CN118039178A - Health management method and system based on health monitoring data - Google Patents
Health management method and system based on health monitoring data Download PDFInfo
- Publication number
- CN118039178A CN118039178A CN202410337015.0A CN202410337015A CN118039178A CN 118039178 A CN118039178 A CN 118039178A CN 202410337015 A CN202410337015 A CN 202410337015A CN 118039178 A CN118039178 A CN 118039178A
- Authority
- CN
- China
- Prior art keywords
- data
- processing
- collection
- preset
- collecting
- 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.)
- Pending
Links
- 230000036541 health Effects 0.000 title claims abstract description 75
- 238000012544 monitoring process Methods 0.000 title claims abstract description 29
- 238000007726 management method Methods 0.000 title claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 189
- 238000013480 data collection Methods 0.000 claims abstract description 53
- 238000007405 data analysis Methods 0.000 claims abstract description 43
- 238000013500 data storage Methods 0.000 claims abstract description 36
- 230000035935 pregnancy Effects 0.000 description 6
- 238000000034 method Methods 0.000 description 5
- 230000010349 pulsation Effects 0.000 description 5
- 210000004204 blood vessel Anatomy 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000017531 blood circulation Effects 0.000 description 2
- 230000036772 blood pressure Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000002792 vascular Effects 0.000 description 2
- 206010047139 Vasoconstriction Diseases 0.000 description 1
- 230000004931 aggregating effect Effects 0.000 description 1
- 238000000540 analysis of variance Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 230000003169 placental effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
- 230000025033 vasoconstriction Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention relates to the field of data processing, in particular to a health management method and system based on health monitoring data, wherein the system comprises the following steps: the data acquisition unit comprises a plurality of data storage ends, and each data storage end is used for storing data information input by a user; the data analysis unit is used for determining a data processing mode according to the data collection state, carrying out combination processing or single processing under different data processing modes, and determining a combination processing sub-mode according to the distribution states of the data enrichment collection end and the data depletion collection end; the combined processing unit is used for carrying out combined processing on the data of the data rich collecting end and/or the data lean collecting end according to the data processing mode determined by the data analysis unit; the single processing unit is used for eliminating redundant data according to the data quantity and the data redundancy of the single data enrichment collecting end; the invention improves the processing efficiency and the safety of the health monitoring data.
Description
Technical Field
The invention relates to the field of data processing, in particular to a health management system based on health monitoring data.
Background
Chinese patent publication No. CN113870994a discloses an intelligent medical system based on edge calculation and federal learning, comprising: medical data acquisition is carried out by using edge equipment such as a medical sensor and the like, and acquired data are stored in a local edge server. The edge server utilizes network equipment such as a router to form a centralized annular edge network, processes and analyzes local data by using a principal component analysis method and an analysis of variance method, and performs model training by using a convolutional neural network CNN algorithm. And uploading the locally trained model gradient to a federal server by each medical institution, aggregating the model gradient by the federal server by using a federal average algorithm, returning a new model gradient, and updating the local model by each medical institution according to the new model gradient. Through continuous iteration, the medical model effect is continuously improved. It follows that the intelligent medical system based on edge calculation and federal learning has the following problems:
1. The acquired medical health data cannot be preprocessed, and the problem that the risk of data leakage is high due to the redundancy of the medical health data easily exists;
2. the effectiveness of the medical health data is not considered, and the problem of poor model learning efficiency is easily caused.
Disclosure of Invention
Therefore, the invention provides a health management method and system based on health monitoring data, which are used for solving the problems of poor data learning efficiency and high leakage risk caused by invalid data redundancy due to poor preprocessing efficiency of collected data in the prior art of learning the health data.
To achieve the above object, the present invention provides a health management system based on health monitoring data, comprising:
the data acquisition unit comprises a plurality of data acquisition devices and a plurality of data storage ends, wherein the data acquisition devices are used for acquiring patient medical health data of users, and the data storage ends are used for storing the patient medical health data of the users and storing the patient body health data input in advance;
A data analysis unit connected with the data acquisition unit for determining data processing modes according to the data collection state, correspondingly selecting combined processing or single processing under different data processing modes,
The data analysis unit is provided with a combination processing rule, and a combination processing sub-mode is determined according to the distribution of the data enrichment collecting end and the data depletion collecting end;
A combination processing unit connected with the data acquisition unit and the data analysis unit and used for carrying out combination processing on the data of the data rich collection end and/or the data lean collection end according to the data processing mode determined by the data analysis unit,
In the combination processing, a combination processing unit determines the corresponding label of each data enrichment collecting end and the corresponding label of each data depletion collecting end according to the data enrichment degree, and combines according to a preset combination sequence, or determines a matching processing mode according to the matching degree between different data depletion collecting ends;
and the single processing unit is connected with the data acquisition unit and the data analysis unit and is used for eliminating redundant data according to the data quantity and the data redundancy of the single data enrichment collection end.
