A big data-based smart community management method and system

Abstract

The application discloses a kind of big data-based intelligent community management method and system, it is related to data processing analysis technical field, including the type analysis of all data of intelligent community, determine high-frequency accident and high-frequency accident occurrence position;High-frequency accident and high-frequency accident occurrence position are analyzed, and the characteristics of high-frequency accident occurrence are determined.The application first is to the type analysis of all data of intelligent community, determine high-frequency accident and high-frequency accident occurrence position, then, by the data analysis of all high-frequency accident occurrence position data, determine high-frequency accident occurrence characteristics, finally, by high-frequency accident occurrence characteristics, the characteristics of all regions of intelligent community are matched, determine the area that needs to be monitored, the above-mentioned mode not only realizes the prediction of high-frequency accident occurrence position of intelligent community, but also monitors high-frequency accident occurrence position, when accident occurs, the position of accident can be determined in time, avoid causing greater damage to intelligent community.

Description

Technical Field

[0001] This invention relates to the field of data processing and analysis technology, specifically to a smart community management method and system based on big data. Background Technology

[0002] A smart community refers to a model that integrates existing community service resources by utilizing various intelligent technologies and methods to provide residents with convenient services such as government affairs, business, entertainment, education, medical care, and mutual assistance. Smart communities represent a new concept in community management, and their development can effectively promote economic transformation and foster the development of modern service industries.

[0003] Some accidents may occur in smart communities, and some of these accidents are frequent. Without analyzing these frequent accidents, it is impossible to predict where they will happen next. If accidents are not detected in time, they can cause damage to the smart community. Summary of the Invention

[0004] To address the aforementioned technical problems, this paper provides a smart community management method and system based on big data. This technical solution solves the problem mentioned in the background that some accidents occur in smart communities, and some of these accidents are frequent. Without analyzing these frequent accidents, it is impossible to predict where the next accident will occur. If an accident is not detected in time, it will cause a certain degree of damage to the smart community.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] A smart community management method based on big data includes:

[0007] Acquire all data from the smart community, and based on the intelligent management terminal, perform type analysis on all data from the smart community to determine high-frequency incidents and their locations;

[0008] Based on intelligent management terminals, feature analysis is performed on high-frequency accidents and their locations to determine the characteristics of high-frequency accidents.

[0009] Based on intelligent management terminals, the smart community is monitored in real time using the characteristics of high-frequency accidents as a reference.

[0010] Preferably, the step of acquiring all data from the smart community, and based on the intelligent management terminal, performing type analysis on all data from the smart community to determine high-frequency incidents and their locations specifically includes the following steps:

[0011] Based on the intelligent management terminal, data is read and processed from the database system of the smart community to obtain all the data of the smart community;

[0012] Based on the intelligent management terminal, data reading and processing are performed on all data in the smart community using data type as a feature, to obtain all accident data in the smart community;

[0013] Based on the intelligent management terminal, all accident data in the smart community are classified and processed according to the accident type to obtain a data set of different types of accidents in the smart community;

[0014] Based on intelligent management terminals, comparative analysis is conducted on data sets of different types of accidents in smart communities to identify high-frequency accidents and their locations.

[0015] Preferably, the step of comparing and analyzing data sets of different types of accidents in the smart community based on the intelligent management terminal to determine high-frequency accidents and their locations specifically includes the following steps:

[0016] Based on the intelligent management terminal, the data in the dataset of different types of accidents in the smart community are counted to determine the frequency of occurrence of different types of accidents;

[0017] Based on the intelligent management terminal, the frequency of occurrence of different types of accidents is compared and processed to identify high-frequency accidents to be verified.

[0018] Based on the intelligent management terminal, the high-frequency incidents to be verified are processed using the data set corresponding to the high-frequency incidents to be verified as features, thereby determining the high-frequency incidents and their locations.

[0019] Preferably, the step of comparing the occurrence frequency of different types of accidents based on the intelligent management terminal to determine the high-frequency accidents to be verified specifically includes the following steps:

[0020] Based on the intelligent management terminal, the occurrence frequency of different types of accidents and the set threshold for the occurrence frequency of accidents are judged and processed;

[0021] If the number of occurrences of different types of accidents exceeds the set threshold for the number of occurrences of accidents, then that type of accident is set as a high-frequency accident to be verified.

