate the oil consumption health value of the user based on the proportion (weight) occupied by the health standards.
In addition, the invention also dynamically sends the change of the health index to the user terminal and dynamically adjusts the health scheme pushed to the user terminal. That is, the present invention can perform dynamic analysis according to the oil consumption data and the home user information which are continuously updated by the user, and provide the user with the changed health index, statistical information, health scheme, etc. The process of dynamically adjusting the health scheme mainly means that when oil data or input data of a user change, the user data can enter different health models according to a clustering algorithm, namely different labels are attached to the user data, and the corresponding health scheme also changes due to the change of the labels. For example, the weight of a member in original data of a family exceeds the standard, the member is clustered into a model by combining with other data items to give a health scheme, and after half a year, the weight data of the user is modified and does not exceed the standard, so that the corresponding model changes, and the pushed health scheme also changes. Because users cannot perceive the processes of system clustering, labeling and the like, the health index concept is introduced in the embodiment of the invention, the indexes of the user data items are used for weighting and scoring, and the scores are used for providing visual experience for the users.
In the embodiment of the invention, the dynamic pushing of the health scheme is embodied by at least three aspects as follows: first, the content is refreshed, and the system sets the refresh action for pushing the content to the user. Secondly, data of users in different periods are different, for example, oil consumption in the first three months exceeds 50%, oil consumption in the last three months is normal, the corresponding model in the process is changed, the corresponding label is changed, and the content of different labels is pushed by a decision algorithm. Thirdly, the system can count the click-to-read proportion of the pushed contents, optimize the contents of the ground reading rate according to the counting result, and reclassify the contents. Such content may also be pushed to users in additional health models.
In another embodiment of the invention, a health prevalence probability algorithm for bayesian is also provided. The database of the server can store authoritative edible oil and the crowd with three highs in advance, the edible oil and the cardiovascular and cerebrovascular related reference coefficients, and the user group data of the server are also used as reference points for analysis and basis. In the embodiment of the invention, the A factor under the condition that the B factor appears in the type is calculated by using a naive Bayesian probability algorithm formulai(some diseases may be hyperlipemia, hypertension, hyperglycemia, cardiovascular and cerebrovascular diseases). Finally, a health index is calculated for the user and then transmitted to the user for reference.
In the above formula, B is a health factor, Ai is a disease type, P (A)iI B) denotes A in the case of B occurrenceiProbability of occurrence, P (B | A)i) Is shown in AiProbability of occurrence of B, P (A)i) Is represented by AiI represents the unhealthy type, n represents the number of data, i.e., the number of oil families. Based on the algorithm, the more accurate relationship between the oil and the diseases can be calculated based on the mass data of all users and the diseased information of the users, so that the users are guided to scientifically control the intake of the edible oil more scientifically, and the diseases are placed as far as possible.
Fig. 5 is a schematic diagram illustrating an algorithm module of the server-side health oil management system according to an embodiment of the present invention. As shown in fig. 5, the server performs cluster calculations based on the user data using a clustering algorithm module and generates health decisions based on the results of the cluster calculations using a decision tree associated with the health model. In addition, the system is also provided with a health index calculation module so as to calculate the health index of the user according to the health model corresponding to the user. Further, the user can also carry out big data analysis, and the Bayesian probability algorithm is utilized to calculate the disease probability based on oil consumption and disease data of many families, so that disease risk prompts can be provided for the user, and the user can be guided to scientifically control the intake of edible oil more scientifically. In addition, the system of the invention can also utilize the data storage statistical module to carry out statistics of oil consumption data, disease data and the like of each family, and can also carry out overall data statistics and storage based on data of a plurality of families.
The household oil health management method and the household oil health management system can automatically collect oil consumption data of each household, perform statistical analysis, feed back oil consumption statistical results to users, and provide a targeted health scheme for oil consumption conditions of each household, so that household oil health is guaranteed and user experience is improved under the condition that the users do not need to manually input excessive data.
In addition, the embodiment of the invention can also provide a set of dynamic, systematic and targeted health management scheme based on the oil consumption condition of each family and the health condition of the user, thereby greatly improving the monitoring and management strength of the health of the user.
