Method, device and equipment for aggregated statistical analysis of accident data based on image maps

Abstract

The present application relates to an accident data aggregation statistical analysis method, device and equipment based on an image map, the method comprising: collecting accident data and performing deduplication processing on the accident data; aggregating the accident data and anonymizing unit information and personal information; performing correlation analysis on the aggregated accident data to determine the statistical laws between the accident data; visualizing the accident data on an image map at multiple scales according to the statistical laws; the multi-scale display comprises aggregating and displaying the number of accidents corresponding to each accident data at a first scale, and displaying the accident occurrence points corresponding to each accident data at a second scale, wherein the first scale is larger than the second scale. The accident data includes the time information, location information, category information, unit information and personal information of the accident. The purpose of significantly improving the quality of statistical analysis of accident information is achieved.

Description

Technical Field

[0001] The present invention belongs to the technical field of safety supervision information processing, and relates to an accident data aggregation statistical analysis method, device and equipment based on image maps. Background Art

[0002] With the continuous improvement of the safety management system, the overall safety production situation in all walks of life has gradually improved, but in general, the casualties and major property losses caused by accidents are still very serious. It is of great significance to fully understand the characteristics and laws of various types of accidents, and do a good job in accident prevention and safety hazard investigation. With the development of big data technology today, the statistics and analysis of accident laws are also developing in the direction of digitalization, informatization, and intelligence. The collection, statistics, and display of accident information play an important role in helping the heads of relevant units understand the overall situation, make good situation analysis, and arrange key tasks.

[0003] In traditional accident information statistical analysis technology, accident information is usually reported initially and then reported again. Most of the real information is directly disclosed and the relationship between accident information is simply counted. Finally, all accident points are displayed in a visual way in one figure. However, in the process of realizing the present invention, the inventor found that the traditional accident information statistical analysis technology still has the technical problem of low quality of accident information statistical analysis. Summary of the invention

[0004] In response to the problems existing in the above-mentioned traditional methods, the present invention proposes an accident data aggregation statistical analysis method based on image maps, an accident data aggregation statistical analysis device based on image maps, a computer device and a computer-readable storage medium, which can greatly improve the quality of statistical analysis of accident information.

[0005] In order to achieve the above objectives, the embodiments of the present invention adopt the following technical solutions:

[0006] On the one hand, a method for aggregated statistical analysis of accident data based on image maps is provided, comprising the steps of:

[0007] Collect accident data and perform deduplication processing on the accident data; accident data includes the time information, location information, category information, unit information and personal information of the accident;

[0008] Aggregate accident data and anonymize unit and personal information;

[0009] Conduct correlation analysis on the aggregated accident data to determine the statistical regularities between the accident data;

[0010] According to statistical laws, accident data is visualized in a multi-scale display on the image map; the multi-scale display includes aggregated display of the number of accidents corresponding to each accident data at a first scale, and separate display of the accident occurrence points corresponding to each accident data at a second scale, where the first scale is larger than the second scale.

[0011] In one embodiment, the process of deduplicating accident data includes:

[0012] Determine whether the accident data is a duplicate record accident based on the weighted fuzzy comparison method;

[0013] If so, the accident data is merged into the same accident data already recorded;

[0014] If not, the accident data is stored in the accident database.

[0015] In one embodiment, the step of aggregating the accident data and anonymizing the unit information and personal information includes:

[0016] A setting ID is used to represent the accident name, unit information and personal information of the accident data stored in the accident database; the setting ID includes an a-ID for representing the accident name, a u-ID for representing the unit information and a p-ID for representing the personal information.

[0017] In one embodiment, the step of aggregating the accident data and anonymizing the unit information and personal information further includes:

[0018] If the unit information contains a hierarchical relationship, the unit information of the superior unit and the unit information of the subordinate unit are established separately, and the association relationship between the subordinate unit and the accident is incorporated into the association relationship between the superior unit and the accident.