Further, the data analysis unit periodically detects the data collection state of each data storage end, and determines a data processing mode according to the data collection state, wherein the data processing mode comprises a first data processing mode for carrying out combined processing on the stored data of different data storage ends and a second data processing mode for carrying out single processing on the stored data of each data storage end in sequence;
And recording the medical health data of the patient corresponding to the single data storage end and the physical health data of the patient as storage data corresponding to the data storage end.
Further, the data analysis unit is provided with a first preset data collection state and a second preset data collection state, wherein the first preset data collection state is that the number of data enrichment collection ends is smaller than the number of preset data enrichment collection ends, and the second preset data collection state is that the number of data enrichment collection ends is larger than or equal to the number of preset data enrichment collection ends;
the data enrichment collection end is a data storage end with the corresponding data collection enrichment degree being larger than the preset data collection enrichment degree.
Further, the data analysis unit is provided with a combination processing rule, wherein the combination processing rule is that the data analysis unit detects the distribution state of the data enrichment collecting end and the data depletion collecting end, and determines a combination processing sub-mode according to the distribution state, and the combination processing sub-mode comprises a first combination processing sub-mode for combining the data enrichment collecting end and the data depletion collecting end and a second combination processing sub-mode for combining according to the data matching degree;
The data depletion collection end is a data storage end with corresponding data collection richness smaller than or equal to a preset data collection richness.
Further, under the first data combination processing condition, the combination processing unit sequentially determines the marks Ni corresponding to all the data enrichment collecting ends according to the sequence from big to small of the data collection richness, wherein Ni is sequentially marked as N1, N2, … … and Nc, sequentially determines the marks My corresponding to all the data depletion collecting ends according to the sequence from small to big of the data collection richness, sequentially marked as M1, M2, … … and Mx, and groups the data depletion collecting ends according to the sequence from small to big of y to data depletion collecting ends, wherein each group comprises (x/c) data depletion collecting ends, x/c is rounded downwards, and stored data corresponding to all the data enrichment collecting ends and stored data corresponding to the data depletion collecting ends are combined according to a preset combination sequence;
Wherein i=1, 2,3, … …, c, c is the total number of data-rich collection ends, y=1, 2,3, … …, x, x is the total number of data-lean collection ends;
The first data combination processing condition is that the data analysis unit judges that the combination processing sub-mode is a first combination processing sub-mode.
Further, under the second data combination processing condition, the combination processing unit sequentially calculates the matching degree of the data-poor collecting end and other data-poor collecting ends according to the sequence from the small data volume to the large data volume, and determines a matching processing mode according to the matching state, wherein the matching processing mode comprises a first matching processing mode for judging that the matching is successful and stopping the matching when the matching state is in a first preset matching state, and a second matching processing mode for judging that the matching is successful and continuing the matching when the matching state is in a second preset matching state;
and the second data combination processing condition is that the data analysis unit judges that the combination processing sub-mode is a second combination processing sub-mode.
Further, the combined processing unit is provided with a first preset matching state and a second preset matching state, wherein the first preset matching state is that the matching degree of the two data depletion collecting ends is larger than the preset matching degree, the sum of the data amounts corresponding to the two data depletion collecting ends is larger than or equal to the preset reference data amount, and the second preset matching state is that the matching degree of the two data depletion collecting ends is larger than the preset matching degree, and the sum of the data amounts corresponding to the two data depletion collecting ends is smaller than the preset reference data amount.
Further, the value of the degree of matching of the two data-lean collection ends is related to the patient's physical health data.