[0022] If the number of occurrences of different types of accidents is less than or equal to the set accident occurrence threshold, the data set corresponding to that type of accident is set as the accidental accident data set.

[0023] Preferably, the step of verifying the high-frequency incidents based on the intelligent management terminal, using the data set corresponding to the high-frequency incidents to be verified as features, and determining the high-frequency incidents and their locations specifically includes the following steps:

[0024] Based on the intelligent management terminal, the data set corresponding to the high-frequency incidents to be verified is processed to obtain the occurrence time of the high-frequency incidents to be verified.

[0025] Based on the intelligent management terminal, the occurrence time of the high-frequency incidents to be verified is calculated by subtracting the occurrence time to determine the data set of the occurrence time intervals of the high-frequency incidents to be verified; wherein, the subtracting calculation is performed on the occurrence time of the high-frequency incidents to be verified at adjacent times.

[0026] Based on the maximum value function, the data in the dataset of high-frequency accident occurrence time intervals to be verified are sorted to obtain the maximum occurrence time interval of the accident.

[0027] Based on the intelligent management terminal, a comparative analysis of the maximum time interval between accidents is conducted to determine high-frequency accidents and their locations.

[0028] Preferably, the step of comparing and analyzing the maximum time interval between accidents based on the intelligent management terminal to determine high-frequency accidents and their locations specifically includes the following steps:

[0029] Based on the intelligent management terminal, the occurrence time of the high-frequency incident to be verified is processed to obtain the most recent occurrence time of the high-frequency incident to be verified; wherein, the most recent occurrence time of the high-frequency incident to be verified is the latest occurrence time of the incident among the occurrence times of the high-frequency incident to be verified.

[0030] Based on the intelligent management terminal, data is read and processed from the timing devices in the smart community to obtain the real-time time of the smart community;

[0031] Based on the intelligent management terminal, the difference between the real-time time of the smart community and the most recent occurrence time of the high-frequency accident to be verified is calculated to determine the real-time occurrence time interval of the accident.

[0032] Based on the intelligent management terminal, the real-time occurrence time interval and the maximum occurrence time interval of the accident are judged and processed;

[0033] If the real-time occurrence time interval of an accident is less than or equal to the maximum occurrence time interval of an accident, the accident is set as a high-frequency accident. Based on the intelligent management terminal, the data sets of different types of accidents in the smart community are matched with high-frequency accidents as characteristics to determine the location of the high-frequency accident.

[0034] If the time interval between real-time occurrences of an incident is greater than the maximum time interval between incident occurrences, the incident is set as a resolved incident.

[0035] Preferably, the step of performing feature analysis on high-frequency accidents and their locations based on the intelligent management terminal to determine the characteristics of high-frequency accidents specifically includes the following steps:

[0036] Based on the intelligent management terminal, data is read and processed from the dataset corresponding to high-frequency accidents to obtain the occurrence time of the high-frequency accidents;

[0037] Based on the intelligent management terminal, information matching processing is performed on the occurrence time and location of high-frequency accidents to determine the occurrence time of accidents at different locations of high-frequency accidents.

[0038] Based on the intelligent management terminal, the data of all accidents in the smart community are extracted and processed using the occurrence time of accidents at different locations of high-frequency accidents as a feature to obtain a set of parameter information; wherein, the set of parameter information specifically includes parameter data of high-frequency accidents at different locations before the occurrence time of the accident and parameter data of high-frequency accidents at different locations after the occurrence time of the accident.

[0039] Based on the intelligent management terminal, data analysis and processing of parameter information sets are performed to determine the characteristics of high-frequency accidents.

[0040] Preferably, the step of performing data analysis and processing on the parameter information set based on the intelligent management terminal to determine the characteristics of high-frequency accidents specifically includes the following steps:

[0041] Based on the intelligent management terminal, the data in the parameter information set is classified and processed according to the occurrence time of the accident at different locations of high-frequency accidents, so as to obtain parameter data for different accident occurrence times;

[0042] Based on the intelligent management terminal, the parameter data of different accident occurrence times are intersected to determine the parameter data of the same type; specifically, the parameter data of the same type are the same type parameters of all high-frequency accidents at different occurrence locations;

[0043] Based on the intelligent management terminal, data change analysis is performed on parameter data of the same type to determine the parameter types that cause high-frequency accidents;

[0044] Based on the intelligent management terminal, the parameter types that cause high-frequency accidents are set as high-frequency accident occurrence characteristics.