[0019] In one embodiment, the step of performing correlation analysis on the aggregated accident data to determine the statistical regularity between the accident data includes:

[0020] Analyze and determine the statistical patterns of high-incidence accidents in months, time periods, locations, categories and large units based on time information, location information, category information and unit information;

[0021] Conduct combined correlation analysis on time information, location information, category information and unit information to determine the statistical laws of accident classification; the statistical laws of accident classification include the statistical laws of category and time, the statistical laws of category and unit, the statistical laws of time and location, the statistical laws of category and number of casualties, and the statistical laws of unit and time.

[0022] In one embodiment, the step of visually displaying accident data at multiple scales on an image map according to statistical rules includes:

[0023] Mark the occurrence point of each accident data on the two-dimensional image map according to the latitude and longitude of the location information and display the statistical rules;

[0024] Calculate the distance between each accident data point and surrounding points respectively;

[0025] If the distances between each point in the target map area do not exceed the set distance threshold, the number of accidents corresponding to each accident data is aggregated and displayed at the first scale;

[0026] If the distance between each point in the target map area exceeds the set distance threshold, the accident occurrence point corresponding to each accident data is displayed on the second scale.

[0027] In one embodiment, time information includes the date data and hour and minute data of the accident, location information includes the province, city, county (district) and longitude and latitude of the accident site, category information includes vehicle traffic accidents, fire accidents or poisoning accidents, unit information includes the superior and subordinate units involved in the accident, and personal information includes job data and casualties.

[0028] On the other hand, a device for aggregating and statistically analyzing accident data based on an image map is also provided, comprising:

[0029] The data collection module is used to collect accident data and perform deduplication processing on the accident data; the accident data includes the time information, location information, category information, unit information and personal information of the accident;

[0030] Aggregation processing module, used to aggregate accident data and anonymize unit information and personal information;

[0031] The correlation analysis module is used to perform correlation analysis on the aggregated accident data and determine the statistical rules between the accident data;

[0032] The visualization module is used to visualize the accident data in a multi-scale manner on the image map according to statistical laws; the multi-scale display includes aggregated display of the number of accidents corresponding to each accident data at a first scale, and separate display of the accident occurrence points corresponding to each accident data at a second scale, wherein the first scale is larger than the second scale.

[0033] On the other hand, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned image map-based accident data aggregation statistical analysis method when executing the computer program.

[0034] On the other hand, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned image map-based accident data aggregation statistical analysis method are implemented.

[0035] One of the above technical solutions has the following advantages and beneficial effects:

[0036] The above-mentioned accident data aggregation statistical analysis method, device and equipment based on image map collects accident data and removes duplication, aggregates it, anonymizes the privacy information of units and individuals, and then performs correlation analysis on the accident data. Finally, it performs multi-scale visualization on the image map, thereby avoiding problems such as information duplication and privacy exposure, and fully utilizes the multi-dimensional attributes and correlation relationships between accident data to maximize the value of the data. Finally, it optimizes the display effect through visual multi-scale display on the image map.

[0037] Compared with traditional accident information statistical analysis technology, the above solution uses a comprehensive deduplication method based on multiple parameters such as the time, location and unit of the accident, solving the problem of how to determine whether the accident data reported through multiple channels are reported repeatedly. The real unit and personal information are hidden in an anonymous manner to solve the problem of protecting the privacy of units and individuals. By displaying information at multiple scales on the image map, the problem of information sharing and analysis is solved, and accidents at similar locations can be aggregated and displayed, with different display effects displayed at multiple scales, solving the problem of being unable to see the information on the map due to too dense points, thereby achieving the purpose of significantly improving the quality of statistical analysis of accident information. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the conventional technology, the drawings required for use in the embodiments or the conventional technology descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0039] Figure 1 It is a flowchart of an accident data aggregation statistical analysis method based on an image map in one embodiment;

[0040] Figure 2 It is a flowchart of an accident data aggregation statistical analysis method based on an image map in another embodiment;

[0041] Figure 3 A schematic diagram for visual display in an embodiment;

[0042] Figure 4 Schematic diagram of the module structure of an accident data aggregation and statistical analysis device based on image maps in one embodiment. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0044] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0045] It should be noted that the reference to "embodiment" in this document means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The presentation of the phrase at various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments.

