Intelligent equipment use monitoring system and method based on big data

Abstract

The invention relates to the technical field of equipment intelligent monitoring, in particular to an equipment use intelligent monitoring system and method based on big data, and the system comprises a data management platform construction module, a differential user extraction module, a preliminary unit early warning index analysis module, a monitoring sequence pair analysis module, a critical early warning sequence pair analysis module and an early warning response module. The data management platform construction module constructs a data management platform with a hospital management platform terminal, a mobile intelligent device and a monitoring device as main bodies. The differential user extraction module is used for comparing the first user data with the second user data; the preliminary unit early warning index analysis module is used for calculating and analyzing a preliminary unit early warning index of the differential user; the monitoring sequence pair analysis module is used for analyzing and generating a monitoring sequence pair corresponding to the differential user; the critical early warning sequence pair analysis module is used for determining a critical early warning sequence pair of the monitoring equipment; and the early warning response module is used for performing early warning response according to the output result of the critical early warning sequence pair.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent monitoring, evaluation and management, and specifically provides an intelligent monitoring system and method for device usage based on big data. Background Art

[0002] With the adaptation and implementation of the medical system and the Internet, more and more 5G data management platforms are applied to the medical system to bring the greatest convenience to users and realize the intelligent dataization of the medical system; nowadays, in the development process of fetal heart monitors, there have emerged home portable fetal heart monitors. The emergence of this product enables pregnant women to simply understand the heart rate of their fetuses without leaving home, avoiding the damage to the body caused by the trouble of pregnant women traveling back and forth to medical institutions; however, at the same time, the emergence of portable fetal heart monitors lacks the guidance of professional technical personnel. During the independent use process by users, there are often deviations in the amount of coupling agent required for the fetal heart monitor, resulting in inaccurate output data of the monitoring device due to too little usage, increasing the psychological burden of pregnant women and reducing the effective usage rate of fetal heart monitoring devices. Summary of the Invention

[0003] The purpose of the present invention is to provide an intelligent monitoring system and method for device usage based on big data to solve the problems raised in the above background art.

[0004] To solve the above technical problems, the present invention provides the following technical solution: An intelligent monitoring method for device usage based on big data, the method comprising the following steps: Step S1: Construct a data management platform with the hospital management platform terminal, mobile intelligent device, and monitoring device as the main body. The data management platform records the first user data transmitted by the monitoring device and the second user data transmitted by the hospital management platform terminal; compare and analyze the first user data and the second user data to determine the differential users and extract the differential data corresponding to the differential users; Step S2: Divide the user monitoring frequency period with the recorded users and monitoring data in the data management platform as the carrier. Based on the user monitoring frequency period, calculate and analyze the preliminary unit warning index of the differential users; Step S3: Based on the preliminary unit warning index, analyze the trend relationship between the first user data of the differential users recorded in the data management platform and the preliminary unit warning index and generate a monitoring sequence pair corresponding to the differential users. The monitoring sequence pair consists of the preliminary unit warning index and the first user data; Step S4: Obtain other users in the data management platform who are excluded from the differential users and have no record of the second user data as the standard users; extract the first user data of the standard users and compare and analyze it with the monitoring sequence pair to determine the critical warning sequence pair of the monitoring device and perform a warning response.

[0005] Further, in step S1, the first user data and the second user data are compared and analyzed to extract differential user data, including the following analysis steps: The first user data includes monitoring result data, monitoring medium usage, and user status data. The user status data includes the usage duration t of the user using the monitoring device, the state change amount q before and after the user uses the monitoring device, and the attribute characteristics corresponding to the user using the monitoring device; The usage duration refers to the cycle duration corresponding to when the user turns on the monitoring device until the monitoring device outputs monitoring result data that meets the user status evaluation criteria; Meeting the user status evaluation criteria includes normal status evaluation criteria and abnormal status evaluation criteria; The state change amount refers to the ratio of the change amount of the user's weight when currently using the monitoring device to the initial weight compared to the weight before first using the monitoring device; That is, q i =(w i -w0) / w0, where w0 represents the weight of the user before first using the monitoring device, and w i represents the weight of the i-th user when currently using the monitoring device, and q i represents the state change amount of the i-th user; Analyzing the change amount of weight is because from an objective factual perspective, there are obvious differences in the weights of pregnant women in different gestational age cycles. Therefore, analyzing from the state change amount can effectively obtain the influence relationship of the amount of coupling agent used when using the fetal heart rate monitoring device; The second user data refers to the target result data obtained by secondary detection and recording of the monitoring result data in the first user data at the hospital end; Extract the users in the data management platform who have monitoring result data and second user data as target users, and obtain the target result data and monitoring result data corresponding to the target users; When the types of the target result data and the monitoring result data are inconsistent, output the target users as differential users, and the first user data corresponding to the differential users is differential data. The data types include the normal state corresponding to the normal state evaluation criteria and the abnormal state corresponding to the abnormal state evaluation criteria. Determining differential users is for further judgment and analysis when users obtain inaccurate data after using the monitoring device to improve the result accuracy when users independently use the monitoring device, as well as for quantitative analysis of influencing factors.

