An IoT data and equipment sharing management system

By considering the correlation and location of sensor data in urban area division, and using the Moran index to correct the clustering results, the problem of inaccurate regional division in the prior art is solved, and more accurate urban area division and data sharing are achieved.

CN118660068BActive Publication Date: 2024-11-12ZHEJIANG PINGSHU TECHNOLOGY (GROUP) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411132238.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-11-12
Estimated Expiration
2044-08-19

AI Technical Summary

Technical Problem

The prior art ignores the data correlation and spatial correlation between sensors when dividing urban areas, resulting in inaccurate regional division.

Method used

The data collection module collects sensor data, and the urban area division module clusters according to the sensor location and data similarity, and uses indicators such as Moran index to evaluate the clustering results, correcting the Moran index to improve the accuracy of the clustering results and achieving more accurate Urban area division.

Benefits of technology

It improves the accuracy of urban area division, ensures the security and privacy protection of data sharing, and is suitable for sharing and analysis between different regions of air quality data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118660068B_ABST
    Figure CN118660068B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of data processing technology, and specifically to an Internet of Things data and equipment sharing management system, which includes: a data collection module for collecting monitoring data collected by sensors deployed at different locations in a target city; an urban area division module for clustering sensors deployed at different locations in the target city according to the location information of the sensors and the similarity between the monitoring data collected by the data collection module, and realizing urban area division according to the clustering results of the sensors; a data sharing module for storing the monitoring data collected by the data collection module according to the urban areas divided by the urban area division module, and realizing the sharing of monitoring data between different urban areas. The technical solution of the present invention can improve the accuracy of urban area division, thereby improving the accuracy of urban Internet of Things data sharing.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an Internet of Things data and device sharing management system. Background Art

[0002] City-level Internet of Things (IoT) data refers to data collected through various sensors, devices, and systems within the city. These data can cover traffic flow, air quality, energy use, public safety, waste management, urban infrastructure status, and many other aspects. The collection and analysis of city-level IoT data is crucial to improving urban management efficiency, optimizing resource allocation, improving residents' quality of life, and promoting sustainable development.

[0003] In addition, in order to help city managers more accurately understand the characteristics and needs of different regions, achieve refined management, and rationally allocate resources, such as public services, infrastructure construction and maintenance, the city needs to be further divided, and the basis for this division is usually based on the data collected by the sensor network to identify and distinguish different areas and functions in the city. The division of the city is different depending on the monitored data. By combining these data with relevant equipment, the residents can be reminded of the divided areas; city managers can also make corresponding decisions based on these data.

[0004] The existing technology usually divides urban areas according to the location of sensors, with the location of sensors representing the corresponding area. The sensors are clustered and the elbow method is used to judge the quality of the clustering results, thereby obtaining the final clustering results of the sensors and realizing the regional division of the city. However, this will have the following problems: the existing clustering algorithm only considers the distance between sensors, ignoring the correlation of monitoring data in the same category, and the existing method of evaluating the quality of clustering results ignores the correlation between sensors in space, resulting in inaccurate regional division of the city. Summary of the invention

[0005] In order to solve the technical problem that the existing technology does not accurately divide urban areas, the purpose of the present invention is to provide an Internet of Things data and device sharing management system, and the technical solution adopted is as follows:

[0006] An Internet of Things data and equipment sharing management system, comprising:

[0007] A data collection module, used to collect monitoring data collected by sensors deployed at different locations in the target city;

[0008] The city area division module is used to obtain the monitoring data collected by the data collection module and the location information of each sensor, cluster the sensors deployed at different locations of the target city according to the location information of the sensors and the similarity between the monitoring data, and divide the target city into urban areas according to the clustering results of the sensors;

[0009] The data sharing module is used to store the monitoring data collected by the data collection module according to the urban areas divided by the urban area division module, and realize the sharing of monitoring data between different urban areas.