As described above, the present invention realizes data collection of household oil using an intelligent oil can capable of automatically recording the amount of oil, and long-term statistical data is more valuable for improving health problems with respect to oil consumption data for each time or every day. The system can accurately measure household daily oil data, digitalizes and electronizes a measurement result, transmits the measurement result to the server through the smart phone, and can work out a set of complete healthy oil scheme by utilizing the strong data storage and analysis capability of the server and combining with the personalized information of the user. Meanwhile, the server forms a closed-loop system by using the deep learning algorithm with the user data and the formulated scheme, and gradually influences, guides and changes the use habits of the user by combining the pushing of the scientific content. The system provided by the invention is beneficial to changing unhealthy oil using habits and concepts of people, forming a healthy oil using method and reducing the risk of chronic diseases.
In addition, the invention can provide more scientific statistical data for representing the relationship between the used oil and health or diseases.
The method steps of the invention are not limited to the order of execution shown in the figures, some steps may be permuted or even performed in parallel.
Portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following technologies, which are well known in the art, may be implemented: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
The logic and/or steps represented in the flowcharts or otherwise described herein, such as an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions.
Features that are described and/or illustrated above with respect to one embodiment may be used in the same way or in a similar way in one or more other embodiments and/or in combination with or instead of the features of the other embodiments.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.
Claims (13)
1. A method for health management of household oil, characterized in that the method comprises the following steps:
receiving domestic oil data in a period of time from a user terminal and storing the domestic oil data in a database, wherein the domestic oil data comprises oil consumption log information, and the oil consumption log information comprises oil consumption amount and oil consumption time information;
receiving and storing home user information from a user terminal, wherein the home user information comprises home population information and also comprises user representation information and/or user health information;
generating a household oil statistical result based on the household oil data and the household population number information, and feeding back the oil statistical result to the user terminal, wherein the oil statistical result comprises the usage amount of the breakfast, the lunch and the dinner in each time period;
based on the family oil data and the family user information, the cluster calculation is carried out by utilizing the preset health model characteristics, the health model corresponding to the matched health model characteristics in the pre-established health model base is selected according to the matched health model characteristics, the health model is a multi-level health model, the cluster model of one level in the multi-level health model is the oil data cluster, and the health model characteristics in the multi-level health model comprise: oil consumption characteristics, user physical signs, user health conditions, and user chronic medical history conditions;
generating a health decision using a decision tree associated with the selected health model and sending a health plan to the user terminal based on the health decision, the health plan including an oil plan; the oil consumption plan comprises daily oil consumption and information of oil consumption of breakfast, lunch and dinner;
the method further comprises the following steps: and feeding back standard oil reference data to the user terminal.
2. The method of claim 1, wherein:
the health regimen further comprises at least one of: daily catering, recipes, cooking modes, exercise advice, general health and life knowledge, and online health value-added services.
3. The method of claim 1, wherein:
the step of performing cluster calculation by using preset health model characteristics based on the household oil data and the household user information comprises the following steps:
performing primary clustering by using preset health model characteristics according to the household oil data and the household population number information, and performing secondary clustering by using the health model characteristics according to the updated user health auxiliary information and/or the household oil data; or
And performing primary clustering by using the health model characteristics according to the family user information, and performing secondary clustering by using the health model characteristics according to the updated family oil data and/or the updated family user information.
4. The method of claim 3, wherein:
the user characterization information includes at least one of the following information: height, weight, age, sex, job category;
the user health data information comprises: history of disease, sign parameters, and/or severity of disease.
5. The method of claim 1, wherein:
and in the step of carrying out clustering calculation by utilizing the preset health model characteristics based on the received domestic oil data and the domestic user information, carrying out clustering calculation by adopting a k-nearest neighbor clustering algorithm.
6. The method of claim 1, further comprising:
the health model is optimized using a deep learning algorithm.
7. The method of claim 1, further comprising:
after the health model is selected, a health index calculation is performed using the health factor scores and their weights associated with the health model.