[0045] Preferably, the real-time monitoring of the smart community based on the intelligent management terminal and with reference to the characteristics of high-frequency accidents specifically includes the following steps:

[0046] Based on intelligent management terminals, parameters are matched for all areas of the smart community using the characteristics of high-frequency accidents as a reference to determine the locations with high-frequency accident characteristics.

[0047] Based on intelligent management terminals, data analysis is performed on the characteristics of high-frequency accidents to determine accident monitoring equipment;

[0048] Based on intelligent management terminals, accident monitoring equipment is installed at locations with high-frequency accident occurrence characteristics to conduct real-time monitoring of smart communities.

[0049] Furthermore, a big data-based smart community management system is proposed to implement the aforementioned big data-based smart community management method, including:

[0050] The intelligent management terminal is used to control various modules to classify, compare, verify, and analyze the location of all data in the smart community, and to monitor the smart community in real time; the intelligent management terminal is also used to control data transmission and information interaction between various modules.

[0051] A database system is used to store all data related to the smart community.

[0052] The data classification module is used to classify and process all data in the smart community and obtain all accident data in the smart community.

[0053] The accident data first verification module is used to compare and judge the occurrence frequency of different types of accidents to determine the high-frequency accidents to be verified.

[0054] The second accident data verification module is used to perform time comparison and judgment processing on the high-frequency accidents to be verified, and to determine the high-frequency accidents.

[0055] A high-frequency accident feature determination module is used to perform type analysis on data of the location of high-frequency accidents to determine the characteristics of high-frequency accidents.

[0056] The monitoring equipment installation location determination module performs parameter matching on all areas of the smart community based on the characteristics of high-frequency accidents to determine the locations with high-frequency accident occurrence characteristics.

[0057] Compared with existing technologies, this invention provides a smart community management method and system based on big data, which has the following beneficial effects:

[0058] This invention first performs type analysis on all data of the smart community to identify high-frequency accidents and their locations. Then, it analyzes the data of all high-frequency accident locations to determine the characteristics of high-frequency accidents. Finally, it performs feature matching on all areas of the smart community based on the characteristics of high-frequency accidents to determine the areas that need to be monitored. This method not only predicts the location of high-frequency accidents in the smart community but also monitors them. When an accident occurs, the location can be determined in a timely manner to avoid causing significant damage to the smart community. Attached Figure Description

[0059] Figure 1 This is a flowchart illustrating steps S100-S300 in a smart community management method based on big data proposed in this invention.

[0060] Figure 2 This is a structural block diagram of a smart community management system based on big data proposed in this invention. Detailed Implementation

[0061] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.

[0062] Reference Figure 1 As shown, a smart community management method based on big data includes:

[0063] S100: Acquire all data from the smart community, perform type analysis on all data from the smart community based on the intelligent management terminal, and determine high-frequency accidents and the locations where high-frequency accidents occur.

[0064] S200: Based on the intelligent management terminal, perform feature analysis on high-frequency accidents and their locations to determine the characteristics of high-frequency accidents.

[0065] S300, based on intelligent management terminals, conducts real-time monitoring of smart communities using the characteristics of high-frequency accidents as a reference;

[0066] Those skilled in the art will understand that similar incidents frequently occur in smart communities. If not detected in time, these incidents may cause damage to the smart community. Therefore, by filtering all data in the smart community, frequently occurring incidents (i.e., high-frequency incidents) can be identified. However, the locations of these high-frequency incidents may be the same or different. If the locations are the same, monitoring equipment can be installed at the location of the high-frequency incident to monitor the area. When the same type of incident occurs again in that area, it can be detected in time, avoiding significant damage to the smart community. If the high-frequency incidents occur in different areas, but the same type of high-frequency incident will definitely have the same characteristics, parameters of high-frequency incidents in different areas can be compared to determine which parameters cause the high-frequency incidents. Subsequently, the parameters causing the high-frequency incidents are matched to the entire smart community to determine the areas where these parameters appear. Finally, corresponding monitoring equipment is installed in these areas to achieve monitoring of the smart community.