[0046] Those skilled in the art will appreciate that the embodiments described herein may be combined with other embodiments. The term "and / or" used in the present specification and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0047] During the research work, the inventor found that there are still some problems to be solved in the traditional statistical analysis technology of accident information: First, when an accident occurs, the information reported initially is often incomplete or inaccurate, and needs to be supplemented by follow-up reports. If multiple units or departments are involved, there is a problem of repeated reporting. It is necessary to make quick judgments through information technology to reduce the pressure of manual review and verification. Second, if the units or individuals involved in the accident have some sensitive information, it is not convenient to expose too much, and it is necessary to maintain a balance between statistically complete real information and hiding sensitive information. Third, in the era of big data, a large amount of valuable information often exists in the correlation of information, rather than the information itself. How to use the multidimensional attributes and correlation of information itself is an important topic of statistical analysis. Fourth, when all accident points are displayed in one picture, the dense points are shocking, but they will also affect the display effect, and then interfere with the judgment of decision makers. How to choose between the simplicity and authenticity of map display is also worth studying. In general, the statistical analysis quality of accident information is not high, which is not conducive to efficient application in actual work.

[0048] Based on the above situation, this application designs an accident data aggregation statistical analysis method based on image maps, which uses a weighted comprehensive analysis method of multiple parameters such as the time, location and unit of the accident to determine the similarity of the reported information and remove duplicate information; uses set ID codes to hide the sensitive information of real units and individuals to ensure that sensitive information is not exposed; displays accident information and shows related relationships on image maps through multi-condition and multi-layer screening; accidents in similar locations can be displayed in an aggregated manner, and accident points can be displayed at multiple scales.

[0049] The following will describe the implementation of the present invention in detail with reference to the accompanying drawings in the embodiment diagram of the present invention.

[0050] See also Figure 1 In one embodiment, the present application provides an accident data aggregation statistical analysis method based on an image map, comprising the following processing steps S12 to S18:

[0051] S12, collecting accident data and performing deduplication processing on the accident data; the accident data includes time information, location information, category information, unit information and personal information of the accident.

[0052] It is understandable that there may be multiple accident data, which may be collected through, but not limited to, reporting from various places, online monitoring of the accident monitoring system, and data server crawling. Each accident data may include, but is not limited to, the recorded accident name, time information, location information, category information, unit information, and personal information. Deduplication of accident data refers to merging / deleting two or more identical accident data (such as duplicate reports) in the collected accident data so that only one accident data of the same type is retained.

[0053] S14, aggregate the accident data and anonymize unit information and personal information.

[0054] It can be understood that aggregation processing refers to the use of set symbols to represent private information in accident data, such as but not limited to using the same set symbol to represent accidents of the same category, using the same set symbol to represent the same superior / subordinate unit involved in different accidents, and using the same set symbol to represent the same person involved in different accidents. Each set symbol can be a computer language symbol, geometric symbol or natural language symbol that can be recognized and processed by the computer. The collected accident data will be stored in the accident database, which can be configured with information tables for storing accident (name / category), unit and individual information, which can record real unit information and personal information. However, when visually displaying statistical information to the outside world, the unit and personal information will be displayed instead of set symbols, that is, anonymization will be performed by setting symbols to achieve the purpose of personal privacy inclusion.

[0055] S16, performing correlation analysis on the aggregated accident data to determine the statistical regularities between the accident data.

[0056] It can be understood that for all the collected accident data, correlation statistical analysis can be performed based on their element information to determine the statistical rules between the accident data, such as but not limited to the correlation statistics between high-incidence accident statistics and various elements.

[0057] S18, visually displaying the accident data at multiple scales on the image map according to statistical rules; the multiple scale display includes displaying the number of accidents corresponding to each accident data in an aggregated manner at a first scale, and displaying the accident occurrence points corresponding to each accident data at a second scale, wherein the first scale is larger than the second scale.