[0010] Furthermore, the monitoring data is air quality data, and the air quality data includes concentration data of multiple preset types of pollutants.

[0011] Furthermore, clustering sensors arranged at different locations of the target city according to the location information of the sensors and the similarity between the monitoring data, and dividing the target city into urban areas according to the clustering results of the sensors, includes:

[0012] Cluster the sensors deployed at different locations in the target city according to the location information of the sensors and the similarity between the monitoring data to obtain a variety of candidate clustering results. Evaluate each candidate clustering result separately, calculate the evaluation index value of each candidate clustering result, and select the candidate clustering result with the largest evaluation index value as the final clustering result.

[0013] According to the clustering results of sensors, sensors in the same category are divided into the same area to achieve urban area division.

[0014] Furthermore, the step of evaluating each candidate clustering result and calculating the evaluation index value of each candidate clustering result includes:

[0015] Get the Moran index corresponding to each category in the current candidate clustering result;

[0016] Based on the latency of monitoring data, the distance between the sensor and the cluster center, the importance of the sensor in its category, and the shape of the area surrounded by the locations of all sensors in each category, the rationality of the classification of each category in the current candidate clustering results is calculated;

[0017] The calculated classification rationality is used as the correction coefficient of the Moran index. The correction coefficient corresponding to the same category in the current candidate clustering result is multiplied by the Moran index to obtain the corrected Moran index corresponding to each category. The average value of the corrected Moran index corresponding to all categories in the current candidate clustering result is used as the evaluation index value of the current candidate clustering result.

[0018] Furthermore, based on the latency of the monitoring data, the distance between the sensor and the cluster center, the importance of the sensor in its category, and the shape of the area surrounded by the locations of all sensors in each category, the rationality of the classification of each category in the current candidate clustering result is calculated, including:

[0019] Obtain the category center position and category center monitoring data of the current category; and based on the category center position and category center monitoring data of the current category, calculate the delay error and delay time of each sensor in the current category; wherein the category center position of the current category is represented by the mean value of the sensor positions in the current category; the category center monitoring data of the current category is obtained by weighted combination of the monitoring data of each sensor in the current category to obtain the category center monitoring data of the current category; wherein the weight of the monitoring data of each sensor is the inverse of the distance between its position and the category center position;

[0020] Based on the sensor's delay error, delay time, the distance from the sensor's location to the center of the category, and the importance of the sensor in its category, the classification error rate of each sensor in the current category is calculated;

[0021] Based on the shape of the area enclosed by the locations of all sensors in the current category and the classification error rate of each sensor in the current category, the classification rationality of the current category is calculated.

[0022] Further, the calculating of the error between each delayed data sequence and the monitoring data sequence corresponding to the category center monitoring data includes:

[0023] For the delayed data sequence of the error to be calculated and the monitoring data sequence corresponding to the category center monitoring data, take the extreme value points in the delayed data sequence to form a delayed data key point sequence; take the extreme value points in the monitoring data sequence corresponding to the category center monitoring data to form a monitoring data key point sequence corresponding to the category center monitoring data;

[0024] The error between the delayed data key point sequence and the monitoring data key point sequence corresponding to the category center monitoring data is calculated as the error between the corresponding delayed data sequence and the monitoring data sequence corresponding to the category center monitoring data.

[0025] Furthermore, calculating the delay error and delay time of each sensor in the current category includes:

[0026] According to different delay times, the monitoring data sequences corresponding to the monitoring data of the current sensor are delayed respectively to obtain delayed data sequences with multiple different delay times corresponding to the current sensor;

[0027] The errors between each delayed data sequence and the monitoring data sequence corresponding to the category center monitoring data are calculated respectively, and the calculated minimum error is used as the delay error of the current sensor, and the delay time corresponding to the delayed data sequence corresponding to the calculated minimum error is used as the delay time of the current sensor.