[0067] Example 1

[0068] S100. Acquire all data from the smart community, and based on the intelligent management terminal, perform type analysis on all data from the smart community to determine high-frequency incidents and their locations. This includes the following steps:

[0069] S101. Based on the intelligent management terminal, perform data reading and processing on the database system of the smart community to obtain all data of the smart community;

[0070] Understandably, to obtain accident data from a smart community, it is necessary to read data from the smart community's data storage devices (i.e., database systems), and then classify this data to determine all accident data in the smart community.

[0071] S102. Based on the intelligent management terminal, perform data reading and processing on all data of the smart community using data type as a feature, and obtain all accident data of the smart community;

[0072] S103. Based on the intelligent management terminal, classify and process all accident data of the smart community according to the accident type to obtain a data set of different types of accidents in the smart community.

[0073] It is understandable that different types of accidents manifest themselves in different ways and the parameters that cause them are also different. Therefore, before identifying high-frequency accidents, it is necessary to classify all accidents that have occurred within the smart community.

[0074] S104. Based on the intelligent management terminal, compare and analyze the data sets of different types of accidents in the smart community to determine high-frequency accidents and the locations where high-frequency accidents occur.

[0075] S104, based on the intelligent management terminal, compares and analyzes the data sets of different types of accidents in the smart community to determine high-frequency accidents and their locations, specifically including the following steps:

[0076] S1041. Based on the intelligent management terminal, count the data in the dataset of different types of accidents in the smart community to determine the number of occurrences of different types of accidents;

[0077] Understandably, high-frequency accidents are determined by the number of times an accident occurs. If an accident only occurs once or twice, it cannot be classified as a high-frequency accident. Therefore, the number of times an accident occurs needs to be determined before identifying a high-frequency accident.

[0078] S1042. Based on the intelligent management terminal, the frequency of occurrence of different types of accidents is compared and processed to determine the high-frequency accidents to be verified.

[0079] S1043. Based on the intelligent management terminal, the high-frequency accident to be verified is verified using the data set corresponding to the high-frequency accident to be verified as a feature, and the high-frequency accident and the location of the high-frequency accident are determined.

[0080] Specifically, S1042, based on the intelligent management terminal, compares the occurrence frequency of different types of accidents to determine the high-frequency accidents to be verified, including the following steps:

[0081] S10421. Based on the intelligent management terminal, the occurrence frequency of different types of accidents and the set threshold for the occurrence frequency of accidents are judged and processed.

[0082] S10422. If the number of occurrences of different types of accidents exceeds the set accident occurrence threshold, set the accident of that type as a high-frequency accident to be verified.

[0083] S10423. If the number of occurrences of different types of accidents is less than or equal to the set accident occurrence threshold, the data set corresponding to that type of accident shall be set as the accidental accident data set.

[0084] Understandably, high-frequency accidents cannot be determined solely by the number of times they occur. Judging by the number of occurrences is only to eliminate those accidents that occur infrequently. Accidents that occur infrequently are generally occasional and it is impossible to obtain a pattern for this type of accident because the sample size is too small to identify any corresponding patterns. In order to reduce the subsequent computational workload, accidents that occur infrequently are eliminated, and accidents that occur more frequently are verified to determine high-frequency accidents. However, accidents that occur more frequently are not necessarily high-frequency accidents; it is also necessary to analyze them in conjunction with the time of occurrence.

[0085] Specifically, S1043, based on the intelligent management terminal, uses the data set corresponding to the high-frequency incidents to be verified as features to perform verification processing on the high-frequency incidents to be verified, and determines the high-frequency incidents and their locations, includes the following steps:

[0086] S10431. Based on the intelligent management terminal, perform data extraction and processing on the data set corresponding to the high-frequency accident to be verified, and obtain the occurrence time of the high-frequency accident to be verified.

[0087] S10432. Based on the intelligent management terminal, the occurrence time of the high-frequency accident to be verified is calculated by subtraction to determine the occurrence time interval data set of the high-frequency accident to be verified; wherein, the subtraction calculation is performed on the occurrence time of the high-frequency accident to be verified at adjacent times.

[0088] S10433. Based on the maximum value function, sort the data in the dataset of high-frequency accident occurrence time intervals to be verified, and obtain the maximum occurrence time interval of the accident.