[0006] Further, step S2 includes the following analysis steps: Divide into n user monitoring frequency cycles. The n user monitoring frequency cycles refer to the user dividing from 1 to 10 months into n cycles in units of months; Based on the user monitoring frequency period, the records of users in the data management platform are divided into n differential user sets according to the attribute characteristics when using the monitoring device corresponding to the monitoring frequency period, and the attribute characteristics, usage duration, and status change amount of the users in the differential user sets are paired with the monitoring medium usage amount when the user uses the monitoring device to form differential element pairs [A ij →(q ij ,t ij ,j)]; j represents the jth user monitoring frequency period, j ≤ n; A ij represents the monitoring medium usage amount recorded by the ith differential user using the monitoring device in the jth user monitoring frequency period; q ij represents the status change amount recorded by the ith differential user using the monitoring device in the jth user monitoring frequency period; t ij represents the usage duration recorded by the ith differential user using the monitoring device in the jth user monitoring frequency period; Using the formula: r ij =a1*q ij +a2*t ij Calculate the preliminary unit warning index r of the ith differential user in the jth user monitoring frequency period ij ; where a1 represents the reference coefficient corresponding to the status change amount, a2 represents the reference coefficient corresponding to the usage duration, a1 + a2 = 1, 1 > a1 > 0, 1 > a2 > 0.

[0007] Further, step S3 includes the following analysis steps: Extract the preliminary unit warning index corresponding to the n differential user sets and the monitoring medium usage amount A in the differential element pairs ij ; The monitoring medium usage amounts of different differential users in the jth differential user set form a medium analysis set J j , J j ={A 1j ,A 2j ,A 3j ,......,A ij} j ; Select the maximum value in the jth medium analysis set J j as max[J j , max[J j =max{A 1j ,A 2j ,A 3j ,......,A ij} j ; Output the maximum value max[J in the jth medium analysis set jThe preliminary unit warning index in the corresponding differential element pair is the target warning index, and the user corresponding to the target warning index is the first user to be analyzed; Extract the preliminary unit warning index r of the i-th differential user in the j-th differential user set ij , and output the maximum value max[r ij in the preliminary unit warning index r ij j The corresponding user is the second user to be analyzed; Calculate the average medium consumption A corresponding to the j-th differential user set 0j , A 0j =(1 / m)[∑A ij ; and the average warning index r corresponding to the j-th differential user set 0j , r 0j =(1 / m)[∑r ij ; i ≤ m, where m represents the total number of users recorded in the differential set; Sort the n differential user sets in descending order according to the value of the average medium consumption, generate the first sequence of differential user sets, and sort the n differential user sets in descending order according to the value of the average warning index, generate the second sequence of differential user sets; If the trend relationship is: the first user to be analyzed is the same as the second user to be analyzed and the first sequence is the same as the second sequence, output the monitoring sequence pair Uj of the j-th differential user set, Uj={max[J j , max[r ij j}; If it does not satisfy that the first user to be analyzed is the same as the second user to be analyzed and the first sequence is the same as the second sequence, then output the maximum value D in the n medium analysis sets J j , D = max{J1, J2, J3,......, J n}.

[0008] Further, step S4 includes the following analysis steps: When there is a monitoring sequence pair, match the standard users in the data management platform with the differential user sets according to the attribute characteristics; after the matching is completed, extract the minimum value B0 of the monitoring medium consumption corresponding to the standard users with the same attribute characteristics, and calculate the average standard warning index e0 of the standard users corresponding to the same attribute characteristics; the calculation method of the average standard warning index is the same as the above calculation method of the average warning index; If B0 > max[J j and |e0 - r 0j | ≤ s, where s is a preset difference threshold, then output the critical warning sequence as V 1j , V 1j={j → max[J j}; B0 > max[J j indicates that in the first user data of the standard user, a certain amount of monitoring medium usage can meet the user's use of the monitoring device and data output; |e0 - r 0j | ≤ s indicates that the influencing factor indicators corresponding to the differential users with the same attribute characteristics of the standard user are similar, achieving variable control; and according to the critical warning sequence, for the users within the j-th user monitoring frequency period, a warning reminder is given for the corresponding monitoring medium usage max[J j . If B0 > max[J j and |e0 - r 0j | ≤ s are not satisfied, or when there is no monitoring sequence pair, then the critical warning sequence V 2j , V 2j = {j → D} is output; and according to the critical warning sequence, for the users within the j-th user monitoring frequency period, a warning reminder is given for the monitoring medium usage D. When the judgment condition is not satisfied, the maximum value of the coupling agent used in the abnormal data recorded in the data management platform is used as the reminder usage when the user uses the coupling agent during the entire period, which can avoid the inaccurate fetal heart rate monitoring caused by the problem of coupling agent usage to the greatest extent, and when obtaining the critical values of the coupling agent usage corresponding to different periods, the purpose of saving the coupling agent usage can be achieved according to the analysis results; because during the fetal heart rate monitoring process, the role of the coupling agent is to make the probe closely adhere to the abdominal wall, prevent air from existing between the probe and the belly to cause noise, or prevent the heard sound from being the heart rate sound of the pregnant woman herself, so when the user operates independently, it is often difficult to accurately grasp the amount of the coupling agent, increasing the possibility of errors in the monitoring results.

