WO2022126979A1 - 灾难密度的统计方法、装置、计算机设备以及存储介质 - Google Patents

灾难密度的统计方法、装置、计算机设备以及存储介质 Download PDF

Info

Publication number
WO2022126979A1
WO2022126979A1 PCT/CN2021/090837 CN2021090837W WO2022126979A1 WO 2022126979 A1 WO2022126979 A1 WO 2022126979A1 CN 2021090837 W CN2021090837 W CN 2021090837W WO 2022126979 A1 WO2022126979 A1 WO 2022126979A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
user
database
points
disaster
Prior art date
Application number
PCT/CN2021/090837
Other languages
English (en)
French (fr)
Inventor
杨玲
Original Assignee
平安科技(深圳)有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安科技(深圳)有限公司 filed Critical 平安科技(深圳)有限公司
Publication of WO2022126979A1 publication Critical patent/WO2022126979A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29Geographical information databases
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24Querying
    • G06F16/245Query processing
    • G06F16/2458Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2462Approximate or statistical queries
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24Querying
    • G06F16/248Presentation of query results
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/906Clustering; Classification
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063Operations research, analysis or management
    • G06Q10/0635Risk analysis of enterprise or organisation activities
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10Services
    • G06Q50/26Government or public services
    • G06Q50/265Personal security, identity or safety