[0058] It can be understood that the image map can be a two-dimensional image map or a three-dimensional or higher-dimensional image map, which can be determined according to the needs of visualization. The first scale can also be called a large scale relative to the second scale, and correspondingly, the second scale can also be called a small scale. The large scale and the small scale can be distinguished according to the scale of the image map. For example, the display of accident data on an image map zoomed in to a certain scale can be called a large-scale display. At this time, accidents (points) at similar locations are aggregated and displayed, such as only showing the number of accidents; correspondingly, the display of accident data on an image map zoomed out to a certain scale (smaller than the scale of the large scale) can be called a small-scale display. At this time, the number of accidents originally displayed in an aggregated manner is displayed separately as each accident point in the area.

[0059] Specifically, the statistical rules between accident data can be visualized in the form of statistical charts, or directly displayed on the image map, in conjunction with the point aggregation or separate display of each accident data, to display the correlation between each accident, etc., with a concise and flexible visualization display method that can be filtered by multiple conditions and multiple layers, effectively improving the quality of statistical analysis of accident information, thereby avoiding the problem of being unable to see the information on the map due to too dense points at a single scale, and ensuring that decision makers will not be disturbed by the complexity of information when viewing the image map.

[0060] The above-mentioned accident data aggregation and statistical analysis method based on image maps collects accident data and removes duplications, aggregates it, anonymizes the privacy information of units and individuals, and then performs correlation analysis on the accident data. Finally, it performs multi-scale visualization on the image map, thereby avoiding problems such as information duplication and privacy exposure. It also makes full use of the multi-dimensional attributes and correlation relationships between accident data to maximize the value of the data. Finally, it optimizes the display effect through multi-scale visualization on the image map.

[0061] Compared with traditional accident information statistical analysis technology, the above solution uses a comprehensive deduplication method based on multiple parameters such as the time, location and unit of the accident, solving the problem of how to determine whether the accident data reported through multiple channels are reported repeatedly. The real unit and personal information are hidden in an anonymous manner to solve the problem of protecting the privacy of units and individuals. By displaying information at multiple scales on the image map, the problem of information sharing and analysis is solved, and accidents at similar locations can be aggregated and displayed, with different display effects displayed at multiple scales, solving the problem of being unable to see the information on the map due to too dense points, thereby achieving the purpose of significantly improving the quality of statistical analysis of accident information.

[0062] In one embodiment, the recorded time information may include in detail the date data and time and minute data of the accident, the location information may include the province, city, county (district) and longitude and latitude of the accident site, the category information may include vehicle traffic accidents, fire accidents or poisoning accidents, the unit information may include the superior and subordinate units involved in the accident, and the personal information may include job data and casualties.

[0063] By recording in-depth and detailed information about accident-related factors, the accuracy of statistical analysis of accident data can be effectively improved without exposing personal privacy.

[0064] In one embodiment, the process of deduplicating the accident data in step S12 includes:

[0065] Determine whether the accident data is a duplicate record accident based on the weighted fuzzy comparison method;

[0066] If so, the accident data is merged into the same accident data already recorded;

[0067] If not, the accident data is stored in the accident database.

[0068] It can be understood that the weighted fuzzy comparison method is also a method that uses similarity weighting processing. j Compared with the original accident data A in the accident database i Compare the data and record the similarity S between the two ij =α1f1+α2f2+α3f3+α4f4+α5f5, where f1, f2, f3, f4, f5 represent the similarity of time information, location information, category information, unit information and personal information respectively, and α1, α2, α3, α4, α5 represent the weight value of the similarity of these element information respectively. If the similarity of two accident data exceeds the set similarity threshold, they are considered to be the same accident, and the newly collected accident data is merged into the original accident data.

[0069] Taking location as an example, if the province is the same, the similarity is 30%; if the city is the same, the similarity is 60%; if the county is the same, the similarity is 90%; if the latitude and longitude are the same to 3 decimal places, the similarity is 100%. The similarity and weight of each element information can be set based on experience in the early stage, and can be adjusted accordingly as data accumulates. It should be noted that the sum of all weight values ​​should be 1.

[0070] Through the above-mentioned deduplication based on weighted fuzzy comparison, a method of weighted comprehensive analysis of multiple parameters such as the time, location and unit of the accident is utilized to solve the problem of how to determine whether the accident information reported through multiple channels is a duplicate report.