[0009] An intelligent monitoring system for device usage based on big data, characterized in that the system includes a data management platform construction module, a differential user extraction module, a preliminary unit warning index analysis module, a monitoring sequence pair analysis module, a critical warning sequence pair analysis module, and a warning response module; The data management platform construction module is used to construct a data management platform with the hospital management platform terminal, mobile intelligent device, and monitoring device as the main body; the data management platform records the first user data transmitted by the monitoring device and the second user data transmitted by the hospital management platform terminal; The differential user extraction module is used to compare and analyze the first user data and the second user data to determine the differential users and extract the differential data corresponding to the differential users; The preliminary unit warning index analysis module is used to calculate and analyze the preliminary unit warning index of the differential users; The monitoring sequence pair analysis module is used to analyze the trend relationship between the first user data of differential users recorded in the data management platform and the preliminary unit warning index, and generate the monitoring sequence pair corresponding to the differential users; The critical warning sequence pair analysis module is used to extract the first user data of standard users and compare and analyze it with the monitoring sequence pair to determine the critical warning sequence pair of the monitoring device; The warning response module is used to perform warning response based on the output result of the critical warning sequence pair.

[0010] Furthermore, the preliminary unit warning index analysis module includes a monitoring frequency period division unit, a differential user set extraction unit, a differential element pair construction unit, and a preliminary unit warning index calculation unit; The monitoring frequency period division unit is used to divide n user monitoring frequency periods; The differential user set extraction unit is used to divide the recorded users in the data management platform into n differential user sets according to the attribute characteristics when using the monitoring device corresponding to the monitoring frequency period; The differential element pair construction unit is used to form differential element pairs from the attribute characteristics, usage duration, and state change amount of users in the differential user set and the monitoring medium usage amount when the users use the monitoring device; The preliminary unit warning index calculation unit is used to calculate the preliminary unit warning index according to the user state change amount and usage duration.

[0011] Furthermore, the monitoring sequence pair analysis module includes a monitoring medium set analysis unit, a user to be analyzed extraction unit, a sequence generation unit, and a monitoring sequence pair output unit; The monitoring medium set analysis unit is used to extract the preliminary unit warning index corresponding to the differential user set and the monitoring medium usage amount in the differential element pair, and form a medium analysis set from the monitoring medium usage amounts of different differential users in the differential user set; The user to be analyzed extraction unit is used to determine the first user to be analyzed based on the monitoring medium usage amount and the second user to be analyzed based on the preliminary unit warning index; The sequence generation unit is used to sort the differential user set based on the average medium usage amount and the average warning index to generate the first sequence and the second sequence; The monitoring sequence pair output unit is used to output the corresponding monitoring sequence pair based on the comparison result output by the sequence generation unit.

[0012] Furthermore, the critical warning sequence pair analysis module includes a standard user division unit, an attribute feature matching unit, and a critical warning sequence output unit; The standard user division unit is used to obtain other users in the data management platform except for differential users and without second user data records as standard users; The attribute feature matching unit is used to match the standard users in the data management platform with the differential user set according to the attribute features, and after the matching is completed, extract the minimum value of the monitoring medium usage corresponding to the standard users with the same type of attribute features, and calculate the average value of the standard warning indexes corresponding to the standard users with the same type of attribute features; The critical warning sequence output unit gives early warning reminders for the corresponding medium usage of users in different monitoring frequency periods based on the output results of the attribute feature matching unit.

[0013] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: By analyzing the abnormal data output by the fetal heart monitoring device and the influencing factors affecting the fetal heart abnormality, the present invention distinguishes the user data in different gestational age periods to realize the specific analysis of the usage of the coupling agent by users in the smallest range, retains the objective regularity of users in different monitoring periods, realizes the intelligent management when users independently use the fetal heart monitoring device, starts from the user input perspective, improves the accuracy and efficiency of the effective output of the actual state value of users when they independently use the fetal heart monitoring device, avoids the possibility of errors in the monitoring results caused by inaccurate grasping of the amount of coupling agent during user independent operation, and realizes the intelligent reminder of restricting the amount of use according to specific situations. Description of the Drawings

[0014] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention, and do not constitute a limitation to the present invention. In the drawings: Figure 1 is a schematic structural diagram of an intelligent monitoring system for device usage based on big data according to the present invention. Detailed Embodiments

[0015] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0016] Please refer to Figure 1 , the present invention provides a technical solution: An intelligent monitoring method for device usage based on big data, the method includes the following steps: Step S1: Construct a data management platform with the hospital management platform terminal, mobile intelligent device, and monitoring device as the main body. The data management platform records the first user data transmitted by the monitoring device and the second user data transmitted by the hospital management platform terminal; compare and analyze the first user data and the second user data to determine the differential users and extract the differential data corresponding to the differential users; in this application, the mobile intelligent device is a fetal heart rate monitoring device; As in the prior art, a hospital uses a remote fetal heart rate monitoring system. By connecting the instrument to a mobile phone and a hospital terminal through the mobile Internet and installing a specified software on the smartphone, a user can monitor the fetal heart rate at home by himself / herself. After uploading the monitoring data through the mobile phone, the hospital terminal can obtain the monitoring data of the corresponding user; Step S2: Divide the user monitoring frequency period with the recorded users and monitoring data in the data management platform as the carrier. Based on the user monitoring frequency period, calculate and analyze the preliminary unit warning index of the differential users; Step S3: Based on the preliminary unit warning index, analyze the trend relationship between the first user data of the differential users recorded in the data management platform and the preliminary unit warning index and generate a monitoring sequence pair corresponding to the differential users. The monitoring sequence pair is composed of the preliminary unit warning index and the first user data; Step S4: Obtain other users in the data management platform who exclude the differential users and have no record of the second user data as the standard users; extract the first user data of the standard users and compare and analyze it with the monitoring sequence pair to determine the critical warning sequence pair of the monitoring device and perform a warning response.