[0028] Furthermore, based on the delay error of the sensor, the delay time, the distance from the location of the sensor to the center of the category, and the importance of the sensor in its category, the classification error rate of each sensor in the current category is calculated, including:

[0029] Based on the delay time of the sensor, the fitting distance of the sensor is calculated;

[0030] According to the following formula, the classification error rate of each sensor in the current category is calculated:

[0031] ;

[0032] in, represents the classification error rate of the i-th sensor in the l-th category; represents the delay error of the i-th sensor in the l-th category; represents the fitting distance of the i-th sensor in the l-th category; It represents the distance from the location of the i-th sensor in the l-th category to the category center of the category it belongs to; Indicates the data relevance of the lth category; represents the data correlation of the remaining data after removing the monitoring data of the ith sensor in the lth category; Represents an exponential function with the natural constant e as the base.

[0033] Further, the step of calculating the fitting distance of the sensor based on the delay time of the sensor includes:

[0034] Get the distance between the sensor location and the category center location and the delay time corresponding to each data point in the current category;

[0035] The least square method is used to fit the distance between the sensor location and the category center location and the delay time corresponding to all data points in the current category, and the functional relationship between the distance between the sensor location and the category center location corresponding to the data point and the delay time is obtained;

[0036] Based on the functional relationship, the fitting distance corresponding to the current sensor is calculated according to the delay time of the current sensor.

[0037] Furthermore, the calculation of the classification rationality of the current category based on the shape of the area enclosed by the positions of all sensors in the current category and the classification error rate of each sensor in the current category includes:

[0038] According to the classification error rate of each sensor in the current category, the average of the classification error rates of all sensors in the current category is calculated;

[0039] Based on the shape of the area enclosed by the positions of all sensors in the current category, the area occupied by the area enclosed by the positions of all sensors in the current category is calculated, and the minimum circumscribed circle of the area enclosed by the positions of all sensors in the current category is determined, and the area occupied by the minimum circumscribed circle of the area enclosed by the positions of all sensors in the current category is calculated;

[0040] Use the following formula to calculate the classification rationality of the current category:

[0041] ;

[0042] in, Indicates the rationality of the classification of the lth category; It represents the area occupied by the region enclosed by the locations of all sensors in the lth category; represents the area occupied by the minimum circumscribed circle of the area enclosed by the locations of all sensors in the lth category; represents the mean of the classification error rates of all sensors in the lth category.

[0043] The present invention has the following beneficial effects:

[0044] Since there are certain differences in the air quality data corresponding to different areas in the city, such as the city's commercial area, residential area, industrial area, etc., affected by the production and living environment, there must be certain differences in the air quality data of each area. Therefore, by clustering the sensors and dividing the city into regions according to the corresponding positions of the clustered sensors, data can be collected and analyzed more targetedly. After the city is divided into different urban areas, the air quality conditions in each area are similar. On this basis, a data sharing platform can be created to allow air quality data to be shared and accessed between different areas. Policies and standards for data sharing should be formulated to ensure the security, compliance and privacy protection of data sharing. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 This is a structural block diagram of an Internet of Things data and device sharing management system provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation, structure, features and effects of an IoT data and device sharing management system proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present invention.

[0048] The following is a detailed description of a specific solution of an IoT data and device sharing management system provided by the present invention in conjunction with the accompanying drawings. It should be noted that the IoT data and device sharing management system of the present invention is suitable for processing any city-level IoT data. The following takes the processing of air quality data as an example to illustrate the specific implementation process of the IoT data and device sharing management system of the present invention. Figure 1 , which shows a structural block diagram of an Internet of Things data and device sharing management system provided by an embodiment of the present invention, the system includes the following modules:

[0049] A data collection module, used to collect monitoring data collected by sensors deployed at different locations in the target city;

[0050] It should be noted that the system can be used to process any city-level IoT data, and since air quality data directly affects people's respiratory health and travel, relevant policies can be effectively formulated by monitoring air quality data, such as traffic management, industrial emission urban planning, etc. Therefore, the monitoring data collected in this embodiment is air quality data, which includes concentration data of multiple preset types of pollutants, such as carbon dioxide concentration, sulfide concentration, PM2.5 data, etc.

