Physical health monitoring and evaluation system and method based on big data
Through a physical health monitoring and evaluation system based on big data, health information is collected and analyzed and physical fitness evaluation reports are generated, which solves the shortcomings of the existing technology that cannot be monitored in depth and intervened in advance in health problems, and achieves efficient monitoring of health problems such as brain diseases. and intervention.
Patent Information
- Application Number
- CN202410993529.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-23
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-07-23
AI Technical Summary
Existing health monitoring products cannot conduct in-depth monitoring and cannot intervene in health problems such as brain diseases in advance. They can only provide early warnings when the patient is onset or when the disease is about to occur.
We adopt a physical health monitoring and evaluation system based on big data, and collect and analyze health information through the information collection module, intelligent analysis module, physical fitness confirmation module and health evaluation module, and generate physical fitness evaluation reports to help intervene in health issues in advance.
In-depth monitoring and high-quality intervention on physical fitness have been achieved, the quality of health monitoring has been improved, and users have helped them identify and prevent health problems in advance, and maintain a good attitude and physical health.
Smart Images

Figure CN118983045A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of health evaluation, and in particular to a physical health monitoring and evaluation system and method based on big data. Background Art
[0002] Physical health is the monitoring of the quality of the human body. People maintain physical health by doing various activities in their daily lives. It is very necessary to monitor the physical fitness of patients with brain diseases. The life and work pressure of contemporary middle-aged and young people is increasing, resulting in an increasing number of patients with brain diseases. In recent years, the incidence of various diseases such as epilepsy, memory loss, and brain trauma has been increasing, which will not only seriously affect the normal life of patients but also endanger human health. Many patients' amygdalae, cranial nerves, etc. suddenly became abnormal, causing the condition to worsen. Although there are many health monitoring or physical fitness monitoring products on the market, these products can generally only perform surface monitoring, and alarm when the patient is ill or warn when he is about to get sick. Although it can play a certain preventive role, it cannot be monitored in depth and cannot intervene in advance.
[0003] Therefore, the present invention provides a physical health monitoring and evaluation system and method based on big data. Summary of the invention
[0004] The present invention provides a physical health monitoring and evaluation system and method based on big data, which can conduct in-depth monitoring of the patient's physical health, help improve the quality of national physical fitness monitoring, and facilitate patients to carry out high-quality intervention in brain diseases.
[0005] The present invention provides a physical health monitoring and evaluation system based on big data, comprising:
[0006] An information collection module is used to collect basic health information of the monitored person and analyze the health characteristics of the monitored person in combination with a preset big data model;
[0007] An intelligent analysis module, used to analyze the dynamic health changes of the monitored person based on the health characteristics corresponding to the monitored person at different monitoring moments, and obtain the organ function characteristics corresponding to each designated organ of the monitored person;
[0008] A physical fitness confirmation module, used to establish physical performance information of the monitored person based on the organ function characteristics corresponding to each of the designated organs, and match a corresponding physical fitness marker for the monitored person based on the physical performance information;
[0009] The health evaluation module is used to retrieve the corresponding physical characteristics according to the physical mark, compare the health characteristics with the physical characteristics, obtain a number of non-health information, and generate a physical evaluation report of the monitored person.
[0010] In one practicable manner,
[0011] The information collection module comprises:
[0012] A data collection unit, used to collect the corresponding manifestation data of the monitored person under different monitoring dimensions, and generate basic health information of the monitored person;
[0013] A simulation analysis unit, used to simulate the basic health information using a preset big data model to obtain simulated presentation information of the monitored person in different activity states;
[0014] The feature construction unit is used to determine the activity presentation physiological characteristics and activity presentation psychological characteristics corresponding to the monitored person in each activity state based on the simulated presentation information and perform health assessment to obtain the health characteristics of the monitored person.
[0015] In one practicable manner,
[0016] The data acquisition unit comprises:
[0017] A conventional information collection subunit, used to collect the first monitoring data σ of the monitored person
[0018] The designated information collection subunit is used to collect the second monitoring data of the designated collection organ of the monitored person.
[0019] The manifestation processing integration subunit is used to sort and integrate the first monitoring data and the second monitoring data by combining the monitoring dimensions corresponding to the first monitoring data and the second monitoring data in a preset dimension matching order to obtain the manifestation data of the monitored person.
[0020] In one practicable manner,
[0021] The intelligent analysis module comprises:
[0022] A time domain processing unit is used to randomly search the time domain health feature column based on the characteristic period corresponding to each health feature and the spatial domain and non-spatial domain σ contained in the n1 corresponding characteristic periods.
[0023] A spatial analysis unit is used to establish a spatial distribution column based on the presentation position of the randomly searched spatial domains under all health features in the time domain health feature column, and input the positional relationship of each spatial position in the spatial distribution column and the number of empty occurrences of each spatial position into an ordered analysis model to obtain the ordered spatial domain and the disordered spatial domain contained in the spatial distribution column, and input the disordered presentation position corresponding to the disordered spatial domain and all the features under the corresponding disordered spatial domain, and the ordered presentation position corresponding to the ordered spatial domain and all the features under the corresponding ordered spatial domain into the information establishment model to obtain the first dynamic information and the second dynamic information of the monitored person;
[0024] A non-spatial domain analysis unit, configured to decompose the non-spatial domain health feature to obtain a plurality of sub-health features, and map the sub-health features to a high-dimensional space for regression analysis to obtain a plurality of linear fitting results, and combine the linear fitting results based on the non-spatial domain presentation position in the time domain health feature column to obtain loss information;
[0025] The model acquisition unit is used to construct an overall organ model of the monitored person according to the organ information corresponding to each of the designated organs in combination with the preset big data model, map all loss information into the overall organ model respectively, and run the overall organ model in combination with the first dynamic information and the second dynamic information to obtain a health model.