[0017] In Step S1, when comparing and analyzing the first user data and the second user data and extracting the differential user data, the following analysis steps are included: The first user data includes monitoring result data, monitoring medium usage, and user status data. The user status data includes the usage duration t of the user using the monitoring device, the state change amount q before and after the user uses the monitoring device, and the attribute characteristics corresponding to the user using the monitoring device; in this application, the attribute characteristic refers to the gestational age cycle when the user uses the monitoring device; the monitoring medium usage is input into the data management platform manually. The fetal heart rate monitor device provides a certain amount of coupling agent, such as a 10g coupling agent per piece on the market, and the user inputs and records the data according to the actual usage amount; The usage duration refers to the cycle duration corresponding to the period from when the user turns on the monitoring device until the monitoring device outputs monitoring result data that meets the user status evaluation criteria; meeting the user status evaluation criteria includes normal status evaluation criteria and abnormal status evaluation criteria; meeting the user status evaluation criteria is based on the monitoring device. If the monitoring device is a portable fetal heart monitor device, then meeting the user normal status evaluation criteria at this time means that regular signals or clear sounds are detected and the corresponding monitoring result data can be output; meeting the user abnormal status evaluation criteria means that no clear sound appears or there are no regular signals within the specified duration. The state change amount refers to the ratio of the change amount between the user's weight when currently using the monitoring device and the weight before initially using the monitoring device to the initial weight; that is, q i =(w i - w0) / w0, where w0 represents the weight of the user before initially using the monitoring device, and w i represents the weight of the i-th user when currently using the monitoring device, and q i represents the state change amount of the i-th user; Analyzing the change amount of weight is because from an objective factual perspective, there are obvious differences in the weights of pregnant women in different gestational age cycles. Therefore, analyzing from the state change amount can effectively obtain the influence relationship of the amount of coupling agent used when using the fetal heart monitoring device. The second user data refers to the target result data obtained by performing secondary detection and recording on the monitoring result data in the first user data at the hospital end. Extract the users in the data management platform who have monitoring result data and second user data as target users, and obtain the corresponding target result data and monitoring result data of the target users; when the types of the target result data and the monitoring result data are inconsistent, output the target users as differential users, and the first user data corresponding to the differential users is differential data. The data types include the normal state corresponding to the normal state evaluation criteria and the abnormal state corresponding to the abnormal state evaluation criteria. Determining the differential users is for further judgment and analysis when the users obtain inaccurate data after using the monitoring device, in order to improve the accuracy of the results when the users independently use the monitoring device and for quantitative analysis of the influencing factors.

[0018] As shown in the embodiment: During the process of the user independently using the fetal heart monitoring device, set the user normal state evaluation criteria to 120 - 160 beats / 1min, and the abnormal state evaluation criteria to no sound detected within 3 minutes or less than 120 beats / 1min or higher than 160 beats / 1min; if the monitoring result data of the user independently using the fetal heart monitor is 90 beats / 1min, then the monitoring device outputs the monitoring result data as the user's abnormal state, and the second user data is 126 beats / 1min, then the corresponding target result data is the user's normal state; therefore, it shows that the types of the target result data and the monitoring result data are inconsistent. In this application, after setting the monitoring device to output the normal state of the user and storing the corresponding data in the data management platform, there is no need to go to the hospital for secondary detection. If the monitoring device outputs abnormal state data of the user, the user needs to perform secondary detection in a medical institution and record it in the data management platform in the form of second user data; and the monitoring device in this application is a device without faults. Since there are usually fault reminders for devices with faults in the prior art, the impact of the faults of the device itself is not analyzed.

[0019] Step S2 includes the following analysis steps: Divide into n user monitoring frequency cycles. The n user monitoring frequency cycles refer to dividing the months from 1 to 10 into n cycles with months as the unit for the user; in actual applications, it is divided according to the monitoring object attribute characteristics of the monitoring device used by the user. For example, when using a fetal heart monitor, the monitoring object attribute is the monitoring frequency of the pregnant woman's pregnancy growth cycle. Therefore, it is generally divided into the first cycle from January to May, the second cycle from June to August, and the third cycle from September to October; Based on the user monitoring frequency cycles, divide the users recorded in the data management platform into n differential user sets according to the monitoring frequency cycles corresponding to the attribute characteristics when using the monitoring device, and form differential element pairs with the attribute characteristics, usage duration, and state change amount of the users in the differential user sets and the monitoring medium usage amount when the user uses the monitoring device [A ij →(q ij ,t ij ,j); j represents the jth user monitoring frequency cycle, j ≤ n; A ij represents the monitoring medium usage amount recorded by the ith differential user using the monitoring device in the jth user monitoring frequency cycle; q ij represents the state change amount recorded by the ith differential user using the monitoring device in the jth user monitoring frequency cycle; t ij represents the usage duration recorded by the ith differential user using the monitoring device in the jth user monitoring frequency cycle; Use the formula: r ij =a1*q ij +a2*t ij Calculate the preliminary unit warning index r of the ith differential user in the jth user monitoring frequency cycle ij ; where a1 represents the reference coefficient corresponding to the state change amount, a2 represents the reference coefficient corresponding to the usage duration, a1 + a2 = 1, 1 > a1 > 0, 1 > a2 > 0.