Definitions

  • the present application relates to the technical field of big data, and in particular, to a statistical method, apparatus, computer equipment and storage medium for disaster density.
  • Fire is one of the most common disasters that threaten life and property safety. Its causes are complex and changeable, and once it occurs, it will give people a very short time to respond. Effective assessment of the urban fire risk level can lead to greater fire prevention measures in the area in advance, such as: strengthening the investigation of escape routes, increasing fire-fighting equipment, etc. At present, many people in the industry have done a lot of research on fire prediction, but they are limited to certain specific scenarios, and the data acquisition is difficult and the accuracy is low.
  • the occurrence of fire is composed of disaster-pregnant environment and disaster-causing factors.
  • Hazardous factors are composed of events, such as throwing cigarette butts, long-term heating of circuits, use of open flames, etc. The occurrence of these events is difficult to observe and prevent.
  • the surrounding environment is relatively stable, so it is feasible to conduct a fire risk assessment on the disaster-pregnant environment.
  • the present application provides a statistical method of disaster density to solve the technical problems of low verification efficiency and high verification labor cost in high-risk areas.
  • the statistical method of disaster density proposed in this application includes the following steps:
  • a disaster density statistics device comprising:
  • a first data acquisition module configured to acquire a user's name, and acquire user information from a first preset database according to the user's name;
  • a second data acquisition module configured to acquire user association information from the second preset database according to the selected disaster event type and the user information
  • a third data acquisition module configured to input the user association information into a third preset database to obtain the latitude and longitude information of the user association information
  • the density clustering statistics module is used to calculate the longitude and latitude information according to the clustering algorithm to obtain disaster event clusters.
  • a computer device comprising a memory and a processor, wherein computer-readable instructions are stored in the memory, and when the computer-readable instructions are executed by the processor, the following steps are performed:
  • one or more readable storage media storing computer-readable instructions that, when executed by one or more processors, cause the one or more The processor performs the following steps:
  • the statistical method, device, computer and medium of disaster density proposed in this application can reduce a large amount of labor costs required for on-site investigation at the user's location, and only need to obtain user-related data from the company's own or a third-party preset database. Then, through the density clustering algorithm, it can be counted whether there are dense clusters of disaster events near the geographic location of the insured user. Combined with map visualization, it can make operators intuitive Displays the density of possible catastrophic events around the user.
  • Fig. 1 is the flow chart of the disaster density statistical method based on the density clustering algorithm proposed by the present application
  • FIG. 2 is a flowchart of another embodiment of the disaster density statistical method based on the density clustering algorithm proposed by the present application;
  • Fig. 3 is the concrete flow chart of the disaster density statistical method when the disaster type is fire
  • Fig. 4 is the concrete flow chart of the disaster density statistical method when the disaster type is traffic accident
  • Fig. 5 is the concrete flow chart of the disaster density statistical method when the disaster type is flooding
  • FIG. 6 is a schematic diagram of the structure of the disaster density statistics device.
  • S1 obtain the user's name, and obtain user information from the first preset database according to the user's name;
  • the above-mentioned user information includes user information, types of insurance policies that the user applies for, etc., and specific disaster event types, such as fires, traffic accidents, etc., can be set corresponding to different types of insurance policies.
  • S2 Obtain user association information from the second preset database according to the selected disaster event type and user information, where the user association information includes disaster event points related to the user;
  • the user-related data obtains various information associated with the above-mentioned user input from the second preset database of the user or a third party, so as to be used for subsequent analysis.
  • the specific disaster events corresponding to the types of insurance policies of different users can be It is required to select a different second preset database of itself or a third party, and the second preset database includes the insurance company's risk information database, industrial and commercial information database, public security information database, traffic police information database, and court information database as the above-mentioned second preset database. .
  • the user association information in the above step S2 includes the disaster event point related to the user and its occurrence address or location.
  • Disaster events can include fires, traffic accidents, flooding, etc., depending on specific needs.
  • S3 Input the user association information into a third preset database to obtain the latitude and longitude information of the user association information;
  • necessary data is extracted from the associated data obtained in the second preset database, such as geographic information such as addresses and locations of disaster events, and the latitude and longitude of the geographic information such as the addresses and locations of disaster events are matched from the third preset database.
  • the above-mentioned third preset database is a geographic information system.
  • GIS Geographic Information System
  • GIS Geographic Information System
  • GIS can apply information from different sources in different forms.
  • the basic requirement for the source data is to determine the location of the variable, possibly labelled by x, y, z coordinates of longitude, latitude and altitude.
  • the above variable refers to the user association information in step S2, that is, the address/location information in the user association information is input into the geographic information system, and the corresponding latitude and longitude of the user association information is obtained. So far, through the geographic information system, the location of the disaster, which is the user-related information, can be converted into a point p composed of latitude and longitude (x, y), and then used for the next density-based clustering algorithm for analysis.
  • S4 Obtain disaster event clusters, calculate longitude and latitude information according to a clustering algorithm, and obtain disaster event clusters.
  • the density-based clustering algorithm in the above step S4 may be a DBSCAN density clustering algorithm.
  • DBSCAN Density-Based Spatial Clustering of Applications with Noise
  • the algorithm divides regions with sufficient density into clusters and finds clusters of arbitrary shape in a noisy inter-database, which defines a cluster as the largest set of density-connected points.
  • the algorithm utilizes the concept of density-based clustering, which requires that the number of objects (points or other spatial objects) contained in a certain area in the clustering space is not less than a given threshold.
  • the significant advantage of the DBSCAN algorithm is that the clustering speed is fast and it can effectively deal with noise points and find spatial clusters of arbitrary shapes.
  • sample set D (x1,x2,...,xm), neighborhood parameters ( ⁇ , MinPts), sample distance measure
  • cluster partition C ⁇ C1,C2,...,Ck ⁇ .
  • each disaster location has latitude and longitude (x, y), x and y correspond to the longitude and latitude of the disaster location respectively, and each disaster location obtained in step S3 can be used as data set D of a point.
  • MinPts is the minimum number of domain points for a given computer to become a core object in the ⁇ domain, that is, if there are MinPts other disaster occurrence locations in the radius ⁇ of a disaster location p, then the p can be regarded as a core point. .
  • the dataset D containing the latitude and longitude of all disaster locations is initialized to all unprocessed points, and the neighborhood parameters ( ⁇ , MinPts) are set in the algorithm.
  • is set to 10 meters, that is, a disaster is expected If there is another disaster occurrence location within a radius of 10 meters, the two disaster occurrence locations can form a cluster; MinPts is set to 3, that is, there are 3 other disaster occurrence locations within a radius of 10 meters from the disaster location p, Then the p can be regarded as a core point.
  • the purpose of the DBSCAN algorithm is to filter low-density areas and find dense sample points. Unlike traditional hierarchical-based clustering and partition-clustering convex clusters, this algorithm can find clusters of arbitrary shapes.
  • the underwriter can know whether there is a disaster event cluster near the location of the insured user.
  • Parameters such as the size of the event cluster evaluate the possibility of the insured user going out of danger.
  • the step further includes setting a prompt distance, and when the user's position distance is less than the distance of the disaster event cluster, a prompt is issued.
  • the prompt distance can be set in the method in advance. Only when the user's location distance is less than the distance of the above disaster event cluster, the notification will be sent to the underwriters. Prompt information to further intervene in the underwriting work.
  • the above-mentioned statistical method for disaster density further includes step S5 after step S4:
  • S5 Output the disaster event cluster to the map application to overlay and display the high-risk areas represented by the disaster event cluster on the map.
  • the above-mentioned clusters of disaster events can be output to the map application, and the high-risk areas represented by the clusters can be superimposed on the map, so that the underwriters can more intuitively determine the locations of high-risk areas with dense disaster events. for early countermeasures.
  • the above-mentioned statistical method for disaster density further includes step S6 after step S5:
  • the digest information is obtained by hashing the map, for example, by using the SHA256s algorithm.
  • Uploading summary information to the blockchain ensures its security and fairness and transparency to users.
  • the user equipment can download the summary information from the blockchain in order to verify whether the disaster event cluster has been tampered with.
  • the blockchain referred to in this example is a new application mode of computer technology such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm.
  • Blockchain essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information to verify its Validity of information (anti-counterfeiting) and generation of the next block.
  • the blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.
  • step S2 further includes the following specific steps:
  • the second preset database includes an accident record database, an industrial and commercial information disclosure database, and a fire alarm record database;
  • User-related information also includes companies with high fire rates in the same industry as the user.
  • the specific steps are as follows:
  • S201 Acquire the user associated information according to the user information in at least one of an accident record database, an industrial and commercial information disclosure database, and a fire alarm record database;
  • S202 Screening enterprises with high fire risk in the same industry as the user from the user association information
  • S203 Acquire address information of the high-fire-incidence enterprise.
  • step S3 further includes: inputting the address information of the high-fire-incidence enterprise into the third preset database to obtain longitude and latitude information of the address information of the fire-high-incidence enterprise.
  • the occurrence of fire is composed of disaster-pregnant environment and disaster-causing factors.
  • Hazardous factors are composed of events, such as throwing cigarette butts, long-term heating of circuits, use of open flames, etc. The occurrence of these events is difficult to observe and prevent.
  • the surrounding environment is relatively stable, so it is feasible to evaluate the fire density of the disaster-pregnant environment.
  • some enterprises have a high fire risk density due to their operational nature and high staff density, especially some manufacturing industries, which generally accumulate a large amount of goods. Once a fire occurs, the consequences will be disastrous.
  • the existing fire risk statistical methods generally go to the site to conduct a fire risk assessment. In this way, very detailed field information can be collected, but it cannot cover a large number of targets.
  • the above-mentioned disaster density statistics device obtains customer information from the user information obtaining module, and specifically selects customers corresponding to insurance policies whose disaster event is "fire".
  • customer information various information related to the above-mentioned user input is obtained from the second preset database of itself or a third party.
  • the second preset database is specifically matched from the industrial and commercial information database.
  • the above-mentioned industrial and commercial information database includes the insurance company's own accident record database, as well as the third-party national enterprise public information network, Tianyancha, Qichacha and other data interfaces.
  • the enterprises are too concentrated, which will cause a chain reaction of fire. .
  • it can be analyzed whether the above-mentioned insured customers are in high-risk areas. If so, according to the actual business needs, personnel can be dispatched to conduct on-site inspections to judge the possibility of the insured customers being out of danger, so as to further decide whether to increase the policy price. or even outright refusal of insurance and other countermeasures.
  • the second preset database includes an accident record database, a court information database and a traffic police record database;
  • User-related information also includes traffic accidents that occurred in the same area as the user. Specifically include the following steps:
  • S211 Acquire the user associated information according to the user information in at least one of an accident record database, an industrial and commercial information disclosure database, and a fire alarm record database;
  • S212 Screen traffic accidents that occur in the same area as the user from the user association information