Further, the single processing unit sequentially counts the data quantity of the single data enrichment collecting end under the first single processing condition, if the data quantity of the single data enrichment collecting end is larger than the preset maximum data quantity, the single processing unit detects the data redundancy of the data enrichment collecting end, and if the data redundancy is larger than the preset data redundancy, the single processing unit rejects the redundant data;
wherein the first single processing condition is a second data processing mode in which the data analysis unit determines that the data processing mode is single processing.
Further, the data redundancy and the number of similar data are in positive correlation, and if the data similarity corresponding to the two pieces of data information is smaller than the preset data similarity, the two pieces of data information are judged to be similar data.
The invention also provides a health management method based on health monitoring data, which is applied to the system and comprises the following steps:
Each data storage end stores data information input by a user;
determining a data processing mode according to the data collection state, and carrying out combined processing or single processing under different data processing modes;
Determining a combined processing sub-mode according to the distribution of the data enrichment collecting end and the data depletion collecting end;
Combining data of the data rich collection end and/or the data lean collection end according to the data processing mode determined by the data analysis unit;
In single processing, redundant data are removed according to the data quantity and the data redundancy of a single data enrichment collecting end;
In the combination processing, the corresponding label of each data rich collection end and the corresponding label of each data lean collection end are determined according to the data richness, and the data are combined according to a preset combination sequence, or the matching processing mode is sequentially calculated and determined according to the matching degree of the data lean collection end and other data lean collection ends.
Compared with the data collection mode without pretreatment, the method has the advantages that the validity of the data is reflected through the data collection richness, the collected data can meet the actual model learning requirement, the model learning speed is further improved, the data analysis unit is provided with a combination processing rule, different combinations are carried out according to the condition of the actually collected data, so that a data set which is more beneficial to model learning is obtained according to the actual data self-adaption.
Drawings
FIG. 1 is a block diagram of a health management system based on health monitoring data according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a health management method based on health monitoring data according to an embodiment of the present invention;
FIG. 3 is a flow chart illustrating a method for determining a data processing mode according to a data collection status according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating a method for determining a combination processing sub-mode according to a distribution state according to an embodiment of the present invention.
Detailed Description
In order that the objects and advantages of the invention will become more apparent, the invention will be further described with reference to the following examples; it should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present invention, and are not intended to limit the scope of the present invention.
It should be noted that, in the description of the present invention, terms such as "upper," "lower," "left," "right," "inner," "outer," and the like indicate directions or positional relationships based on the directions or positional relationships shown in the drawings, which are merely for convenience of description, and do not indicate or imply that the apparatus or elements must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention.
Furthermore, it should be noted that, in the description of the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those skilled in the art according to the specific circumstances.
Referring to fig. 1 to 4, the present invention provides a health management system based on health monitoring data, comprising:
the data acquisition unit comprises a plurality of data acquisition devices and a plurality of data storage ends, wherein the data acquisition devices are used for acquiring patient medical health data of users, and the data storage ends are used for storing the patient medical health data of the users and storing the patient body health data input in advance;
A data analysis unit connected with the data acquisition unit for determining data processing modes according to the data collection state, correspondingly selecting combined processing or single processing under different data processing modes,
The data analysis unit is provided with a combination processing rule, and a combination processing sub-mode is determined according to the distribution of the data enrichment collecting end and the data depletion collecting end;
A combination processing unit connected with the data acquisition unit and the data analysis unit and used for carrying out combination processing on the data of the data rich collection end and/or the data lean collection end according to the data processing mode determined by the data analysis unit,
In the combination processing, a combination processing unit determines the corresponding label of each data enrichment collecting end and the corresponding label of each data depletion collecting end according to the data enrichment degree, and combines according to a preset combination sequence, or determines a matching processing mode according to the matching degree between different data depletion collecting ends;
and the single processing unit is connected with the data acquisition unit and the data analysis unit and is used for eliminating redundant data according to the data quantity and the data redundancy of the single data enrichment collection end.
The invention is applied to medical health data federal learning, and aims at collecting and transmitting body health data and medical health data of pregnant women patients to a model generation end for model learning.
The data acquisition device comprises an intelligent bracelet for acquiring blood pressure data of a human body and an ultrasonic detection device for acquiring color Doppler ultrasonic images.