[0051] The city area division module is used to obtain the monitoring data collected by the data collection module and the location information of each sensor, cluster the sensors deployed at different locations of the target city according to the location information of the sensors and the similarity between the monitoring data, and divide the target city into urban areas according to the clustering results of the sensors;

[0052] Among them, it should be noted that there are certain differences in air quality data in different areas. Therefore, it is necessary to divide the city into regions and realize the rapid positioning of abnormal problem areas through the correlation of data in the same area. Moreover, since the position of the sensor is fixed during construction, the optimal clustering result based solely on the distance between sensors cannot be changed. Since the same area often exhibits similar air quality characteristics, areas with similar air quality can be divided into the same category, which can be more helpful in implementing targeted environmental management measures. Therefore, this embodiment uses the location information of each sensor, combined with the similarity of the monitoring data obtained by the sensor, to achieve clustering of sensors, and then to achieve the division of urban areas.

[0053] Specifically, in this embodiment, the specific process of the city area division module implementing the city area division is as follows:

[0054] S1, clustering sensors deployed at different locations in the target city according to the location information of the sensors and the similarity between the monitoring data, obtaining a variety of candidate clustering results, evaluating each candidate clustering result respectively, calculating the evaluation index value of each candidate clustering result, and selecting the candidate clustering result with the largest evaluation index value as the final clustering result;

[0055] Among them, each candidate clustering result is evaluated separately, and the evaluation index value of each candidate clustering result is calculated, including:

[0056] S11, obtaining the Moran index corresponding to each category in the current candidate clustering result;

[0057] Among them, it should be noted that due to the differences in air quality data corresponding to different areas in the city, for example, the commercial area, residential area, industrial area, etc. of the city are affected by the production and life, and the air quality data of each area must be different. Therefore, by clustering the sensors, the regional division of the city can be realized according to the corresponding positions of the clustered sensors, and the data can be collected and analyzed more targetedly. Therefore, it is very important to correctly evaluate the quality of the clustering results. The mean square error is a commonly used evaluation criterion. However, the mean square error ignores the correlation between sensors in space, so the Moran index is often used as a criterion for measuring the quality of clustering results in spatial clustering. Select the clustering result of a sensor, and use the inverse of the distance between sensors as the weight matrix of the Moran index to obtain the Moran index corresponding to the current clustering result.

[0058] However, the Moran index is easily affected by the data scale, that is, the difference in the degree of aggregation and the amplitude of change of sensors in the same category will affect the judgment of the Moran index on the quality of the clustering results. For example, for sensors that should belong to the same category, the large difference in distance between sensors may lead to errors in sensor classification; or due to the influence of air diffusion, sensors that should belong to the same category are classified into the remaining categories with the closest distance, resulting in misjudgment. Therefore, the Moran index cannot accurately describe the distribution characteristics of air quality data in the city. Therefore, the Moran index needs to be corrected through the following steps.

[0059] S12, based on the latency of the monitoring data, the distance between the sensor and the cluster center, the importance of the sensor in its category, and the shape of the area surrounded by the locations of all sensors in each category, calculate the rationality of the classification of each category in the current candidate clustering result. The specific process is as follows:

[0060] S121, obtaining the category center position and category center monitoring data of the current category; and based on the category center position and category center monitoring data of the current category, calculating the delay error and delay time of each sensor in the current category;