[0026] In one practicable manner,
[0027] The intelligent analysis module further includes:
[0028] An index establishment unit, used to establish time indexes for the health features corresponding to the monitored person at different monitoring times, sort the health features according to the time indexes to generate a time-domain health feature column, combine health features with adjacent relationships in the time-domain health feature column to obtain a plurality of combined health features, and establish a combined index for each of the combined health features;
[0029] A combined analysis unit, used to construct an index tree of the monitored person based on two time indexes and one combined index corresponding to each of the combined health features, and at the same time, establish a plurality of short-term dynamic health of the monitored person based on the feature values corresponding to the combined health features;
[0030] Establishing a mapping order based on the time index, mapping each of the short-term dynamic health to the index tree respectively, and generating the initial dynamic health of the monitored person;
[0031] A dynamic analysis unit, used to determine the functional demand corresponding to each designated organ of the monitored person using the initial dynamic health, input each of the functional demands into the health model of the monitored person to perform demand rationality analysis, obtain the energy consumption characteristics corresponding to each of the designated organs, use the energy consumption characteristics to perform energy consumption compensation on the initial dynamic health, and generate dynamic health changes of the monitored person;
[0032] A functional feedback unit is used to construct activity information corresponding to each of the designated organs according to the dynamic health changes, map each of the activity information to the health model, obtain the presentation data corresponding to each of the activity information in the health model, and establish the organ function characteristics of the corresponding designated organ based on the presentation data.
[0033] In one practicable manner,
[0034] The intelligence and physique confirmation module includes:
[0035] An organ monitoring unit is used to establish an organ model based on the organ function characteristics corresponding to each of the designated organs, and to capture the monitoring information corresponding to each of the designated organs of the monitored person in combination with the organ function characteristics of the monitored person.
[0036] A deep monitoring unit, configured to analyze a plurality of physical performance information of the monitored person based on the influence relationship between different designated organs, in combination with the monitoring information corresponding to each designated organ and the basic health information of the monitored person;
[0037] A physique matching unit, used to match the corresponding suspected physique for each of the body performance information, and extract a number of target physiques with a matching number greater than a preset number;
[0038] The physique confirmation unit is used to set a matching weight for the corresponding target physique based on the matching number, fuse the target physique based on the matching weight, obtain the individual physique of the monitored person, and mark it accordingly.
[0039] In one practicable manner,
[0040] The intellectual health evaluation module includes:
[0041] A feature extraction unit, used to extract a plurality of physical characteristics from a health feature library according to the physical marker, determine a feature level corresponding to each physical characteristic according to the physical marker, and further determine a feature presentation value corresponding to each physical characteristic;
[0042] A feature comparison unit is used to match the health feature with the physical feature to obtain a plurality of health combinations, respectively obtain the combination presentation value difference corresponding to each of the health combinations, and determine the bias feature corresponding to the combination presentation value difference;
[0043] A result feedback unit is used to determine a number of non-health information of the monitored person based on the bias characteristics, and generate and display a physical fitness evaluation report of the monitored person according to the combined presentation value difference corresponding to each non-health information.
[0044] In one practicable manner,
[0045] Also includes:
[0046] The information display module is used to display the physical fitness evaluation report and retrieve and display the corresponding display information according to the search instruction.
[0047] In one practicable manner,
[0048] Also includes:
[0049] A specific monitoring module is used to retrieve the instruction organ function characteristic σ corresponding to the instruction specified organ according to the special instruction issued by the monitored person.
[0050] The function of the organ specified by the instruction is evaluated in combination with the body representation information of the monitored person, and a multi-dimensional function report of the organ specified by the instruction is obtained.
[0051] The present invention provides a physical health monitoring and evaluation method based on big data, comprising:
[0052] Step 1: Collect the basic health information of the monitored person and analyze the health characteristics of the monitored person in combination with the preset big data model
[0053] Step 2: Analyze the dynamic health changes of the monitored person based on the health characteristics corresponding to the monitored person at different monitoring times to obtain the organ function characteristics corresponding to each designated organ of the monitored person;
[0054] Step 3: establishing the physical performance information of the monitored person based on the organ function characteristics corresponding to each of the designated organs, and matching the corresponding physical marker for the monitored person based on the physical performance information;
[0055] Step 4: Retrieve the corresponding physical characteristics according to the physical marker, compare the health characteristics with the physical characteristics, obtain a number of non-health information, and generate a physical evaluation report of the monitored person.
[0056] Compared with the prior art, the beneficial effects of this application are as follows:
[0057] In order to improve the quality and effectiveness of monitoring, a big data model is introduced to analyze the basic health information of the monitored person, determine the health characteristics of the monitored person, and then describe the dynamic health changes of the monitored person based on the health characteristics of the monitored person at different monitoring times, so as to determine the organ function characteristics of the brain, heart, lungs and organs set in advance by the monitored person, and further establish the physical performance information of the monitored person. In order to distinguish different constitutions, different constitution marks are made according to the physical performance information of the monitored person, and then the health characteristics corresponding to the constitution are retrieved, and the physical characteristics are compared with the actual health characteristics of the patient. The non-health information of the monitored person can be determined, thereby generating a physical evaluation report on the monitored person. In this way, the monitored person can not only monitor his or her physical health at any time, but also identify his or her own constitution to a certain extent, which will help the monitored person to intervene in his or her basic health in advance, maintain a good mentality, and have a healthy body.
[0058] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.
[0059] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS
[0060] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:
[0061] Figure 1 It is a schematic diagram of the composition of a physical health monitoring and evaluation system based on big data in an embodiment of the present invention;
[0062] Figure 2 The figure is a schematic diagram of the workflow of a physical health monitoring and evaluation method based on big data in an embodiment of the present invention. DETAILED DESCRIPTION
[0063] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.
[0064] Example 1
[0065] This embodiment provides a physical health monitoring and evaluation system based on big data. Figure 1 As shown, including:
[0066] An information collection module is used to collect basic health information of the monitored person and analyze the health characteristics of the monitored person in combination with a preset big data model;
[0067] An intelligent analysis module, used to analyze the dynamic health changes of the monitored person based on the health characteristics corresponding to the monitored person at different monitoring moments, and obtain the organ function characteristics corresponding to each designated organ of the monitored person;
[0068] A physical fitness confirmation module, used to establish physical performance information of the monitored person based on the organ function characteristics corresponding to each of the designated organs, and match a corresponding physical fitness marker for the monitored person based on the physical performance information;
[0069] The health evaluation module is used to retrieve the corresponding physical characteristics according to the physical mark, compare the health characteristics with the physical characteristics, obtain a number of non-health information, and generate a physical evaluation report of the monitored person.