[0020] Step S3 includes the following analysis steps: Extract the preliminary unit warning indexes corresponding to the n differential user sets and the monitoring medium usage amount A in the differential element pairs ij ; Construct a medium analysis set J from the monitoring medium usage amounts of different differential users in the j-th differential user set j , J j = {A 1j , A 2j , A 3j ,......, A ij} j ; Select the maximum value in the j-th medium analysis set J j as max[J j , max[J j = max{A 1j , A 2j , A 3j ,......, A ij} j ; Output the preliminary unit warning index in the differential element pair corresponding to the maximum value max[J j in the j-th medium analysis set as the target warning index, and the user corresponding to the target warning index is the first user to be analyzed; Extract the preliminary unit warning index r ij of the i-th differential user in the j-th differential user set, and output the maximum value max[r ij in the preliminary unit warning index r ij in the j-th differential user set j ; The user corresponding to it is the second user to be analyzed; Calculate the average medium usage amount A 0j corresponding to the j-th differential user set, A 0j = (1 / m)[∑A ij ; And the average warning index r 0j corresponding to the j-th differential user set, r 0j = (1 / m)[∑r ij ; i ≤ m, where m represents the total number of users recorded in the differential set; Sort the n differential user sets in descending order according to the value of the average medium usage amount to generate the first sequence of differential user sets, and sort the n differential user sets in descending order according to the value of the average warning index to generate the second sequence of differential user sets; If the trend relationship is: the first user to be analyzed is the same as the second user to be analyzed and the first sequence is the same as the second sequence, output the monitoring sequence pair Uj of the j-th differential user set, Uj = {max[J j , max[r ij j}; If it does not satisfy that the first user to be analyzed is the same as the second user to be analyzed and the first sequence is the same as the second sequence, then output the n medium analysis sets J​j The maximum value D in it, D = max{J1, J2, J3,......, J n}.

[0021] In this application, monitoring the dosage of the medium refers to the coupling agent that needs to be equipped and used during the use of a fetal heart monitor device. The dosage of the coupling agent affects the output of the device results. At the same time, there are also differences in the positions for monitoring the fetal heart using the monitoring device during different gestational age cycles. The weight reflects the body shape changes caused by the differences in the user's cycles. The increase in the monitoring area makes the dosage of the coupling agent different, which will also affect the time. When the first user to be analyzed is the same as the second user to be analyzed, it means that among the abnormal data corresponding to the differential users, there is a corresponding warning relationship between the dosage of the coupling agent caused by the influencing factors of the users within the same cycle, that is, when the maximum value of the comprehensive index calculated by the influencing factors recorded in the differential data corresponds to the maximum dosage of the coupling agent and the device data output is still in an abnormal state, it means that this data can be used as the preliminary warning value for the differential users within the corresponding cycle. The reason for using it as the preliminary warning value is that it is not clear whether the maximum value analyzed at this time is the critical value. Analyzing adjacent user sets is because there will be obvious differences in the weights of the users in the adjacent user sets. If the dosages of the coupling agent corresponding to different weights show regularity at this time, it further indicates that there is a trend relationship between the dosage of the coupling agent and the influencing factors.

[0022] Step S4 includes the following analysis steps: When there is a monitoring sequence pair, match the standard users in the data management platform with the differential user set according to the attribute characteristics. For example, if the attribute characteristic recorded in the standard user is 3 months, then the first differential user set (January - May) is matched; after the matching is completed, extract the minimum value B0 of the monitoring medium dosage corresponding to the standard users with the same type of attribute characteristics, and calculate the average value e0 of the standard warning index corresponding to the standard users with the same type of attribute characteristics; the calculation method of the average value of the standard warning index is the same as the above warning index average value calculation method; If B0 > max[J j and |e0 - r 0j | ≤ s, where s is a preset difference threshold, then output the critical warning sequence as V 1j , V 1j = {j → max[J j}; B0 > max[J j indicates that in the first user data of the standard users, a certain dosage of the monitoring medium can meet the user's use of the monitoring device and the output of the data; |e0 - r 0j | ≤ s indicates that the influencing factor indexes corresponding to the differential users with the same attribute characteristics of the standard users are similar, realizing the control of variables; and monitor the corresponding users within the monitoring frequency cycle of the jth user according to the critical warning sequence for the maximum dosage of the monitoring medium max[J jWarning reminder; If B0 > max[J is not satisfied j and |e0 - r 0j | ≤ s, or when there is no monitoring sequence pair, the critical warning sequence is output as V 2j , V 2j = {j → D}; and a warning reminder for the user's monitoring medium usage D within the monitoring frequency period of the j-th user is carried out according to the critical warning sequence. When the judgment condition is not satisfied, the maximum value of the coupling agent used in the abnormal data recorded in the data management platform is used as the reminder usage when the user uses the coupling agent during the entire period, which can avoid the inaccurate fetal heart rate monitoring caused by the problem of the coupling agent usage to the greatest extent. When obtaining the critical values of the coupling agent usage corresponding to different periods, the purpose of saving the coupling agent usage can be achieved according to the analysis results; because during the fetal heart rate monitoring process, the role of the coupling agent is to make the probe close to the abdominal wall, prevent air from existing between the probe and the belly to cause noise, or prevent the sound heard from being the heart rate sound of the pregnant woman herself, so when the user operates independently, it is often difficult to accurately grasp the amount of the coupling agent, increasing the possibility of errors in the monitoring results.