[0061] Among them, it should be noted that due to the influence of factors such as air diffusion and industrial zone emissions, pollutants in some areas are difficult to diffuse or have obvious directionality; thus, the air quality data corresponding to different locations in the same area at the same time do not correspond in time series, that is, the air quality data monitored at different locations have a certain delay. Therefore, the accuracy of each sensor category division can be obtained by using the delay time and distance relationship of sensors classified into the same category. Among them, the category center position of the current category is represented by the mean of the location of the sensor in the current category; the category center monitoring data of the current category is obtained by weighted combination of the monitoring data of each sensor in the current category to obtain the category center monitoring data of the current category; wherein, the weight of the monitoring data of each sensor is the inverse of the distance between its location and the category center. Moreover, if the monitoring data of the sensor is directly shifted in time to determine the delay time of each sensor, the acquired monitoring data will not be aligned before and after. Therefore, it is necessary to use the key points in the monitoring data for comparison to determine the delay of the sensor in the category in time series.

[0062] Specifically, the method for determining the delay error and the delay time is as follows: according to different delay times, the monitoring data sequence corresponding to the monitoring data of the current sensor is delayed respectively to obtain a plurality of delay data sequences with different delay times corresponding to the current sensor; the error between each delay data sequence and the monitoring data sequence corresponding to the category center monitoring data is calculated respectively, and the calculated minimum error is used as the delay error of the current sensor, and the delay time corresponding to the delay data sequence corresponding to the calculated minimum error is used as the delay time of the current sensor. Wherein, the calculation of the error between each delay data sequence and the monitoring data sequence corresponding to the category center monitoring data includes: for the delay data sequence of the error to be calculated and the monitoring data sequence corresponding to the category center monitoring data, taking the extreme value points in the delay data sequence to form a delay data key point sequence; taking the extreme value points in the monitoring data sequence corresponding to the category center monitoring data to form a monitoring data key point sequence corresponding to the category center monitoring data; calculating the error between the delay data key point sequence and the monitoring data key point sequence corresponding to the category center monitoring data as the error between the corresponding delay data sequence and the monitoring data sequence corresponding to the category center monitoring data. Based on the above, the formula for determining the delay error and the delay time is expressed as follows:

[0063]

[0064]

[0065] in, Indicates The delay error of the i-th sensor in the category; Indicates The historical data sequence of the monitoring data of the i-th sensor in the category; Indicated by Delay in time The sequence of extreme points in the sequence obtained after units; Indicates The historical data series of the category center monitoring data of each category; Indicated by A sequence of extreme points in ; express and The error between them reflects the matching situation between the sequences. Indicates The delay time of the i-th sensor in the category. A positive value indicates a positive delay, and a negative value indicates a negative delay. is the minimum error, which is also the delay error of the current sensor; is the minimum error; The delay time corresponding to the corresponding delayed data sequence is also the delay time of the current sensor.

[0066] S122, calculating the classification error rate of each sensor in the current category based on the delay error and delay time of the sensor, the distance from the location of the sensor to the center of the category, and the importance of the sensor in the category to which it belongs;

[0067] Among them, it should be noted that through the characteristics of the pollution source spreading to the surrounding, the correlation between the location of the sensor in the category and the monitoring data can be used to determine the accuracy of the sensor division. However, not all sensors’ monitoring data delays have a strong correlation with distance. For example, the monitored air quality data is easily disturbed by the wind, which causes the change of air quality data to be directional in space, which leads to unsatisfactory fitting effect. Even if the fitting effect is not good, it should actually belong to the same category. Therefore, the importance of the sensor in the current category must also be considered.

[0068] Based on the above, the following formula is constructed to calculate the classification error rate of each sensor in the current category:

[0069]

[0070] in, represents the classification error rate of the i-th sensor in the l-th category; represents the delay error of the i-th sensor in the l-th category; represents the fitting distance of the i-th sensor in the l-th category; It represents the distance from the location of the i-th sensor in the l-th category to the category center of the category it belongs to; Indicates the data relevance of the lth category; represents the data correlation of the remaining data after removing the monitoring data of the ith sensor in the lth category; Represents an exponential function with the natural constant e as the base.