[0089] Understandably, in order to improve the accuracy of identifying high-frequency accidents, it is necessary to select the accident occurrence interval to verify the high-frequency accidents to be verified. When a type of accident occurs frequently, the time interval between occurrences may not be the same. Therefore, these time intervals are screened, and the maximum accident occurrence time interval is selected as the reference group. This is because when the factors that cause this type of accident are resolved, this type of accident will reappear, and the interval between the last occurrence of the accident and the actual time is greater than the maximum accident occurrence time interval.

[0090] S10434. Based on the intelligent management terminal, compare and analyze the maximum time interval between the occurrence of accidents to determine high-frequency accidents and the location of high-frequency accidents.

[0091] Specifically, S10434, based on the intelligent management terminal, involves comparative analysis of the maximum occurrence time interval of accidents to determine high-frequency accidents and their locations, including the following steps:

[0092] S104341. Based on the intelligent management terminal, the occurrence time of the high-frequency accident to be verified is processed by data extraction to obtain the most recent occurrence time of the high-frequency accident to be verified; wherein, the most recent occurrence time of the high-frequency accident to be verified is specifically the latest occurrence time of the accident among the occurrence times of the high-frequency accidents to be verified.

[0093] S104342. Based on the intelligent management terminal, data reading and processing are performed on the timing devices of the smart community to obtain the real-time time of the smart community;

[0094] S104343. Based on the intelligent management terminal, the difference between the real-time time of the smart community and the most recent occurrence time of the high-frequency accident to be verified is calculated to determine the real-time occurrence time interval of the accident.

[0095] S104344. Based on the intelligent management terminal, the real-time occurrence time interval and the maximum occurrence time interval of the accident are judged and processed.

[0096] S104345. If the real-time occurrence time interval of an accident is less than or equal to the maximum occurrence time interval of an accident, the accident is set as a high-frequency accident. Based on the intelligent management terminal, the data sets of different types of accidents in the smart community are matched with high-frequency accidents as characteristics to determine the location of the high-frequency accident.

[0097] S104346. If the real-time occurrence time interval of an accident is greater than the maximum occurrence time interval of an accident, the accident shall be set as a resolved accident.

[0098] It's understandable that a high frequency of accidents doesn't necessarily equate to high-frequency accidents. Some accidents may occur frequently, but a significant time has passed between the last occurrence and the current occurrence, and the same type of accident hasn't recurred during this interval. This indicates that the underlying causes of the accident have been resolved, meaning it's no longer considered a high-frequency accident. For example, an intersection that used to be frequently congested might have had its congestion eliminated after lanes were added. However, the previous congestion counts are still stored in the database. Determining high-frequency accidents solely based on the number of occurrences is incomplete and wasteful of resources. While the problem has been resolved, the records remain in the database. If high-frequency accidents were identified based solely on the number of occurrences, monitoring equipment would be needed, which is wasteful since the underlying causes have been addressed. Therefore, using the interval between occurrences to eliminate resolved high-frequency accidents improves the accuracy of identifying them.

[0099] Example 2

[0100] S200. Based on the intelligent management terminal, perform feature analysis on high-frequency accidents and their locations to determine the characteristics of high-frequency accidents. This specifically includes the following steps:

[0101] S201. Based on the intelligent management terminal, perform data reading and processing on the data set corresponding to high-frequency accidents to obtain the occurrence time of the high-frequency accidents;

[0102] S202. Based on the intelligent management terminal, perform information matching processing on the occurrence time and location of high-frequency accidents to determine the occurrence time of accidents at different locations of high-frequency accidents.

[0103] Understandably, when high-frequency incidents occur in different areas, it is necessary to analyze the parameters of that type of high-frequency incident in order to identify it. However, the parameters when high-frequency incidents do not occur are not meaningful. Therefore, data in the database system is extracted based on the occurrence time of the incidents at different locations of the high-frequency incidents to determine the parameter changes at that location when the high-frequency incidents occurred. Subsequently, analyzing these parameters can determine the parameters that caused the high-frequency incidents.