  • the above step S3 further includes: inputting the traffic accident location information into the third preset database to obtain longitude and latitude information of the traffic accident location information.
  • Car damage insurance refers to a kind of commercial automobile insurance in which the insured or his permitted driver has an insured accident when using the insured vehicle and causes damage to the insured vehicle, and the insurance company compensates it within a reasonable range.
  • Car owners who have purchased car damage insurance can apply to the insurance company for insurance and get compensation. Therefore, in order to reduce the compensation for accidents, it is necessary to clarify the accident-prone points in various regions and remind the car owners in time. Expenses for car insurance.
  • the above-mentioned disaster density statistics device obtains customer information from the user information acquisition module, specifically, to filter the customers corresponding to the insurance policy whose disaster event is "traffic accident", preferably the above-mentioned user's address and work unit need to be obtained. address.
  • customer information various information associated with the above-mentioned input user is obtained from the second preset database of itself or a third party.
  • the second preset database is specifically from the insurance company's insurance record.
  • the database, the police record database of public security traffic police, the record database of the trailer rescue company, and the judgment on the traffic accident in the court judgment document database are matched to the records of the accident location near the user's information address, and the matched accident location records will be matched.
  • the location information is recorded or cached in the device.
  • the matched location information of the accident location is matched with the latitude and longitude of the location through the geographic information system, and the longitude and latitude of all accident locations that have experienced motor vehicle traffic accidents are recorded.
  • the dense clusters of motor vehicle traffic accidents are calculated, and the points of the same color are denser clusters, which can be considered as the locations where motor vehicle traffic accidents are more likely to occur.
  • the second preset database includes an accident record database, a traffic police alarm record database and a fire alarm record database;
  • the user-related information also includes flooding events that occurred in the same area as the user. Specifically include the following steps:
  • S221 Acquire the user associated information according to the user information in at least one of an accident record database, a traffic police alarm record database, and a fire alarm record database;
  • S222 Screen the location information of the flooding event that occurs in the same area as the user from the user association information
  • the above step S3 further includes: inputting the location information of the flooding event into the third preset database to obtain longitude and latitude information of the location information of the flooding event.
  • Water wading insurance is an additional insurance in commercial auto insurance, which mainly protects the direct damage to the engine caused by the water entering the engine during the use of the insured motor vehicle, and the necessary payment to prevent or reduce the loss of the insured motor vehicle. reasonable and reasonable rescue costs.
  • the owner of a motor vehicle may accidentally drive into an area where flooding or waterlogging occurs, causing the motor vehicle engine to enter water. If the owner has purchased flood insurance, he can apply to the insurance company for insurance and obtain claims. Therefore, in order to reduce the compensation for accidents, it is necessary to identify the high-risk areas of flooding and waterlogging in various regions, and timely remind the owner to avoid it. The company pays for water-related insurance expenses.
  • the above-mentioned disaster density statistics device obtains customer information from the user information acquisition module, specifically, to filter the customers corresponding to the insurance policy whose disaster event is "motor vehicle flooding", preferably the address and work of the above-mentioned users need to be obtained. unit address.
  • customer information various information associated with the above-mentioned input user is obtained from the second preset database of itself or a third party.
  • the second preset database is specifically from the insurance company's insurance record.
  • the database, the alarm record database of the public security traffic police and the record library of the trailer rescue company match the accident/alarm records near the user's information address, and record or cache the location information of the matched accident/alarm records in the device.
  • the present application also provides a density-based disaster density statistics device 1100, as shown in FIG. 6, including: a first data acquisition module 1101, a second data acquisition module 1102, a third data acquisition module 1103, and density clustering statistics Module 1104.
  • the first data acquisition module 1101 is used to acquire the user's name, and acquire user information from the first preset database according to the user's name;
  • the second data acquisition module 1102 is configured to acquire user association information from the second preset database according to the selected disaster event type and user information;
  • the third data acquisition module 1103 is configured to input the user associated information into a third preset database to obtain the latitude and longitude information of the user associated information;
  • the density clustering statistics module 1104 is configured to calculate the longitude and latitude information according to a clustering algorithm to obtain disaster event clusters.
  • the first data acquisition module 1101 is configured to acquire user information from the first preset database 1200, where the user information includes user information, the type of insurance policy the user applies for, and the like.
  • the user-related information further includes a location where the disaster event point occurs, and the disaster event type includes fire, traffic accident and/or flooding.
  • the second data acquisition module 1102 is configured to acquire various information associated with the above-mentioned user input from the second preset database 1300 of itself or a third party, so as to be used for subsequent analysis, corresponding to specific disaster events of different policy types , the second preset database 1300 of a different self or a third party can be selected according to requirements, and the second preset database includes the insurance company's risk information database, industrial and commercial information database, public security information database, traffic police information database, and court information database.
  • the user association information further includes a non-disaster event point related to the user, and when the disaster event is a fire, the second preset database includes an accident record database, an industrial and commercial information disclosure Database and fire alarm record database, the second data acquisition module 1102 further includes a fire information acquisition unit.
  • the fire information acquisition unit is configured to: acquire the user associated information according to the user information in at least one of the accident record database, the industrial and commercial information disclosure database, and the fire alarm record database;
  • the user association information also includes address information of enterprises with high fire incidence in the same industry as the user, and the third data acquisition module 1103 includes a fire latitude and longitude information acquisition unit.
  • the fire latitude and longitude information acquisition unit is used for: inputting the address information of enterprises with high fire incidence into the third preset database 1400 to obtain the longitude and latitude information of the enterprise address information with high fire incidence.
  • the second preset database 1300 includes an accident record database, a court information database and a traffic police record database
  • the second data acquisition module 1102 further includes traffic accident information acquisition unit.
  • the traffic accident information acquisition unit is configured to: acquire the user associated information according to the user information in at least one of the accident record database, the industrial and commercial information disclosure database, and the fire alarm record database;
  • the user association information also includes location information of traffic accidents that occurred in the same area as the user, and the third data acquisition module 1103 includes a traffic accident latitude and longitude information acquisition unit.
  • the traffic accident latitude and longitude information acquisition unit is configured to: input the traffic accident location information into the third preset database 1400 to obtain the longitude and latitude information of the traffic accident location information.
  • the second preset database 1300 includes an accident record database, a traffic police alarm record database, and a fire alarm record database
  • the second data acquisition module 1102 further includes a flood information acquisition unit .
  • the water immersion information acquisition unit is configured to acquire the user associated information according to the user information in at least one of the accident record database, the traffic police alarm record database and the fire alarm record database;
  • the user associated information further includes location information of flooding events that occurred in the same area as the user, and the third data acquisition module 1103 includes a flooding latitude and longitude information acquisition unit.
  • the water immersion latitude and longitude information acquisition unit is configured to: input the location information of the water immersion event into the third preset database 1400 to obtain the latitude and longitude information of the location information of the water immersion event.
  • the above-mentioned input user-related information includes: disaster event points related to the user and their occurrence addresses or locations, further, the above-mentioned disaster event points include subjects or locations of disaster events that have occurred in the past, and obtained according to statistical analysis. the subject or location where a catastrophic event may occur.
  • the density clustering statistics module 1104 further includes a clustering algorithm calculation unit, and the clustering algorithm calculation unit is used for:
  • Detect the number of adjacent points of the second point within the preset distance one by one mark the second point with the number of adjacent points greater than the minimum number of points as the core point, and label all the adjacent points as the core point.
  • the adjacent point is also assigned to the first cluster label
  • any one of the points is repeatedly selected as the new first point, and all the points less than or equal to the preset distance from the new first point are used as the new first point. Two points, until processing completes all said points.
  • the disaster density statistics device 1100 further includes a map output module, which is used for:
  • the disaster event cluster is output to the map application, and the high-risk area represented by the disaster event cluster is displayed through the map application.
  • the above-mentioned device extracts necessary data, such as geographic information such as addresses, locations of disaster events, from the associated data obtained from the second preset database 1300 of itself or a third party through the second data acquisition module 1102, and from the third preset database 1400 The latitude and longitude information that matches the geographic information such as the above address and the location of the disaster.
  • a computer device including a memory and a processor, where computer-readable instructions are stored in the memory, and when the computer-readable instructions are executed by the processor, cause the processor to perform any of the above-mentioned embodiments.
  • the terminal such as a mobile phone, a driving recorder, etc.
  • the above-mentioned disaster density statistics device can further analyze the above-mentioned driving trajectory and parking position and the risk of traffic accidents around it according to the above-mentioned driving trajectory and parking position information recorded by the above-mentioned customer through the terminal.
  • the above-mentioned disaster density statistics device is mounted in a terminal (such as a mobile phone, a driving recorder, etc.) carried by the user, and the disaster density statistics device is connected through a network interface of the terminal (such as a cellular network, WIFI, etc.) Connect to the Internet and connect to the above-mentioned second preset database and third preset database (ie, geographic information system), which can analyze the surrounding risks of the user's location in real time, and calculate the surrounding risks of the current location through the DBSCAN density clustering method.
  • the dense clusters of motor vehicle traffic accidents/water immersion are displayed on the user's terminal through the visualization module, and can be superimposed with the map, so that the user can further clearly know the disaster risk density around the current location and avoid it in time.
  • the above statistical method of disaster density can be performed by computer readable instructions recorded on a computer readable medium.
  • Nonvolatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory.
  • Volatile memory may include random access memory (RAM) or external cache memory.
  • RAM is available in various forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Road (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
  • FIG. 6 is only a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. Include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components. Finally, it should also be noted that in this document, relational terms such as first and second are used only to distinguish one entity or operation from another, and do not necessarily require or imply these entities or that there is any such actual relationship or sequence between operations.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Tourism & Hospitality (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Computational Linguistics (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Probability & Statistics with Applications (AREA)
  • General Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Quality & Reliability (AREA)
  • Remote Sensing (AREA)
  • Computer Security & Cryptography (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Operations Research (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种灾难密度的统计方法,包括:从第一预设数据库获取用户信息;根据灾难事件种类和用户信息从第二预设数据库获取用户关联信息;经纬度信息通过将用户关联信息输入第三预设数据库所得到;根据经纬度信息,通过聚类算法计算得到灾难事件簇。通过DBSCAN密度聚类法,直观地显示用户周围可能发生的灾难事件的密集程度。

