Artificial intelligence-based intelligent monitoring method and system for blood glucose of diabetes and medium

Abstract

The application belongs to the technical field of data processing, and particularly relates to a diabetes blood glucose intelligent monitoring method and system based on artificial intelligence and a medium, the method comprising collecting personal information of a diabetes patient, periodically monitoring physiological data of the diabetes patient, and performing transformation processing on the personal information; the diabetes patient is classified, physiological data of different types of diabetes patients is analyzed to obtain an analysis result, a correlation score of each physiological index and blood glucose level is calculated based on the analysis result, and a first physiological index is obtained based on the correlation score; a machine learning algorithm is used to train learning data to generate a corresponding type of prediction model; physiological data of a to-be-monitored patient is measured using an intelligent wearable device, the corresponding type of prediction model is obtained, a predicted blood glucose level is output by the prediction model, and whether the blood glucose level monitored by the intelligent wearable device is accurate is judged based on the predicted blood glucose level. The application can improve the accuracy of blood glucose monitoring of diabetes patients.

Description

Technical Field

[0001] The present invention belongs to the field of data processing technology, and in particular relates to an artificial intelligence-based diabetic blood glucose intelligent monitoring method, system and medium. Background Art

[0002] Diabetes is a chronic disease that requires patients to regularly monitor their blood sugar levels to manage the condition. Traditional blood sugar monitoring methods rely on fingertip blood sampling, which is not only inconvenient for patients but also fails to continuously monitor blood sugar changes in real time. With the development of artificial intelligence technology, non-invasive smart wearable devices for blood sugar monitoring have emerged. However, these devices have high requirements for the wearing method, and inaccurate wearing methods can lead to inaccurate blood sugar monitoring.

[0003] A similar prior art Chinese patent application with publication number CN107203700A provides a method and device based on continuous blood glucose monitoring, the method comprising: obtaining blood glucose data of at least two users, forming a first blood glucose data matrix according to a preset data splicing method, obtaining multiple first blood glucose data input vectors and output data corresponding to each first blood glucose data input vector from the first blood glucose data matrix; using a machine learning algorithm, training a preset mathematical model based on multiple groups of first blood glucose data input vectors and output data corresponding to each first blood glucose data input vector to obtain a blood glucose data prediction model; obtaining existing blood glucose data of a user to be predicted, forming a second blood glucose data input vector according to a preset data splicing method; inputting the second blood glucose data input vector into the blood glucose data prediction model to obtain a predicted value of the blood glucose data of the user to be predicted after the current moment.

[0004] A similar prior art includes a Chinese patent application with publication number CN105653865A, which discloses a blood glucose monitoring method, device, and system. The method includes: establishing a food nutrient database; collecting a user's dietary information; fitting a glucose metabolism curve according to the glucose metabolism process; calculating the amount of sugar consumed by the user based on the food nutrient database and the dietary information; calculating the user's glucose change information based on the amount of sugar consumed by the user and the glucose metabolism curve; obtaining the user's historical blood glucose data; and fitting a glucose change curve based on the historical blood glucose data and the glucose change information.

[0005] However, neither of the above two documents considers the problem that the monitored blood sugar may be inaccurate. Therefore, the present invention provides an artificial intelligence-based diabetes blood sugar intelligent monitoring method, system and medium. Summary of the Invention

[0006] The application collects physiological data of a large number of diabetic patients, trains a prediction model for predicting blood glucose level based on physiological indicators based on the physiological data, and judges the blood glucose level monitored by the intelligent wearable device based on the prediction model, to ensure that the correct blood glucose level is monitored.

[0007] To achieve the above-mentioned application purposes, the application provides an artificial intelligence-based intelligent monitoring method for blood glucose of diabetes, which is implemented by performing the following steps:

[0008] S1, collecting personal information of a diabetic patient, the personal information including height, weight, age and medical record data, periodically monitoring physiological data of the diabetic patient, the physiological data including at least blood glucose level, heart rate, blood pressure, skin temperature, skin humidity and monitoring time, and performing transformation processing on the personal information;

[0009] S2, classifying the diabetic patient based on the transformed personal information, obtaining a plurality of different types of diabetic patients, analyzing the physiological data of different types of diabetic patients to obtain analysis results, calculating the correlation score of each physiological indicator and the blood glucose level based on the analysis results, and obtaining a first physiological indicator with a correlation score greater than a preset first threshold;

[0010] S3, taking the first physiological indicator of each type of diabetic patient as input data, taking the blood glucose level detected at the same time as output data, combining the input data and the output data to generate learning data, and using a machine learning algorithm to train the learning data to generate a corresponding prediction model;

[0011] S4, measuring the physiological data of a to-be-monitored patient using an intelligent wearable device, also collecting the personal information of the to-be-monitored patient, obtaining the type to which the to-be-monitored patient belongs based on the personal information, extracting the first physiological indicator from the physiological data and inputting the corresponding prediction model, outputting the predicted blood glucose level from the prediction model, and judging whether the blood glucose level monitored by the intelligent wearable device is accurate based on the predicted blood glucose level.