[0071] In one embodiment, the above step S14 may specifically include the following processing steps:

[0072] A setting ID is used to represent the accident name, unit information and personal information of the accident data stored in the accident database; the setting ID includes an a-ID for representing the accident name, a u-ID for representing the unit information and a p-ID for representing the personal information.

[0073] It can be understood that in this embodiment, a-ID can be used to represent the (name) number of the accident, u-ID can represent the unit involved in the accident, and p-ID can represent the individual involved in the accident. The accident database stores information tables of the accident (name), unit, and individual, etc., but when visually displaying statistical information to the outside, sensitive privacy information such as specific unit details and personnel identities are hidden, and only the aforementioned numbers are retained to achieve anonymization and protect the privacy of the unit or individual.

[0074] In one embodiment, the above step S14 may further include the following processing steps:

[0075] If the unit information contains a hierarchical relationship, the unit information of the superior unit and the unit information of the subordinate unit are established separately, and the association relationship between the subordinate unit and the accident is incorporated into the association relationship between the superior unit and the accident.

[0076] Specifically, if the unit information in the accident data includes units involved in the accident that have a superior-subordinate relationship, then unit information will be established for both the superior and subordinate units, and the relationship between the subordinate unit and the accident will be included in the relationship between the subordinate superior unit and the accident, thereby achieving further data aggregation effects and further utilizing the relationship between the accident data.

[0077] In one embodiment, the above step S16 may specifically include the following processing steps:

[0078] Analyze and determine the statistical patterns of high-incidence accidents in months, time periods, locations, categories and large units based on time information, location information, category information and unit information;

[0079] Conduct combined correlation analysis on time information, location information, category information and unit information to determine the statistical laws of accident classification; the statistical laws of accident classification include the statistical laws of category and time, the statistical laws of category and unit, the statistical laws of time and location, the statistical laws of category and number of casualties, and the statistical laws of unit and time.

[0080] Specifically, the statistical patterns of high-incidence accidents in months, time periods, locations, categories and units can be analyzed based on information on factors such as time, location, category and unit, so as to determine which months are accident-prone months, which time periods are accident-prone periods, which categories of accidents are high-incidence accidents, and which units are accident-prone units.

[0081] In addition, it is also possible to conduct combined correlation analysis on each element information, such as analyzing the statistical laws between category and time, category and unit, time and location, category and number of casualties, etc., so as to display them on statistical charts or image maps, especially to classify and count the category and time of the accident according to the nature of the unit. In this way, the multi-dimensional attributes and correlation relationships of the accident data itself can be fully explored and utilized to maximize the value of statistical analysis applications.

[0082] In one embodiment, Figure 2 and Figure 3 As shown, the above step S18 may specifically include the following processing steps:

[0083] Mark the occurrence point of each accident data on the two-dimensional image map according to the latitude and longitude of the location information and display the statistical rules;

[0084] Calculate the distance between each accident data point and surrounding points respectively;

[0085] If the distances between each point in the target map area do not exceed the set distance threshold, the number of accidents corresponding to each accident data is aggregated and displayed at the first scale;

[0086] If the distance between each point in the target map area exceeds the set distance threshold, the accident occurrence point corresponding to each accident data is displayed on the second scale.

[0087] It can be understood that in this embodiment, the visualization is performed on the two-dimensional image map, and generally a multi-layer, multi-scale display method is adopted in which accident data with similar occurrence locations are aggregated and displayed on the large-scale map and separately displayed on the small-scale map.

[0088] like Figure 2The figure shows a specific statistical analysis processing flow diagram of the above-mentioned accident data aggregation statistical analysis method based on image maps. In the visual display, specifically, each accident point is marked on the two-dimensional image map according to the longitude and latitude information, and the distance between each accident point and its surrounding points is calculated respectively. Given a set threshold, if the distance between points within a certain range on an image map of a certain scale (such as a large scale) does not exceed the set threshold, then these points will be aggregated and displayed on the large-scale image map, such as only showing the number of accidents; when the map scale is adjusted to an appropriate range (such as zooming in on the image map to reduce the scale), when the display distance between the points is large enough, the accident points will be displayed separately again, such as Figure 3 shown.

