Intelligent monitoring management system based on data analysis

Abstract

The invention discloses an intelligent monitoring management system based on data analysis, relates to the technical field of subsidy data analysis, and solves the problem that follow-up subsidy measures are adjusted due to the fact that corresponding good areas and poor areas are not directly given according to subsidy data of different areas. According to the invention, through the acquired subsidy data, the subsidy cardinal numbers of different areas are confirmed preferentially, then periodic monitoring is carried out subsequently, the change of the subsidy cardinal numbers is analyzed, the area with the best subsidy effect and the area with the worst subsidy effect are determined from different subsidy areas, and the determined areas are displayed. According to the system, the subsidy data is fully managed and analyzed according to the collected subsidy data, and the analysis result is displayed, so that external personnel can fully understand the subsidy data and do not need to analyze the data by themselves, and meanwhile, the subsidy result can be fully understood, and the best area and the worst area can be timely understood.

Description

Technical Field

[0001] This invention relates to the field of subsidy data analysis technology, specifically to an intelligent monitoring and management system based on data analysis. Background Technology

[0002] The invention disclosed in patent publication number CN110276706A relates to a technology for publicly disclosing targeted subsidy information, specifically an on-demand matching system for publicly disclosing targeted subsidy information. It solves the problems of traditional targeted subsidy information disclosure technologies failing to guarantee timeliness and effectiveness, and failing to balance information transparency and security. The system includes a QR code deployed in the area where the impoverished entity is located, a mobile smart terminal held by the targeted subsidy recipient, a front-end server, and a database server deployed in the management department. The QR code stores an identification code for the impoverished entity. The targeted subsidy recipient uses a mobile smart terminal to scan the QR code and uploads the obtained identification code to the front-end server. The front-end server has a built-in hierarchical and categorized information matching matrix, a security audit module, and a complaint handling module. This invention is applicable to the public disclosure of information on public investment projects such as targeted subsidies.