[0012] As a preferred technical solution of the application, the transformation processing on the personal information also performs the following steps:

[0013] S11, obtaining the data type of each data parameter in the personal information, the data type including numerical type and text type, and obtaining a first data parameter of text data type;

[0014] S12, the first data parameter with the same semantic type is called a second data parameter, a data value of the second data parameter is obtained, a data amount of different data values is obtained, a first code is initialized to zero, a bit number of the first code is the data amount, each data value is sorted in sequence, and each bit of the first code is one-to-one corresponding;

[0015] S13, a data value of the second data parameter is obtained, a bit number corresponding to the data value in the first code is modified to one, the modified first code is converted into decimal data, and the decimal data is taken as a substitute value of the data value.

[0016] As a preferred technical solution of the present application, the diabetic patients are classified based on the standardized personal information, comprising the following steps:

[0017] S211, a plurality of different classification numbers are preset, the personal information is classified multiple times to obtain a plurality of different classification results, and a corresponding classification score is calculated for each classification result;

[0018] S212, a difference absolute value is obtained by subtracting a preset first numerical value from each classification score, a minimum value in the difference absolute value is obtained, and the classification result corresponding to the minimum value is taken as a final classification result.

[0019] As a preferred technical solution of the present application, a corresponding classification score is calculated for each classification result, comprising the following steps:

[0020] S2111, a corresponding first distance is calculated for each data information in the personal information, the first distance refers to the distance between the data information and other data information belonging to the same type, and a first average distance is calculated for each data information corresponding to all first distances;

[0021] S2112, for each type of personal information, a type distance between each type and other types is calculated, and the type with the smallest type distance is taken as the adjacent type of each type;

[0022] S2113, a corresponding second distance is further calculated for each data information in the personal information, the second distance refers to the distance between the data information and the data information of the adjacent type, and a second average distance of a plurality of second distances corresponding to each data information is calculated;

[0023] S2114, a result value obtained by subtracting the first average distance from the second average distance is divided by the second average distance as a first score;

[0024] S2115, calculate an average value of the first scores corresponding to all the data information in the personal information, and take the average value as a classification score corresponding to the classification result.

[0025] As a preferred technical solution of the present application, the correlation score of each physiological indicator and the blood glucose level is calculated, including the following steps:

[0026] S221, randomly select a diabetic patient as a first patient from all diabetic patients, select an arbitrary monitoring time as a first monitoring time from the physiological data of the first patient, and obtain the physiological data corresponding to the first monitoring time as first physiological data;

[0027] S222, obtain a plurality of diabetic patients belonging to the same type as the first patient as second patients, obtain second physiological data of the second patients, and take each physiological indicator in the physiological data except the blood glucose level as a feature physiological indicator. Set the initial correlation score of each feature physiological indicator of each type of patient to zero;

[0028] S223, take the type to which the first patient belongs as a first type, randomly select one from each other type of diabetic patient as a third patient, and obtain third physiological data corresponding to the first monitoring time from the physiological data of each third patient;

[0029] S224, calculate the correlation score of each feature physiological indicator based on the first physiological data, the second physiological data and the third physiological data.

[0030] As a preferred technical solution of the present application, the correlation score of each first physiological indicator is calculated, including the following steps:

[0031] Calculate the first difference value of each feature physiological indicator in the second physiological data and the first physiological data, and also calculate the second difference value of each feature physiological indicator in each third physiological data and the first physiological data. For each feature physiological indicator, calculate a first average value of a plurality of first difference values. If the first average value is less than the second difference value, increase the correlation score corresponding to the feature physiological indicator of the corresponding type of patient by a predetermined second value. If the first average value is less than the second difference value, the correlation score remains unchanged, otherwise, increase the correlation score by a predetermined third value, and the third value is greater than the second value.

[0032] As a preferred technical solution of the present application, a machine learning algorithm is used to train the learning data to generate a prediction model corresponding to the type, including the following steps:

[0033] S31, analyze the relationship complexity between the input data and the output data in the learning data, and select one from a plurality of machine learning algorithms based on the relationship complexity;

[0034] S32, divide the learning data into a first data set and a second data set, and train the selected machine learning algorithm using the first data set;

[0035] S32, during the training process, test the prediction model using the second data set, adjust the model parameters based on the test results, and obtain the final prediction model.

[0036] As a preferred technical solution of the present application, adjusting the model parameters based on the test results comprises the following steps:

[0037] S321, set a corresponding optimization coefficient for the model parameters, set a selection range for the optimization coefficient, and set a plurality of different optimization coefficient combinations in the selection range;

[0038] S322, adjust the model parameters based on each optimization coefficient combination, calculate the corresponding prediction error of the prediction model after adjusting the model parameters, and take the prediction model corresponding to the minimum prediction error as the final prediction model

[0039] The present application also provides an intelligent diabetes blood glucose monitoring system based on artificial intelligence, comprising the following modules:

[0040] The conversion unit is used to collect personal information of a diabetic patient, the personal information including height, weight, age and medical record data, periodically monitor physiological data of the diabetic patient, the physiological data including at least blood glucose level, heart rate, blood pressure, skin temperature, skin humidity and monitoring time, and perform conversion processing on the personal information.

[0041] The classification unit is used to classify the diabetic patient based on the processed personal information, obtain a plurality of different types of diabetic patients, analyze different types of physiological data to obtain analysis results, calculate a correlation score of each physiological indicator and the blood glucose level based on the analysis results, and obtain a first physiological indicator with a correlation score greater than a preset first threshold.