Specifically, the data information input by the user comprises patient physical health data and patient medical health data, the patient physical health data comprises patient age, patient weight and patient pregnancy time, the patient medical health data comprises blood pressure data, a resistance index RI, a pulsation index PI and an S/D ratio, the pregnancy time is the pregnancy time of a pregnant woman patient, the resistance index, the pulsation index and the S/D ratio are all evaluation indexes related to blood vessel blood flow states, and the resistance index is one of indexes for evaluating blood vessels commonly used by color Doppler ultrasound and is used for reflecting the conditions of vasoconstriction and downstream vascular resistance; the pulsation index is an elastic index and is used for reflecting the compliance of the blood vessel and the elasticity of the blood vessel; the S/D ratio, i.e., the ratio of end-systole peak (S) to end-diastole peak (D), is used to reflect blood flow and placental vascular resistance, as is well understood in the art and will not be described in detail herein.
Specifically, the data analysis unit periodically detects a data collection state of each data storage end, determines a data processing mode according to the data collection state, and includes a first data processing mode for performing combined processing on the stored data of different data storage ends, and a second data processing mode for sequentially performing single processing on the stored data of each data storage end;
And recording the medical health data of the patient corresponding to the single data storage end and the physical health data of the patient as storage data corresponding to the data storage end.
Specifically, the data analysis unit is provided with monitoring periods, each monitoring period is detected according to the data collection state when the monitoring period is finished, the duration of the monitoring period is related to the collection capacity of each data storage end, if the data volume collected in unit time of the data storage end is larger, the duration of the monitoring period is smaller, a value of the monitoring period is provided, and the monitoring period is 15 days.
Specifically, the data analysis unit is provided with a first preset data collection state and a second preset data collection state, wherein the first preset data collection state is that the number of data enrichment collection ends is smaller than the number of preset data enrichment collection ends, and the second preset data collection state is that the number of data enrichment collection ends is larger than or equal to the number of preset data enrichment collection ends;
the data enrichment collection end is a data storage end with the corresponding data collection enrichment degree being larger than the preset data collection enrichment degree.
The first data processing mode is selected in a first preset data collection state, and the second data processing mode is selected in a second preset data collection state.
Specifically, the calculation formula of the data collection richness S is:
S0＝(S1+S2+S3)/3)
Wherein S0 is an average value, S1 is the number of reference values in a first threshold range, S2 is the number of reference values in a second threshold range, S3 is the number of reference values in a third threshold range, reference value = patient age x α1+ patient weight x α2+ patient pregnancy duration x α3, α1 is a first weight coefficient, α2 is a second weight coefficient, α3 is a third weight coefficient, the value of the weight coefficient is related to the patient age, patient weight and the influence degree of the pregnancy duration of the patient, the greater the influence degree is, a weight coefficient value is provided, α1=0.2, α2=0.3, and α3=5; extracting a reference value with the largest value and a reference value with the smallest value and marking the reference value as the smallest value, uniformly dividing the maximum threshold value and the smallest threshold value into a first threshold value range, a second threshold value range and a third threshold value range, wherein the values in the first threshold value range are larger than the smallest threshold value and smaller than 30% of the largest threshold value, the values in the second threshold value range are larger than or equal to 30% of the largest threshold value and smaller than 60% of the largest threshold value, and the values in the third threshold value range are larger than or equal to 60% of the largest threshold value; the preset data collection richness value is 1/(s0×0.2).
Specifically, the data analysis unit is provided with a combination processing rule, wherein the combination processing rule is that in a first data processing mode, the data analysis unit detects the distribution state of a data enrichment collecting end and a data depletion collecting end, determines a combination processing sub-mode according to the distribution state, and comprises a first combination processing sub-mode for combining the data enrichment collecting end and the data depletion collecting end and a second combination processing sub-mode for combining according to the data matching degree;
The data depletion collection end is a data storage end with corresponding data collection richness smaller than or equal to a preset data collection richness.
Specifically, the distribution states of the data enrichment collecting end and the data depletion collecting end include a first preset distribution state and a second preset distribution state, wherein the first preset distribution state is that the number of the data enrichment collecting ends/the number of the data depletion collecting ends is greater than 30%, and the second preset distribution state is that the number of the data enrichment collecting ends/the number of the data depletion collecting ends is less than or equal to 30%.
The first combination processing sub-mode is selected in the first preset distribution state, and the second combination processing sub-mode is selected in the second preset distribution state.