[0003] The system analyzes and displays the subsidy effects in different regions based on subsidy data. However, external managers still need to analyze regions with better and worse subsidy effects. The system does not directly assign corresponding better and worse regions based on subsidy data from different regions, so as to adjust subsequent subsidy measures. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides an intelligent monitoring and management system based on data analysis, which solves the problem of not directly identifying better and worse regions based on subsidy data from different areas, thus failing to adjust subsequent subsidy measures accordingly.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an intelligent monitoring and management system based on data analysis, comprising: The data collection unit uses a WeChat mini-program to collect the average income of different people in different regions and transmits the collected average income of different people in different regions to the data analysis unit. The data analysis unit, based on the average income of different individuals in different regions, uses a numerical comparison program to confirm the number of people eligible for subsidies in the corresponding regions. Then, a numerical conversion program confirms the subsidy base for each region based on the average salary of these individuals. The confirmed subsidy base is then transmitted to the base partitioning unit. The numerical conversion program runs on the secondary CPU within the system, specifically in the following manner: The average income of different people in different regions is denoted as SR.i-k Where i represents different regions and k represents different individuals, and this average income SR i-k Compare with the preset parameter Y1, where Y1 is the preset value; When SR i-k If the value is greater than Y1, no action is taken; otherwise, the corresponding personnel are marked as warning personnel. Record the specific number of people under alert in this area, and simultaneously average the average income generated by several people under alert to obtain the poverty average for this area. Label the specific number of people under alert as RS. i The poverty mean of the corresponding region is marked as JZ. i ; use JS subsidy base for different regions i C1 and C2 are both preset fixed coefficient factors, which are used to determine the subsidy base JS belonging to different regions. i Transmitted to the cardinality partition unit; The base partitioning unit, based on the confirmed subsidy base and the preset interval, uses a numerical comparison program to partition different regions and transmits the partitioning results to the storage unit for storage. The numerical comparison program runs based on the machine learning comparison model in the system, and the machine learning comparison model is stored in the storage disk. The baseline monitoring unit confirms the average income for different time periods within the monitoring period via a WeChat mini-program, then converts the corresponding monitoring baseline using an internal numerical conversion program. The internal monitoring program monitors the baseline at the determined monitoring time point and transmits it to the baseline analysis unit. The monitored baseline is stored on the system's storage disk, with a storage partition different from the machine learning comparison model. The monitoring period T is one year, generating 12 different monitoring baselines within this period. Within one year, the subsidy baseline for different regions needs to be calculated monthly, resulting in 12 different monitoring baselines. The monitoring baseline analysis unit analyzes different monitoring baselines in different intervals and regions using a numerical analysis program. It divides different regions into rising or falling regions using a numerical comparison program, and selects and confirms the best and worst regions from these regions. The numerical analysis program runs on the system's main CPU, and the main program code within the numerical analysis program is drafted by the operator. Specifically: Based on the time progression of the monitoring period T, the last monitoring base was identified from among the 12 different monitoring bases and marked as JC. i Then, based on the marker i, extract the original subsidy base JS. iJC i =JS i The corresponding area is not included in the classification process, and then it is determined whether the monitoring baseline meets JC. i >JS i If the condition is met, the corresponding region is marked as an ascending region; otherwise, the corresponding region is marked as a descending region. Within the identified rising region, several monitoring bases belonging to the corresponding rising region are confirmed, and the confirmed different monitoring bases are marked as JC. i-t Where t represents different time points, and t=1, 2, ..., 12, from different monitoring bases JC i-t Extract the maximum value and mark it as JC. i-tmax Then use JC i-t -JC i-（t-1） =CC i Obtain the q groups of differences CC i and the difference CC of group q i Perform summation to obtain the merge processing parameter HL. i HD i =HL i ×A1+JC i-tmax ×A2 yields the verified value HD i A1 and A2 are both preset fixed coefficient factors, which are used to determine the HD values ​​for different rising regions. i The values ​​are confirmed sequentially, and the maximum value is selected from several sets of verified values. The corresponding rising area is marked as the optimal area, and the marked optimal area is transmitted to the partition adaptive confirmation unit. Within the identified descent region, several monitoring baselines belonging to the corresponding descent region are confirmed, and these different confirmed monitoring baselines are marked as CT. i-t Where t represents different time points, and t=1, 2, ..., 12, the minimum value is identified from different monitoring bases and marked as CT. i-tmin Then use CT i-t -CT i-（t-1） =TC i q sets of differences TC i and the difference TC of group q i Perform summation to obtain another combination and process the parameter HC. i Using XD i =HC i ×A1+CT i-tmin ×A2 yields the limit value XD i Where A1 and A2 are both preset fixed coefficient factors, which limit the value XD for different descent regions. iThe system sequentially confirms the minimum value from several sets of limiting values, marks the corresponding decreasing region as the worst region, and transmits the marked worst region to the partition adaptive confirmation unit.

[0006] Preferably, it also includes a storage unit, and the storage unit is provided with three sets of preset intervals, and the specific method by which the cardinality partitioning unit partitions different regions is as follows: The three preset intervals are (0, X1], (X1, X2], and (X2, X3], where X1, X2, and X3 are preset values. The subsidy base JS for different regions is... i The system compares the data with three preset intervals to confirm the interval it belongs to, and then bundles the numbers of different areas belonging to the same intervals and transmits them to the storage unit for storage.

[0007] Preferably, the numerical comparison program, numerical conversion program, numerical analysis program, and the internal running code of the machine learning comparison model are all set in advance by the operator based on experience, and their running conditions are all based on this system.

[0008] Preferably, the partition adaptive confirmation unit transmits the confirmed best and worst regions to the display unit for display.