[0042] The prediction unit is used to take the first physiological indicator of each type of diabetic patient as input data, take the blood glucose level detected at the same time as output data, combine the input data and the output data to generate learning data, train the learning data using a machine learning algorithm, and generate a corresponding type of prediction model.

[0043] A judgment unit is used to use a smart wearable device to measure the physiological data of the patient to be monitored, collect the personal information of the patient to be monitored, obtain the type of the patient to be monitored based on the personal information, extract the first physiological indicator from the physiological data and input the corresponding type of prediction model, the prediction model outputs a predicted blood glucose level, and judge whether the blood glucose level monitored by the smart wearable device is accurate based on the predicted blood glucose level.

[0044] The present invention also provides a storage medium storing program instructions, wherein when the program instructions are executed, the device where the storage medium is located is controlled to execute any one of the above-mentioned artificial intelligence-based intelligent diabetes blood glucose monitoring methods.

[0045] Compared with the prior art, the beneficial effects of the present invention are at least as follows:

[0046] In the present invention, a large amount of personal data and physiological data of diabetic patients are collected, and the diabetic patients are classified multiple times based on the personal data to obtain different classification results. The corresponding classification scores are calculated for the different classification results to obtain the best classification result. Each type of diabetic patients is analyzed to obtain the first physiological indicator that contributes most to the prediction of blood glucose level. Learning data is generated based on the first physiological indicator and the blood glucose level. The prediction model corresponding to each type is trained based on the learning data. In the process of training the prediction model, the model parameters are continuously adjusted based on the optimization coefficient to avoid overfitting of the prediction model, thereby improving the prediction accuracy of the prediction model. Based on the blood glucose level predicted by the prediction model, it is judged whether the blood glucose level monitored by the smart wearable device is correct. The present invention can ensure that an accurate blood glucose level is detected. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a flowchart of the steps of the artificial intelligence-based diabetes blood glucose intelligent monitoring method of the present invention;

[0048] Figure 2 This is a structural diagram of the artificial intelligence-based diabetes blood sugar intelligent monitoring system of the present invention. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0050] It is understood that the terms "first," "second," etc., used herein may be used to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script without departing from the scope of this application.

[0051] With the increasing number of diabetic patients, blood glucose monitoring has become an indispensable part of their daily lives. In order to accurately monitor the blood glucose of diabetic patients, the existing technology has realized the non-invasive monitoring of blood glucose levels using smart wearable devices. However, when using smart wearable devices to monitor blood glucose, monitoring errors may occur due to incorrect wearing methods of the smart wearable devices. Therefore, the present invention provides a method for determining whether the blood glucose level monitored by the smart wearable device is accurate.

[0052] Thus, the present invention provides Figure 1 The artificial intelligence-based diabetes blood sugar intelligent monitoring method shown is implemented by executing the following steps:

[0053] S1. Collect personal information of diabetic patients, including height, weight, age and medical history data, periodically monitor physiological data of diabetic patients, including at least blood sugar level, heart rate, blood pressure, skin temperature, skin humidity and monitoring time, and convert personal information.

[0054] Specifically, a large amount of personal information of diabetic patients is collected, and physiological data of diabetic patients are periodically monitored. In order to ensure the accuracy of personal information and physiological data, personal information and physiological data are measured and obtained using standard hospital equipment. After collecting personal information and physiological data, in order to facilitate subsequent use of personal information, the personal information is converted and processed. For example, text-type data in personal information is converted into digital information to facilitate subsequent classification of personal information. The specific steps for converting and processing personal information will be explained in detail later.

[0055] S2. Classify the diabetic patients based on the converted personal information, obtain multiple different types of diabetic patients, analyze the physiological data of the different types of diabetic patients to obtain analysis results, calculate the correlation score between each physiological indicator and blood glucose level based on the analysis results, and obtain a first physiological indicator whose correlation score is greater than a preset first threshold.

[0056] Specifically, different diabetic patients may have different personal circumstances, so diabetic patients are first classified based on personal information, and similar diabetic patients are divided into one category. Subsequently, the prediction model is trained based on the physiological data of each type of diabetic patient to make the prediction model more targeted and at the same time make the prediction accuracy higher. After obtaining different types of diabetic patients, since we have obtained a lot of physiological data, some physiological indicators may not have much effect on the prediction of blood sugar levels. If these physiological indicators are also used as learning data for training the prediction model, the efficiency of training the prediction model will be reduced, and the prediction accuracy of the prediction model will also be reduced. Therefore, by calculating the correlation score between the physiological indicator and the blood sugar level, the first physiological indicator with a correlation score greater than the first threshold is obtained. The first physiological indicator refers to a physiological indicator that has a strong correlation with the blood sugar level. The specific method of calculating the correlation score will be explained in detail later.

[0057] S3. Use the first physiological indicator of each type of diabetic patient as input data, and the blood glucose level detected simultaneously with the first physiological indicator as output data. Combine the input data and the output data to generate learning data, and use a machine learning algorithm to train the learning data to generate a corresponding type of prediction model.

[0058] Specifically, in order to train a prediction model that can accurately predict blood sugar levels, the first physiological indicator of each type of diabetic patient that is strongly correlated with the blood sugar level is used as input data, and the blood sugar level that is detected at the same time as the first physiological indicator, that is, the same detection time, is used as output data. The input data and the output data are combined to generate learning data, and the learning data is trained using a machine learning algorithm to generate a corresponding type of prediction model. The specific training method will be explained in detail later. Subsequently, the physiological data detected in real time can be input into the prediction model, and the prediction model outputs the corresponding predicted blood sugar level. Based on the predicted blood sugar level, it is determined whether the blood sugar level detected using the smart wearable device is correct.