[0023] And reminding different users with different amounts is to prevent the uncontrollability caused by the user's inability to accurately grasp the amount and the generation of abnormal data; at the same time, since the operation is carried out by individuals without medical staff monitoring, there are differences in the amount used. Simply emphasizing a large amount cannot effectively guide the user; and when the amount used is small, the signal sound is very likely to be caused by the user's own heartbeat, which is likely to cause the user to use the monitoring device under wrong cognition. Providing a specific and effective amount is to exclude the above possible interferences to the user and ensure the true and effective output of the device data.

[0024] An intelligent monitoring system for device usage based on big data, characterized in that the system includes a data management platform construction module, a differential user extraction module, a preliminary unit warning index analysis module, a monitoring sequence pair analysis module, a critical warning sequence pair analysis module, and a warning response module; The data management platform construction module is used to construct a data management platform with the hospital management platform terminal, mobile intelligent devices, and monitoring devices as the main body; the data management platform records the first user data transmitted by the monitoring device and the second user data transmitted by the hospital management platform terminal; The differential user extraction module is used to compare and analyze the first user data and the second user data to determine the differential user and extract the differential data corresponding to the differential user; The preliminary unit warning index analysis module is used to calculate and analyze the preliminary unit warning index of the differential user; The monitoring sequence pair analysis module is used to analyze the trend relationship between the first user data of differential users recorded in the data management platform and the preliminary unit warning index, and generate the monitoring sequence pair corresponding to the differential users; The critical warning sequence pair analysis module is used to extract the first user data of standard users and compare and analyze it with the monitoring sequence pair to determine the critical warning sequence pair of the monitoring device; The warning response module is used to perform warning response based on the output result of the critical warning sequence pair.

[0025] The preliminary unit warning index analysis module includes a monitoring frequency period division unit, a differential user set extraction unit, a differential element pair construction unit, and a preliminary unit warning index calculation unit; The monitoring frequency period division unit is used to divide n user monitoring frequency periods; The differential user set extraction unit is used to divide the recorded users in the data management platform into n differential user sets according to the attribute characteristics when using the monitoring device corresponding to the monitoring frequency period; The differential element pair construction unit is used to construct differential element pairs from the attribute characteristics, usage duration, and state change amount of users in the differential user set and the monitoring medium usage amount when the user uses the monitoring device; The preliminary unit warning index calculation unit is used to calculate the preliminary unit warning index according to the user state change amount and usage duration.

[0026] The monitoring sequence pair analysis module includes a monitoring medium set analysis unit, a user to be analyzed extraction unit, a sequence generation unit, and a monitoring sequence pair output unit; The monitoring medium set analysis unit is used to extract the preliminary unit warning index corresponding to the differential user set and the monitoring medium usage amount in the differential element pair, and construct a medium analysis set from the monitoring medium usage amounts of different differential users in the differential user set; The user to be analyzed extraction unit is used to determine the first user to be analyzed based on the monitoring medium usage amount and the second user to be analyzed based on the preliminary unit warning index; The sequence generation unit is used to sort the differential user set based on the average medium usage amount and the average warning index to generate the first sequence and the second sequence; The monitoring sequence pair output unit is used to output the corresponding monitoring sequence pair based on the comparison result output by the sequence generation unit.

[0027] The critical warning sequence pair analysis module includes a standard user division unit, an attribute feature matching unit, and a critical warning sequence output unit; The standard user division unit is used to obtain other users in the data management platform except for differential users and without second user data records as standard users; The attribute feature matching unit is used to match the standard users in the data management platform with the differential user set according to the attribute features, and after the matching is completed, extract the minimum value of the monitored medium usage corresponding to the standard users of the same type of attribute features, and calculate the average value of the standard warning indexes corresponding to the standard users of the same type of attribute features; The critical warning sequence output unit gives early warning reminders for the corresponding medium usage of users in different monitoring frequency periods based on the output result of the attribute feature matching unit.