Description

灾难密度的统计方法、装置、计算机设备以及存储介质
本申请要求于2020年12月16日提交中国专利局、申请号为202011489923.X、申请名称为“灾难密度的统计方法、装置、计算机设备以及存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及大数据技术领域,尤其涉及一种灾难密度的统计方法、装置、计算机设备以及存储介质。
背景技术
火灾是最常出现的威胁生命及财产安全的灾害之一,其发生原因复杂多变且一旦发生,给予人们反应的时间很短。有效评估城市火灾风险等级可提前对该区域进行更大力度火灾防御措施,如:加强排查逃生通道,增加灭火设备等。当前已经有很多业内人士针对火灾的预测做了大量研究,但都限定在某些具体场景,数据获取难度大,准确性低。
火灾发生由孕灾环境与致灾因子构成。致灾因子由事件构成,如:乱扔烟头、电路长期发热、使用明火等,这些事件的发生很难观测和预防。而周围环境则相对稳定,因此对孕灾环境进行火灾风险评估则具有可操作性。
发明人意识到,某些企业因为其运营性质及工作人员密集度高,具有较高的火灾风险,特别是某些制造业,一般会堆积大量的货物,一旦发生火灾,后果不堪设想。现有的火灾风险评估方法一般会到现场勘察,从而进行火灾风险评估。这样做虽然能够采集到非常详细的现场信息,但无法覆盖大量高风险区域,需要耗费较多人力进行现场勘查,才能实现高风险区域的全面覆盖,从而造成高风险区域核查效率低。
发明内容
本申请提供了一种灾难密度的统计方法,以解决高风险区域核查效率低、核查人力成本高的技术问题。本申请提出的灾难密度的统计方法包括以下步骤:
获取用户的名称,根据用户的名称从第一预设数据库中获取用户信息;
根据选择的灾难事件种类以及用户信息从第二预设数据库中获取用户关联信息;
将用户关联信息输入第三预设数据库中,得到用户关联信息的经纬度信息;
根据聚类算法计算所述经纬度信息,得到灾难事件簇。
在本申请的另一个方面,提供了一种灾难密度统计装置,包括:
第一数据获取模块,用于获取用户的名称,根据所述用户的名称从第一预设数据库中获取用户信息;
第二数据获取模块,用于根据选择的灾难事件种类以及所述用户信息从第二预设数据库中获取用户关联信息;
第三数据获取模块,用于将所述用户关联信息输入第三预设数据库中,得到所述用户关联信息的经纬度信息;
密度聚类统计模块,用于根据聚类算法计算所述经纬度信息,得到灾难事件簇。
在本申请的另一个方面,提供了一种计算机设备,包括存储器和处理器,存储器中存储有计算机可读指令,计算机可读指令被处理器执行时,执行以下步骤:
获取用户的名称,根据用户的名称从第一预设数据库中获取用户信息;
根据选择的灾难事件种类以及用户信息从第二预设数据库中获取用户关联信息;
将用户关联信息输入第三预设数据库中,得到用户关联信息的经纬度信息;
根据聚类算法计算所述经纬度信息,得到灾难事件簇。
在本申请的另一个方面,还提供了一个或多个存储有计算机可读指令的可读存储介质,所述计算机可读指令被一个或多个处理器执行时,使得所述一个或多个处理器执行如下步骤:
获取用户的名称,根据用户的名称从第一预设数据库中获取用户信息;
根据选择的灾难事件种类以及用户信息从第二预设数据库中获取用户关联信息;
将用户关联信息输入第三预设数据库中,得到用户关联信息的经纬度信息;
根据聚类算法计算所述经纬度信息,得到灾难事件簇。
本申请提出的灾难密度的统计方法、装置、计算机以及介质,能够减少在用户地点进行现场勘查所需要耗费的大量人力成本,只需要从企业自有或者第三方的预设数据库中获取与用户相关联的灾难事件,并将上述灾难事件的位置输入到地理信息系统,然后通过密度聚类算法,统计出投保用户的地理位置附近是否有灾难事件密集的簇,结合地图可视化,可以使得操作人员直观地显示用户周围可能发生的灾难事件的密集程度。
附图说明
图1是本申请提出的基于密度聚类算法的灾难密度统计方法的流程图;
图2是本申请提出的基于密度聚类算法的灾难密度统计方法的另一个实施例的流程图;
图3是在灾难类型为火灾的灾难密度统计方法的具体流程图;
图4是在灾难类型为交通事故的灾难密度统计方法的具体流程图;
图5是在灾难类型为浸水的灾难密度统计方法的具体流程图;
图6是灾难密度统计装置的构成示意图。
具体实施方式
下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅是本申请一部分实施例,而不是全部的实施例。基于本申请中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本申请保护的范围。
根据图1可知,本申请包括以下步骤:
S1:获取用户的名称,根据用户的名称从第一预设数据库中获取用户信息;
具体地,上述用户信息包括用户资料、用户投保的保单种类等,在对应不同保单种类可以设置具体的灾难事件种类,例如火灾、交通事故等。
S2:根据选择的灾难事件种类以及用户信息从第二预设数据库中获取用户关联信息,用户关联信息包括与用户相关的灾难事件点;
用户关联数据从自身或者第三方的第二预设数据库中获取与上述输入的用户相关联的各种信息,以便用于后续的分析,对应不同用户的保单种类对应的具体的灾难事件,可以按照要求选取不同的自身或者第三方第二预设数据库,第二预设数据库包括保险公司的出险信息数据库、工商信息数据库、公安信息数据库、交警信息数据库、以及法院信息数据库作为上述第二预设数据库。
上述步骤S2的用户关联信息包括与用户相关的灾难事件点及其发生地址或者位置。根据具体的需要,灾难事件可以包括火灾、交通事故、浸水等。
S3:将用户关联信息输入第三预设数据库中,得到用户关联信息的经纬度信息;
具体地,通过第二预设数据库中获取的关联数据中提取必要的数据,如地址、灾难事件发生地点等地理信息,从第三预设数据库中匹配上述地址、灾难发生地点等地理信息的经纬度信息,上述第三预设数据库是地理信息系统。
地理信息系统(GIS,Geographic Information System)是一门综合性学科,结合地理学与地图学以及遥感和计算机科学,已经广泛的应用在不同的领域,是用于输入、存储、查询、分析和显示地理数据的计算机系统。GIS是一种基于计算机的工具,它可以对空间信息进行分析和处理。GIS技术把地图这种独特的视觉化效果和地理分析功能与一般的数据库操作(例如查询和统计分析等)集成在一起。
地理信息系统能够将不同来源的信息以不同的形式应用。对于源数据的基本要求是确定变量的位置,位置可能由经度、纬度和海拔的x,y,z坐标来标注。在本申请的一个实施方式中,上述变量是指步骤S2中的用户关联信息,即将用户关联信息中的地址/位置信息输入地理信息系统,并且得到用户关联信息的对应经纬度。至此,通过地理信息系统,可以将作为用户关联信息的灾难发生地点转换成由经纬度(x,y)构成的点p,然后用于下一步的基于密度的聚类算法进行分析。
S4:获取灾难事件簇,根据聚类算法计算经纬度信息,得到灾难事件簇。
在本申请的另一个方面,上述步骤S4中的基于密度的聚类算法可以是DBSCAN密度聚类算法。
DBSCAN(Density-Based Spatial Clustering of Applications with Noise,具有噪声的基于密度的聚类方法)是一种基于密度的聚类算法。该算法将具有足够密度的区域划分为簇,并在具有噪声的间数据库中发现任意形状的簇,它将簇定义为密度相连的点的最大集合。
该算法利用基于密度的聚类的概念,即要求聚类空间中的一定区域内所包含对象(点或其他空间对象)的数目不小于某一给定阈值。DBSCAN算法的显著优点是聚类速度快且能够有效处理噪声点和发现任意形状的空间聚类。
DBSCAN密度聚类算法的简单步骤如下:
输入:样本集D=(x1,x2,...,xm),邻域参数(∈,MinPts),样本距离度量方式
输出:簇划分C.
1)初始化核心对象集合Ω=0,初始化聚类簇数k=0,初始化未访问样本集合Γ=D,簇
划分C=0
2)对于j=1,2,...m,按下面的步骤找出所有的核心对象:
a)通过距离度量方式,找到样本xj的∈-邻域子样本集N∈(xj)
b)如果子样本集样本个数满足|N∈(xj)|≥MinPts,将样本xj加入核心对象样本集合:
Ω=Ω∪{xj}
3)如果核心对象集合Ω=0,则算法结束,否则转入步骤4.
4)在核心对象集合Ω中,随机选择一个核心对象o,初始化当前簇核心对象队列Ω
cur={o},初始化类别序号k=k+1,初始化当前簇样本集合Ck={o},更新未访问样本集
合Γ=Γ-{o}
5)如果当前簇核心对象队列Ωcur=0,则当前聚类簇Ck生成完毕,更新簇划分
C={C1,C2,...,Ck},更新核心对象集合Ω=Ω-Ck,转入步骤3。
6)在当前簇核心对象队列Ωcur中取出一个核心对象o′,通过邻域距离阈值∈找出所
有的∈-邻域子样本集N∈(o′),令Δ=N∈(o′)∩Γ,更新当前簇样本集合Ck=Ck∪Δ,
更新未访问样本集合Γ=Γ-Δ,转入步骤5.
输出结果为:簇划分C={C1,C2,...,Ck}。
在一个具体的示例中,每一个灾难发生地点具有经纬度(x,y),x、y分别对应灾难发生地点的经度和纬度,而在步骤S3中获得的每一个灾难发生地点可以作为数据集D的一个点。设置邻域参数(∈,MinPts),其中∈为半径,可以视为期望的一个灾难发生地点的半径∈中如有另一个灾难发生地点,则该两个灾难发生地点可以形成一个簇;在满足上述条件的前提下,MinPts是给定电脑在∈领域内成为核心对象的最小领域点数,即如果一个灾难发生地点p的半径∈中另外有MinPts个灾难发生地点,则该p可以视作核心点。