Specifically, under the first data combination processing condition, the combination processing unit sequentially determines the marks Ni corresponding to all the data enrichment collecting ends according to the sequence from big to small of the data collection richness, wherein Ni is sequentially marked as N1, N2, … … and Nc, sequentially determines the marks My corresponding to all the data depletion collecting ends according to the sequence from small to big of the data collection richness, sequentially marked as M1, M2, … … and Mx, and groups the data depletion collecting ends according to the sequence from small to big of y to data depletion collecting ends, wherein each group comprises (x/c) data depletion collecting ends, x/c is downward rounded, and stored data corresponding to all the data enrichment collecting ends and stored data corresponding to the data depletion collecting ends are combined according to a preset combination sequence;
Wherein i=1, 2,3, … …, c, c is the total number of data-rich collection ends, y=1, 2,3, … …, x, x is the total number of data-lean collection ends;
The first data combination processing condition is that the data analysis unit judges that the combination processing sub-mode is a first combination processing sub-mode.
Specifically, the preset combination sequence is to sort the data depletion collection end sets according to the data collection richness from small to large and sequentially combine the data depletion collection end sets with the data corresponding to the data enrichment collection ends according to the data collection richness from large to small, and the combination is to integrate and send the data of the corresponding data storage ends to the model generation end.
Specifically, under the second data combination processing condition, the combination processing unit sequentially calculates the matching degree of the single data-lean collecting end and other data-lean collecting ends according to the sequence of the data volume from small to large, and determines a matching processing mode according to the matching state, wherein the matching processing mode comprises a first matching processing mode for judging that the matching is successful and stopping the matching when the matching state is in a first preset matching state, and a second matching processing mode for judging that the matching is successful and continuing the matching when the matching state is in a second preset matching state;
and the second data combination processing condition is that the data analysis unit judges that the combination processing sub-mode is a second combination processing sub-mode.
In the first matching processing mode, the data of the data-poor collecting end which is successfully matched are combined, namely, the data of the corresponding data storage end is integrated and sent to the model generating end.
Specifically, the combined processing unit is provided with a first preset matching state and a second preset matching state, wherein the first preset matching state is that the matching degree of the two data depletion collecting ends is larger than the preset matching degree, the sum of the data amounts corresponding to the two data depletion collecting ends is larger than or equal to a preset reference data amount, and the second preset matching state is that the matching degree of the two data depletion collecting ends is larger than the preset matching degree, and the sum of the data amounts corresponding to the two data depletion collecting ends is smaller than the preset reference data amount.
Specifically, the values of the matching degree of the two data depletion collecting ends are related to the physical health data of the patient, the two data depletion collecting ends are respectively marked as a first data depletion collecting end and a second data depletion collecting end, the matching degree= -is (ria-rib) [ and/ria+ (PI a-PI b) [ and/or PI a+ [ and/or (S/Da-S/Db) ] is/Da, wherein RI a is a resistance index corresponding to the first data depletion collecting end, RI b is a resistance index corresponding to the second data depletion collecting end, PI a is a pulsation index corresponding to the first data depletion collecting end, PI b is a pulsation index corresponding to the second data depletion collecting end, S/Da is an S/D ratio corresponding to the first data depletion collecting end, S/Db is an S/D ratio corresponding to the second data depletion collecting end, the value of the preset matching degree can be set according to an actual working scene, the matching degree of the two data collecting ends is larger, the difference between the two data collecting ends is proved to be larger, the preset data depletion degree is higher than the learning model, and the matching degree is 30% higher than the preset value.
The absolute value of the difference in the number of reference values in the first threshold range corresponding to the two data-lean collection ends + the absolute value of the difference in the number of reference values in the second threshold range corresponding to the two data-lean collection ends + the absolute value of the difference in the number of reference values in the third threshold range corresponding to the two data-lean collection ends.
Specifically, the single processing unit sequentially counts the data quantity of the single data enrichment collecting end under the first single processing condition, if the data quantity of the single data enrichment collecting end is larger than the preset maximum data quantity, the single processing unit detects the data redundancy of the data enrichment collecting end, and if the data redundancy is larger than the preset data redundancy, the single processing unit randomly selects half of redundant data to be removed;
wherein the first single processing condition is a second data processing mode in which the data analysis unit determines that the data processing mode is single processing.