[0104] S203. Based on the intelligent management terminal, extract and process all accident data in the smart community using the occurrence time of high-frequency accidents at different locations as a feature to obtain a set of parameter information; wherein, the set of parameter information specifically includes parameter data of high-frequency accidents at different locations before the occurrence time and parameter data of high-frequency accidents at different locations after the occurrence time.

[0105] S204. Based on the intelligent management terminal, perform data analysis and processing on the parameter information set to determine the characteristics of high-frequency accidents;

[0106] It is understandable that some high-frequency accidents do not occur in the same area, but in different areas. However, these high-frequency accidents are of the same type. Therefore, by performing intersection processing on the parameters of these high-frequency accidents, we can identify parameters of the same type. Among these parameters of the same type, there will be parameters that cause high-frequency accidents, and these parameters are the characteristics that trigger high-frequency accidents.

[0107] Specifically, S204, based on the intelligent management terminal, involves data analysis and processing of the parameter information set to determine the characteristics of high-frequency accidents, including the following steps:

[0108] S2041. Based on the intelligent management terminal, the data in the parameter information set is classified and processed according to the occurrence time of the accident at different locations of high-frequency accidents, so as to obtain parameter data for different accident occurrence times.

[0109] S2042. Based on the intelligent management terminal, the parameter data of different accident occurrence times are intersected to determine the parameter data of the same type; wherein, the parameter data of the same type specifically refers to the same type parameters of all high-frequency accidents at different occurrence locations;

[0110] S2043. Based on the intelligent management terminal, perform data change analysis on parameter data of the same type to determine the parameter type that causes high-frequency accidents;

[0111] S2044. Based on the intelligent management terminal, the parameter type that causes high-frequency accidents is set as a high-frequency accident occurrence characteristic;

[0112] Understandably, when high-frequency accidents occur in different areas, analyzing accident data from only one location is insufficient to determine the parameters that triggered the high-frequency accidents. Therefore, it is necessary to analyze the parameters from all locations where high-frequency accidents occurred, because high-frequency accidents of the same type follow similar patterns. First, the parameters from all locations where high-frequency accidents occurred are intersected to identify the common parameters. Then, based on the time of the high-frequency accident, these common parameters are analyzed. The parameters that change at the time of the high-frequency accident are the factors that cause it. Therefore, by analyzing the parameters from these different locations where high-frequency accidents occurred, the parameters whose data changed simultaneously at these locations at the time of the high-frequency accident are the factors that triggered it.

[0113] Example 3

[0114] S300, based on intelligent management terminals, conducts real-time monitoring of smart communities using high-frequency accident characteristics as a reference, specifically including the following steps:

[0115] S301. Based on the intelligent management terminal, parameter matching is performed on all areas of the smart community with reference to the characteristics of high-frequency accidents to determine the locations with high-frequency accident characteristics.

[0116] S302. Based on the intelligent management terminal, perform data analysis on the characteristics of high-frequency accidents to determine the accident monitoring equipment;

[0117] S303. Based on intelligent management terminals, accident monitoring equipment is installed at locations with high-frequency accident occurrence characteristics to conduct real-time monitoring of smart communities;

[0118] Understandably, once the characteristics of high-frequency accidents are identified, the location of such accidents is uncertain, but the characteristics of these accidents have been determined. Subsequently, it is only necessary to match the smart community with these characteristics to determine which areas of the smart community will have these characteristics. These areas are the areas where accidents are likely to occur. Therefore, by installing monitoring equipment in these areas, when such accidents occur in these areas, the location of the accidents can be determined in a timely manner, reducing the damage to the smart community.

[0119] Reference Figure 2 As shown, a big data-based smart community management system is used to implement the above-described big data-based smart community management method, including:

[0120] The intelligent management terminal is used to control various modules to classify, compare, verify, and analyze the location of all data in the smart community, and to monitor the smart community in real time; the intelligent management terminal is also used to control data transmission and information interaction between various modules.

[0121] A database system is used to store all data related to the smart community.

[0122] The data classification module is used to classify and process all data in the smart community and obtain all accident data in the smart community.

[0123] The accident data first verification module is used to compare and judge the occurrence frequency of different types of accidents to determine the high-frequency accidents to be verified.

[0124] The second accident data verification module is used to perform time comparison and judgment processing on the high-frequency accidents to be verified, and to determine the high-frequency accidents.