基于上述前提,将包含有所有灾难发生地点的经纬度的数据集D初始化为全部未处理的点,在算法中设置邻域参数(∈,MinPts),本示例设置∈为10米,即期望一个灾难发生地点的半径10米内中如有另一个灾难发生地点,则该两个灾难发生地点可以形成一个簇;MinPts设置为3个,即灾难发生地点p的半径10米内另外有3个灾难发生地点,则该p可以视作核心点。
首先,从数据集D中找出所有的核心点,即判断一个点p是否在其半径10米内另外有3个灾难发生地点的点,若是,则将该点p标记为核心点,然后建立新的簇C,并将p 1的邻域 内所有点加入簇C;若否,则将该点p标记为边界点或者噪音点。这样如此循环,直至数据集D中的点全部处理完成,得到的一个或者多个簇C就是灾难发生地点密集的区域。
DBSCAN算法的目的在于过滤低密度区域,发现稠密度样本点。跟传统的基于层次的聚类和划分聚类的凸形聚类簇不同,该算法可以发现任意形状的聚类簇。
核保人员根据计算结果,可知投保用户位置附近是否有灾难事件簇,若投保用户位置附近存在一个或者多个灾难事件簇,核保人员可以根据该投保用户与灾难事件簇之间的距离、灾难事件簇的大小等参数评估该投保用户出险的可能性。
在一个可选的实施例中,在根据聚类算法计算经纬度信息,得到灾难事件簇的步骤之后,还包括设定提示距离,当用户的位置距离小于上述灾难事件簇的距离时,发出提示。当需要核保的保单数量较多时,为了减少核保人员的工作负担,可以预先在方法中设定提示距离,只有用户的位置距离小于上述灾难事件簇的距离时,才发出向核保人员发出提示信息,以进一步介入核保工作。
在一个可选的实施例中,如图2所示,上述灾难密度的统计方法在步骤S4之后还包括步骤S5:
S5:将灾难事件簇输出到地图应用,以将灾难事件簇表示的高风险地区叠加并显示在地图上。
在该步骤中,可以将上述表示灾难事件簇输出到在地图应用上,将以簇表示的高风险地区叠加到地图上,方便核保人员更加直观地确定灾难事件密集的高风险区域的位置,以便及早作出对策。
在一个可选的实施例中,如图2所示,上述灾难密度的统计方法在步骤S5之后还包括步骤S6:
S6:将包括灾难事件簇的地图上传至区块链中。
基于上述方法得到的地图,取得对应的摘要信息,具体来说,摘要信息由地图进行散列处理得到,比如利用SHA256s算法处理得到。将摘要信息上传至区块链可保证其安全性和对用户的公正透明性。用户设备可以从区块链中下载得该摘要信息,以便查证灾难事件簇是否被篡改。本示例所指区块链是分布式数据存储、点对点传输、共识机制、加密算法等计算机技术的新型应用模式。区块链(Blockchain),本质上是一个去中心化的数据库,是一串使用密码学方法相关联产生的数据块,每一个数据块中包含了一批次网络交易的信息,用于验证其信息的有效性(防伪)和生成下一个区块。区块链可以包括区块链底层平台、平台产品服务层以及应用服务层等。
在具体应用场景中,对应各种不同的灾难类型,上述步骤S2还包括如下具体的步骤:
(1)当上述灾难事件为火灾时,参考图3,第二预设数据库包括出险记录数据库、工商信息公开数据库以及消防出警记录数据库;
用户关联信息还包括与用户同行业的火灾高发的企业。具体的步骤如下:
S201:根据所述用户信息在出险记录数据库、工商信息公开数据库以及消防出警记录数据库中的至少一个获取所述用户关联信息;
S202:从所述用户关联信息中筛选与所述用户同行业的火灾高发的企业;
S203:获取所述火灾高发企业的地址信息。
上述步骤S3还包括:将所述火灾高发企业的地址信息输入所述第三预设数据库,得到所述火灾高发企业的地址信息的经纬度信息。
与之对应的实际运用场景如下:
火灾发生由孕灾环境与致灾因子构成。致灾因子由事件构成,如:乱扔烟头、电路长期发热、使用明火等,这些事件的发生很难观测和预防。而周围环境则相对稳定,因此对孕灾环境进行火灾密度评估则具有可操作性。一般而言,某些企业因为其运营性质及工作人员密集度高,具有较高的火灾风险密度,特别是某些制造业,一般会堆积大量的货物,一旦发生火灾,后果不堪设想。现有的火灾风险统计方法一般会到现场勘察,从而进行火灾风险评估。这样做能够采集到非常详细的现场信息,但无法覆盖大量的标的。
在这个具体的实施方式中,上述灾难密度统计装置从用户信息获取模块中获取客户信息,具体是筛选灾难事件为“火灾”的保单对应的客户。根据上述客户信息,从自身或者第三方的第二预设数据库中获取与上述输入的用户相关联的各种信息,在此实施方式中,第二预设数据库具体地是从工商信息数据库中匹配客户的行业,上述工商信息数据库包括保险公司自身的出险记录数据库,以及第三方的国家企业公开信息网、天眼查、企查查等的数据接口。
统计行业该类火灾出险比例,筛选出火灾高发的企业,即有可能发生灾难事件的主体,并且将筛选出的火灾高发的企业的地址信息记录或者缓存到装置中。然后,将上述筛选出的火灾高发的企业的地址信息通过地理信息系统匹配上述地址的经纬度,并且记录所有筛选出的火灾高发的企业的经纬度。最后,根据上述经纬度,通过DBSCAN密度聚类算法,计算出企业密集的簇,相同颜色的点均为较密集的簇,可认为密度集中的簇可能引起火灾的企业过于集中,会引发火灾连锁反应。至此,可以分析上述投保的客户是否处于高风险的地区,若是,可以根据实际业务的需要,派遣人员到实地进行考察,以判断投保的客户出险的可能性,从而进一步地决定是否提高保单价格,乃至直接拒保等应对措施。
(2)当上述灾难事件为交通事故时,参考图4,当灾难事件为交通事故时,第二预设数据库包括出险记录数据库、法院信息数据库以及交警出警记录数据库;
用户关联信息还包括与用户在同一区域内发生的交通事故。具体包括以下步骤:
S211:根据所述用户信息在出险记录数据库、工商信息公开数据库以及消防出警记录数据库中的至少一个获取所述用户关联信息;
S212:从所述用户关联信息中筛选与所述用户在同一区域内发生的交通事故;
S213:获取所述交通事故位置信息。
上述步骤S3还包括:将所述交通事故位置信息输入所述第三预设数据库,得到所述交通事故位置信息的经纬度信息。
与之对应的实际运用场景如下:
车损险是指被保险人或其允许的驾驶员在使用保险车辆时发生保险事故而造成保险车辆受损,保险公司在合理范围内予以赔偿的一种汽车商业保险。在道路上,存在一些由于设计不合理或者驾驶员容易出现疏忽从而导致交通事故的事故多发点,车主购买了车损险,则可以向保险公司申请出险并获得理赔。因此,为了减少出险的赔偿,有必要明确各个地区的事故多发点,以及时提醒车主,一方面减少了车主机动车因为交通事故而受损的可能性,另一方面也可以减少保险公司因赔付车损险的支出。
在这个具体的实施方式中,上述灾难密度统计装置从用户信息获取模块中获取客户信息,具体是筛选灾难事件为“交通事故”的保单对应的客户,优选地需要获取上述用户的住址以及工作单位地址。根据上述客户信息,从自身或者第三方的第二预设数据库中获取与上述输入的用户相关联的各种信息,在此实施方式中,第二预设数据库具体地是从保险公司的出险记录数据库、公安交警的报警记录数据库、拖车救援公司的记录库、以及法院裁判文书数据库中关于交通事故的判决中匹配到该用户信息地址附近的事故发生地点记录,并且将匹配到的事故发生地点的位置信息记录或者缓存到装置中。
然后,将上述匹配到的事故发生地点的位置信息通过地理信息系统匹配上述位置的经纬度,并且记录所有发生过机动车交通事故的事故发生地点的经纬度。最后,根据上述经纬度,通过DBSCAN密度聚类算法,计算出机动车交通事故密集的簇,相同颜色的点均为较密集的簇,可认为是较容易出现机动车交通事故的位置,当机动车驶入时,当驾驶员稍有不慎,则有可能导致发生机动车事故,进而向保险公司申请出险并且赔付。至此,在投保用户所登记的地址附近若有机动车交通事故高发的位置,则应当及时告知客户,并及时进行回避。(3)当上述灾难事件为浸水时,参考图5,当灾难事件为浸水时,第二预设数据库包括出险记录数据库、交警出警记录数据库以及消防出警记录数据库;
所述用户关联信息还包括与所述用户同一区域内发生的浸水事件。具体包括以下步骤:
S221:根据所述用户信息在出险记录数据库、交警出警记录数据库以及消防出警记录数据库中的至少一个获取所述用户关联信息;
S222:从所述用户关联信息中筛选与所述用户同一区域内发生的浸水事件位置信息;
S223:获取所述浸水事件位置信息。
上述步骤S3还包括:将所述浸水事件位置信息输入所述第三预设数据库,得到所述浸水事件位置信息的经纬度信息。
与之对应的实际运用场景如下:
涉水险是属于商业车险中的附加险,主要保障被保险机动车在使用过程中,因发动机进水后导致的发动机的直接损毁,以及为防止或者减少被保险机动车的损失所支付的必要的、合理的施救费用。当在暴雨台风频繁的季节中,驾驶机动车的车主可能不慎驶入发生浸水或者内涝的地区而导致机动车发动机进水,若车主购买了涉水险,则可以向保险公司申请出险并获得理赔。因此,为了减少出险的赔偿,有必要明确各个地区浸水内涝的高危险地区,以及时提醒车主进行规避,一方面减少了车主机动车因为浸水而受损的可能性,另一方面也可以减少保险公司因赔付涉水险的支出。