[0028] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0029] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An intelligent monitoring method for device usage based on big data, characterized in that, The method includes the following steps: Step S1: Construct a data management platform with the hospital management platform terminal, mobile intelligent device, and monitoring device as the main body. The data management platform records the first user data transmitted by the monitoring device and the second user data transmitted by the hospital management platform terminal; compare and analyze the first user data and the second user data to determine the differential users and extract the differential data corresponding to the differential users; Step S2: Divide the user monitoring frequency period with the recorded users and monitoring data in the data management platform as the carrier. Based on the user monitoring frequency period, calculate and analyze the preliminary unit warning index of the differential users; Step S3: Based on the preliminary unit warning index, analyze the trend relationship between the first user data of the differential users recorded in the data management platform and the preliminary unit warning index and generate a monitoring sequence pair corresponding to the differential users. The monitoring sequence pair is composed of the preliminary unit warning index and the first user data; Step S4: Obtain the other users in the data management platform except the differential users and without the record of the second user data as the standard users; extract the first user data of the standard users and compare and analyze it with the monitoring sequence pair to determine the critical warning sequence pair of the monitoring device and perform a warning response.

2. The intelligent monitoring method for device usage based on big data according to claim 1, wherein: In step S1, when comparing and analyzing the first user data and the second user data and extracting the differential user data, it includes the following analysis steps: The first user data includes monitoring result data, monitoring medium usage, and user status data. The user status data includes the usage duration t of the user using the monitoring device, the state change amount q before and after the user uses the monitoring device, and the attribute characteristics corresponding to the user using the monitoring device; The usage duration refers to the cycle duration from when the user turns on the monitoring device to when the monitoring device outputs monitoring result data that meets the user status evaluation standard. The meeting the user status evaluation standard includes the normal status evaluation standard and the abnormal status evaluation standard; The state change amount refers to the ratio of the change amount between the user's current weight when using the monitoring device and the weight before initially using the monitoring device to the initial weight; That is, q i =(w i - w0) / w0, where w0 represents the weight before the user first uses the monitoring device, and w i represents the weight of the i-th user when currently using the monitoring device. q i represents the state change amount of the i-th user; The second user data refers to the target result data recorded by the secondary detection of the monitoring result data in the first user data at the hospital end; Extract the users in the data management platform with monitoring result data and second user data as the target users, and obtain the target result data and monitoring result data corresponding to the target users; When the types of the target result data and the monitoring result data are inconsistent, output the target users as differential users, and the first user data corresponding to the differential users as differential data. The data types include the normal state corresponding to the normal state evaluation standard and the abnormal state corresponding to the abnormal state evaluation standard.

3. The intelligent monitoring method for device usage based on big data according to claim 2, wherein: Step S2 includes the following analysis steps: Divide into n user monitoring frequency periods. The n user monitoring frequency periods refer to the user dividing into n periods from 1 to 10 months in units of months; Based on the user monitoring frequency period, the users recorded in the data management platform are divided into n differential user sets according to the attribute characteristics when using the monitoring device corresponding to the monitoring frequency period, and the attribute characteristics, usage duration, and state change amount of the users in the differential user set are combined with the monitoring medium usage amount when the user uses the monitoring device to form a differential element pair [A ij →(q ij ,t ij ,j)]; j represents the jth user monitoring frequency period, j ≤ n; A ij represents the monitoring medium usage amount recorded by the ith differential user using the monitoring device within the jth user monitoring frequency period; q ij represents the state change amount recorded by the ith differential user using the monitoring device within the jth user monitoring frequency period; t ij represents the usage duration recorded by the monitoring device for the i-th differential user within the j-th user monitoring frequency period; using the formula: r ij = a1 * q ij + a2 * t ij Calculate the preliminary unit warning index r of the i-th differential user in the j-th user monitoring frequency period ij ; where a1 represents the reference coefficient corresponding to the state change amount, a2 represents the reference coefficient corresponding to the usage duration, a1 + a2 = 1, 1 > a1 > 0, 1 > a2 > 0.

4. An intelligent monitoring method for device usage based on big data according to claim 3, characterized in that: Step S3 includes the following analysis steps: Extract the preliminary unit warning index corresponding to n differential user sets and the usage amount A of the monitoring medium in the differential element pair ij ; Construct a media analysis set J from the monitoring media usage amounts of different differential users in the j-th differential user set j , J j = {A 1j , A 2j , A 3j ,......, A ij} j ; Select the maximum value in the j-th media analysis set J j as max[J j , max[J j = max{A 1j , A 2j , A 3j ,......, A ij} j ; Output the maximum value max[J in the j-th medium analysis set j The preliminary unit warning index in the corresponding differential element pair is the target warning index, and the user corresponding to the target warning index is the first user to be analyzed; Extract the preliminary unit warning index r of the i-th differential user in the j-th differential user set ij , and output the preliminary unit warning index r in the j-th differential user set ij The maximum value max[r ij j The corresponding user is the second user to be analyzed;​ Calculate the average medium usage A corresponding to the j-th differential user set 0j , A 0j = (1 / m)[∑A ij ; and the average warning index r corresponding to the j-th differential user set 0j , r 0j = (1 / m)[∑r ij ; i ≤ m, where m represents the total number of recorded users in the differential set; Sort the n differential user sets in descending order according to the numerical value of the average medium usage amount to generate the first sequence of differential user sets, and sort the n differential user sets in descending order according to the numerical value of the average warning index to generate the second sequence of differential user sets; If the trend relationship is that the first user to be analyzed is the same as the second user to be analyzed and the first sequence is the same as the second sequence, output the monitoring sequence pair Uj of the j-th differential user set, Uj = {max[J j , max[r ij j};​ If it does not satisfy that the first user to be analyzed is the same as the second user to be analyzed and the first sequence is the same as the second sequence, then output the maximum value D of n media analysis sets J j in, D = max{J1, J2, J3,......, J n}.