[0125] A high-frequency accident feature determination module is used to perform type analysis on data of the location of high-frequency accidents to determine the characteristics of high-frequency accidents.

[0126] The monitoring equipment installation location determination module performs parameter matching on all areas of the smart community based on the characteristics of high-frequency accidents to determine the locations with high-frequency accident occurrence characteristics.

[0127] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1.A big data-based smart community management method, characterized by, The method comprises the following steps: acquiring all data of a smart community, performing type analysis on all data of the smart community based on an intelligent management terminal, and determining high-frequency accidents and positions where the high-frequency accidents occur; performing feature analysis on the high-frequency accidents and the positions where the high-frequency accidents occur based on the intelligent management terminal, and determining high-frequency accident occurrence features; performing real-time monitoring on the smart community based on the intelligent management terminal and taking the high-frequency accident occurrence features as references; the step of acquiring all data of the smart community, performing type analysis on all data of the smart community based on the intelligent management terminal, and determining high-frequency accidents and positions where the high-frequency accidents occur comprises the following steps: performing data reading and processing on a database system of the smart community based on the intelligent management terminal, and acquiring all data of the smart community; performing data reading and processing on all data of the smart community based on the intelligent management terminal and taking data types as features, and acquiring all accident data of the smart community; performing classification processing on all accident data of the smart community based on the intelligent management terminal and taking accident types as features, and acquiring data sets of different types of accidents of the smart community; performing comparative analysis on the data sets of different types of accidents of the smart community based on the intelligent management terminal, and determining high-frequency accidents and positions where the high-frequency accidents occur; the step of performing comparative analysis on the data sets of different types of accidents of the smart community based on the intelligent management terminal, and determining high-frequency accidents and positions where the high-frequency accidents occur comprises the following steps: performing counting processing on data in the data sets of different types of accidents of the smart community based on the intelligent management terminal, and determining occurrence times of different types of accidents; performing comparative processing on the occurrence times of different types of accidents based on the intelligent management terminal, and determining high-frequency accidents to be verified; performing verification processing on the high-frequency accidents to be verified based on the intelligent management terminal and taking data sets corresponding to the high-frequency accidents to be verified as features, and determining high-frequency accidents and positions where the high-frequency accidents occur; the step of performing verification processing on the high-frequency accidents to be verified based on the intelligent management terminal and taking data sets corresponding to the high-frequency accidents to be verified as features, and determining high-frequency accidents and positions where the high-frequency accidents occur comprises the following steps: performing data extraction processing on the data sets corresponding to the high-frequency accidents to be verified based on the intelligent management terminal, and acquiring occurrence times of the high-frequency accidents to be verified; performing difference calculation on the occurrence times of the high-frequency accidents to be verified based on the intelligent management terminal, and determining an occurrence time interval data set of the high-frequency accidents to be verified; wherein the difference calculation is performed on occurrence times of adjacent time of the high-frequency accidents to be verified; performing sorting processing on data in the occurrence time interval data set of the high-frequency accidents to be verified based on a maximum value function, and acquiring a maximum occurrence time interval of accidents; performing comparative analysis on the maximum occurrence time interval of accidents based on the intelligent management terminal, and determining high-frequency accidents and positions where the high-frequency accidents occur; the step of performing comparative analysis on the maximum occurrence time interval of accidents based on the intelligent management terminal, and determining high-frequency accidents and positions where the high-frequency accidents occur comprises the following steps: The intelligent management terminal is used for data extraction and processing on the occurrence time of the high-frequency accident to be verified, to obtain the latest occurrence time of the high-frequency accident to be verified; wherein the latest occurrence time of the high-frequency accident to be verified is the latest data in the occurrence time of the high-frequency accident to be verified; The intelligent management terminal is used for data reading and processing on the timing device of the smart community, to obtain the real-time time of the smart community; The intelligent management terminal is used for difference calculation on the real-time occurrence time interval of the accident and the latest occurrence time of the high-frequency accident to be verified; The intelligent management terminal is used for judgment processing on the real-time occurrence time interval of the accident and the maximum occurrence time interval of the accident; If the real-time occurrence time interval of the accident is less than or equal to the maximum occurrence time interval of the accident, the accident is set as a high-frequency accident, and the intelligent management terminal is used for location matching on the data set of different types of accidents of the smart community with the high-frequency accident as a feature, to determine the occurrence location of the high-frequency accident; If the real-time occurrence time interval of the accident is greater than the maximum occurrence time interval of the accident, the accident is set as a solved accident. 