[0071] It reflects the error between the fitted distance and the actual distance. The larger the error, the greater the possibility that the sensor is abnormal in the current category, that is, the greater the possibility that the sensor is misclassified; Indicated in The impact of the current sensor on the entire category under a category. If the data of the sensor is removed, the data correlation of the entire category is improved, that is, , it means that there is a large difference between the delay and distance relationship of the monitoring data of this sensor and the other sensors in this category, and the possibility of it being misclassified is greater; on the contrary, if the data correlation of the entire category decreases significantly after removing the data of this sensor, that is, , it means that the sensor plays a good auxiliary judgment role for the entire category, and the higher the possibility of correct classification.

[0072] Furthermore, the method for calculating the fitting distance of the sensor based on the delay time of the sensor is specifically as follows: obtaining the distance between the sensor position and the center position of the category and the delay time corresponding to each data point in the current category; fitting the distance between the sensor position and the center position of the category and the delay time corresponding to all data points in the current category using the least squares method to obtain a functional relationship between the distance between the sensor position corresponding to the data point and the center position of the category and the delay time; based on the functional relationship, calculating the fitting distance corresponding to the current sensor according to the delay time of the current sensor.

[0073] S123, calculating the rationality of classification of the current category based on the shape of the area enclosed by the positions of all sensors in the current category and the classification error rate of each sensor in the current category;

[0074] It should be noted that, due to the diffusion characteristics of pollutants and the interference of wind, the area with similar air quality data will be in the shape of a convex area as a whole. Therefore, on the basis of the above S122, the rationality of the classification of the current category can be further calculated according to the shape of the area surrounded by the locations of all sensors in the current category. The specific process is as follows:

[0075] S1231, calculating the average of the partitioning error rates of all sensors in the current category according to the partitioning error rate of each sensor;

[0076] S1232, based on the shape of the area enclosed by the positions of all sensors in the current category, calculate the area occupied by the area enclosed by the positions of all sensors in the current category, determine the minimum circumscribed circle of the area enclosed by the positions of all sensors in the current category, and calculate the area occupied by the minimum circumscribed circle;

[0077] S1233, use the following formula to calculate the classification rationality of the current category:

[0078]

[0079] in, Indicates the rationality of the classification of the lth category; It represents the area occupied by the region enclosed by the locations of all sensors in the lth category; represents the area occupied by the minimum circumscribed circle of the area enclosed by the locations of all sensors in the lth category; represents the mean of the classification error rates of all sensors in the lth category;

[0080] The larger the value of , the greater the possibility that the current category is continuous in spatial position, and the greater the possibility that it presents a convex area shape, that is, the more reasonable the category division is, and thus the greater the possibility that it is a correct division.

[0081] S13, using the calculated classification rationality as the correction coefficient of the Moran index, multiplying the correction coefficient corresponding to the same category in the current candidate clustering result by the Moran index to obtain the corrected Moran index corresponding to each category, and taking the average of the corrected Moran indexes corresponding to all categories in the current candidate clustering result as the evaluation index value of the current candidate clustering result.

[0082] S2, based on the clustering results of sensors, divide the sensors in the same category into the same area to achieve urban area division.

[0083] The data sharing module is used to store the monitoring data collected by the data collection module according to the urban areas divided by the urban area division module, and realize the sharing of monitoring data between different urban areas.

[0084] It should be noted that after dividing the city into different air quality zones, the air quality conditions in each zone are similar. On this basis, a data sharing platform can be created to allow air quality data to be shared and accessed between different zones. Policies and standards for data sharing should be formulated to ensure the security, compliance and privacy protection of data sharing.

[0085] The technical solution of the present invention determines the abnormal situation of each sensor in its category, determines the possibility of its classification error, and determines the correction factor of the Moran index in combination with the shape enclosed by the positions of each sensor in the current category, and then corrects the evaluation index of the clustering result. According to the corrected evaluation index, more reasonable sensor clustering results can be screened out, thereby improving the accuracy of urban area division, and then effectively improving the accuracy of urban Internet of Things data sharing.