[0059] S4. Use a smart wearable device to measure the physiological data of the patient to be monitored, and also collect the personal information of the patient to be monitored, obtain the type of the patient to be monitored based on the personal information, extract the first physiological indicator from the physiological data and input it into a prediction model of the corresponding type, the prediction model outputs a predicted blood glucose level, and based on the predicted blood glucose level, determine whether the blood glucose level monitored by the smart wearable device is accurate.

[0060] Specifically, the physiological data of the to-be-monitored patient is measured by using the smart wearable device, and personal information of the to-be-monitored patient is also collected, the personal information can be collected in advance before using the smart wearable device, the type of the to-be-monitored patient is determined based on the personal information, a first physiological index is extracted from the physiological data, and the first physiological index is input into a prediction model, a predicted blood glucose level is output by the prediction model, whether the blood glucose level monitored by the smart wearable device is accurate is determined based on the predicted blood glucose level, for example, a difference value can be preset, the predicted blood glucose level is subtracted from the blood glucose level monitored by the smart wearable device to obtain an absolute value of the corresponding difference value, if the absolute value is less than the difference value, it indicates that the blood glucose level monitored by the smart wearable device is accurate, if the absolute value is greater than the difference value, it indicates that the blood glucose level monitored by the smart wearable device is inaccurate, at this time, the smart wearable device can be notified to emit an abnormal sound to prompt the to-be-monitored patient to re-measure.

[0061] Further, the personal information is processed, including the following steps:

[0062] S11, obtaining a data type of each data parameter in the personal information, the data type including a numerical type and a text type, and obtaining a first data parameter of which the data type is text data;

[0063] S12, obtaining a second data parameter of which a semantic type is same as the first data parameter, obtaining a data value of the second data parameter, obtaining a data amount of different data values, initializing a first code as zero, a bit number of the first code being the data amount, sorting each data value in order, and corresponding to each bit of the first code one by one;

[0064] S13, obtaining the data value of the second data parameter, modifying data of the bit number corresponding to the data value in the first code as one, converting the modified first code into a decimal data, and taking the decimal data as a substitute value of the data value.

[0065] Specifically, since some data in the personal information, such as gender and medical record data, can be text type data, when the personal information is classified, some are digital type data and some are text type data, which is not convenient for classification, so the text data in the personal information is processed. First, the first data parameter of the text data is obtained, such as the first data parameter of the text data is male, female, type 1 diabetes, type 2 diabetes, gestational diabetes, special diabetes, etc. The first data parameter of the same semantic type is that male and female belong to the semantic type of gender data parameter, and type 1 diabetes, type 2 diabetes, gestational diabetes, and special diabetes belong to the semantic type of diabetes type data parameter. The first data parameter of the same semantic type is obtained, such as male and female are two second data parameters, and the diabetes type is type 1 diabetes, type 2 diabetes, gestational diabetes, and special diabetes is four second data parameters. Taking the semantic type of diabetes type as an example, there are 4 different parameter values in total, and a first code with a bit number of 4 can be initialized. The four types of diabetes are sorted and one-to-one corresponding to the four bits of the first code. The data value of the diabetes type of the second data parameter is obtained, such as if the data value is type 1 diabetes, the corresponding data value is set to 1000, if the data value is type 2 diabetes, the corresponding data value is set to 0100, if the data value is gestational diabetes, the corresponding data value is set to 0010, and if the data value is special diabetes, the corresponding data value is set to 0001. Then the data value is converted to decimal data, and the decimal data is replaced by the original text data. Through the above method, the text type data is converted to digital type data, which is convenient for subsequent classification of personal information.

[0066] Further, the diabetic patients are classified based on the standardized personal information, including the following steps:

[0067] S211, a plurality of different classification numbers are preset, the personal information is classified a plurality of times, a plurality of different classification results are obtained, and a classification score corresponding to each classification result is calculated;

[0068] S212, each classification score is subtracted from a preset first numerical value to obtain a corresponding difference absolute value, a minimum value in the difference absolute value is obtained, and the classification result corresponding to the minimum value is taken as a final classification result.

[0069] Specifically, in order to accurately classify personal information, first, a plurality of different classification numbers are preset, such as 3, 4 and 5, the personal information can be divided into 3 types, 4 types and 5 types using a classification algorithm such as K-means, 3 different classification results are obtained, and the classification score corresponding to each classification result is also calculated. The classification score represents the accuracy of the classification. If the personal information is divided into too many types, the personal information with high similarity may belong to different types. If the number of types of personal information is too small, the personal information with small similarity may be classified into the same type. Therefore, the accuracy of the classification is judged by calculating the classification score. The specific calculation method will be explained in detail later. Then, the classification score of each classification result is subtracted from the preset first value to obtain the corresponding absolute value of the difference. The absolute value of the difference is the absolute value of the difference. The smaller the absolute value of the difference, the better the classification result and the higher the accuracy of the classification. Therefore, the classification result corresponding to the smallest absolute value of the difference is taken as the final classification result.