[0009] This also includes: an optimal strategy determination unit, which analyzes and confirms the rising and falling regions generated in different intervals, and determines the optimal strategy from the confirmation results. The specific method is as follows: Within the corresponding interval, the number of ascending regions is marked as Sg, and the number of descending regions is marked as Xg, where g represents different intervals; The strategy verification value VBg is obtained by using VBg=Sg×Z1-Xg×Z2, where Z1 and Z2 are preset fixed coefficient factors. The maximum value is selected from the strategy verification values ​​VBg in different intervals, and the subsidy strategy corresponding to the maximum value is marked as the best strategy. The selected best strategy is then transmitted to the display unit for display.

[0010] This invention provides an intelligent monitoring and management system based on data analysis. Compared with existing technologies, it has the following advantages: This invention uses the acquired subsidy data to first identify the subsidy base in different regions. Subsequently, it conducts periodic monitoring to analyze changes in the subsidy base. Based on specific change parameters, it identifies the regions with the best and worst subsidy effects from different subsidy regions and displays the identified regions. This system fully manages and analyzes the collected subsidy data and displays the analysis results, allowing external personnel to fully understand the subsidy data without needing to analyze the data themselves. At the same time, it also allows them to fully understand the subsidy results and promptly identify the best and worst regions. Based on the specific analysis results, the corresponding optimal strategy is identified and displayed. Subsequently, based on the displayed optimal strategy, operators can modify other subsidy strategies to improve the overall subsidy effect. Attached Figure Description

[0011] Figure 1 This is a schematic diagram of the principle framework of the present invention; Figure 2 This is a schematic diagram illustrating the identification of early warning personnel according to the present invention. Detailed Implementation

[0012] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0013] Example 1

[0014] Please see Figure 1 This application provides an intelligent monitoring and management system based on data analysis, including a data acquisition unit, a monitoring and management center, and a display unit; The data acquisition unit is electrically connected to the input terminal of the monitoring and management center, and the monitoring and management center is electrically connected to the input terminal of the display unit; The monitoring and management center includes a data analysis unit, a base partitioning unit, a base monitoring unit, a storage unit, a partition adaptive confirmation unit, a monitoring base analysis unit, and an optimal strategy determination unit. The data analysis unit is electrically connected to the input of the base partitioning unit, the base partitioning unit is bidirectionally connected to the storage unit, the base partitioning unit is electrically connected to the input of the base monitoring unit, the base monitoring unit is electrically connected to the input of the monitoring base analysis unit, and the monitoring base analysis unit is electrically connected to the inputs of both the optimal strategy determination unit and the partition adaptive confirmation unit. The data acquisition unit is used to collect the average income of different people in different regions and transmit the collected average income of different people in different regions to the monitoring and management center. Combination Figure 2 The data analysis unit, based on the average income of different individuals in different regions collected from data analysis, identifies the number of people eligible for subsidies in the corresponding region, and confirms the subsidy base for each region based on the average salary of the people eligible for subsidies. The confirmed subsidy base is then transmitted to the base partitioning unit. The specific method for confirmation is as follows: The average income of different people in different regions is denoted as SR. i-k Where i represents different regions and k represents different individuals, and this average income SR i-k Compare with the preset parameter Y1, where Y1 is the preset value, and its specific value is determined by the operator based on experience; When SR i-k If the value is greater than Y1, no action is taken; otherwise, the corresponding personnel are marked as warning personnel. Record the specific number of people under alert in this area, and simultaneously average the average income generated by several people under alert to obtain the poverty average for this area. Label the specific number of people under alert as RS. i The poverty mean of the corresponding region is marked as JZ. i ; use JS subsidy base for different regions i C1 and C2 are both preset fixed coefficient factors, the specific values ​​of which are determined by the operator based on experience, and the obtained subsidy base JS belongs to different regions. i Transmitted to the cardinality partition unit.

[0015] The base partitioning unit, based on the confirmed subsidy base JS i The system partitions different regions based on preset intervals and transmits the partitioning results to storage units for storage. The specific method for partitioning is as follows: The storage unit is configured with three preset intervals: (0, X1], (X1, X2], and (X2, X3]. X1, X2, and X3 are preset values, whose specific values ​​are determined by the operator based on experience. The subsidy base JS for different regions is then set. i The system compares the data with three preset intervals to confirm the interval it belongs to, and then bundles the numbers of different areas belonging to the same intervals and transmits them to the storage unit for storage.