Specifically, under the first single processing condition, the data of the data depletion collecting end is taken as invalid data to be removed, the preset maximum data size is set by a user, the higher the requirement of the user on model accuracy is, the larger the value of the preset maximum data size is, the preset maximum data size is provided, the preset maximum data size is 30 pieces, the data size is the number of data information, and one piece of data information comprises patient physical health data of a patient and patient medical health data.
Specifically, the data redundancy and the number of similar data are in positive correlation, and if the data similarity corresponding to the two pieces of data information is smaller than the preset data similarity, the two pieces of data information are judged to be similar data.
Specifically, the similarity is the similarity of the patient health data corresponding to the two pieces of data information, a calculation formula of the similarity is provided, the similarity= (the absolute value of the difference value of the patient ages corresponding to the two pieces of data information + the absolute value of the difference value of the patient weights corresponding to the two pieces of data information + the absolute value of the difference value of the pregnancy duration corresponding to the two pieces of data information), the value of the preset similarity is set by the user, the greater the requirement of the user for redundancy inhibition of the data is, the greater the preset similarity is, and the minimum value of the preset similarity is 0.
The invention also provides a health management method based on health monitoring data, which is applied to the system and comprises the following steps:
Each data storage end stores data information input by a user;
determining a data processing mode according to the data collection state, and carrying out combined processing or single processing under different data processing modes;
Determining a combined processing sub-mode according to the distribution of the data enrichment collecting end and the data depletion collecting end;
Combining data of the data rich collection end and/or the data lean collection end according to the data processing mode determined by the data analysis unit;
In single processing, redundant data are removed according to the data quantity and the data redundancy of a single data enrichment collecting end;
In the combination processing, the corresponding label of each data rich collection end and the corresponding label of each data lean collection end are determined according to the data richness, and the data are combined according to a preset combination sequence, or the matching processing mode is sequentially calculated and determined according to the matching degree of the data lean collection end and other data lean collection ends.
Thus far, the technical solution of the present invention has been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present invention is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present invention, and such modifications and substitutions will be within the scope of the present invention.
The foregoing description is only of the preferred embodiments of the invention and is not intended to limit the invention; various modifications and variations of the present invention will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A health management system based on health monitoring data, comprising:
the data acquisition unit comprises a plurality of data acquisition devices and a plurality of data storage ends, wherein the data acquisition devices are used for acquiring patient medical health data of users, and the data storage ends are used for storing the patient medical health data of the users and storing the patient body health data input in advance;
A data analysis unit connected with the data acquisition unit for determining data processing modes according to the data collection state, correspondingly selecting combined processing or single processing under different data processing modes,
The data analysis unit is provided with a combination processing rule, and a combination processing sub-mode is determined according to the distribution of the data enrichment collecting end and the data depletion collecting end;
A combination processing unit connected with the data acquisition unit and the data analysis unit and used for carrying out combination processing on the data of the data rich collection end and/or the data lean collection end according to the data processing mode determined by the data analysis unit,
In the combination processing, a combination processing unit determines the corresponding label of each data enrichment collecting end and the corresponding label of each data depletion collecting end according to the data enrichment degree, and combines according to a preset combination sequence, or determines a matching processing mode according to the matching degree between different data depletion collecting ends;
and the single processing unit is connected with the data acquisition unit and the data analysis unit and is used for eliminating redundant data according to the data quantity and the data redundancy of the single data enrichment collection end.
2. The health management system based on health monitoring data according to claim 1, wherein the data analysis unit periodically detects a data collection status of each data storage terminal, determines a data processing mode according to the data collection status, and includes a first data processing mode for performing combined processing on the stored data of different data storage terminals, and a second data processing mode for sequentially performing single processing on the stored data of each data storage terminal;
And recording the medical health data of the patient corresponding to the single data storage end and the physical health data of the patient as storage data corresponding to the data storage end.
3. The health management system based on health monitoring data according to claim 2, wherein the data analysis unit is provided with a first preset data collection state and a second preset data collection state, wherein the first preset data collection state is that the number of data-rich collection ends is smaller than the number of preset data-rich collection ends, and the second preset data collection state is that the number of data-rich collection ends is greater than or equal to the number of preset data-rich collection ends;
the data enrichment collection end is a data storage end with the corresponding data collection enrichment degree being larger than the preset data collection enrichment degree.