[0070] Further, the classification score corresponding to each classification result is calculated, including the following steps:

[0071] S2111, calculate the first distance corresponding to each data information in the personal information. The first distance is the distance between the data information and other data information belonging to the same type. Calculate the first average distance of all first distances corresponding to each data information;

[0072] S2112, for each type of personal information, calculate the type distance between each type and other types, and take the type with the smallest type distance as the adjacent type of each type;

[0073] S2113, for each data information in the personal information, also calculate the second distance corresponding to the data information. The second distance is the distance between the data information and the data information of the adjacent type. Calculate the second average distance of the plurality of second distances corresponding to each data information;

[0074] S2114, divide the result value obtained by subtracting the first average distance from the second average distance by the second average distance as the first score;

[0075] S2115, calculate the average value of the first score corresponding to all data information in the personal information, and take the average value as the classification score of the corresponding classification result.

[0076] Specifically, for each classification result, taking the classification into 3 types as an example, for each data information in each type, the first distance is calculated. The first distance refers to the distance between other data information and data information of the same type as the data information. For example, the 3 types of data are A: {a1, a2, a3, a4}, B: {b1, b2, b3, b4, b5}, C: {c1, c2, c3}. For data information a1, the first distance between a1 and a2, a3, a4 is calculated, and then the average distance of the 3 first distances is calculated as the first average distance. The smaller the first average distance, the higher the aggregation degree of the data within the type, and the better the classification effect. The inter-type distance between A and B and A and C is also calculated. Based on the inter-type distance, the type closest to A is obtained as the adjacent type of A. Assuming that the adjacent type of A is B, the second distance of each data information in type a1 and B is calculated, and the second average distance of the second distance is calculated. The second average distance represents the inter-class distance. The larger the inter-class distance, the greater the difference in data between types, and the better the classification effect. The second average distance minus the first average distance represents the difference between the distance between each data information and its nearest classification and the distance between the same type. A positive value represents a center closer to its own type rather than the center of the adjacent type. The result of the subtraction is divided by the second average distance as the first score, ensuring that the first score is between -1 and 1, so that the first score is not affected by the distance dimension and can be compared across different types of data. The above method is used to calculate the first score of each data information, and then the average of all first scores is calculated. The average value is used as the classification score for the classification results corresponding to the three types. The classification score is the average of the first scores of all data information, taking into account the classification quality of each data information in the personal information. By calculating the average value, a single value is obtained to quantify the classification effect of the personal information. The closer this classification score is to 1, the better the classification effect, so the above first value is set to 1.

[0077] It should be noted that the distance D between two pieces of data can be calculated using the following formula: where x ai Refers to the i-th data parameter in data information a1, x bi It refers to the i-th data parameter in the data information b1, and n refers to the number of data parameters included in the data information.

[0078] It should also be noted that to calculate the inter-type distance between each type and other types, you can first calculate the average value of each data parameter in the data information of each type, combine the average values ​​of each data parameter as the data center of each type, and then use the above formula to calculate the distance between the two data centers as the inter-type distance.

[0079] Further, a correlation score of each physiological indicator and blood glucose level is calculated, including the following steps:

[0080] S221, randomly selecting one diabetic patient as a first patient from all diabetic patients, selecting an arbitrary monitoring time as a first monitoring time from the physiological data of the first patient, and obtaining the physiological data corresponding to the first monitoring time as first physiological data;

[0081] S222, obtaining a plurality of diabetic patients belonging to the same type as the first patient as second patients, obtaining second physiological data of the second patients, and regarding each physiological indicator in the physiological data except the blood glucose level as a characteristic physiological indicator, setting the initial correlation score of each characteristic physiological indicator of each type of patient to zero;

[0082] S223, taking the type to which the first patient belongs as a first type, randomly selecting one from each other type of diabetic patient as a third patient, and obtaining third physiological data corresponding to the first monitoring time from the physiological data of each third patient;

[0083] S224, calculating the correlation score of each characteristic physiological indicator based on the first physiological data, the second physiological data and the third physiological data.

[0084] Specifically, as shown in Table 1, using the physiological indicators with strong correlation with blood glucose level as input data in the form of physiological data can not only improve the training efficiency of the model but also improve the prediction accuracy of the model. In order to calculate the physiological indicators with strong correlation with blood glucose level, the diabetic patients have been classified based on personal information in advance, and an arbitrary diabetic patient is selected as the first patient, for example, patient E is selected as the first patient. Since the physiological data of each diabetic patient is measured periodically, an arbitrary physiological data is selected as the first physiological data. It is assumed that physiological data 1 is selected as the first physiological data. A plurality of physiological data of each patient corresponds to different monitoring times. When calculating the correlation score, only the physiological data of one monitoring time is used. Therefore, the monitoring time of the physiological data is obtained as the first monitoring time, and the first monitoring time is monitoring time 1. A plurality of diabetic patients belonging to the same type as the first patient are selected as the second patient. The first patient belongs to type C. Patients E, G and H in type C are selected as the second patient. The physiological data 1 of the first monitoring time of patients E, G and H is obtained as the second physiological data. Then, the difference value between the same type of patients can be calculated based on the first physiological data and the second physiological data. Patient A in type A is obtained as the third patient, and the physiological data 1 corresponding to the third patient is obtained as the third physiological data. The difference value between different types of patients is calculated based on the first physiological data and the second physiological data. The correlation score of each feature physiological indicator is calculated based on the first physiological data, the second physiological data and the third physiological data. The specific calculation method will be explained in detail later.