在这个具体的实施方式中,上述灾难密度统计装置从用户信息获取模块中获取客户信息,具体是筛选灾难事件为“机动车浸水”的保单对应的客户,优选地需要获取上述用户的住址以及工作单位地址。根据上述客户信息,从自身或者第三方的第二预设数据库中获取与上述输入的用户相关联的各种信息,在此实施方式中,第二预设数据库具体地是从保险公司的出险记录数据库、公安交警的报警记录数据库以及拖车救援公司的记录库中匹配到该用户信息地址附近的出险/出警记录,并且将匹配到的出险/出警记录的位置信息记录或者缓存到装置中。然后,将上述匹配到的出险/出警记录的位置信息通过地理信息系统匹配上述位置的经纬度,并且记录所有发生过机动车浸水事件的出险/出警记录的经纬度。最后,根据上述经纬度,通过DBSCAN密度聚类算法,计算出机动车浸水事件密集的簇,相同颜色的点均为较密集的簇,可认为是在暴雨天气时较容易出现浸水和内涝的位置,当机动车驶入时,会导致机动车浸水并且损坏,进而向保险公司申请出险并且赔付。至此,在投保用户当地的气象部门发出暴雨警告时,及时告知客户附近可能出现浸水和内涝的位置,并及时进行回避。
本申请还提供了一种基于密度的灾难密度统计装置1100,如图6所示,包括:第一数据获取模块1101、第二数据获取模块1102、第三数据获取模块1103、以及密度聚类统计模块1104。
第一数据获取模块1101,用于获取用户的名称,根据用户的名称从第一预设数据库中获取用户信息;
第二数据获取模块1102,用于根据选择的灾难事件种类以及用户信息从第二预设数据库中获取用户关联信息;
第三数据获取模块1103,用于将用户关联信息输入第三预设数据库中,得到用户关联信息的经纬度信息;
密度聚类统计模块1104,用于根据聚类算法计算所述经纬度信息,得到灾难事件簇。
第一数据获取模块1101用于从第一预设数据库1200中获取用户信息,上述用户信息包括用户资料、用户投保的保单种类等。
在其中一个实施例中,所述用户关联信息还包括所述灾难事件点发生的位置,所述灾难事件种类包括火灾、交通事故和/或浸水。
在对应不同用户可以设置具体的灾难事件种类,例如火灾、交通事故等。
第二数据获取模块1102用于从自身或者第三方的第二预设数据库1300中获取与上述输入的用户相关联的各种信息,以便用于后续的分析,对应不同保单种类的具体的灾难事件,可以按照要求选取不同的自身或者第三方的第二预设数据库1300,上述第二预设数据库包括保险公司的出险信息数据库、工商信息数据库、公安信息数据库、交警信息数据库、以及法院信息数据库。
在一个具体的实施例中,所述用户关联信息还包括与所述用户相关的非灾难事件点,当所述灾难事件为火灾时,所述第二预设数据库包括出险记录数据库、工商信息公开数据库以 及消防出警记录数据库,第二数据获取模块1102还包括火灾信息获取单元。
火灾信息获取单元用于:根据所述用户信息在出险记录数据库、工商信息公开数据库以及消防出警记录数据库中的至少一个获取所述用户关联信息;
用户关联信息还包括与用户同行业的火灾高发的企业地址信息,所述第三数据获取模块1103包括火灾经纬度信息获取单元。
所述火灾经纬度信息获取单元用于:将火灾高发的企业地址信息输入第三预设数据库1400,得到所述火灾高发的企业地址信息的经纬度信息。
在一个具体的实施例中,当灾难事件为交通事故时,所述第二预设数据库1300包括出险记录数据库、法院信息数据库以及交警出警记录数据库,第二数据获取模块1102还包括交通事故信息获取单元。
交通事故信息获取单元用于:根据所述用户信息在出险记录数据库、工商信息公开数据库以及消防出警记录数据库中的至少一个获取所述用户关联信息;
所述用户关联信息还包括与所述用户在同一区域内发生的交通事故位置信息,所述第三数据获取模块1103包括交通事故经纬度信息获取单元。
交通事故经纬度信息获取单元用于:将所述交通事故位置信息输入第三预设数据库1400,得到交通事故位置信息的经纬度信息。
在一个具体的实施例中,当灾难事件为浸水时,所述第二预设数据库1300包括出险记录数据库、交警出警记录数据库以及消防出警记录数据库,第二数据获取模块1102还包括浸水信息获取单元。
浸水信息获取单元用于根据所述用户信息在出险记录数据库、交警出警记录数据库以及消防出警记录数据库中的至少一个获取所述用户关联信息;
所述用户关联信息还包括与所述用户同一区域内发生的浸水事件位置信息,所述第三数据获取模块1103包括浸水经纬度信息获取单元。
浸水经纬度信息获取单元用于:将所述浸水事件位置信息输入第三预设数据库1400,得到浸水事件位置信息的经纬度信息。
更具体地,上述输入的用户关联信息包括:与用户相关的灾难事件点以及其发生地址或者位置,进一步地,上述灾难事件点包括过去发生过的灾难事件的主体或者地点,以及根据统计分析得到的可能发生灾难事件的主体或者地点。
在一个具体的实施例中,密度聚类统计模块1104还包括聚类算法计算单元,聚类算法计算单元用于::
将所有所述灾难事件点的所述经纬度信息转换为用经纬度坐标表示的点,
选取任意一个所述点作为第一点,并将距离所述第一点小于或等于预设距离的所有的所述点作为第二点;
如果所述第二点的个数小于预设的最少点数,那么将所述第一点标记为噪声;
如果所述第二点个数大于所述最少点数,那么将所述第一点标记为核心点,并将该所述第一点以及所有的所述第二点分配到第一簇标签;
逐个检测所述第二点的在所述预设距离内的邻接点个数,将所述邻接点个数大于所述最少点数的所述第二点也标记为所述核心点,并将所述邻接点也分配到所述第一簇标签;
检测所有的所述第二点之后,重复选取任意一个所述点作为新的第一点,并将距离所述新的第一点小于或等于预设距离的所有的所述点作为新的第二点,直至处理完成所有的所述点。
在一个可选的实施例中,灾难密度统计装置1100还包括地图输出模块,该地图输出模块用于:
将灾难事件簇输出到地图应用,通过地图应用显示灾难事件簇表示的高风险地区。上述装置通过第二数据获取模块1102从自身或者第三方的第二预设数据库1300中获取的关联数据中提取必要的数据,如地址、灾难事件发生地点等地理信息,从第三预设数据库1400中匹配上述地址、灾难发生地点等地理信息的经纬度信息。
在一个具体的实施例中,提供了一种计算机设备,包括存储器和处理器,存储器中存储有计算机可读指令,计算机可读指令被处理器执行时,使得处理器执行上述任一实施例的灾难密度的统计方法。在一种优选的实施例中,在征得客户同意的前提下,通过客户携带的终端(如手机、行车记录仪等)记录客户驾驶机动车的行车轨迹以及停车位置,并上传到第一预设数据库中。上述灾难密度统计装置可以根据上述客户通过终端记录的行车轨迹以及停车位置信息,进一步分析上述行车轨迹以及停车位置及其周边发生交通事故的风险。
在另一种优选的实施例中,上述灾难密度统计装置搭载在用户携带的终端(如手机、行车记录仪等)内,灾难密度统计装置通过终端的网络接口(如蜂窝网、WIFI等)连接到互联网,并连接到上述第二预设数据库以及第三预设数据库(即地理信息系统),可以实时地分析用户所在位置的周边风险,并通过DBSCAN密度聚类法,计算出当前位置附近的机动车交通事故/浸水密集的簇,并且通过可视化模块显示在用户的终端上,并可以与地图叠加,使得用户可以进一步明确的获知当前位置周边的灾难风险密度,并及时作出回避。
上述灾难密度的统计方法可以通过计算机可读指令执行,该计算机可读指令记录在计算机可读取介质上。
此外,本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程,是可以通过计算机可读指令来指令相关的硬件来完成,所述的计算机可读指令可存储于计算机可读存储介质中,所述计算机可读存储介质可以是非易失性,也可以是易失性,该计算机可读指令在执行时,可包括如上述各方法的实施例的流程。其中,本申请所提供的各实施例中所使用的对存储器、存储、数据库或其它介质的任何引用,均可包括非易失性和/或易失性存储器。非易失性存储器可包括只读存储器(ROM)、可编程ROM(PROM)、电可编程ROM(EPROM)、电可擦除可编程ROM(EEPROM)或闪存。易失性存储器可包括随机存取存储器(RAM)或者外部高速缓冲存储器。作为说明而非局限,RAM以多种形式可得,诸如静态RAM(SRAM)、动态RAM(DRAM)、同步DRAM(SDRAM)、双数据率SDRAM(DDRSDRAM)、增强型SDRAM(ESDRAM)、同步链路(Synchlink)DRAM(SLDRAM)、存储器总线(Rambus)直接RAM(RDRAM)、直接存储器总线动态RAM(DRDRAM)、以及存储器总线动态RAM(RDRAM)等。
本领域技术人员可以理解,图6中示出的结构,仅仅是与本申请方案相关的部分结构的框图,并不构成对本申请方案所应用于其上的计算机设备的限定,具体的计算机设备可以包括比图中所示更多或更少的部件,或者组合某些部件,或者具有不同的部件布置。最后,还需要说明的是,在本文中,诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来,而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。
本说明书中各个实施例采用递进的方式描述,每个实施例重点说明的都是与其他实施例的不同之处,各个实施例之间相同相似部分互相参见即可。
对所公开的实施例的上述说明,使本领域专业技术人员能够实现或使用本申请。对这些实施例的多种修改对本领域的专业技术人员来说将是显而易见的,本文中所定义的一般原理可以在不脱离本申请的精神或范围的情况下,在其它实施例中实现。因此,本申请将不会被限制于本文所示的这些实施例,而是要符合与本文所公开的原理和新颖特点相一致的最宽的范围。