[0016] Example 2

[0017] Based on the above embodiments, this embodiment further includes the following in its specific implementation: The baseline monitoring unit defines a monitoring period T. For different intervals, different subsidy strategies are selected, and the different monitoring baselines generated within this monitoring period T are transmitted to the monitoring baseline analysis unit. T is generally taken as 1 year. Within this monitoring period T, 12 different monitoring baselines are generated. Within 1 year, the subsidy baseline for different regions needs to be calculated every month to obtain 12 different monitoring baselines, and the 12 different monitoring baselines are transmitted to the monitoring baseline analysis unit. The monitoring baseline analysis unit analyzes 12 different monitoring baselines from different intervals and regions, pre-dividing the different regions into rising or falling regions, and selecting and confirming the best and worst regions from the different rising and falling regions. The specific method for dividing the different regions is as follows: Based on the time progression of the monitoring period T, the last monitoring base was identified from among the 12 different monitoring bases and marked as JC. i Then, based on the marker i, extract the original subsidy base JS. i JC i =JS i The corresponding area is not included in the classification process, and then it is determined whether the monitoring baseline meets JC. i >JS i If the condition is met, the corresponding region is marked as an ascending region; otherwise, the corresponding region is marked as a descending region. Within the identified rising region, several monitoring bases belonging to the corresponding rising region are confirmed, and the confirmed different monitoring bases are marked as JC. i-t Where t represents different time points, and t=1, 2, ..., 12, from different monitoring bases JC i-t Extract the maximum value and mark it as JC. i-tmax Then use JC i-t -JC i-（t-1） =CC i Obtain the q groups of differences CC i Where q takes the value 11, and the differences of q groups are CC i Perform summation to obtain the merge processing parameter HL. i HD i =HL i ×A1+JC i-tmax ×A2 yields the verified value HD i A1 and A2 are both preset fixed coefficient factors, which determine the verification values ​​HD for different rising regions. iThe values ​​are confirmed sequentially, and the maximum value is selected from several sets of verified values. The corresponding rising area is marked as the optimal area, and the marked optimal area is transmitted to the partition adaptive confirmation unit. Within the identified descent region, several monitoring baselines belonging to the corresponding descent region are confirmed, and these different confirmed monitoring baselines are marked as CT. i-t Where t represents different time points, and t=1, 2, ..., 12, the minimum value is identified from different monitoring bases and marked as CT. i-tmin Then use CT i-t -CT i-（t-1） =TC i q sets of differences TC i Where q takes the value 11, and the difference TC of q groups is... i Perform summation to obtain another combination and process the parameter HC. i Using XD i =HC i ×A1+CT i-tmin ×A2 yields the limit value XD i Where A1 and A2 are both preset fixed coefficient factors, which limit the value XD for different descent regions. i The system sequentially confirms the minimum value from several sets of limiting values, marks the corresponding decreasing region as the worst region, and transmits the marked worst region to the partition adaptive confirmation unit.

[0018] The partition adaptive confirmation unit determines the best and worst regions, confirms the corresponding intervals of the best and worst regions, and transmits the best region and the corresponding interval to the display unit for display. Similarly, the worst region and the corresponding interval are also displayed at the same time. Example 3

[0019] Based on the above embodiments, this embodiment further includes the following in its specific implementation: The optimal strategy determination unit analyzes and confirms the rising and falling regions generated within different intervals, thereby identifying the set of intervals where the applied subsidy strategy is most effective. The corresponding subsidy strategy is then labeled as the optimal strategy and transmitted to the display unit for presentation. The specific method of analysis is as follows: Within the corresponding interval, the number of ascending regions is marked as Sg, and the number of descending regions is marked as Xg, where g represents different intervals; The strategy verification value VBg is obtained by using VBg=Sg×Z1-Xg×Z2, where Z1 and Z2 are preset fixed coefficient factors, and the specific values ​​are determined by the operator based on experience. Based on the strategy verification value VBg in different intervals, the maximum value is selected, and the subsidy strategy corresponding to the maximum value is marked as the best strategy. The selected best strategy is then transmitted to the display unit for display, so that external personnel can view it.