[0085]

[0086] Table 1

[0087] Further, the correlation score of each first physiological indicator is calculated, including the following steps:

[0088] The first difference value of each feature physiological indicator in the second physiological data and the first physiological data is calculated, and the second difference value of each feature physiological indicator in the third physiological data and the first physiological data is also calculated. For each feature physiological indicator, the first average value of a plurality of first difference values is calculated. If the first average value is less than the second difference value, the correlation score corresponding to the feature physiological indicator corresponding to the corresponding type of patient is increased by a preset second value. If the first average value is less than the second difference value, the correlation score is unchanged. Otherwise, the third value is increased by a preset third value. The third value is greater than the second value.

[0089] Specifically, for each feature physiological indicator, a corresponding first difference value and a second difference value are calculated, the first difference value is the difference value between the feature physiological indicators of the same type of patients, and the second difference value is the difference value between the feature physiological indicators of different types of patients, a first average value of the first difference is calculated, if the first average value is less than the second difference value, it indicates that the feature physiological indicator has significantly different values between different patients who do not belong to the same patient type, and has similar values between different patients who belong to the same patient type, which indicates that the contribution of the feature physiological indicator to the prediction of the blood glucose level of this type of patient may not be so great, so the corresponding correlation score of the corresponding feature physiological indicator is added by a first value, the first value can be set to 0.1, if the first average value is less than the second difference value, it indicates that the average difference of the feature physiological indicator between different patients who belong to the same patient type is the same as the difference between different patients who do not belong to the same patient type, which indicates that the contribution of the feature physiological indicator to the prediction of the blood glucose level of this type of patient is similar to the contribution to the prediction of the blood glucose level of other types of patients, so no change is made to the corresponding correlation score of the corresponding feature physiological indicator, otherwise, it indicates that the average difference value of the feature physiological indicator between the same type is greater than the difference value between different types of patients, which indicates that the contribution of the feature physiological indicator to the prediction of the blood glucose level of this type of patient may be greater, so the corresponding correlation score of the corresponding feature physiological indicator is added by a second value, the second value can be set to 0.3 or 0.5. In the embodiment, there are three patient types in total, and the corresponding second difference values have two, and the size of the average difference value and the other second difference value is also judged by the above method, and the corresponding correlation score is modified. Through the above method, the correlation score of each feature physiological indicator of different types of patients can be quickly calculated, which facilitates subsequent acquisition of physiological indicators with strong correlation with blood glucose level through the correlation score.

[0090] Further, a machine learning algorithm is used to train the learning data to generate a corresponding type of prediction model, including the following steps:

[0091] S31, analyze the relationship complexity between the input data and the output data in the learning data, and select one from a plurality of machine learning algorithms based on the relationship complexity;

[0092] S32, divide the learning data into a first data set and a second data set, and use the first data set to train the selected machine learning algorithm;

[0093] S32, in the process of training, the second data set is used to test the prediction model, the model parameters are adjusted based on the test result, and the final prediction model is obtained.

[0094] Specifically, since the machine learning algorithm has multiple kinds, such as a decision tree, a random forest model or a neural network model, the relationship complexity between the input data and the output data is analyzed using different analysis methods such as linear relationship and nonlinear relationship analysis, a neural network model is selected based on the relationship complexity to train the first data set, the first data set is a training set, and the second data set is a test set, in the training process, in order to avoid overfitting, the model parameters are adjusted until the prediction model with the minimum prediction error is obtained, and the method for adjusting the model parameters will be explained in detail later.

[0095] Further, the model parameters are adjusted based on the test results, including the following steps:

[0096] S321, set corresponding optimization coefficients for the model parameters, set a selection range for the optimization coefficients, and set a plurality of different optimization coefficient combinations in the selection range;

[0097] S322, adjust the model parameters based on each optimization coefficient combination, calculate the corresponding prediction error of the prediction model after adjusting the model parameters, and take the prediction model corresponding to the minimum prediction error as the final prediction model

[0098] Specifically, the optimization coefficients are preset, the selection range for the optimization coefficients is set, for example, the optimization coefficients include a first coefficient and a second coefficient, the minimum value and the maximum value for the first coefficient and the second coefficient are set, a plurality of different optimization coefficient combinations of the first coefficient and the second coefficient are obtained in the range of the minimum value and the maximum value, the model parameters are adjusted based on each optimization coefficient combination, the prediction error of the prediction model after adjusting the model parameters is calculated based on the second data set, and the prediction model corresponding to the minimum prediction error is taken as the final prediction model. Through the above method, the model parameters can be adjusted based on the optimization coefficients to prevent overfitting of the model and improve the prediction accuracy of the prediction model.

[0099] According to another aspect of the embodiment of the present application, with reference to Figure 2 as shown, a diabetes blood glucose intelligent monitoring system based on artificial intelligence is also provided, which includes a collection unit, an extraction unit, a classification unit and a storage unit, and is used to implement the diabetes blood glucose intelligent monitoring method based on artificial intelligence as described above. The specific functions of each module are as follows:

[0100] The conversion unit is used to collect personal information of the diabetes patient, the personal information including height, weight, age and medical record data, periodically monitor physiological data of the diabetes patient, the physiological data at least including blood glucose level, heart rate, blood pressure, skin temperature, skin humidity and monitoring time, and perform conversion processing on the personal information.