[0086] In summary, this embodiment provides an Internet of Things data and device sharing management system, in which the possibility of classification error is determined by determining the abnormal situation of each sensor in its category, and the shape enclosed by the positions of each sensor in the current category is combined to determine the correction factor of the Moran index, and then the evaluation index of the clustering result is corrected. According to the corrected evaluation index, more reasonable sensor clustering results can be screened out, thereby improving the accuracy of urban area division, and then effectively improving the accuracy of urban Internet of Things data sharing.

[0087] In addition, it should be noted that the above is only a preferred embodiment of the present invention. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-tasking and parallel processing are also possible or may be advantageous. Moreover, although the preferred embodiments of the present invention have been described, it is a person of ordinary skill in the art that once the basic creative concepts of the present invention are known, several improvements and modifications can be made without departing from the principles of the present invention, and these improvements and modifications should also be regarded as the scope of protection of the present invention. Therefore, the attached claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

Claims

1. An Internet of Things data and equipment sharing management system, characterized in that: The system comprises: A data collection module, used to collect monitoring data collected by sensors deployed at different locations in the target city; The city area division module is used to obtain the monitoring data collected by the data collection module and the location information of each sensor, cluster the sensors deployed at different locations of the target city according to the location information of the sensors and the similarity between the monitoring data, and divide the target city into urban areas according to the clustering results of the sensors; The method comprises: clustering sensors arranged at different locations of the target city according to the location information of the sensors and the similarity between the monitoring data, and dividing the target city into urban areas according to the clustering results of the sensors, including: clustering sensors arranged at different locations of the target city according to the location information of the sensors and the similarity between the monitoring data, obtaining a plurality of different candidate clustering results, evaluating each candidate clustering result respectively, calculating the evaluation index value of each candidate clustering result, and selecting the candidate clustering result with the largest evaluation index value as the final clustering result; dividing sensors in the same category into the same area according to the clustering results of the sensors, and realizing urban area division; Among them, the method for obtaining the evaluation index value is as follows: obtain the Moran index corresponding to each category in the current candidate clustering result; based on the latency of the monitoring data, the distance relationship between the sensor and the cluster center, the importance of the sensor in its category, and the shape of the area surrounded by the locations of all sensors in each category, calculate the classification rationality of each category in the current candidate clustering result; use the calculated classification rationality as the correction coefficient of the Moran index, multiply the correction coefficient corresponding to the same category in the current candidate clustering result by the Moran index, and obtain the corrected Moran index corresponding to each category; use the average value of the corrected Moran index corresponding to all categories in the current candidate clustering result as the evaluation index value of the current candidate clustering result; The data sharing module is used to store the monitoring data collected by the data collection module according to the urban areas divided by the urban area division module, and realize the sharing of monitoring data between different urban areas.

2. The IoT data and device sharing management system according to claim 1, characterized in that: The monitoring data is air quality data, and the air quality data includes concentration data of multiple preset types of pollutants.

3. The IoT data and device sharing management system according to claim 1, characterized in that: Based on the latency of the monitoring data, the distance between the sensor and the cluster center, the importance of the sensor in its category, and the shape of the area surrounded by the locations of all sensors in each category, the rationality of the classification of each category in the current candidate clustering results is calculated, including: Obtain the category center position and category center monitoring data of the current category; and based on the category center position and category center monitoring data of the current category, calculate the delay error and delay time of each sensor in the current category; wherein the category center position of the current category is represented by the mean value of the sensor positions in the current category; the category center monitoring data of the current category is obtained by weighted combination of the monitoring data of each sensor in the current category to obtain the category center monitoring data of the current category; wherein the weight of the monitoring data of each sensor is the inverse of the distance between its position and the category center position; Based on the sensor's delay error, delay time, the distance from the sensor's location to the center of the category, and the importance of the sensor in its category, the classification error rate of each sensor in the current category is calculated; Based on the shape of the area enclosed by the locations of all sensors in the current category and the classification error rate of each sensor in the current category, the classification rationality of the current category is calculated.