8. The method of claim 7, further comprising:
and dynamically sending the change of the health index to the user terminal, and dynamically adjusting the health scheme sent to the user terminal.
9. The method according to claim 1 or 2, characterized in that the method further comprises:
receiving GPS positioning information of the user terminal or residence information input from the user terminal to adjust a health plan transmitted to the user terminal based on the positioning information or residence information of the user terminal.
10. The method of claim 1, further comprising:
the user terminal receives user oil log information from the oil can.
11. The method according to claim 3, characterized in that the method further comprises the step of:
transmitting the detected data to the user terminal through at least one of the following intelligent electronic devices: the intelligent weighing machine comprises an intelligent weighing machine, an intelligent sphygmomanometer, an intelligent blood glucose meter, an intelligent heart rate meter, an intelligent electrocardiograph, an intelligent bed and an intelligent bracelet, wherein the user terminal automatically uploads received data to serve as user representation information and/or user health information.
12. A home oil health management system comprising a server including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein: the processor, when executing the program, implements the method of any of claims 1-9.
13. The system of claim 12, further comprising the user terminal receiving user oil log information from an oil can.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710936543.8A CN107658001B (en) | 2017-10-10 | 2017-10-10 | Household oil health management method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710936543.8A CN107658001B (en) | 2017-10-10 | 2017-10-10 | Household oil health management method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107658001A CN107658001A (en) | 2018-02-02 |
| CN107658001B true CN107658001B (en) | 2020-10-13 |
Family
ID=61116489
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710936543.8A Active CN107658001B (en) | 2017-10-10 | 2017-10-10 | Household oil health management method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107658001B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7119754B2 (en) * | 2018-08-20 | 2022-08-17 | オムロンヘルスケア株式会社 | HEALTH MANAGEMENT DEVICE, HEALTH MANAGEMENT METHOD, AND PROGRAM |
| CN109376759A (en) * | 2018-09-10 | 2019-02-22 | 平安科技（深圳）有限公司 | User information classification method, device, computer equipment and storage medium |
| CN109545303A (en) * | 2018-10-30 | 2019-03-29 | 平安医疗健康管理股份有限公司 | A kind of health data processing method, equipment, server and computer-readable medium |
| CN110236479B (en) * | 2019-05-24 | 2022-03-08 | 苏州国科康成医疗科技有限公司 | Vision detection and management system |
| CN110706781A (en) * | 2019-08-13 | 2020-01-17 | 深圳市华膳科技有限公司 | Diet configuration system |
| CN110647670A (en) * | 2019-09-20 | 2020-01-03 | 四川省绵阳太古软件有限公司 | Environment and health data classified storage method and device |
| CN111261260B (en) * | 2020-01-13 | 2023-02-14 | 深圳市华膳科技有限公司 | Diet recommendation system |
| CN111564199B (en) * | 2020-05-08 | 2023-02-03 | 成都尚医信息科技有限公司 | Intelligent nutrition intervention method and terminal |
| CN115171847A (en) * | 2020-05-29 | 2022-10-11 | 陕西杨凌来富油脂有限公司 | Diet health intelligent management system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103226647A (en) * | 2012-11-30 | 2013-07-31 | 天津唐虞科技发展有限公司 | Health data management system and method based on network |
| CN103905549A (en) * | 2014-03-28 | 2014-07-02 | 成都悦图科技有限公司 | System and method for health management based on internet of things and cloud computing |
| CN104636631A (en) * | 2015-03-09 | 2015-05-20 | 江苏中康软件有限责任公司 | Diabetes mellitus probability calculation method based on large data of diabetes mellitus system |
| CN104834827A (en) * | 2015-05-26 | 2015-08-12 | 惠州Tcl移动通信有限公司 | Health data processing method and system based on terminal equipment and cloud computation storage |
| CN105512497A (en) * | 2015-12-29 | 2016-04-20 | 深圳市鼎芯无限科技有限公司 | Method and device for monitoring medical data |
| CN205281277U (en) * | 2016-01-05 | 2016-06-01 | 浪潮集团有限公司 | Domestic storage information terminal of intelligence |