[0101] a classification unit, configured to classify the diabetic patients based on the processed personal information, obtain a plurality of different types of diabetic patients, analyze the different types of physiological data to obtain analysis results, calculate a correlation score between each physiological indicator and the blood glucose level based on the analysis results, and obtain a first physiological indicator having a correlation score greater than a preset first threshold;

[0102] a prediction unit, configured to take a first physiological indicator of each type of diabetic patient as input data, take a blood glucose level detected simultaneously with the first physiological indicator as output data, combine the input data and the output data to generate learning data, and train the learning data using a machine learning algorithm to generate a prediction model of the corresponding type;

[0103] The judgment unit is used to use the smart wearable device to measure the physiological data of the patient to be monitored, collect the personal information of the patient to be monitored, obtain the type of the patient to be monitored based on the personal information, extract the first physiological indicator from the physiological data and input it into a prediction model of the corresponding type, the prediction model outputs a predicted blood glucose level, and judges whether the blood glucose level monitored by the smart wearable device is accurate based on the predicted blood glucose level.

[0104] According to another aspect of an embodiment of the present invention, a storage medium is also provided, which stores program instructions, wherein when the program instructions are executed, the device where the storage medium is located is controlled to execute any of the above-mentioned artificial intelligence-based intelligent diabetes blood glucose monitoring methods.

[0105] In summary, the present invention proposes an artificial intelligence-based intelligent diabetes blood glucose monitoring method, system, and medium. The method includes collecting personal information of diabetic patients, periodically monitoring the physiological data of diabetic patients, and converting and processing the personal information; classifying diabetic patients, analyzing the physiological data of different types of diabetic patients to obtain analysis results, calculating the correlation scores between each physiological indicator and blood glucose level based on the analysis results, and obtaining a first physiological indicator based on the correlation score; using a machine learning algorithm to train the learning data to generate a corresponding type of prediction model; using a smart wearable device to measure the physiological data of the patient to be monitored, obtaining the corresponding type of prediction model, and outputting a predicted blood glucose level from the prediction model. Based on the predicted blood glucose level, the accuracy of the blood glucose level monitored by the smart wearable device is determined. The present invention can ensure the accuracy of blood glucose monitoring for diabetic patients.

[0106] It should be understood that, although the steps in the flowcharts of the embodiments of the present application are shown in a certain order according to the arrows, the steps are not necessarily executed in the order of the arrows. Unless otherwise specified herein, the execution of the steps is not strictly limited in order, and the steps can be executed in other orders. Moreover, at least some of the steps in the embodiments can include a plurality of sub-steps or a plurality of stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of the sub-steps or stages is not necessarily sequential, but can be round-robin or alternately executed with other steps or sub-steps or stages of other steps.

[0107] It can be understood by those skilled in the art that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware. The above-mentioned program can be stored in a non-volatile computer readable storage medium, and when the program is executed, it can include the processes of the above-mentioned embodiments of the methods. Any reference to memory, storage, database or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0108] The technical features of the above-mentioned embodiments can be combined in any way. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described, but as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0109] The above embodiments are only some embodiments of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled persons in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of protection of the present application. Therefore, the scope of protection of the patent of the present application should be subject to the appended claims.

[0110] The above is only a preferred embodiment of the present application, and does not limit the present application. Any modification, equivalent replacement and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An artificial intelligence-based diabetes blood sugar intelligent monitoring method, characterized in that: include: S1. Collect personal information of diabetic patients, including height, weight, age, and medical history data; periodically monitor physiological data of diabetic patients, including at least blood glucose level, heart rate, blood pressure, skin temperature, skin humidity, and monitoring time; and convert the personal information; S2. Classify diabetic patients based on the converted personal information, obtain multiple different types of diabetic patients, analyze the physiological data of the different types of diabetic patients to obtain analysis results, calculate correlation scores between each physiological indicator and blood glucose level based on the analysis results, and obtain a first physiological indicator with a correlation score greater than a preset first threshold; S3. Use the first physiological indicator of each type of diabetic patient as input data and the blood glucose level detected simultaneously with the first physiological indicator as output data, combine the input data and the output data to generate learning data, and use a machine learning algorithm to train the learning data to generate a prediction model of the corresponding type; S4. Use a smart wearable device to measure the physiological data of the patient to be monitored, and also collect the personal information of the patient to be monitored, obtain the type of the patient to be monitored based on the personal information, extract the first physiological indicator from the physiological data and input it into the prediction model of the corresponding type, the prediction model outputs a predicted blood glucose level, and judge whether the blood glucose level monitored by the smart wearable device is accurate based on the predicted blood glucose level; S1 includes obtaining the data type of each data parameter in the personal information, the data types including numeric type and text type, obtaining a first data parameter whose data type is text data; obtaining a first data parameter with the same semantic type as the second data parameter, obtaining a data value of the second data parameter, obtaining a data amount of different data values, initializing a first code to zero, the number of bits of the first code as the data amount, sorting each data value in sequence, and corresponding one-to-one with each bit of the first code; obtaining the data value of the second data parameter, modifying the data of the bit corresponding to the data value in the first code to one, converting the modified first code into decimal data, and using the decimal data as a replacement value for the data value; S2 includes S211, presetting a plurality of different classification numbers, classifying the personal information multiple times, obtaining a plurality of different classification results, and calculating a corresponding classification score for each classification result; S212: Subtract each classification score from a preset first value to obtain the corresponding absolute value of the difference, obtain the minimum value among the absolute values ​​of the difference, and use the classification result corresponding to the minimum value as the final classification result; S211 includes calculating a corresponding first distance for each piece of data information in the personal information, where the first distance refers to the distance between other data information of the same type as the data information, and calculating a first average distance for all first distances corresponding to each piece of data information; calculating an inter-type distance between each type and other types for each type of personal information, and taking the type with the smallest inter-type distance as the adjacent type of each type; further calculating a corresponding second distance for each piece of data information in the personal information, where the second distance refers to the distance between the data information and data information of an adjacent type, and calculating a second average distance of multiple second distances corresponding to each piece of data information; and dividing the result obtained by subtracting the first average distance from the second average distance by the second average distance as a first score; Calculate the average of the first scores corresponding to all data information in the personal information, and use the average as the classification score of the corresponding classification result.