4. The health management system based on health monitoring data according to claim 3, wherein the data analysis unit is provided with a combination processing rule, the combination processing rule is that the data analysis unit detects distribution states of the data-rich collecting end and the data-lean collecting end, and determines a combination processing sub-mode according to the distribution states, and the combination processing sub-mode comprises a first combination processing sub-mode in which the data-rich collecting end and the data-lean collecting end are combined, and a second combination processing sub-mode in which the data-rich collecting end and the data-lean collecting end are combined according to the data matching degree;
The data depletion collection end is a data storage end with corresponding data collection richness smaller than or equal to a preset data collection richness.
5. The health management system based on health monitoring data according to claim 4, wherein the combination processing unit sequentially determines, under a first data combination processing condition, a label Ni corresponding to each data enrichment collecting end in a sequence from big to small in data collection richness, wherein Ni is sequentially denoted as N1, N2, … …, nc, sequentially determines, in a sequence from small to big in data collection richness, a label My corresponding to each data depletion collecting end, sequentially denoted as M1, M2, … …, mx, and groups the data depletion collecting ends in a sequence from small to big in y as a data depletion collecting end set, each group including (x/c) data depletion collecting ends, wherein x/c is rounded down, and the stored data corresponding to each data enrichment collecting end and the stored data corresponding to the data depletion collecting end set are combined according to a preset combination sequence;
Wherein i=1, 2,3, … …, c, c is the total number of data-rich collection ends, y=1, 2,3, … …, x, x is the total number of data-lean collection ends;
The first data combination processing condition is that the data analysis unit judges that the combination processing sub-mode is a first combination processing sub-mode.
6. The health management system based on health monitoring data according to claim 5, wherein the combination processing unit sequentially calculates the matching degree of the data-lean collecting end and the other data-lean collecting end in order of the data amount from small to large under the second data combination processing condition, and determines a matching processing mode according to the matching state, including the first matching processing mode of judging that the matching is successful and stopping the matching when the matching state is in a first preset matching state, and the second matching processing mode of judging that the matching is successful and continuing the matching when the matching state is in a second preset matching state;
and the second data combination processing condition is that the data analysis unit judges that the combination processing sub-mode is a second combination processing sub-mode.
7. The health management system based on health monitoring data according to claim 6, wherein the combined processing unit is provided with a first preset matching state and a second preset matching state, wherein the first preset matching state is that the matching degree of the two data depletion collecting ends is larger than the preset matching degree, the sum of the data amounts corresponding to the two data depletion collecting ends is larger than or equal to a preset reference data amount, the second preset matching state is that the matching degree of the two data depletion collecting ends is larger than the preset matching degree, and the sum of the data amounts corresponding to the two data depletion collecting ends is smaller than the preset reference data amount;
wherein the matching degree of the two data-poor collecting ends is related to the physical health data of the patient.
8. The health management system based on health monitoring data according to claim 7, wherein the single processing unit counts data amounts of the single data-rich collection end sequentially under a first single processing condition, if the data amount of the single data-rich collection end is greater than a preset maximum data amount, the single processing unit detects data redundancy of the single data-rich collection end, and if the data redundancy is greater than the preset data redundancy, the single processing unit rejects the redundant data;
wherein the first single processing condition is a second data processing mode in which the data analysis unit determines that the data processing mode is single processing.
9. The health management system based on health monitoring data according to claim 8, wherein the data redundancy and the number of similar data are in positive correlation, and if the data similarity corresponding to the two pieces of data information is smaller than the preset data similarity, the two pieces of data information are determined to be similar data.