Claims (20)

  1. 一种灾难密度的统计方法,其中,包括:
    获取用户的名称,根据所述用户的名称从第一预设数据库中获取用户信息;
    根据选择的灾难事件种类以及所述用户信息从第二预设数据库中获取用户关联信息,所述用户关联信息包括与所述用户相关的灾难事件点;
    将所述用户关联信息输入第三预设数据库中,得到所述用户关联信息的经纬度信息;
    根据聚类算法计算所述经纬度信息,得到灾难事件簇。
  2. 根据权利要求1所述的灾难密度的统计方法,其中,所述用户关联信息还包括所述灾难事件点发生的位置,所述灾难事件种类包括火灾、交通事故和/或浸水。
  3. 根据权利要求2所述的灾难密度的统计方法,其中,所述用户关联信息还包括与所述用户相关的非灾难事件点,当所述灾难事件为火灾时,所述第二预设数据库包括出险记录数据库、工商信息公开数据库以及消防出警记录数据库,所述根据选择的灾难事件种类以及所述用户信息从第二预设数据库中获取用户关联信息的步骤包括:
    根据所述用户信息在出险记录数据库、工商信息公开数据库以及消防出警记录数据库中的至少一个获取所述用户关联信息;
    所述用户关联信息还包括与所述用户同行业的火灾高发企业的地址信息,所述将所述用户关联信息输入第三预设数据库中的步骤包括:
    将所述火灾高发企业的地址信息输入所述第三预设数据库,得到所述火灾高发企业的地址信息的经纬度信息。
  4. 根据权利要求2所述的灾难密度的统计方法,其中,当所述灾难事件为交通事故时,所述第二预设数据库包括出险记录数据库、法院信息数据库以及交警出警记录数据库,所述根据选择的灾难事件种类以及所述用户信息从第二预设数据库中获取用户关联信息的步骤包括:
    根据所述用户信息在出险记录数据库、工商信息公开数据库以及消防出警记录数据库中的至少一个获取所述用户关联信息;
    所述用户关联信息还包括与所述用户在同一区域内发生的交通事故位置信息,所述将所述用户关联信息输入第三预设数据库中的步骤包括:
    将所述交通事故位置信息输入所述第三预设数据库,得到所述交通事故位置信息的经纬度信息。
  5. 根据权利要求2所述的灾难密度的统计方法,其中,当所述灾难事件为浸水时,所述第二预设数据库包括出险记录数据库、交警出警记录数据库以及消防出警记录数据库,所述根据选择的灾难事件种类以及所述用户信息从第二预设数据库中获取用户关联信息的步骤包括:
    根据所述用户信息在出险记录数据库、交警出警记录数据库以及消防出警记录数据库中的至少一个获取所述用户关联信息;
    所述用户关联信息还包括与所述用户同一区域内发生的浸水事件位置信息,所述将所述用户关联信息输入第三预设数据库中的步骤包括:
    将所述浸水事件位置信息输入所述第三预设数据库,得到所述浸水事件位置信息的经纬度信息。
  6. 根据权利要求1至5中任一项所述的灾难密度的统计方法,其中,在所述根据聚类算法计算所述经纬度信息,得到灾难事件簇的步骤之后,还包括:
    将所述灾难事件簇输出到地图应用,通过所述地图应用显示所述灾难事件簇表示的高风险地区。
  7. 根据权利要求1至5中任一项所述的统计方法,其中,所述根据聚类算法计算所述灾难事件簇的步骤包括:
    将所有所述灾难事件点的所述经纬度信息转换为用经纬度坐标表示的点,
    选取任意一个所述点作为第一点,并将距离所述第一点小于或等于预设距离的所有的所述点作为第二点;
    如果所述第二点的个数小于预设的最少点数,将所述第一点标记为噪声;
    如果所述第二点个数大于所述最少点数,将所述第一点标记为核心点,并将该所述第一点以及所有的所述第二点分配到第一簇标签;
    逐个检测所述第二点的在所述预设距离内的邻接点个数,将所述邻接点个数大于所述最少点数的所述第二点也标记为所述核心点,并将所述邻接点也分配到所述第一簇标签;
    检测所有的所述第二点之后,重复选取任意一个所述点作为新的第一点,并将距离所述新的第一点小于或等于预设距离的所有的所述点作为新的第二点,直至处理完成所有的所述点。
  8. 一种灾难密度的统计装置,其中,包括:
    第一数据获取模块,用于获取用户的名称,根据所述用户的名称从第一预设数据库中获取用户信息;
    第二数据获取模块,用于根据选择的灾难事件种类以及所述用户信息从第二预设数据库中获取用户关联信息;
    第三数据获取模块,用于将所述用户关联信息输入第三预设数据库中,得到所述用户关联信息的经纬度信息;
    密度聚类统计模块,用于根据聚类算法计算所述经纬度信息,得到灾难事件簇。
  9. 一种计算机设备,包括存储器和处理器,其中,所述存储器中存储有计算机可读指令,所述计算机可读指令被所述处理器执行时执行以下步骤:
    获取用户的名称,根据所述用户的名称从第一预设数据库中获取用户信息;
    根据选择的灾难事件种类以及所述用户信息从第二预设数据库中获取用户关联信息,所述用户关联信息包括与所述用户相关的灾难事件点;
    将所述用户关联信息输入第三预设数据库中,得到所述用户关联信息的经纬度信息;
    根据聚类算法计算所述经纬度信息,得到灾难事件簇。
  10. 根据权利要求9所述的计算机设备,其中,所述用户关联信息还包括所述灾难事件点发生的位置,所述灾难事件种类包括火灾、交通事故和/或浸水。
  11. 根据权利要求10所述的计算机设备,其中,所述用户关联信息还包括与所述用户相关的非灾难事件点,当所述灾难事件为火灾时,所述第二预设数据库包括出险记录数据库、工商信息公开数据库以及消防出警记录数据库,所述计算机可读指令被所述处理器执行时还执行以下步骤:
    根据所述用户信息在出险记录数据库、工商信息公开数据库以及消防出警记录数据库中的至少一个获取所述用户关联信息;
    所述用户关联信息还包括与所述用户同行业的火灾高发企业的地址信息,所述将所述用户关联信息输入第三预设数据库中的步骤包括:
    将所述火灾高发企业的地址信息输入所述第三预设数据库,得到所述火灾高发企业的地址信息的经纬度信息。
  12. 根据权利要求10所述的计算机设备,其中,当所述灾难事件为交通事故时,所述第二预设数据库包括出险记录数据库、法院信息数据库以及交警出警记录数据库,所述计算机可读指令被所述处理器执行时还执行以下步骤:
    根据所述用户信息在出险记录数据库、工商信息公开数据库以及消防出警记录数据库中的至少一个获取所述用户关联信息;
    所述用户关联信息还包括与所述用户在同一区域内发生的交通事故位置信息,所述将所述用户关联信息输入第三预设数据库中的步骤包括:
    将所述交通事故位置信息输入所述第三预设数据库,得到所述交通事故位置信息的经纬度信息。
  13. 根据权利要求10所述的计算机设备,其中,当所述灾难事件为浸水时,所述第二预设数据库包括出险记录数据库、交警出警记录数据库以及消防出警记录数据库,所述计算机可读指令被所述处理器执行时还执行以下步骤:
    根据所述用户信息在出险记录数据库、交警出警记录数据库以及消防出警记录数据库中的至少一个获取所述用户关联信息;
    所述用户关联信息还包括与所述用户同一区域内发生的浸水事件位置信息,所述将所述用户关联信息输入第三预设数据库中的步骤包括:
    将所述浸水事件位置信息输入所述第三预设数据库,得到所述浸水事件位置信息的经纬度信息。
  14. 根据权利要求9至13中任一项所述的计算机设备,其中,所述计算机可读指令被所述处理器执行时还执行以下步骤:
    在所述根据聚类算法计算所述经纬度信息,得到灾难事件簇的步骤之后,将所述灾难事件簇输出到地图应用,通过所述地图应用显示所述灾难事件簇表示的高风险地区。
  15. 根据权利要求9至13中任一项所述的计算机设备,其中,所述计算机可读指令被所述处理器执行时还执行以下步骤:
    将所有所述灾难事件点的所述经纬度信息转换为用经纬度坐标表示的点,
    选取任意一个所述点作为第一点,并将距离所述第一点小于或等于预设距离的所有的所述点作为第二点;
    如果所述第二点的个数小于预设的最少点数,将所述第一点标记为噪声;
    如果所述第二点个数大于所述最少点数,将所述第一点标记为核心点,并将该所述第一点以及所有的所述第二点分配到第一簇标签;
    逐个检测所述第二点的在所述预设距离内的邻接点个数,将所述邻接点个数大于所述最少点数的所述第二点也标记为所述核心点,并将所述邻接点也分配到所述第一簇标签;
    检测所有的所述第二点之后,重复选取任意一个所述点作为新的第一点,并将距离所述新的第一点小于或等于预设距离的所有的所述点作为新的第二点,直至处理完成所有的所述点。
  16. 一个或多个存储有计算机可读指令的可读存储介质,所述计算机可读指令被一个或多个处理器执行时,使得所述一个或多个处理器执行如下步骤:
    获取用户的名称,根据所述用户的名称从第一预设数据库中获取用户信息;
    根据选择的灾难事件种类以及所述用户信息从第二预设数据库中获取用户关联信息,所述用户关联信息包括与所述用户相关的灾难事件点;
    将所述用户关联信息输入第三预设数据库中,得到所述用户关联信息的经纬度信息;
    根据聚类算法计算所述经纬度信息,得到灾难事件簇。
  17. 根据权利要求16所述的一个或多个存储有计算机可读指令的可读存储介质,其中,所述用户关联信息还包括所述灾难事件点发生的位置,所述灾难事件种类包括火灾、交通事故和/或浸水。
  18. 根据权利要求17所述的一个或多个存储有计算机可读指令的可读存储介质,其中,所述用户关联信息还包括与所述用户相关的非灾难事件点,当所述灾难事件为火灾时,所述第二预设数据库包括出险记录数据库、工商信息公开数据库以及消防出警记录数据库,所述计算机可读指令被一个或多个处理器执行时,使得所述一个或多个处理器还执行如下步骤:
    根据所述用户信息在出险记录数据库、工商信息公开数据库以及消防出警记录数据库中的至少一个获取所述用户关联信息;
    所述用户关联信息还包括与所述用户同行业的火灾高发企业的地址信息,所述将所述用户关联信息输入第三预设数据库中的步骤包括:
    将所述火灾高发企业的地址信息输入所述第三预设数据库,得到所述火灾高发企业的地址信息的经纬度信息。
  19. 根据权利要求17所述的一个或多个存储有计算机可读指令的可读存储介质,其中, 当所述灾难事件为交通事故时,所述第二预设数据库包括出险记录数据库、法院信息数据库以及交警出警记录数据库,所述计算机可读指令被一个或多个处理器执行时,使得所述一个或多个处理器还执行如下步骤:
    根据所述用户信息在出险记录数据库、工商信息公开数据库以及消防出警记录数据库中的至少一个获取所述用户关联信息;
    所述用户关联信息还包括与所述用户在同一区域内发生的交通事故位置信息,所述将所述用户关联信息输入第三预设数据库中的步骤包括:
    将所述交通事故位置信息输入所述第三预设数据库,得到所述交通事故位置信息的经纬度信息。
  20. 根据权利要求17所述的一个或多个存储有计算机可读指令的可读存储介质,其中,当所述灾难事件为浸水时,所述第二预设数据库包括出险记录数据库、交警出警记录数据库以及消防出警记录数据库,所述计算机可读指令被一个或多个处理器执行时,使得所述一个或多个处理器还执行如下步骤:
    根据所述用户信息在出险记录数据库、交警出警记录数据库以及消防出警记录数据库中的至少一个获取所述用户关联信息;
    所述用户关联信息还包括与所述用户同一区域内发生的浸水事件位置信息,所述将所述用户关联信息输入第三预设数据库中的步骤包括:
    将所述浸水事件位置信息输入所述第三预设数据库,得到所述浸水事件位置信息的经纬度信息。
PCT/CN2021/090837 2020-12-16 2021-04-29 灾难密度的统计方法、装置、计算机设备以及存储介质 WO2022126979A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011489923.X 2020-12-16
CN202011489923.XA CN112527936A (zh) 2020-12-16 2020-12-16 灾难密度的统计方法、装置、计算机设备以及存储介质