2. The method according to claim 1, characterized in that Calculating the correlation scores between each physiological indicator and blood glucose level includes the following steps: S221. Randomly select a diabetic patient from all diabetic patients as a first patient, select any monitoring time from the physiological data of the first patient as a first monitoring time, and obtain physiological data corresponding to the first monitoring time as first physiological data; S222. Acquire multiple diabetic patients of the same type as the first patient as second patients, acquire second physiological data of the second patients, refer to each physiological indicator in the physiological data except the blood glucose level as a characteristic physiological indicator, and set an initial correlation score of each characteristic physiological indicator of each type of patient to zero; S223: Specify the type of the first patient as the first type, arbitrarily select one diabetic patient from each of the other types as a third patient, and obtain third physiological data corresponding to the first monitoring time from the physiological data of each third patient; S224 : Calculate a correlation score of each characteristic physiological indicator based on the first physiological data, the second physiological data, and the third physiological data.

3. The method according to claim 2, characterized in that Calculating the correlation score of each first physiological indicator includes the following steps: Calculate the first difference value of each characteristic physiological indicator between the second physiological data and the first physiological data, and also calculate the second difference value of each characteristic physiological indicator between each third physiological data and the first physiological data. For each characteristic physiological indicator, calculate the first average value of multiple first difference values. If the first average value is less than the second difference value, increase the correlation score corresponding to the characteristic physiological indicator corresponding to the corresponding type of patient by a preset second value. If the first average value is less than the second difference value, the correlation score remains unchanged. Otherwise, increase the preset third value, and the third value is greater than the second value.

4. The method according to claim 3, characterized in that Using machine learning algorithms to train learning data to generate corresponding types of prediction models includes the following steps: S31. Analyze the complexity of the relationship between input data and output data in the learning data, and select one of multiple machine learning algorithms based on the complexity of the relationship; S32. Divide the learning data into a first data set and a second data set, and use the first data set to train the selected machine learning algorithm; S32. During the training process, the prediction model is tested using the second data set, and the model parameters are adjusted based on the test results to obtain a final prediction model.

5. The method according to claim 4, characterized in that Adjust the model parameters based on the test results, including the following steps: S321, setting corresponding optimization coefficients for model parameters, setting a selection range for the optimization coefficients, and setting multiple different optimization coefficient combinations within the selection range; S322. Adjust the model parameters based on each optimization coefficient combination, calculate the corresponding prediction error for the prediction model after adjusting the model parameters, and use the prediction model corresponding to the minimum prediction error as the final prediction model.

6. An artificial intelligence-based diabetes blood sugar intelligent monitoring system, used to implement the artificial intelligence-based diabetes blood sugar intelligent monitoring method according to any one of claims 1 to 5, characterized in that: Includes the following modules: A conversion unit is used to collect personal information of diabetic patients, including height, weight, age, and medical history data, periodically monitor physiological data of diabetic patients, including at least blood sugar level, heart rate, blood pressure, skin temperature, skin humidity, and monitoring time, and convert the personal information; a classification unit, configured to classify the diabetic patients based on the processed personal information, obtain a plurality of different types of diabetic patients, analyze the different types of physiological data to obtain analysis results, calculate a correlation score between each physiological indicator and the blood glucose level based on the analysis results, and obtain a first physiological indicator having a correlation score greater than a preset first threshold; a prediction unit, configured to take a first physiological indicator of each type of diabetic patient as input data, take a blood glucose level detected simultaneously with the first physiological indicator as output data, combine the input data and the output data to generate learning data, and train the learning data using a machine learning algorithm to generate a prediction model of the corresponding type; The judgment unit is used to use the smart wearable device to measure the physiological data of the patient to be monitored, collect the personal information of the patient to be monitored, obtain the type of the patient to be monitored based on the personal information, extract the first physiological indicator from the physiological data and input it into a prediction model of the corresponding type, the prediction model outputs a predicted blood glucose level, and judges whether the blood glucose level monitored by the smart wearable device is accurate based on the predicted blood glucose level.

7. A storage medium, characterized in that: The storage medium stores program instructions, wherein when the program instructions are executed, the device where the storage medium is located is controlled to execute the artificial intelligence-based diabetes blood glucose intelligent monitoring method according to any one of claims 1 to 5.

Images