[0020] Example 4

[0021] In its specific implementation, this embodiment includes all the implementation processes of the above three sets of embodiments.

[0022] The numerical comparison program, numerical conversion program, numerical analysis program, and the internal running code of the machine learning comparison model are all set in advance by the operators based on their experience, and their running conditions are all based on this system. The code for the numerical comparison program is as follows: VM172:1 [Deprecation] 'window.webkitStorageInfo' is deprecated. Please use 'navigator.webkitTemporaryStorage' or 'navigator.webkitPersistentStorage' instead; The code for the numerical conversion program is as follows: Numerical conversion ; The following is a partial code snippet from the numerical analysis program: / *$(document).on("click", "a", function(e) { var $a = $(this); var t = $("meta[name=_t]").attr("content"); / / Get t, you can first write it in html>head>meta alert(t); if(t!=''){ if (!$a.data("_t")) { var href = $a.href; if (href.indexOf("?") == -1) { href = href + "?_t=" + t; } else { href = href + "&_t=" + t; } $a.data("_t", t); } } })* / .

[0023] Some of the data in the above formulas are numerical calculations with dimensions removed, and the contents not described in detail in this specification are all prior art known to those skilled in the art.

[0024] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A data-based intelligent monitoring and management system, characterized in that, include: The data collection unit uses a WeChat mini-program to collect the average income of different people in different regions and transmits the collected average income of different people in different regions to the data analysis unit. The data analysis unit uses a numerical comparison program to confirm the number of people in the corresponding region who are eligible for subsidies, based on the average income of different people in different regions collected. It also uses a numerical conversion program to confirm the subsidy base for each region based on the average salary of the people eligible for subsidies, and transmits the confirmed subsidy base to the base partitioning unit. The numerical conversion program runs on the secondary CPU within the system. The base partitioning unit, based on the confirmed subsidy base and the preset interval, uses a numerical comparison program to partition different regions and transmits the partitioning results to the storage unit for storage. The numerical comparison program runs based on the machine learning comparison model in the system, and the machine learning comparison model is stored in the storage disk. The baseline monitoring unit confirms the average income for different time periods within the monitoring period through a WeChat mini-program, then converts the corresponding monitoring baseline through an internal numerical conversion program, and uses an internal monitoring program to monitor the monitoring baseline at the determined monitoring time point and transmits the monitoring baseline to the monitoring baseline analysis unit. The monitored baseline is stored in the system's storage disk, and its storage partition is different from that of the machine learning comparison model. The monitoring baseline analysis unit analyzes different monitoring baselines in different intervals and regions through a numerical analysis program. By using a numerical comparison program, different regions are divided into rising or falling regions. From different rising and falling regions, the best and worst regions are selected and confirmed. The numerical analysis program runs on the main CPU of the system. The data analysis unit confirms the subsidy base for each different region in the following specific way: The average income of different people in different regions is denoted as SR. i-k Where i represents different regions and k represents different individuals, and this average income SR i-k Compare with the preset parameter Y1, where Y1 is the preset value; When SR i-k If the value is greater than Y1, no action is taken; otherwise, the corresponding personnel are marked as warning personnel. Record the specific number of people under alert in this area, and simultaneously average the average income generated by several people under alert to obtain the poverty average for this area. Label the specific number of people under alert as RS. i The poverty mean of the corresponding region is marked as JZ. i ; use JS subsidy base for different regions i C1 and C2 are both preset fixed coefficient factors, which are used to determine the subsidy base JS belonging to different regions. i Transmitted to the cardinality partition unit.