2.The big data-based smart community management method of claim 1, wherein, The intelligent management terminal is used for comparison processing on the occurrence times of different types of accidents, to determine the high-frequency accident to be verified, which specifically includes the following steps: The intelligent management terminal is used for judgment processing on the occurrence times of different types of accidents and the set accident occurrence time threshold; If the occurrence times of different types of accidents are greater than the set accident occurrence time threshold, the type of accident is set as a high-frequency accident to be verified; If the occurrence times of different types of accidents are less than or equal to the set accident occurrence time threshold, the data set corresponding to the type of accident is set as an accidental accident data set. 3.The big data-based smart community management method of claim 1, wherein, The intelligent management terminal is used for feature analysis on the high-frequency accident and the occurrence location of the high-frequency accident, to determine the occurrence feature of the high-frequency accident, which specifically includes the following steps: The intelligent management terminal is used for data reading and processing on the data in the data set corresponding to the high-frequency accident, to obtain the occurrence time of the high-frequency accident; The intelligent management terminal is used for information matching processing on the occurrence time of the high-frequency accident and the occurrence location of the high-frequency accident, to determine the occurrence time of the accident at different occurrence locations of the high-frequency accident; The intelligent management terminal is used for data extraction processing on all accident data of the smart community with the occurrence time of the accident at different occurrence locations of the high-frequency accident as a feature, to obtain a parameter information set; wherein the parameter information set is specifically the parameter data of the different occurrence locations of the high-frequency accident before the occurrence time of the accident and the parameter data of the different occurrence locations of the high-frequency accident after the occurrence time of the accident; The intelligent management terminal is used for data analysis processing on the parameter information set, to determine the occurrence feature of the high-frequency accident. 4.The big data-based smart community management method of claim 3, wherein, The intelligent management terminal is used for data analysis processing on the parameter information set, to determine the occurrence feature of the high-frequency accident, which specifically includes the following steps: The intelligent management terminal is used for classification processing on the data in the parameter information set with the occurrence time of the accident at different occurrence locations of the high-frequency accident as a feature, to obtain parameter data of different accident occurrence times; The parameter data of different accident occurrence times is processed by intersection based on the intelligent management terminal to determine the same type parameter data, and the same type parameter data is specifically the same type parameter of all high-frequency accidents at different occurrence positions. The same type parameter data is analyzed for data change based on the intelligent management terminal to determine the parameter type causing the high-frequency accident. The parameter type causing the high-frequency accident is set as the high-frequency accident occurrence feature based on the intelligent management terminal. 5.The big data-based smart community management method of claim 1, wherein, The intelligent community is monitored in real time based on the intelligent management terminal with the high-frequency accident occurrence feature as a reference, and the specific steps include the following: The parameter matching of all areas of the intelligent community is performed based on the intelligent management terminal with the high-frequency accident occurrence feature as a reference to determine the position with the high-frequency accident occurrence feature. The data analysis of the high-frequency accident occurrence feature is performed based on the intelligent management terminal to determine the accident monitoring device. The accident monitoring device is installed according to the position with the high-frequency accident occurrence feature based on the intelligent management terminal to monitor the intelligent community in real time. 6.A big data-based smart community management system for implementing the big data-based smart community management method according to any one of claims 1-5, characterized in that, It includes: The intelligent management terminal is used to control each module to classify, compare, verify and analyze the data of the intelligent community to monitor the intelligent community in real time. The database system is used to store all data of the intelligent community. The data classification module is used to classify all data of the intelligent community to obtain all accident data of the intelligent community. The accident data first verification module is used to compare and judge the occurrence times of different types of accidents to determine the high-frequency accident to be verified. The accident data second verification module is used to compare and judge the time of the high-frequency accident to be verified to determine the high-frequency accident. The high-frequency accident feature determination module is used to analyze the data type of the high-frequency accident occurrence position to determine the high-frequency accident occurrence feature. The monitoring device installation position determination module matches the parameters of all areas of the intelligent community according to the high-frequency accident occurrence feature to determine the position with the high-frequency accident occurrence feature.

Images