[0089] Through the above-mentioned visualization display, the functions of aggregated display of accidents in similar locations and multi-scale display of different display effects are provided, so as to display the final results of statistical analysis with higher display quality.

[0090] It should be understood that although Figure 1 and Figure 2 The steps in the flowchart are shown in sequence as indicated by the arrows, but the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of the steps, and the steps can be executed in other orders. Figure 1 and Figure 2 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequentially, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0091] See also Figure 4In one embodiment, an accident data aggregation statistical analysis device 100 based on an image map is provided, comprising a data acquisition module 11, an aggregation processing module 13, an association analysis module 15 and a visualization module 17. The data acquisition module 11 is used to collect accident data and perform deduplication processing on the accident data; the accident data includes time information, location information, category information, unit information and personal information of the accident. The aggregation processing module 13 is used to aggregate the accident data and anonymize the unit information and personal information. The association analysis module 15 is used to perform association analysis on the aggregated accident data to determine the statistical laws between the accident data. The visualization module 17 is used to visualize the accident data on the image map in a multi-scale manner according to the statistical laws; the multi-scale display includes aggregating and displaying the number of accidents corresponding to each accident data on a first scale, and displaying the accident occurrence points corresponding to each accident data on a second scale, wherein the first scale is larger than the second scale.

[0092] The above-mentioned accident data aggregation and statistical analysis device 100 based on image map, through the collaboration of various modules, collects accident data and removes duplication, then aggregates it, anonymizes the privacy information of units and individuals, and then performs correlation analysis on the accident data. Finally, it performs multi-scale visual display on the image map, thereby avoiding problems such as information duplication and privacy exposure, and fully utilizes the multi-dimensional attributes and correlation relationships between accident data to maximize the value of the data. Finally, through the visual multi-scale display on the image map, the display effect is optimized.

[0093] Compared with traditional accident information statistical analysis technology, the above solution uses a comprehensive deduplication method based on multiple parameters such as the time, location and unit of the accident, solving the problem of how to determine whether the accident data reported through multiple channels are reported repeatedly. The real unit and personal information are hidden in an anonymous manner to solve the problem of protecting the privacy of units and individuals. By displaying information at multiple scales on the image map, the problem of information sharing and analysis is solved, and accidents at similar locations can be aggregated and displayed, with different display effects displayed at multiple scales, solving the problem of being unable to see the information on the map due to too dense points, thereby achieving the purpose of significantly improving the quality of statistical analysis of accident information.

[0094] In one embodiment, the time information includes the date data and hour and minute data of the accident, the location information includes the province, city, county (district) and longitude and latitude of the accident site, the category information includes vehicle traffic accidents, fire accidents or poisoning accidents, the unit information includes the superior and subordinate units involved in the accident, and the personal information includes job data and casualties.

[0095] In one embodiment, the process of deduplication processing of accident data includes:

[0096] Determine whether the accident data is a duplicate record accident based on the weighted fuzzy comparison method;

[0097] If so, the accident data is merged into the same accident data already recorded;

[0098] If not, the accident data is stored in the accident database.

[0099] In one embodiment, the above-mentioned aggregation processing module 13 can be specifically used to use a set ID to represent the accident name, unit information and personal information of the accident data stored in the accident database. The set ID includes an a-ID for representing the accident name, a u-ID for representing the unit information and a p-ID for representing the personal information.

[0100] In one embodiment, the aggregation processing module 13 can also be used to establish the unit information of the superior unit and the unit information of the subordinate unit respectively when the unit information contains the superior-subordinate affiliation relationship, and incorporate the association relationship between the subordinate unit and the accident into the association relationship between the superior unit and the accident.