2. The intelligent monitoring and management system based on data analysis according to claim 1, characterized in that, It also includes storage units, each containing three preset intervals, and the specific method by which the radix partitioning unit partitions different areas is as follows: The three preset intervals are (0, X1], (X1, X2], and (X2, X3], where X1, X2, and X3 are preset values. The subsidy base JS for different regions is... i The system compares the data with three preset intervals to confirm the interval it belongs to, and then bundles the numbers of different areas belonging to the same intervals and transmits them to the storage unit for storage.

3. The intelligent monitoring and management system based on data analysis according to claim 1, characterized in that, The monitoring period T is set to 1 year. Within this monitoring period T, 12 different monitoring bases are generated. Within 1 year, the subsidy base for different regions needs to be calculated every month to obtain 12 different monitoring bases.

4. The intelligent monitoring and management system based on data analysis according to claim 3, characterized in that, The monitoring baseline analysis unit identifies the best and worst regions in the following specific way: Based on the time progression of the monitoring period T, the last monitoring base was identified from among the 12 different monitoring bases and marked as JC. i Then, based on the marker i, extract the original subsidy base JS. i JC i =JS i The corresponding area is not included in the classification process, and then it is determined whether the monitoring baseline meets JC. i >JS i If the condition is met, the corresponding region is marked as an ascending region; otherwise, the corresponding region is marked as a descending region. Within the identified rising region, several monitoring bases belonging to the corresponding rising region are confirmed, and the confirmed different monitoring bases are marked as JC. i-t Where t represents different time points, and t=1, 2, ..., 12, from different monitoring bases JC i-t Extract the maximum value and mark it as JC. i-tmax Then use JC i-t -JC i-（t-1） =CC i Obtain the q groups of differences CC i and the difference CC of group q i Perform summation to obtain the merge processing parameter HL. i HD i =HL i ×A1+JC i-tmax ×A2 yields the verified value HD i A1 and A2 are both preset fixed coefficient factors, which are used to determine the HD values ​​for different rising regions. i The values ​​are confirmed sequentially, and the maximum value is selected from several sets of verified values. The corresponding rising area is marked as the optimal area, and the marked optimal area is transmitted to the partition adaptive confirmation unit. Within the identified descent region, several monitoring baselines belonging to the corresponding descent region are confirmed, and these different confirmed monitoring baselines are marked as CT. i-t Where t represents different time points, and t=1, 2, ..., 12, the minimum value is identified from different monitoring bases and marked as CT. i-tmin Then use CT i-t -CT i-（t-1） =TC i q sets of differences TC i and the difference TC of group q i Perform summation to obtain another combination and process the parameter HC. i Using XD i =HC i ×A1+CT i-tmin ×A2 yields the limit value XD i Where A1 and A2 are both preset fixed coefficient factors, which limit the value XD for different descent regions. i The system sequentially confirms the minimum value from several sets of limiting values, marks the corresponding decreasing region as the worst region, and transmits the marked worst region to the partition adaptive confirmation unit.

5. The intelligent monitoring and management system based on data analysis according to claim 4, characterized in that, The partition adaptive confirmation unit transmits the confirmed best and worst regions to the display unit for display.

6. The intelligent monitoring and management system based on data analysis according to claim 5, characterized in that, Also includes: The optimal strategy determination unit analyzes and confirms the rising and falling regions generated in different intervals, and determines the optimal strategy from the confirmation results.

7. The intelligent monitoring and management system based on data analysis according to claim 6, characterized in that, The optimal strategy determination unit confirms the optimal strategy in the following specific way: Within the corresponding interval, the number of ascending regions is marked as Sg, and the number of descending regions is marked as Xg, where g represents different intervals; The strategy verification value VBg is obtained by using VBg=Sg×Z1-Xg×Z2, where Z1 and Z2 are preset fixed coefficient factors. The maximum value is selected from the strategy verification values ​​VBg in different intervals, and the subsidy strategy corresponding to the maximum value is marked as the best strategy. The selected best strategy is then transmitted to the display unit for display.

Images