4. The IoT data and device sharing management system according to claim 3, characterized in that: The step of calculating the delay error and delay time of each sensor in the current category includes: According to different delay times, the monitoring data sequences corresponding to the monitoring data of the current sensor are delayed respectively to obtain delayed data sequences with multiple different delay times corresponding to the current sensor; The errors between each delayed data sequence and the monitoring data sequence corresponding to the category center monitoring data are calculated respectively, and the calculated minimum error is used as the delay error of the current sensor, and the delay time corresponding to the delayed data sequence corresponding to the calculated minimum error is used as the delay time of the current sensor.

5. The IoT data and device sharing management system according to claim 4, characterized in that: The calculating the error between each delayed data sequence and the monitoring data sequence corresponding to the category center monitoring data includes: For the delayed data sequence of the error to be calculated and the monitoring data sequence corresponding to the category center monitoring data, take the extreme value points in the delayed data sequence to form a delayed data key point sequence; take the extreme value points in the monitoring data sequence corresponding to the category center monitoring data to form a monitoring data key point sequence corresponding to the category center monitoring data; The error between the delayed data key point sequence and the monitoring data key point sequence corresponding to the category center monitoring data is calculated as the error between the corresponding delayed data sequence and the monitoring data sequence corresponding to the category center monitoring data.

6. The IoT data and device sharing management system according to claim 3, characterized in that: The method of calculating the classification error rate of each sensor in the current category based on the delay error of the sensor, the delay time, the distance from the location of the sensor to the center of the category, and the importance of the sensor in the category to which it belongs includes: Based on the delay time of the sensor, the fitting distance of the sensor is calculated; According to the following formula, the classification error rate of each sensor in the current category is calculated: Among them, e l,i represents the classification error rate of the i-th sensor in the l-th category; E l,i (t) represents the delay error of the i-th sensor in the l-th category; d' l,i represents the fitting distance of the ith sensor in the lth category; d l,i R represents the distance from the location of the i-th sensor in the l-th category to the category center of the category it belongs to; l represents the data relevance of the lth category; R l,i It represents the data correlation of the remaining data after removing the monitoring data of the ith sensor in the lth category; exp represents the exponential function with the natural constant e as the base.

7. The IoT data and device sharing management system according to claim 6, characterized in that: The step of calculating the fitting distance of the sensor based on the delay time of the sensor includes: Get the distance between the sensor location and the category center location and the delay time corresponding to each data point in the current category; The least square method is used to fit the distance between the sensor location and the category center location and the delay time corresponding to all data points in the current category, and the functional relationship between the distance between the sensor location and the category center location corresponding to the data point and the delay time is obtained; Based on the functional relationship, the fitting distance corresponding to the current sensor is calculated according to the delay time of the current sensor.

8. The IoT data and device sharing management system according to claim 3, characterized in that: The calculation of the rationality of classification of the current category based on the shape of the area enclosed by the positions of all sensors in the current category and the classification error rate of each sensor in the current category includes: According to the classification error rate of each sensor in the current category, the average of the classification error rates of all sensors in the current category is calculated; Based on the shape of the area enclosed by the positions of all sensors in the current category, the area occupied by the area enclosed by the positions of all sensors in the current category is calculated, and the minimum circumscribed circle of the area enclosed by the positions of all sensors in the current category is determined, and the area occupied by the minimum circumscribed circle of the area enclosed by the positions of all sensors in the current category is calculated; Use the following formula to calculate the classification rationality of the current category: Among them, p l Indicates the rationality of the classification of the lth category; s l represents the area occupied by the location of all sensors in the lth category; s l,out represents the area occupied by the minimum circumscribed circle of the area enclosed by the locations of all sensors in the lth category; E(e l,i ) represents the mean of the classification error rates of all sensors in the lth category.