[0070] In this embodiment, the basic health information includes the monitored person's general health such as blood pressure, blood sugar, cholesterol level, and organ information of each designated organ.
[0071] In this embodiment, the preset big data model represents a model for health analysis constructed based on big data, which is obtained by training samples based on the health data of different parts in different activity states and physiological and psychological analysis results of a neural network model.
[0072] In this embodiment, the designated organs include: brain, heart, lungs, and organs determined in advance by the monitored person;
[0073] In this embodiment, the organ function characteristics corresponding to each designated organ are different because the device monitoring parameters of each device are different, for example, the brain characteristics are cerebral ischemia characteristics, for example, the lung characteristics are nodule characteristics, etc.
[0074] In this embodiment, dynamic health changes represent changes in the physical health of the monitored person, for example, for brain health: normal blood supply to the brain ~ abnormal blood supply to the brain.
[0075] In this embodiment, the physical constitution mark represents a label used to distinguish different physical constitutions, which contains all the physical constitution information of the monitored person. For example, the physical performance information is U1, and the physical constitution mark is Y1, and the physical performance information refers to the characteristic indicator description of certain parts of the monitored person. For example, the initial blood pressure monitoring is a1, and the subsequent blood pressure monitoring is a2. At this time, a2 is greater than a1, a2 is in the high blood pressure category, and a1 is in the normal blood pressure category. At this time, the physical performance information is dizziness, blurred vision, etc.
[0076] In this embodiment, the physical characteristics represent the health characteristics corresponding to the physical condition, such as completely healthy physical condition, sub-healthy physical condition, unhealthy physical condition, etc., which can be represented by relevant values.
[0077] In this embodiment, non-health information refers to unhealthy characteristics of the monitored person's body, such as epilepsy: for example, the monitored person's momentary loss of consciousness and falling, abnormal limb sensation, hallucinations, repetition of words or single syllables, body or eye rotation, etc., are all unhealthy information.
[0078] In this embodiment, the physical fitness evaluation report includes the physical fitness, health and unhealthy information of the monitored person.
[0079] The working principle and beneficial effects of the above technical solution: In order to improve the quality and effect of monitoring, a big data model is introduced to analyze the basic health information of the monitored person, determine the health characteristics of the monitored person, and then describe the dynamic health changes of the monitored person based on the health characteristics of the monitored person at different monitoring times, thereby determining the organ function characteristics of the brain, heart, lungs and organs set in advance by the monitored person, and further establishing the physical performance information of the monitored person. In order to distinguish different constitutions, different constitution marks are made according to the physical performance information of the monitored person, and then the health characteristics corresponding to the constitution are retrieved, and the physical characteristics are compared with the actual health characteristics of the patient. The non-health information of the monitored person can be determined, thereby generating a physical evaluation report on the monitored person. In this way, the monitored person can not only monitor his or her physical health at any time, but also identify his or her own constitution to a certain extent, which helps the monitored person to intervene in his or her basic health in advance, maintain a good mentality, and allow the monitored person to have a healthy body.
[0080] Example 2
[0081] On the basis of Example 1, the physical health monitoring and evaluation system based on big data, the information collection module includes:
[0082] A data collection unit, used to collect the corresponding manifestation data of the monitored person under different monitoring dimensions, and generate basic health information of the monitored person;
[0083] A simulation analysis unit, used to simulate the basic health information using a preset big data model to obtain simulated presentation information of the monitored person in different activity states;
[0084] The feature construction unit is used to determine the activity presentation physiological characteristics and activity presentation psychological characteristics corresponding to the monitored person in each activity state based on the simulated presentation information and perform health assessment to obtain the health characteristics of the monitored person.
[0085] In this embodiment, the monitoring dimension represents the dimension corresponding to different types of data collected from the monitored person, and one type of data corresponds to one dimension, for example, heart rate value, high blood pressure value, etc., and heart rate and high blood pressure belong to two dimensions.
[0086] In this embodiment, the displayed data represents the data presented corresponding to a monitoring dimension, that is, the relevant physical data of the monitored person directly taken under the dimension, wherein the displayed data under all dimensions constitute the basic health data.
[0087] In this embodiment, the activity status includes: daily activity, intense activity, and rest;
[0088] In this embodiment, the health characteristics include the assessment results of physiological health and psychological health. For example, the physiological characteristic is A1 and the psychological characteristic is A2. The health assessment result at this time is: healthy. Then the corresponding health characteristics are: both physiological and psychological health and the physiological characteristic is A1 and the psychological characteristic is A2.
[0089] The working principle and beneficial effects of the above technical solution are as follows: by collecting the displayed data of the monitored person in different dimensions, and then extracting the key monitoring information in each dimension to construct the basic health information of the monitored person, and combining the model to simulate the simulated presentation information of the monitored person in different activity states, so as to analyze the physiological and psychological characteristics of the monitored person in different activity states, and generate the health characteristics of the monitored person through evaluation, so that both the physiological and psychological aspects of the monitored person can be monitored, realizing all-round monitoring.
[0090] Example 3
[0091] On the basis of Example 2, the physical health monitoring and evaluation system based on big data, the data acquisition unit includes:
[0092] A routine information collection subunit, used for collecting first monitoring data of the monitored person;
[0093] A designated information collection subunit is used to collect second monitoring data of the designated collection organ of the monitored person;
[0094] The manifestation processing integration subunit is used to sort and integrate the first monitoring data and the second monitoring data by combining the monitoring dimensions corresponding to the first monitoring data and the second monitoring data in a preset dimension matching order to obtain the manifestation data of the monitored person.