[0101] In one embodiment, the above-mentioned association analysis module 15 can be specifically used to analyze and determine the statistical patterns of high-incidence accidents in months, time periods, locations, categories and large units based on time information, location information, category information and unit information; perform combined association analysis on time information, location information, category information and unit information to determine the statistical patterns of accident classification; the statistical patterns of accident classification include the statistical patterns of category and time, the statistical patterns of category and unit, the statistical patterns of time and location, the statistical patterns of category and number of casualties, and the statistical patterns of unit and time.

[0102] In one embodiment, the visualization module 17 may be specifically used for:

[0103] Mark the occurrence point of each accident data on the two-dimensional image map according to the latitude and longitude of the location information and display the statistical rules;

[0104] Calculate the distance between each accident data point and surrounding points respectively;

[0105] When the distances between all points in the target map area do not exceed the set distance threshold, the number of accidents corresponding to each accident data is aggregated and displayed at the first scale;

[0106] When the distance between each point in the target map area exceeds the set distance threshold, the accident occurrence point corresponding to each accident data is displayed on the second scale.

[0107] Regarding the specific limitations of the accident data aggregation and statistical analysis device 100 based on image maps, please refer to the corresponding limitations of the accident data aggregation and statistical analysis method based on image maps above, which will not be repeated here. Each module in the above-mentioned accident data aggregation and statistical analysis device 100 based on image maps can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of a device with a specific data processing function in the form of hardware, or can be stored in the memory of the aforementioned device in the form of software, so that the processor can call and execute the operations corresponding to the above modules. The aforementioned devices can be, but are not limited to, various types of accident statistical analysis devices in various industries already available in the field.

[0108] In one embodiment, a computer device is also provided, including a memory and a processor, the memory stores a computer program, and the processor implements the following processing steps when executing the computer program: collecting accident data and performing deduplication processing on the accident data; aggregating the accident data, anonymizing unit information and personal information; performing correlation analysis on the aggregated accident data to determine the statistical laws between the accident data; visualizing the accident data in a multi-scale display on an image map according to the statistical laws; the multi-scale display includes aggregating and displaying the number of accidents corresponding to each accident data at a first scale, and displaying the accident occurrence points corresponding to each accident data at a second scale, wherein the first scale is larger than the second scale. The accident data includes the time information, location information, category information, unit information and personal information of the accident.

[0109] It can be understood that in addition to the memory and processor mentioned above, the above-mentioned computer device also includes other software and hardware components not listed in this specification. The specific components can be determined according to the model of the specific data processing device in different application scenarios, and this specification will not list them one by one in detail.

[0110] In one embodiment, when the processor executes the computer program, it can also implement the steps or sub-steps added in each embodiment of the above-mentioned accident data aggregation statistical analysis method based on image map.

[0111] In one embodiment, a computer-readable storage medium is also provided, on which a computer program is stored, and when the computer program is executed by a processor, the following processing steps are implemented: collecting accident data and performing deduplication processing on the accident data; aggregating the accident data, anonymizing unit information and personal information; performing correlation analysis on the aggregated accident data, and determining the statistical laws between the accident data; visualizing the accident data on an image map at multiple scales according to the statistical laws; the multiple scale display includes aggregating and displaying the number of accidents corresponding to each accident data at a first scale, and displaying the accident occurrence points corresponding to each accident data at a second scale, wherein the first scale is larger than the second scale. The accident data includes the time information, location information, category information, unit information and personal information of the accident.

[0112] In one embodiment, when the computer program is executed by a processor, it can also implement the steps or sub-steps added in each embodiment of the above-mentioned accident data aggregation statistical analysis method based on image map.

[0113] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus dynamic random access memory (Rambus DRAM, referred to as RDRAM) and interface dynamic random access memory (DRDRAM).