10. A health management method based on health monitoring data applied to the system of any one of claims 1 to 9, comprising:
Each data storage end stores data information input by a user;
determining a data processing mode according to the data collection state, and carrying out combined processing or single processing under different data processing modes;
Determining a combined processing sub-mode according to the distribution of the data enrichment collecting end and the data depletion collecting end;
Combining data of the data rich collection end and/or the data lean collection end according to the data processing mode determined by the data analysis unit;
In single processing, redundant data are removed according to the data quantity and the data redundancy of a single data enrichment collecting end;
In the combination processing, the corresponding label of each data rich collection end and the corresponding label of each data lean collection end are determined according to the data richness, and the data are combined according to a preset combination sequence, or the matching processing mode is sequentially calculated and determined according to the matching degree of the data lean collection end and other data lean collection ends.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410337015.0A CN118039178A (en) | 2024-03-22 | 2024-03-22 | Health management method and system based on health monitoring data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410337015.0A CN118039178A (en) | 2024-03-22 | 2024-03-22 | Health management method and system based on health monitoring data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118039178A true CN118039178A (en) | 2024-05-14 |
Family
ID=91004310
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410337015.0A Pending CN118039178A (en) | 2024-03-22 | 2024-03-22 | Health management method and system based on health monitoring data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118039178A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110321349A (en) * | 2019-06-13 | 2019-10-11 | 暨南大学 | A kind of self-adapting data of data-oriented origin system merges storage method |
| KR20190136913A (en) * | 2018-05-30 | 2019-12-10 | 경희대학교 산학협력단 | Method and device for providing user health status |
| CN113761103A (en) * | 2020-12-29 | 2021-12-07 | 京东城市(北京)数字科技有限公司 | Batch data processing method and device and electronic equipment |
| CN114547077A (en) * | 2022-02-22 | 2022-05-27 | 贵州惠智电子技术有限责任公司 | Intelligent processing system and method for basic government affair form data |
-
2024
- 2024-03-22 CN CN202410337015.0A patent/CN118039178A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20190136913A (en) * | 2018-05-30 | 2019-12-10 | 경희대학교 산학협력단 | Method and device for providing user health status |
| CN110321349A (en) * | 2019-06-13 | 2019-10-11 | 暨南大学 | A kind of self-adapting data of data-oriented origin system merges storage method |
| CN113761103A (en) * | 2020-12-29 | 2021-12-07 | 京东城市(北京)数字科技有限公司 | Batch data processing method and device and electronic equipment |
| CN114547077A (en) * | 2022-02-22 | 2022-05-27 | 贵州惠智电子技术有限责任公司 | Intelligent processing system and method for basic government affair form data |
Non-Patent Citations (1)
| Title |
|---|
| 梁杨: "大数据背景下关联规则挖掘算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, 15 March 2020 (2020-03-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108717668A (en) | A kind of milk cow behavior and physiological characteristic Internet of things system and its working method | |
| CN104398254A (en) | Electrocardiogram analyzing system, electrocardiogram analyzing equipment and electrocardiogram predication model acquisition equipment | |
| CN111951965B (en) | Panoramic health dynamic monitoring and predicting system based on time sequence knowledge graph | |
| CN110520935A (en) | Learn sleep stage from radio signal | |
| CN106407699A (en) | Coronary heart disease prediction method and prediction system based on incremental neural network model | |
| CN106446560A (en) | Hyperlipidemia prediction method and prediction system based on incremental neural network model | |
| CN113729648B (en) | Wearable pulse-taking bracelet system based on multiple pulse sensors | |
| CN114403847A (en) | Respiration state detection method and system based on correlation of abdominal and pulmonary data | |
| CN116631558B (en) | Construction method of medical detection project based on Internet | |
| CN118039178A (en) | Health management method and system based on health monitoring data | |
| CN115336977B (en) | Accurate ICU alarm grading evaluation method | |
| CN115099275B (en) | Training method of arrhythmia diagnosis model based on artificial neural network | |
| CN106295238A (en) | A kind of hypertensive nephropathy Forecasting Methodology based on increment type neural network model and prognoses system | |
| CN112786185B (en) | Blood pressure health state acquisition method, device and system | |
| CN115440363A (en) | Household danger identification system for old people | |
| CN109147906A (en) | Evaluate method, terminal and the device with store function of surgery anesthesia quality | |
| CN114947801A (en) | Vital sign state identification method and system based on Transformer network | |
| CN109192315B (en) | Comprehensive age detection system based on weighted kernel regression and packaged deviation search | |
| CN107928652B (en) | Heart monitoring method based on pulse rate variability | |
| CN106407694A (en) | Neurasthenia prediction method and prediction system based on incremental neural network model | |
| CN113903470A (en) | Intelligent life reminding method and system for patient after hemodialysis | |
| CN109961090B (en) | Behavior classification method and system based on intelligent wearable device | |
| CN106202986A (en) | A kind of tonsillitis Forecasting Methodology based on increment type neural network model and prognoses system | |
| CN106250715A (en) | A kind of chronic pharyngolaryngitis Forecasting Methodology based on increment type neural network model and prognoses system | |
| CN109009020A (en) | A kind of health monitoring systems and health monitor method |
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 |