[0095] In this embodiment, the first monitoring data includes: blood pressure, blood sugar, cholesterol level, etc.;
[0096] In this embodiment, the second monitoring data includes data of each designated organ;
[0097] In this embodiment, the preset matching order means that the data matching order is set in advance according to the influence relationship between each monitoring data, and the sorting and integration according to the monitoring dimension refers to matching the first monitoring data with the second monitoring data under the same dimension and then sorting them according to the matching order. For example, the preset dimension matching order is: monitoring dimension 1, monitoring dimension 2, wherein there are first monitoring data b1 and second monitoring data b2 under monitoring dimension 1, and there are first monitoring data b3 and second monitoring data b4 under monitoring dimension 2. At this time, the displayed data is: b1+b2+b3+b4.
[0098] The working principle and beneficial effects of the above technical solution are as follows: different sub-units are used to collect different monitoring data, and then the monitoring data are sorted and integrated to obtain display data. This can not only realize the simultaneous collection of multiple sets of data, but also integrate the data to construct overall data, which will serve as a basis for subsequent work.
[0099] Example 4
[0100] On the basis of Example 1, the physical health monitoring and evaluation system based on big data, the intelligent analysis module includes:
[0101] A time domain processing unit, configured to randomly search the time domain health feature column for the airspace and non-airspace contained in n1 corresponding feature periods based on the feature period corresponding to each of the health features;
[0102] A spatial analysis unit is used to establish a spatial distribution column based on the presentation position of the randomly searched spatial domains under all health features in the time domain health feature column, and input the positional relationship of each spatial position in the spatial distribution column and the number of empty occurrences of each spatial position into an ordered analysis model to obtain the ordered spatial domain and the disordered spatial domain contained in the spatial distribution column, and input the disordered presentation position corresponding to the disordered spatial domain and all the features under the corresponding disordered spatial domain, and the ordered presentation position corresponding to the ordered spatial domain and all the features under the corresponding ordered spatial domain into the information establishment model to obtain the first dynamic information and the second dynamic information of the monitored person;
[0103] A non-spatial domain analysis unit, configured to decompose the non-spatial domain health feature to obtain a plurality of sub-health features, and map the sub-health features to a high-dimensional space for regression analysis to obtain a plurality of linear fitting results, and combine the linear fitting results based on the non-spatial domain presentation position in the time domain health feature column to obtain loss information;
[0104] The model acquisition unit is used to construct an overall organ model of the monitored person according to the organ information corresponding to each of the designated organs in combination with the preset big data model, map all loss information into the overall organ model respectively, and run the overall organ model in combination with the first dynamic information and the second dynamic information to obtain a health model.
[0105] In this embodiment, each health feature corresponds to a feature cycle, and the feature cycle represents the time period when a health feature appears, and the feature cycle is obtained based on a feature-cycle comparison table, and the comparison table is pre-set and designed by experts to include different health features and the corresponding cycles under the features. For example, the health feature R1 that appears for the first time is locked, and the health feature R1 is captured at time u1, time u2, time u3, and time u6, and the corresponding duration period is: t2~t3, that is, time u1 corresponds to t2, and time u6 corresponds to t3. At this time, the feature cycle is: t3-t2, which is pre-planned by experts.
[0106] It should be noted that by performing periodic searches in the time domain feature health column according to the period t3-t2, the required results based on the health feature can be obtained, and the required results are the airspace and non-airspace involved. For example, the time domain feature health column:
[0107] In this embodiment, there may be multiple features at the same monitoring moment, for example, the time domain health feature column: {Moment 1: health feature 1 Moment 2: health feature 1 + health feature 2 Moment 3: health feature 2 Moment 4: health feature 1 + health feature 2 Moment 5: health feature 1 + health feature 2 Moment 6: health feature 1}.
[0108] In this embodiment, a random characteristic period is a random period set for health characteristic 1, such as t2, t3 and t4. At this time, the search information of the random period for health characteristic 1 is empty for t3 and non-empty for t2 and t4. Among them, the characteristic period for health characteristic 1 is set to 3 moments, and so on, to obtain n1 characteristic periods, and n1 characteristic periods are the total moments under the time domain health characteristic column / the maximum characteristic period of all health characteristics.
[0109] In this embodiment, there will be airspace and non-airspace under the same health feature. The airspace and non-airspace under the n1 periods found under all health features are aligned at the same time to obtain the airspace distribution column. At time t1: the airspace of health feature 1 + the airspace of health feature 2, at time t2: non-airspace, at time t3: the airspace of health feature 1, etc. At this time, it can be known that the number of empty occurrences of the airspace position corresponding to time t1 is 2, and the non-airspace relationship is columnar with the airspace position corresponding to time t1, and its adjacent time t2 is non-airspace. At this time, the position relationship is regarded as a non-airspace relationship, otherwise, it is regarded as an airspace relationship.
[0110] In this embodiment, the ordered analysis model is obtained by training the neural network model based on samples of different position relationships and combined relationships of the number of empty occurrences and the expert's evaluation results of the ordered and disordered airspaces on the combined relationships. Therefore, the ordered and disordered airspaces based on the airspace distribution column can be directly obtained.
[0111] In this embodiment, the information building model is obtained by training the neural network based on samples of different disordered airspaces, ordered airspaces and related feature combinations, and dynamic information planned by experts, and the first dynamic information based on disorder and the second dynamic information based on order can be directly obtained.
[0112] In this embodiment, the empty domain represents blank information in the time domain health feature column, and the non-empty domain represents non-blank information in the time domain health feature;
[0113] In this embodiment, the spatial distribution column represents the distribution of all the spatial domains in the time domain health feature;
[0114] In this embodiment, the first dynamic information represents reference information without periodic order presented under the action of the airspace, and the second dynamic information represents reference information with periodic order presented under the action of the airspace. Both are related to the operation of the organ. The ordered airspace represents the airspace with periodic order, and the unordered airspace represents the airspace without periodic order.
[0115] In this embodiment, the mapping to the high-dimensional space is used to make the feature changes more explicit and facilitate separation.
[0116] In this embodiment, regression analysis is fitted by linear regression, and multiple independent variables and dependent variables with linear relationships can be directly obtained. At this time, the non-spatial domain presentation position can be a combination of results at continuous positions, or a combination of results at single positions, or a combination of results at positions involved in a specified continuous segment, to obtain combined features. For example, sub-health feature 1 corresponds to result 01 and result 02, sub-health feature 2 corresponds to result 11 and result 12, sub-health feature 1 corresponds to non-spatial domain presentation position w1, and sub-health feature 2 corresponds to non-spatial domain presentation position w2. Assuming that w1 and w2 are continuous, at this time, result 01 is combined with result 11, and result 02 is combined with result 12. The results are then input into the loss analysis model to obtain loss information. The loss analysis model is obtained by training the neural network model based on samples of different fitting result combinations and expert loss analysis of the combined results.
[0117] In this embodiment, the preset big data model is a model for organs, which is mainly used to fuse organs and information to obtain an overall organ model.
[0118] In this embodiment, the purpose of feature mapping is to visualize the information of the model.
[0119] The working principle and beneficial effects of the above technical solution are as follows: based on the characteristic period of health characteristics, the spatial domain and non-spatial domain of the time domain health feature column are found to complete the preliminary information decomposition, and the disordered spatial domain in the spatial distribution column is used to construct the first dynamic information of the monitored person and obtain the second dynamic information of the ordered spatial domain. The abnormal data of the monitored person can be screened and the subsequent model operation can be assisted. The non-spatial domain can be mapped at high latitudes and regression analyzed, and big data can be used to construct an overall organ model for feature mapping and screening to determine the health model of the monitored person, providing a basis for the follow-up.
[0120] Example 5
[0121] On the basis of Example 4, the physical health monitoring and evaluation system based on big data, the intelligent analysis module includes:
[0122] An index establishment unit, used to establish time indexes for the health features corresponding to the monitored person at different monitoring times, sort the health features according to the time indexes to generate a time-domain health feature column, combine health features with adjacent relationships in the time-domain health feature column to obtain a plurality of combined health features, and establish a combined index for each of the combined health features;
[0123] A combined analysis unit, used to construct an index tree of the monitored person based on two time indexes and one combined index corresponding to each of the combined health features, and at the same time, establish a plurality of short-term dynamic health of the monitored person based on the feature values corresponding to the combined health features;
[0124] Establishing a mapping order based on the time index, mapping each of the short-term dynamic health to the index tree respectively, and generating the initial dynamic health of the monitored person;
[0125] A dynamic analysis unit, used to determine the functional demand corresponding to each designated organ of the monitored person using the initial dynamic health, input each of the functional demands into the health model of the monitored person to perform demand rationality analysis, obtain the energy consumption characteristics corresponding to each of the designated organs, use the energy consumption characteristics to perform energy consumption compensation on the initial dynamic health, and generate dynamic health changes of the monitored person;
[0126] A functional feedback unit is used to construct activity information corresponding to each of the designated organs according to the dynamic health changes, map each of the activity information to the health model, obtain the presentation data corresponding to each of the activity information in the health model, and establish the organ function characteristics of the corresponding designated organ based on the presentation data.
[0127] In this embodiment, the time index corresponds to the health feature one by one, and the time index can reflect the health feature corresponding to a monitoring moment, and is the result of optimizing the query function of the monitoring moment, which facilitates sorting.
[0128] In this embodiment, the time-domain health feature column represents a feature column with time order generated after sorting the health features in the order of the time index. For example, the time index of health feature A is X year Y month N day 12:00, the time index of health feature B is X year Y month N day 12:01, and the time index of health feature C is X year Y month N day 12:02. Then the time-domain health feature column generated after sorting according to the time index is {health feature A, health feature B, health feature C}.
[0129] In this embodiment, the combined health feature means combining two separate health features with adjacent time relationships, reflecting the health characteristics of the monitored person in a short period of time. For example, health feature A appears at time t1, health feature B appears at time t2, and t1 and t2 are adjacent times and t2 is after t1. At this time, the combined health feature is: health feature A + health feature B.
[0130] In this embodiment, the combined health index indicates the monitoring time start point and monitoring time end point corresponding to a combined health feature.
[0131] In this embodiment, the characteristic value reflects the health performance value of the combined health characteristics regarding time and the monitored person during this period of time, and is specifically calculated as follows:
[0132]
[0133]
[0134]
[0135]
[0136] Among them, Jz represents the corresponding eigenvalue; J1(g1, z1) represents the performance function of the first feature g1 in the combined health feature at the corresponding monitoring time z1; J2(g2, z2) represents the performance function of the second feature g2 in the combined health feature at the corresponding monitoring time z2; ΔR represents the error performance value based on feature g1 and feature g2; m1 represents the number of refined division times matching feature g1 at monitoring time z1, σm2 represents the number of refined division times matching feature g2 at monitoring time z2, σg1 i1 represents the value of the first feature g1 at the i1th refinement time; g2 i2 represents the value of the second feature g2 at the i2th refinement time; g1 y represents the maximum value of all features g1 detected in history; g2 y represents the maximum value of all features g2 corresponding to historical detection; ln represents the sign of logarithmic function; g1 1 Indicates the value of the first feature g1 at the first refined division time; g1 m1 represents the value of the first feature g1 at the m1th refinement time; g2 1 Indicates the value of the second feature g2 at the first refined division time; g2 m2 Represents the value σw of the second feature g2 at the m2th refinement time m1 , W m2 Respectively represent the adjustment coefficients based on the first feature g1 and the second feature g2; σ1 2 ,σ2 2 Respectively represent based on all g1 i1 , all g2 i2 The variance of
[0137] The above method determines different values by finely dividing the features, thereby facilitating the comprehensive determination of feature values based on combined health features, providing a basis for the subsequent steps.
[0138] In this embodiment, each moment can be obtained by combining multiple time units after fine division. For example, moment 1 is 1 second, so after fine division there will be: 0.2s, 0.4s, 0.6s, 0.8s and 1s. That is to say, for example, the starting moment of feature A and the end moment of feature B are used to determine the short-term dynamic health in the time period, that is, by multiplying the value under each fine-grained time period with the corresponding Jz to obtain the mean square, and a series of values are obtained as the short-term dynamic health.
[0139] In this embodiment, the short-term health dynamics represent the health changes of the monitored person within a time period corresponding to a combined health feature.
[0140] In this embodiment, the initial dynamic health is actually obtained by comprehensive analysis of the mapped index tree, including the health status of different organs.
[0141] In this embodiment, the index tree includes different time indexes.
[0142] In this embodiment, the functional requirement represents the energy required by a given organ to maintain normal physiological activities;
[0143] In this embodiment, the rationality analysis process represents analyzing the functional requirements of the monitored person, so as to determine whether the designated organs of the monitored person have abnormal requirements, or whether the requirements are too high or too low.
[0144] In this embodiment, the energy consumption characteristic represents the speed and amount of energy consumed by a specified organ in the current state. The energy consumption compensation is to optimize the value under the short-term dynamic health in the initial dynamic health. The general optimization method is: optimization value = original characteristic value + optimization factor under energy consumption characteristic. The result is the dynamic health change.
[0145] In this embodiment, the activity information represents the activity presented by the designated organ of the monitored person in the current situation, and the presented data is the numerical expression of the activity information.
[0146] The working principle and beneficial effects of the above technical solution are as follows: first, a time index is established for the health characteristics of the monitored person, and then the characteristics are combined to generate multiple combined health characteristics. In order to improve the analysis efficiency, a combined index is established for each combined health characteristic, and then an index tree is constructed based on the combined index and the time index. The short-term dynamic health is mapped to the index tree to establish the initial dynamic health, thereby establishing the functional requirements of each designated organ, performing a rational analysis of the functional requirements, and constructing the energy consumption characteristics of different designated organs to compensate for the energy consumption of the initial dynamic health, generating the dynamic health changes of the monitored person, and finally combining the health model to analyze the organ function characteristics of each designated organ, thereby achieving the purpose of synchronously constructing and analyzing characteristics.
[0147] Example 6
[0148] On the basis of Example 1, the physical health monitoring and evaluation system based on big data, the intelligent physical fitness confirmation module, includes:
[0149] An organ monitoring unit, used to establish an organ model based on the organ function characteristics corresponding to each of the designated organs, and to capture monitoring information corresponding to each of the designated organs of the monitored person in combination with a plurality of organ function characteristics of the monitored person;
[0150] A deep monitoring unit, configured to analyze a plurality of physical performance information of the monitored person based on the influence relationship between different designated organs, in combination with the monitoring information corresponding to each designated organ and the basic health information of the monitored person;
[0151] A physique matching unit, used for matching the corresponding suspected physique for each of the body performance information, and extracting a number of target physiques with a matching number greater than a preset number;
[0152] The physique confirmation unit is used to set a matching weight for the corresponding target physique based on the matching number, fuse the target physique based on the matching weight, obtain the individual physique of the monitored person, and mark it accordingly.
[0153] In this embodiment, the preset number is 3.
[0154] In this embodiment, since the organ function of each designated organ is different, the function of the constructed organ model is also different.
[0155] In this embodiment, the monitoring information represents the information collected during the monitoring of the monitored person and presented when each designated organ maintains the current activity, that is, the information obtained during the monitoring;
[0156] In this embodiment, the influence relationship between different designated organs means that due to the close physiological and functional connections between the various organs of the human body, when one of the organs presents a certain state, other organs will also show related states. For example, when the heart beats abnormally, the brain will experience insufficient oxygen supply.
[0157] In this embodiment, the suspected physical constitution refers to the physical constitution corresponding to the physical performance information, that is, the physical constitution that the monitored person may exhibit.
[0158] The working principle and beneficial effects of the above technical solution are as follows: by constructing an organ model to monitor each designated organ, determining the monitoring linearity of each designated organ, and then analyzing the physical performance information of the monitored person according to the influence relationship between different designated organs combined with the basic health line information and the monitoring information, and then matching the corresponding suspected constitution, further integrating and adjusting the suspected constitution, determining the personal constitution of the monitored person, and adding corresponding marks to the monitored person for easy distinction and search.
[0159] Example 7
[0160] On the basis of Example 6, the physical health monitoring and evaluation system based on big data, the intelligent health evaluation module, includes:
[0161] A feature extraction unit, used to extract a plurality of physical characteristics from a health characteristic library according to the physical marker, determine a feature level corresponding to each physical characteristic according to the physical marker, and determine a feature presentation value corresponding to each physical characteristic;
[0162] A feature comparison unit, used for matching the health feature with the physical feature to obtain a plurality of health combinations, respectively obtaining a combination presentation value difference corresponding to each of the health combinations, and determining a bias feature corresponding to the combination presentation value difference;
[0163] A result feedback unit is used to determine a number of non-health information of the monitored person based on the bias characteristics, and generate and display a physical fitness evaluation report of the monitored person according to the combined presentation value difference corresponding to each non-health information.
[0164] In this embodiment, the health characteristic library stores information about multiple constitutions and the physical characteristics corresponding to each constitution, as well as other aspects of information about each constitution.
[0165] In this embodiment, the characteristic level indicates the level corresponding to a physical characteristic. For example, the monitored person has an obese physique, the obesity level is level one, and the body mass index is between 30.0-34.9.
[0166] In this embodiment, the characteristic presentation value represents the numerical value presented by the physical condition of the monitored person.
[0167] In this embodiment, the purpose of combining health features with physical features is to achieve a one-to-one comparison.
[0168] In this embodiment, the combined presentation value difference represents the difference between the health feature and the physical feature in a health combination.
[0169] In this embodiment, the bias feature has two directions. When the difference in the combined presentation value is positive, it points to the health feature; when it is negative, it points to the physical feature; and when it is 0, it has no direction.
[0170] In this embodiment, determining the non-health information based on the bias characteristics means determining the comprehensive result of comparing the monitored person's physical characteristics (ie, normal characteristics under the physical condition) at different monitoring angles based on the bias characteristics.
[0171] In this embodiment, after determining that the combination presents a difference, a physical fitness evaluation report is automatically generated based on all the differences and in combination with a difference evaluation and analysis model. The difference evaluation and analysis model is obtained by training a neural network model based on samples of all difference combinations and expert evaluation results of the combination.
[0172] The working principle and beneficial effects of the above technical solution are as follows: the health information of the monitored person is compared with the physical health information corresponding to the individual physique of the monitored person, and the non-health information of the monitored person is analyzed based on the comparison results, so as to establish a physical evaluation report, so that the monitored person can perform corresponding health recovery work according to the report.
[0173] Example 8
[0174] On the basis of Example 1, the physical health monitoring and evaluation system based on big data further includes:
[0175] The information display module is used to display the physical fitness evaluation report and retrieve and display the corresponding display information according to the search instruction.
[0176] The working principle and beneficial effects of the above technical solution: by setting up the information display module, it is convenient for the monitored person to view the information.
[0177] Example 9
[0178] On the basis of Example 1, the physical health monitoring and evaluation system based on big data further includes:
[0179] A specific monitoring module, used for retrieving the instruction organ function characteristics corresponding to the instruction-specified organ according to the special instruction issued by the monitored person;
[0180] The function of the organ specified by the instruction is evaluated in combination with the body representation information of the monitored person, and a multi-dimensional function report of the organ specified by the instruction is obtained.
[0181] In this embodiment, the organ designated by the instruction can be any organ on the body of the monitored person, and the special instruction is pre-set, so that the monitored person can issue it directly.
[0182] In this embodiment, the multi-dimensional functional report includes the functions of the designated organs of the monitored person under the influence of his or her physical constitution in different dimensions.
[0183] The working principle and beneficial effects of the above technical solution: In order to further improve the intelligence of the system, the monitored person can conduct in-depth monitoring of a certain organ and generate a functional report on the organ, so that the monitored person can understand the status of each organ at any time.
[0184] Example 10
[0185] This embodiment provides a physical health monitoring and evaluation method based on big data, such as Figure 2 As shown, including:
[0186] Step 1: Collect basic health information of the monitored person and analyze the health characteristics of the monitored person in combination with a preset big data model;
[0187] Step 2: Analyze the dynamic health changes of the monitored person based on the health characteristics corresponding to the monitored person at different monitoring times to obtain the organ function characteristics corresponding to each designated organ of the monitored person;
[0188] Step 3: establishing the physical performance information of the monitored person based on the organ function characteristics corresponding to each of the designated organs, and matching the corresponding physical marker for the monitored person based on the physical performance information;
[0189] Step 4: Retrieve the corresponding physical characteristics according to the physical marker, compare the health characteristics with the physical characteristics, obtain a number of non-health information, and generate a physical evaluation report of the monitored person.
[0190] The working principle and beneficial effects of the above technical solution: In order to improve the quality and effect of monitoring, a big data model is introduced to analyze the basic health information of the monitored person, determine the health characteristics of the monitored person, and then describe the dynamic health changes of the monitored person based on the health characteristics of the monitored person at different monitoring times, thereby determining the organ function characteristics of the brain, heart, lungs and organs set in advance by the monitored person, and further establishing the physical performance information of the monitored person. In order to distinguish different constitutions, different constitution marks are made according to the physical performance information of the monitored person, and then the health characteristics corresponding to the constitution are retrieved, and the physical characteristics are compared with the actual health characteristics of the patient. The non-health information of the monitored person can be determined, thereby generating a physical evaluation report on the monitored person. In this way, the monitored person can not only monitor his or her physical health at any time, but also identify his or her own constitution to a certain extent, which helps the monitored person to intervene in his or her basic health in advance, maintain a good mentality, and allow the monitored person to have a healthy body.
[0191] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.
Claims
1. A physical health monitoring and evaluation system based on big data, characterized in that: include: An information collection module is used to collect basic health information of the monitored person and analyze the health characteristics of the monitored person in combination with a preset big data model; An intelligent analysis module, used to analyze the dynamic health changes of the monitored person based on the health characteristics corresponding to the monitored person at different monitoring moments, and obtain the organ function characteristics corresponding to each designated organ of the monitored person; A physical fitness confirmation module, used to establish physical performance information of the monitored person based on the organ function characteristics corresponding to each of the designated organs, and match a corresponding physical fitness marker for the monitored person based on the physical performance information; The health evaluation module is used to retrieve the corresponding physical characteristics according to the physical mark, compare the health characteristics with the physical characteristics, obtain a number of non-health information, and generate a physical evaluation report of the monitored person.
2. According to the big data-based physical health monitoring and evaluation system of claim 1, it is characterized in that: The information collection module comprises: A data collection unit, used to collect the corresponding manifestation data of the monitored person under different monitoring dimensions, and generate basic health information of the monitored person; A simulation analysis unit, used to simulate the basic health information using a preset big data model to obtain simulated presentation information of the monitored person in different activity states; The feature construction unit is used to determine the activity presentation physiological characteristics and activity presentation psychological characteristics corresponding to the monitored person in each activity state based on the simulated presentation information and perform health assessment to obtain the health characteristics of the monitored person.
3. A physical health monitoring and evaluation system based on big data according to claim 2, characterized in that: The data acquisition unit comprises: A routine information collection subunit, used for collecting first monitoring data of the monitored person; A designated information collection subunit is used to collect second monitoring data of the designated collection organ of the monitored person; The manifestation processing integration subunit is used to sort and integrate the first monitoring data and the second monitoring data by combining the monitoring dimensions corresponding to the first monitoring data and the second monitoring data in a preset dimension matching order to obtain the manifestation data of the monitored person.
4. According to the big data-based physical health monitoring and evaluation system of claim 1, it is characterized in that: The intelligent analysis module comprises: A time domain processing unit, configured to randomly search the time domain health feature column for the airspace and non-airspace contained in n1 corresponding feature periods based on the feature period corresponding to each of the health features; A spatial analysis unit is used to establish a spatial distribution column based on the presentation position of the randomly searched spatial domains under all health features in the time domain health feature column, and input the positional relationship of each spatial position in the spatial distribution column and the number of empty occurrences of each spatial position into an ordered analysis model to obtain the ordered spatial domain and the disordered spatial domain contained in the spatial distribution column, and input the disordered presentation position corresponding to the disordered spatial domain and all the features under the corresponding disordered spatial domain, and the ordered presentation position corresponding to the ordered spatial domain and all the features under the corresponding ordered spatial domain into the information establishment model to obtain the first dynamic information and the second dynamic information of the monitored person; A non-spatial domain analysis unit, configured to decompose the non-spatial domain health feature to obtain a plurality of sub-health features, and map the sub-health features to a high-dimensional space for regression analysis to obtain a plurality of linear fitting results, and combine the linear fitting results based on the non-spatial domain presentation position in the time domain health feature column to obtain loss information; The model acquisition unit is used to construct an overall organ model of the monitored person according to the organ information corresponding to each of the designated organs in combination with the preset big data model, map all loss information into the overall organ model respectively, and run the overall organ model in combination with the first dynamic information and the second dynamic information to obtain a health model.
5. A physical health monitoring and evaluation system based on big data according to claim 4, characterized in that: The intelligent analysis module further includes: An index establishment unit, used to establish time indexes for the health features corresponding to the monitored person at different monitoring times, sort the health features according to the time indexes to generate a time-domain health feature column, combine health features with adjacent relationships in the time-domain health feature column to obtain a plurality of combined health features, and establish a combined index for each of the combined health features; A combined analysis unit, used to construct an index tree of the monitored person based on two time indexes and one combined index corresponding to each of the combined health features, and at the same time, establish a plurality of short-term dynamic health of the monitored person based on the feature values corresponding to the combined health features; Establishing a mapping order based on the time index, mapping each of the short-term dynamic health to the index tree respectively, and generating the initial dynamic health of the monitored person; A dynamic analysis unit, used to determine the functional demand corresponding to each designated organ of the monitored person using the initial dynamic health, input each of the functional demands into the health model of the monitored person to perform demand rationality analysis, obtain the energy consumption characteristics corresponding to each of the designated organs, use the energy consumption characteristics to perform energy consumption compensation on the initial dynamic health, and generate dynamic health changes of the monitored person; A functional feedback unit is used to construct activity information corresponding to each of the designated organs according to the dynamic health changes, map each of the activity information to the health model, obtain the presentation data corresponding to each of the activity information in the health model, and establish the organ function characteristics of the corresponding designated organ based on the presentation data.
6. The physical health monitoring and evaluation system based on big data according to claim 1 is characterized in that: The intelligence and physique confirmation module includes: An organ monitoring unit, used to establish an organ model based on the organ function characteristics corresponding to each of the designated organs, and to capture monitoring information corresponding to each of the designated organs of the monitored person in combination with a plurality of organ function characteristics of the monitored person; A deep monitoring unit, configured to analyze a plurality of physical performance information of the monitored person based on the influence relationship between different designated organs, in combination with the monitoring information corresponding to each designated organ and the basic health information of the monitored person; A physique matching unit, used to match the corresponding suspected physique for each of the body performance information, and extract a number of target physiques with a matching number greater than a preset number; The physique confirmation unit is used to set a matching weight for the corresponding target physique based on the matching number, fuse the target physique based on the matching weight, obtain the individual physique of the monitored person, and mark it accordingly.
7. The physical health monitoring and evaluation system based on big data according to claim 1 is characterized in that: The intellectual health evaluation module includes: A feature extraction unit, used to extract a plurality of physical characteristics from a health characteristic library according to the physical marker, determine a feature level corresponding to each physical characteristic according to the physical marker, and further determine a feature presentation value corresponding to each physical characteristic; A feature comparison unit is used to match the health feature with the physical feature to obtain a plurality of health combinations, respectively obtain the combination presentation value difference corresponding to each of the health combinations, and determine the bias feature corresponding to the combination presentation value difference; A result feedback unit is used to determine a number of non-health information of the monitored person based on the bias characteristics, and generate and display a physical fitness evaluation report of the monitored person according to the combined presentation value difference corresponding to each non-health information.
8. The physical health monitoring and evaluation system based on big data according to claim 1 is characterized in that: Also includes: The information display module is used to display the physical fitness evaluation report and retrieve and display the corresponding display information according to the search instruction.
9. The physical health monitoring and evaluation system based on big data according to claim 1 is characterized in that: Also includes: A specific monitoring module, used for retrieving the instruction organ function characteristics corresponding to the instruction-specified organ according to the special instruction issued by the monitored person; The function of the organ specified by the instruction is evaluated in combination with the body representation information of the monitored person, and a multi-dimensional function report of the organ specified by the instruction is obtained.
10. A physical health monitoring and evaluation method based on big data, characterized in that: include: Step 1: Collect basic health information of the monitored person and analyze the health characteristics of the monitored person in combination with a preset big data model; Step 2: Analyze the dynamic health changes of the monitored person based on the health characteristics corresponding to the monitored person at different monitoring times to obtain the organ function characteristics corresponding to each designated organ of the monitored person; Step 3: establishing the physical performance information of the monitored person based on the organ function characteristics corresponding to each of the designated organs, and matching the corresponding physical marker for the monitored person based on the physical performance information; Step 4: Retrieve the corresponding physical characteristics according to the physical marker, compare the health characteristics with the physical characteristics, obtain a number of non-health information, and generate a physical evaluation report of the monitored person.
Citation Information
Patent Citations
Human brain health training system based on SAAS platform
CN103226665A
Mobile wearable monitoring systems
CN107438398A
Human health evaluation method and evaluation system based on sleep big data
CN109087706A
Method, device and system for monitoring physical and psychological health states
CN111243747A
Wearable equipment arrhythmia monitoring system for cardiology department
CN117457173A