[0114] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0115] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and all of them belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for aggregated statistical analysis of accident data based on image maps, characterized in that: Includes steps: Collecting accident data and performing deduplication processing on the accident data; the accident data includes time information, location information, category information, unit information and personal information of the accident; Aggregate the accident data and anonymize the unit information and the personal information; Performing correlation analysis on the aggregated accident data to determine statistical rules among the accident data; According to the statistical law, the accident data is visualized in a multi-scale display on the image map; the multi-scale display includes aggregated display of the number of accidents corresponding to each accident data at a first scale, and respectively displaying the accident occurrence points corresponding to each accident data at a second scale, wherein the first scale is larger than the second scale, wherein the occurrence point of each accident data is marked on the two-dimensional image map according to the longitude and latitude of the location information and the statistical law is displayed; The point distances between each accident data point and the surrounding points are calculated respectively; if the distances between each point in the target map area do not exceed the set distance threshold, the number of accidents corresponding to each accident data is aggregated and displayed on the first scale; if the distances between each point in the target map area exceed the set distance threshold, the accident occurrence points corresponding to each accident data are displayed respectively on the second scale.

2. The method for aggregated statistical analysis of accident data based on image maps according to claim 1, characterized in that: The process of deduplicating the accident data includes: Determining whether the accident data is a repeated record accident according to a weighted fuzzy comparison method; If yes, then the accident data is merged into the same accident data that has been recorded; If not, the accident data is stored in the accident database.

3. The method for aggregated statistical analysis of accident data based on image maps according to claim 1 or 2, characterized in that: The step of aggregating the accident data and anonymizing the unit information and the personal information includes: A setting ID is used to represent the accident name, unit information and personal information of the accident data stored in the accident database; the setting ID includes an a-ID for representing the accident name, a u-ID for representing the unit information and a p-ID for representing the personal information.

4. The method for aggregated statistical analysis of accident data based on image maps according to claim 3 is characterized in that: The step of aggregating the accident data and anonymizing the unit information and the personal information also includes: If the unit information includes a superior-subordinate relationship, the unit information of the superior unit and the unit information of the subordinate unit are established respectively, and the association relationship between the subordinate unit and the accident is incorporated into the association relationship between the superior unit and the accident.

5. The method for aggregated statistical analysis of accident data based on image maps according to claim 1, characterized in that: The step of performing correlation analysis on the aggregated accident data to determine the statistical regularity between the accident data includes: Analyze and determine the statistical regularity of high-incidence accidents in months, time periods, locations, categories and large units according to the time information, the location information, the category information and the unit information; The time information, the location information, the category information and the unit information are combined and correlated to determine the statistical law of accident classification; the statistical law of accident classification includes the statistical law of category and time, the statistical law of category and unit, the statistical law of time and location, the statistical law of category and number of casualties, and the statistical law of unit and time.

6. The method for aggregated statistical analysis of accident data based on image maps according to claim 2, characterized in that: The time information includes the date data and hour and minute data of the accident, the location information includes the province, city, county (district) and longitude and latitude of the accident site, the category information includes vehicle traffic accidents, fire accidents or poisoning accidents, the unit information includes the superior and subordinate units involved in the accident, and the personal information includes job data and casualties.

7. An accident data aggregation and statistical analysis device based on image maps, characterized in that: include: A data collection module, used for collecting accident data and performing deduplication processing on the accident data; The accident data includes the time information, location information, category information, unit information and personal information of the accident; An aggregation processing module, used for performing aggregation processing on the accident data and anonymizing the unit information and the personal information; A correlation analysis module, used to perform correlation analysis on the aggregated accident data to determine the statistical regularity between the accident data; A visualization module, for visually displaying the accident data in multiple scales on an image map according to the statistical law; the multiple scale display includes displaying the number of accidents corresponding to each accident data in an aggregated manner on a first scale, and displaying the accident occurrence points corresponding to each accident data on a second scale, wherein the first scale is larger than the second scale, wherein the occurrence point of each accident data is marked on a two-dimensional image map according to the longitude and latitude of the location information and the statistical law is displayed; The point distances between each accident data point and the surrounding points are calculated respectively; if the distances between each point in the target map area do not exceed the set distance threshold, the number of accidents corresponding to each accident data is aggregated and displayed on the first scale; if the distances between each point in the target map area exceed the set distance threshold, the accident occurrence points corresponding to each accident data are displayed respectively on the second scale.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the accident data aggregation statistical analysis method based on image map are implemented as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the accident data aggregation statistical analysis method based on image maps described in any one of claims 1 to 6 are implemented.

Images