5. The intelligent monitoring method for device usage based on big data according to claim 4, wherein: Step S4 includes the following analysis steps: When there are monitoring sequence pairs, match the standard users in the data management platform with the differential user sets according to the attribute characteristics. After the matching is completed, extract the minimum value B0 of the monitored medium usage amount corresponding to the standard users with the same attribute characteristics, and calculate the average standard warning index e0 of the standard users corresponding to the same attribute characteristics; The calculation method of the average standard warning index is the same as the above calculation method of the warning index; If B0 > max[J j and |e0 - r 0j | ≤ s, where s is a preset difference threshold, then the output critical warning sequence is V 1j , V 1j = {j → max[J j}; and perform a warning reminder for the user's monitoring medium usage max[J j within the monitoring frequency period of the j-th user according to the critical warning sequence; If B0 > max[J is not satisfied j and |e0 - r 0j | ≤ s, or when there is no monitoring sequence pair, the critical warning sequence V 2j , V 2j = {j → D} is output; and the warning reminder of the monitoring medium usage D of the user within the monitoring frequency period of the j-th user is carried out according to the critical warning sequence.

6. An intelligent monitoring system for device usage based on big data, which applies the intelligent monitoring method for device usage based on big data according to any one of claims 1-5, characterized in that, The system includes a data management platform construction module, a differential user extraction module, a preliminary unit warning index analysis module, a monitoring sequence pair analysis module, a critical warning sequence pair analysis module, and a warning response module; The data management platform construction module is used to construct a data management platform with the hospital management platform terminal, mobile intelligent devices, and monitoring devices as the main body; The data management platform records the first user data transmitted by the monitoring device and the second user data transmitted by the hospital management platform terminal; The differential user extraction module is used to compare and analyze the first user data and the second user data to determine the differential users and extract the differential data corresponding to the differential users; The preliminary unit warning index analysis module is used to calculate and analyze the preliminary unit warning index of the differential users; The monitoring sequence pair analysis module is used to analyze the trend relationship between the first user data of the differential users recorded in the data management platform and the preliminary unit warning index and generate the monitoring sequence pairs corresponding to the differential users; The critical warning sequence pair analysis module is used to extract the first user data of the standard users and compare it with the monitoring sequence pairs for analysis to determine the critical warning sequence pairs of the monitoring devices; The warning response module is used to perform a warning response according to the output result of the critical warning sequence pair.

7. An intelligent monitoring system for device usage based on big data according to claim 6, characterized in that: The preliminary unit warning index analysis module includes a monitoring frequency period division unit, a differential user set extraction unit, a differential element pair construction unit, and a preliminary unit warning index calculation unit; The monitoring frequency period division unit is used to divide the monitoring frequency periods of n users; The differential user set extraction unit is used to divide the recorded users in the data management platform into n differential user sets according to the attribute characteristics corresponding to the monitoring frequency periods when using the monitoring devices; The differential element pair construction unit is used to form differential element pairs by the attribute characteristics, usage duration, and state change amount of the users in the differential user sets and the monitored medium usage amount when the users use the monitoring devices; The preliminary unit warning index calculation unit is used to calculate the preliminary unit warning index according to the user state change amount and usage duration.

8. An intelligent monitoring system for device usage based on big data according to claim 7, characterized in that: The monitoring sequence pair analysis module includes a monitoring medium set analysis unit, a user to be analyzed extraction unit, a sequence generation unit, and a monitoring sequence pair output unit; The monitoring medium set analysis unit is used to extract the preliminary unit warning index corresponding to the differential user set and the monitoring medium usage amount in the differential element pair, and form a medium analysis set with the monitoring medium usage amounts of different differential users in the differential user set; The user to be analyzed extraction unit is used to determine the first user to be analyzed based on the monitoring medium usage amount and the second user to be analyzed based on the preliminary unit warning index; The sequence generation unit is used to sort the differential user set based on the mean value of the medium usage amount and the mean value of the warning index to generate a first sequence and a second sequence; The monitoring sequence pair output unit is used to output the corresponding monitoring sequence pair based on the comparison result output by the sequence generation unit.

9. An intelligent monitoring system for device usage based on big data according to claim 8, characterized in that: The critical warning sequence pair analysis module includes a standard user division unit, an attribute feature matching unit, and a critical warning sequence output unit; The standard user division unit is used to obtain other users in the data management platform that exclude differential users and have no second user data records as standard users; The attribute feature matching unit is used to match the standard users in the data management platform with the differential user set according to the attribute features, and after the matching is completed, extract the minimum value of the monitoring medium usage amount corresponding to the standard users with the same type of attribute features, and calculate the mean value of the standard warning indexes corresponding to the standard users with the same type of attribute features; The critical warning sequence output unit gives a warning reminder for the corresponding medium usage amount of the user in different monitoring frequency periods based on the output result of the attribute feature matching unit.

Images