| CN106446560A (en) * | 2016-09-28 | 2017-02-22 | 湖南老码信息科技有限责任公司 | Hyperlipidemia prediction method and prediction system based on incremental neural network model |
-
2017
- 2017-10-10 CN CN201710936543.8A patent/CN107658001B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103226647A (en) * | 2012-11-30 | 2013-07-31 | 天津唐虞科技发展有限公司 | Health data management system and method based on network |
| CN103905549A (en) * | 2014-03-28 | 2014-07-02 | 成都悦图科技有限公司 | System and method for health management based on internet of things and cloud computing |
| CN104636631A (en) * | 2015-03-09 | 2015-05-20 | 江苏中康软件有限责任公司 | Diabetes mellitus probability calculation method based on large data of diabetes mellitus system |
| CN104834827A (en) * | 2015-05-26 | 2015-08-12 | 惠州Tcl移动通信有限公司 | Health data processing method and system based on terminal equipment and cloud computation storage |
| CN105512497A (en) * | 2015-12-29 | 2016-04-20 | 深圳市鼎芯无限科技有限公司 | Method and device for monitoring medical data |
| CN205281277U (en) * | 2016-01-05 | 2016-06-01 | 浪潮集团有限公司 | Domestic storage information terminal of intelligence |
| CN106446560A (en) * | 2016-09-28 | 2017-02-22 | 湖南老码信息科技有限责任公司 | Hyperlipidemia prediction method and prediction system based on incremental neural network model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107658001A (en) | 2018-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107658001B (en) | Household oil health management method and system | |
| CN104867081B (en) | A kind of intelligent health management system and method | |
| CN107423549A (en) | Healthy tracking equipment | |
| US20120179665A1 (en) | Health monitoring system | |
| CN106250673A (en) | A kind of dietary recommendations continued and evaluation methodology, intelligent terminal, Cloud Server and system | |
| CN102214269A (en) | Information processing apparatus, information outputting method and computer program storage device | |
| CN109545328A (en) | A kind of individual inferior health interference method and system based on big data and artificial intelligence | |
| CN104834827A (en) | Health data processing method and system based on terminal equipment and cloud computation storage | |
| CN109754885A (en) | Near-sighted forecasting system and method | |
| CN109285606A (en) | A kind of health control method and system based on big data intelligent algorithm | |
| CN112528009A (en) | Method, device and computer readable medium for generating user chronic disease conditioning scheme | |
| CN108288495A (en) | A kind of dietary management system and method | |
| CN110379487A (en) | Nutritional regimen management system | |
| CN109509117A (en) | A kind of vegetable recommended method, apparatus and system | |
| CN110444271A (en) | Dietary recommendation generation method, device, computer equipment and storage medium | |
| CN110084667A (en) | It is a kind of to select bed system based on what BMI data calculated and select bed process | |
| CN103907131A (en) | Diet management system and method | |
| CN115458123A (en) | Personalized nutrition intake analysis method based on multi-source data analysis | |
| KR102326540B1 (en) | Methods for management of nutrition and disease using food images | |
| CN102053158A (en) | Blood sugar analysis system, device and method | |
| CN110349358B (en) | Catering settlement method, device, terminal and readable medium based on health management | |
| KR20210052123A (en) | Method for providing user-customized food information service and server using the same | |
| CN111180042A (en) | Method for evaluating individual diet based on standard nutrient indexes | |
| US20180199867A1 (en) | Method, system, and computer program product for dynamic analysis of a physiological parameter | |
| CN113569140A (en) | Information recommendation method and device, electronic equipment and computer-readable storage medium |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190220 Address after: Room 1371, Integrated Office Building of Beijing-Tianjin Electronic Commerce Industrial Park, Wuqing District, Tianjin 301700 Applicant after: One Step to Taste (Tianjin) Technology Co., Ltd. Address before: Block D, Building 24, 68 Beiqing Road, Haidian District, Beijing 100094 Applicant before: Ding Mu (Beijing) Technology Co., Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |