A personalized evaluation method of health data based on fuzzy control

Abstract

The present invention discloses a personalized evaluation method for health data based on fuzzy control, which relates to the field of data mining and processing technology, and solves the problem that the automation level is insufficient in the process of user health monitoring in the prior art, and a large amount of useless data exists in the data monitoring process, resulting in waste of computing resources. The present invention collects the user's historical health monitoring data and health monitoring results; obtains the correlation between the historical health monitoring data and the health monitoring results, and obtains the ranking of the degree of correlation between the historical health monitoring data and the health monitoring results; then, based on the ranking of the degree of correlation, selects the top X data, adopts fuzzy control, analyzes the user's health status, and outputs the health level; finally, collects the health level of each sampling number within the monitoring period, and then calculates the level evaluation coefficient, and sets the corresponding period comprehensive evaluation result based on the level evaluation coefficient as the final result output, which is beneficial to user health monitoring and management.

Description

Technical Field

[0001] The present invention relates to the technical field of data mining and processing, and in particular to a personalized evaluation method of health data based on fuzzy control. Background Art

[0002] Health monitoring is an indispensable part of modern healthcare. It plays a vital role in disease prevention, early diagnosis and treatment, and improving the quality of life. By regularly monitoring individual physiological parameters such as blood pressure, heart rate, blood sugar, etc., physical abnormalities can be detected in time, potential health risks can be predicted, and corresponding intervention measures can be taken. There is a close connection between health monitoring data and health monitoring results. The accuracy and completeness of monitoring data directly affect the reliability of health evaluation. Therefore, high-quality health monitoring data is a prerequisite for effective health management. With the development of science and technology, health monitoring equipment and methods are constantly improving, but how to extract valuable information from massive data is still a problem that needs to be solved.

[0003] Most current health monitoring relies on manual data collection for analysis and evaluation. This process is not only time-consuming and labor-intensive, but also affected by the subjective judgment of the monitors, resulting in possible deviations in the results. The experience level of the monitors directly affects the accuracy of the monitoring results, and the training and maintenance costs of experienced personnel are high. In addition, although some automated health monitoring systems or methods have appeared on the market, they often need to process a large amount of information when collecting data, including many complex and redundant data that have little effect on the final results. This not only increases the computational burden of the system and prolongs the data processing time, but also does not substantially improve the output accuracy of the results. In the ocean of data, how to quickly and accurately identify key health indicators and eliminate irrelevant information is the key to improving the efficiency and accuracy of health monitoring.

[0004] In view of this, a personalized evaluation method of health data based on fuzzy control is needed. Summary of the invention

[0005] In view of the problem that the degree of automation is insufficient in the process of user health monitoring in the prior art and a large amount of useless data exists in the data monitoring process, resulting in a waste of computing resources, the present invention provides a personalized evaluation method for health data based on fuzzy control, which can select the data with the greatest impact on health through association analysis, and then further analyze these data using fuzzy control to obtain health monitoring results and issue an alarm. The specific technical solution is as follows:

[0006] A personalized evaluation method for health data based on fuzzy control includes the following steps:

[0007] Collect users' historical health monitoring data and health monitoring results;

[0008] Obtain the correlation between historical health monitoring data and health monitoring results, and rank the correlation between historical health monitoring data and health monitoring results;

[0009] Based on the sorting of the degree of association, the top X data are selected, fuzzy control is used to analyze the user's health status, and the health level is output;

[0010] Set the monitoring cycle and the number of sampling times in the monitoring cycle, collect the health level of each sampling number in the monitoring cycle, and then calculate the level evaluation coefficient. Set the corresponding period comprehensive evaluation result based on the level evaluation coefficient as the final result output. The calculation of the level evaluation coefficient is as follows:

[0011]

[0012] In the formula, θ(x) is the grade evaluation coefficient, x j is the health level identified in the j-th sampled health monitoring data, λ j is the corresponding weight coefficient, and N is the number of sampling times.

[0013] Preferably, the health monitoring data include blood pressure, heart rate, blood sugar, cholesterol, body mass index, body temperature, respiratory rate, blood oxygen saturation, mental health status, and physical activity level; and the health monitoring results include healthy, sub-healthy, and unhealthy.

[0014] Preferably, the ranking of the correlation between the health monitoring data and the health monitoring results is as follows:

[0015] Numerical encoding of all features and health monitoring results in health monitoring data, including: blood pressure, heart rate, blood sugar, cholesterol, body mass index, body temperature, respiratory rate, blood oxygen saturation, mental health status, and physical activity level;

[0016] Format the data into transaction datasets, where each transaction contains a set of feature items;

[0017] Calculate the support of the item, and then use the minimum support threshold Support(X) min , select the support greater than or equal to Support(X) min The calculation formula of the support of the item is as follows:

[0018]

[0019] Where X is an item set, N(X) is the number of transactions containing item set X, and N total is the total number of transactions;

[0020] For each frequent item set, a conditional pattern base and a conditional FP tree are constructed to mine deeper frequent item sets;

[0021] Use FP-tree to recursively mine frequent itemsets until no more frequent itemsets can be found;

[0022] Based on the frequent item sets, association rules are generated and the confidence of each rule is calculated. The calculation formula of the confidence is as follows:

[0023]

[0024] In the formula, X is the antecedent of the rule, Y is the consequent of the rule, Support(X∪Y) is the frequency of item sets X and Y appearing at the same time, and Support(X) is the frequency of item set X appearing;

[0025] Select a confidence level greater than or equal to the minimum confidence threshold min The rules are then sorted according to their confidence.

[0026] Preferably, the process of fuzzy control, analyzing the user's health status, and outputting the health level is as follows:

[0027] Data collection and preprocessing: Collect users’ health monitoring data;

[0028] Establish a fuzzy knowledge base: define fuzzy variables, fuzzy sets and fuzzy rules, where fuzzy variables are the fuzzy representation of input and output variables, fuzzy sets are the membership functions of these variables, and fuzzy rules are the logical relationship between input and output;

[0029] Fuzzification: Convert the collected health data into fuzzy sets;

[0030] Fuzzy reasoning: reasoning using fuzzy rules;

[0031] Defuzzification: converting the results of fuzzy reasoning back to specific health levels;

[0032] Health level output: Output the user's health level based on the defuzzification result;

[0033] Preferably, the calculation formula for the periodic comprehensive evaluation result is as follows:

[0034]

[0035] Wherein, L is the comprehensive evaluation result of the final output, and the comprehensive evaluation result is M levels, that is, L = {L1, L2, ..., L k ,…,L M}, where L is the level sequence, Lk is the kth level in the level sequence; θ(x) is the level evaluation coefficient, x j is the health level identified in the j-th sampled health monitoring data, θ min is the minimum value among all possible values ​​of θ(x), θ max is the maximum value among all possible values ​​of θ(x).

[0036] Preferably, the method further comprises the following steps:

[0037] Set the alarm threshold. When the final output comprehensive evaluation result L reaches a certain set level, or the level evaluation coefficient θ(x) is greater than or equal to the set threshold, an alarm is issued.

[0038] Preferably, a level-period correspondence table is set, wherein the level-period correspondence table includes the level of the comprehensive evaluation result and the corresponding reminder period under the level, and the alarm operation is performed according to the comprehensive evaluation result and the corresponding alarm period.

[0039] Preferably, a level evaluation coefficient-period correspondence table is set, wherein the level evaluation coefficient-period correspondence table includes a level evaluation coefficient range and a corresponding reminder period within the range, and an alarm operation is performed according to the level evaluation coefficient and the corresponding alarm period.

[0040] A computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned personalized health data evaluation method based on fuzzy control.

[0041] A processor is used to run a program, wherein the program executes the above-mentioned personalized health data evaluation method based on fuzzy control when running.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] The present invention collects the user's historical health monitoring data and health monitoring results; obtains the correlation between the historical health monitoring data and the health monitoring results, and obtains the ranking of the degree of correlation between the historical health monitoring data and the health monitoring results; then based on the ranking of the degree of correlation, selects the top X data, adopts fuzzy control, analyzes the user's health status, and outputs the health level; finally, sets the monitoring cycle and the number of sampling times of the monitoring cycle, collects the health level of each sampling number within the monitoring cycle, and then calculates the level evaluation coefficient, and sets the corresponding cycle comprehensive evaluation result based on the level evaluation coefficient as the final result output. In short, the present invention can obtain a cycle comprehensive evaluation result based on the user's health monitoring data, and then reflect the user's health status within the cycle. Through a quantitative method, the user or management terminal can intuitively see the user's health status within the cycle and the change status of the health status between cycles, which is conducive to user health monitoring and management. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0045] Figure 1 is a flow chart of the method of the present invention;

[0046] Figure 2 A schematic diagram of a process for obtaining association conditions of the present invention;

[0047] Figure 3 This is the fuzzy control flow chart of the present invention. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0050] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0051] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0052] In one embodiment of the present invention, a method for personalized evaluation of health data based on fuzzy control is provided. Figure 1 As shown, the following steps are included:

[0053] Step 1: Collect the user's historical health monitoring data and health monitoring results. The historical health monitoring data includes blood pressure, heart rate, blood sugar, cholesterol, body mass index, body temperature, respiratory rate, blood oxygen saturation, mental health status (including anxiety, depression), physical activity level (including daily activity and exercise frequency), etc. The health monitoring results include healthy, sub-healthy and unhealthy. Among them, the health monitoring results are based on the patient's hospital test records or doctors and other industry experts for data-based judgment.

[0054] Step 2: Obtain the correlation between the historical health monitoring data and the health monitoring results, and rank the correlation between the historical health monitoring data and the health monitoring results. The higher the correlation, the higher the ranking.

[0055] like Figure 2 As shown, the process of obtaining the association situation is as follows:

[0056] S201: Numerically encode all features in the health monitoring data (e.g., blood pressure, heart rate, blood sugar, cholesterol, body mass index, body temperature, respiratory rate, blood oxygen saturation, mental health status, physical activity level) and health monitoring results so that the algorithm can process them;

[0057] S202: Format the data into a transaction data set, where each transaction contains a set of feature items. For example, a transaction can be "high blood pressure, medium heart rate, medium blood sugar, medium cholesterol, high body mass index, high body temperature, high respiratory rate, low blood oxygen saturation, medium mental health, and low physical activity level", and add a "health monitoring result" label at the end of the transaction.

[0058] S203: Construct an FP-tree. The FP-tree is a compressed data structure for storing frequent item sets. The construction steps are: calculate the support of the item, and then according to the minimum support threshold Support(X)min , select the support greater than or equal to Support(X) min The calculation formula of the support of the item is as follows:

[0059]

[0060] Where X is an item set, N(X) is the number of transactions containing item set X, and N total is the total number of transactions;

[0061] S204: For each frequent item set, a conditional pattern base (CM) and a conditional FP (CFPT) tree are constructed to mine deeper frequent item sets.

[0062] S205: recursively mine frequent item sets using the FP-tree until no more frequent item sets can be found;

[0063] S206: Generate association rules based on frequent item sets and calculate the confidence of each rule. The calculation formula of the confidence is as follows:

[0064]

[0065] In the formula, X is the antecedent of the rule, Y is the consequent of the rule, Support(X∪Y) is the frequency of item sets X and Y appearing at the same time, and Support(X) is the frequency of item set X appearing.

[0066] S207: Select a confidence level greater than or equal to the minimum confidence threshold Confidence min Then the rules are sorted according to their confidence.

[0067] After the above steps, we can determine the data items that affect the health monitoring results, as well as the order of these data items based on the degree of influence. In other words, we can determine which data in the health monitoring data has the greatest impact on the health monitoring results, which data has the second greatest impact on the health monitoring results, and so on. So far, the Health Monitoring Data Bureau has completed its analysis of the degree of influence on the health monitoring results.

[0068] Step 3: Based on the ranking of the degree of association, select the top X data, such as the top five data of blood pressure, heart rate, blood sugar, cholesterol, and respiratory rate (assuming that the top five data analyzed in step 2 are blood pressure, heart rate, blood sugar, cholesterol, and respiratory rate);

[0069] Step 4: After collecting real-time data from the data selected in step 3, analyze the user's health status based on fuzzy control and output the health level. The following uses blood pressure, heart rate, blood sugar, cholesterol, and respiratory rate as examples to further explain step 4, as follows:

[0070] In the medical field, fuzzy control is used to output the user's health evaluation, such as Figure 3 As shown, this can be achieved through the following specific steps:

[0071] S401: Data collection and preprocessing: First, the user's health data needs to be collected, including blood pressure, heart rate, blood sugar, cholesterol, and respiratory rate. These data will serve as input for the fuzzy control system.

[0072] S402: Establishing a fuzzy knowledge base: defining fuzzy variables, fuzzy sets and fuzzy rules. Fuzzy variables are fuzzy representations of input and output variables, fuzzy sets are membership functions of these variables, and fuzzy rules are logical relationships between input and output.

[0073] S403: Fuzzification: converting the collected health data into fuzzy sets, for example, converting blood pressure values ​​into fuzzy sets such as "low blood pressure", "normal blood pressure" and "high blood pressure".

[0074] S404: Fuzzy reasoning: reasoning using fuzzy rules. Fuzzy rules are usually in the form of "if-then", for example: "If blood pressure is 'high blood pressure' and heart rate is 'fast', then the health level is 'high risk'".

[0075] S405: Defuzzification: Convert the result of fuzzy reasoning back to a specific health level. Common defuzzification methods include the Centroid Method and the Max Membership Method.

[0076] S406: Health level output: Output the user's health level according to the defuzzification result. For example, the health level can be divided into "low risk", "medium risk" and "high risk".

[0077] The following is a specific data example to further illustrate the specific implementation process of this step:

[0078] To simplify the explanation process, only blood pressure and heart rate are used as input:

[0079] 1. Data collection and preprocessing: The following users’ health data were collected:

[0080] Blood pressure (BP): 120 mmHg

[0081] Heart rate (HR): 80bpm

[0082] 2. Establish fuzzy knowledge base:

[0083] Fuzzy variable definition:

[0084] Blood pressure (BP): Three fuzzy sets are defined: “Low blood pressure” (LowBP), “Normal blood pressure” (NormalBP), and “High blood pressure” (HighBP).

[0085] Heart rate (HR): Three fuzzy sets are defined: “Slow HR”, “Normal HR”, and “Fast HR”.

[0086] Health Level: Define three fuzzy sets: “Low Risk”, “Medium Risk”, and “High Risk”.

[0087] Membership function definition:

[0088] Define simple linear membership functions for each fuzzy set. For example:

[0089] For "hypotension": the membership increases as the blood pressure value is lower than 120 mmHg and decreases as it is higher than 120 mmHg.

[0090] For "hypertension": the membership increases as the blood pressure value is higher than 120 mmHg and decreases as it is lower than 120 mmHg.

[0091] For "normal blood pressure": the degree of membership is highest at 120 mmHg and decreases on both sides.

[0092] Fuzzy control rules:

[0093] Define the following fuzzy rules:

[0094] If BP is LowBP and HR is SlowHR, then HealthLevel is LowRisk.

[0095] If BP is NormalBP and HR is NormalHR, HealthLevel is LowRisk.

[0096] If BP is HighBP and HR is FastHR, then HealthLevel is HighRisk.

[0097] If BP is HighBP or HR is FastHR, HealthLevel is MediumRisk.

[0098] 3. Fuzzification:

[0099] Convert actual data into membership values ​​of fuzzy sets:

[0100] BP=120mmHg: LowBP(0.5), NormalBP(0.5), HighBP(0)

[0101] HR=80bpm: SlowHR(0), NormalHR(0.8), FastHR(0.2)

[0102] 4. Fuzzy reasoning:

[0103] Reasoning based on fuzzy rules and membership values:

[0104] Rule 1: Inactive (BP is not LowBP)

[0105] Rule 2: Activation (the membership values ​​of BP and HR are 0.5 and 0.8 respectively)

[0106] Rule 3: Inactive (BP is not HighBP)

[0107] Rule 4: Partial activation (HR membership value is 0.2)

[0108] 5. Deblurring

[0109] Centroid method is used for defuzzification. The weighted average of each health level is calculated, and the weight is the product of the rule activation and membership value.

[0110] LowRisk: (0.5*0.8)=0.4

[0111] MediumRisk: (0.2*1) = 0.2

[0112] HighRisk: 0 (no rule directly activates HighRisk)

[0113] Calculate the centroid:

[0114]

[0115] Among them, x i is the health level value (1, 2, 3 represent LowRisk, MediumRisk, HighRisk respectively), u i is the corresponding membership value.

[0116] Based on the actual data given in this example, the confidence calculation result is:

[0117]

[0118] 6. Health level output

[0119] Based on the defuzzification results, we can map the health level to the nearest integer, i.e., “low risk”.

[0120] Step 5: Set the monitoring cycle and the number of sampling times in the monitoring cycle, collect the health level of each sampling time in the monitoring cycle, and then output the comprehensive evaluation result of the cycle. The comprehensive evaluation result of the cycle is as follows:

[0121]

[0122] Wherein, L is the comprehensive evaluation result of the final output, and the comprehensive evaluation result is M levels, that is, L = {L1, L2, ..., L k ,…,L M}, where L is the level sequence, Lk is the kth level in the level sequence; θ(x) is the level evaluation coefficient, x j is the health level identified in the j-th sampled health monitoring data (e.g., low risk is 1, medium risk is 2, and high risk is 3), λ j is the corresponding weight coefficient. The higher the level, the greater the weight coefficient. The specific weight coefficient can be determined arbitrarily in practical applications, such as 0.3, 0.2, 0.1, etc. N is the number of sampling times, θ min is the minimum value among all possible values ​​of θ(x), θ max is the maximum value among all possible values ​​of θ(x).

[0123] Step 6: Set the alarm threshold. When the final output comprehensive evaluation result L reaches a certain set level, or the level evaluation coefficient θ(x) is greater than or equal to the set threshold, an alarm is issued.

[0124] Step 7: Set a level-period correspondence table, which includes the level of the comprehensive evaluation result and the corresponding reminder period under the level, and then perform an alarm operation according to the comprehensive evaluation result and the corresponding alarm period.

[0125] In this step, a level evaluation coefficient-period correspondence table may also be set, wherein the level evaluation coefficient-period correspondence table includes a level evaluation coefficient range and a corresponding reminder period within the range, and then an alarm operation is performed according to the level evaluation coefficient and the corresponding alarm period.

[0126] In summary, the present invention collects the user's historical health monitoring data and health monitoring results; obtains the correlation between the historical health monitoring data and the health monitoring results, and obtains the ranking of the degree of correlation between the historical health monitoring data and the health monitoring results; then based on the ranking of the degree of correlation, selects the top X data, adopts fuzzy control, analyzes the user's health status, and outputs the health level; finally, sets the monitoring cycle and the number of sampling times of the monitoring cycle, collects the health level of each sampling number within the monitoring cycle, and then calculates the level evaluation coefficient, and sets the corresponding cycle comprehensive evaluation result based on the level evaluation coefficient as the final result output. In short, the present invention can derive a cycle comprehensive evaluation result based on the user's health monitoring data, and then reflect the user's health status within the cycle, and through a quantitative method, the user or management terminal can intuitively see the user's health status within the cycle and the change status of the health status between cycles, which is conducive to user health monitoring and management.

[0127] Those of ordinary skill in the art will appreciate that the units of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition of each example has been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0128] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored, etc.

[0129] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0130] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-0nlyMemory), random access memory (RAM, RandomAccessMemory), mobile hard disk, magnetic disk or optical disk, etc., which can store program code.

[0131] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A personalized evaluation method for health data based on fuzzy control, characterized in that: The following steps are involved: Collect users' historical health monitoring data and health monitoring results; Obtain the correlation between historical health monitoring data and health monitoring results, and rank the correlation between historical health monitoring data and health monitoring results; Based on the sorting of the degree of association, the top X data are selected, fuzzy control is used to analyze the user's health status, and the health level is output; Set the monitoring cycle and the number of sampling times in the monitoring cycle, collect the health level of each sampling number in the monitoring cycle, and then calculate the level evaluation coefficient. Set the corresponding period comprehensive evaluation result based on the level evaluation coefficient as the final result output. The calculation of the level evaluation coefficient is as follows: In the formula, θ(x) is the grade evaluation coefficient, x j is the health level identified in the j-th sampled health monitoring data, λ j is the corresponding weight coefficient, and N is the number of sampling times.

2. According to claim 1, a personalized health data evaluation method based on fuzzy control is characterized in that: The health monitoring data include blood pressure, heart rate, blood sugar, cholesterol, body mass index, body temperature, respiratory rate, blood oxygen saturation, mental health status, and physical activity level; the health monitoring results include healthy, sub-healthy, and unhealthy.

3. The method for personalized evaluation of health data based on fuzzy control according to claim 1, characterized in that: The ranking of the degree of correlation between health monitoring data and health monitoring results is as follows: Numerical encoding of all features and health monitoring results in health monitoring data, including: blood pressure, heart rate, blood sugar, cholesterol, body mass index, body temperature, respiratory rate, blood oxygen saturation, mental health status, and physical activity level; Format the data into transaction datasets, where each transaction contains a set of feature items; Calculate the support of the item, and then use the minimum support threshold Support(X) min , select the support greater than or equal to Support(X) min The calculation formula of the support of the item is as follows: Where X is an item set, N(X) is the number of transactions containing item set X, and N total is the total number of transactions; For each frequent item set, a conditional pattern base and a conditional FP tree are constructed to mine deeper frequent item sets; Use FP-tree to recursively mine frequent itemsets until no more frequent itemsets can be found; Based on the frequent item sets, association rules are generated and the confidence of each rule is calculated. The calculation formula of the confidence is as follows: In the formula, X is the antecedent of the rule, Y is the consequent of the rule, Support(X∪Y) is the frequency of item sets X and Y appearing at the same time, and Support(X) is the frequency of item set X appearing; Select a confidence level greater than or equal to the minimum confidence threshold min The rules are then sorted according to their confidence.

4. The method for personalized evaluation of health data based on fuzzy control according to claim 1, characterized in that: The process of fuzzy control, analyzing the user's health status, and outputting the health level is as follows: Data collection and preprocessing: Collect users’ health monitoring data; Establish a fuzzy knowledge base: define fuzzy variables, fuzzy sets and fuzzy rules, where fuzzy variables are the fuzzy representation of input and output variables, fuzzy sets are the membership functions of these variables, and fuzzy rules are the logical relationship between input and output; Fuzzification: Convert the collected health data into fuzzy sets; Fuzzy reasoning: reasoning using fuzzy rules; Defuzzification: converting the results of fuzzy reasoning back to specific health levels; Health level output: Output the user's health level based on the defuzzification results.

5. The method for personalized evaluation of health data based on fuzzy control according to claim 1, characterized in that: The calculation formula for the periodic comprehensive evaluation results is as follows: Wherein, L is the comprehensive evaluation result of the final output, and the comprehensive evaluation result is M levels, that is, L = {L1, L2, ..., L k ,…,L M }, where L is the level sequence, Lk is the kth level in the level sequence; θ(x) is the level evaluation coefficient, x j is the health level identified in the j-th sampled health monitoring data, θ min is the minimum value among all possible values ​​of θ(x), θ max is the maximum value among all possible values ​​of θ(x).

6. The method for personalized evaluation of health data based on fuzzy control according to claim 5, characterized in that: The following steps are also included: Set the alarm reminder threshold. When the final output comprehensive evaluation result L reaches a certain set level, or the level evaluation coefficient θ(x) is greater than or equal to the set threshold, an alarm is issued.

7. The method for personalized evaluation of health data based on fuzzy control according to claim 6, characterized in that: A level-period correspondence table is set, wherein the level-period correspondence table includes the level of the comprehensive evaluation result and the corresponding reminder period under the level, and an alarm operation is performed according to the comprehensive evaluation result and the corresponding alarm period.

8. The method for personalized evaluation of health data based on fuzzy control according to claim 6, characterized in that: A level evaluation coefficient-period correspondence table is set, wherein the level evaluation coefficient-period correspondence table includes a level evaluation coefficient range and a corresponding reminder period under the corresponding range, and an alarm operation is performed according to the level evaluation coefficient and the corresponding alarm period.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the fuzzy control-based personalized health data evaluation method according to any one of claims 1 to 8.

10. A processor, characterized in that: The processor is used to run a program, wherein the program, when running, executes the personalized health data evaluation method based on fuzzy control as described in any one of claims 1 to 8.

Images