Publications (1)

Publication Number Publication Date
WO2022126979A1 true WO2022126979A1 (zh) 2022-06-23

Family

ID=75000777

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/090837 WO2022126979A1 (zh) 2020-12-16 2021-04-29 灾难密度的统计方法、装置、计算机设备以及存储介质

Country Status (2)

Country Link
CN (1) CN112527936A (zh)
WO (1) WO2022126979A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116047546A (zh) * 2022-07-07 2023-05-02 北京玖天气象科技有限公司 基于多源卫星数据的山火监测方法

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112527936A (zh) * 2020-12-16 2021-03-19 平安科技(深圳)有限公司 灾难密度的统计方法、装置、计算机设备以及存储介质
CN113486128A (zh) * 2021-06-01 2021-10-08 中国人民财产保险股份有限公司 一种大灾黑点信息的展示方法、装置、设备及存储介质

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105427003A (zh) * 2015-12-30 2016-03-23 北京航空航天大学 一种基于出行需求分析的公交站点部署方法
CN109272057A (zh) * 2018-11-21 2019-01-25 北京国网富达科技发展有限责任公司 一种雷害冰灾的聚类分析方法、设备及系统
CN110021018A (zh) * 2019-04-12 2019-07-16 电子科技大学 一种基于遥感数据提取森林火灾足迹的方法
CN110490608A (zh) * 2019-07-12 2019-11-22 招联消费金融有限公司 风险评估方法、装置、计算机设备和存储介质
CN110689218A (zh) * 2019-08-13 2020-01-14 平安科技(深圳)有限公司 风险用户识别方法、装置、计算机设备及存储介质
CN111656140A (zh) * 2018-09-18 2020-09-11 北京嘀嘀无限科技发展有限公司 预测交通事故发生地的人工智能系统和方法
CN112052908A (zh) * 2020-09-17 2020-12-08 公安部交通管理科学研究所 一种交通事故地点聚类方法及系统
CN112527936A (zh) * 2020-12-16 2021-03-19 平安科技(深圳)有限公司 灾难密度的统计方法、装置、计算机设备以及存储介质

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110147982A (zh) * 2019-04-16 2019-08-20 深圳壹账通智能科技有限公司 基于客户请求的自动审核方法、装置、计算机设备及存储介质

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105427003A (zh) * 2015-12-30 2016-03-23 北京航空航天大学 一种基于出行需求分析的公交站点部署方法
CN111656140A (zh) * 2018-09-18 2020-09-11 北京嘀嘀无限科技发展有限公司 预测交通事故发生地的人工智能系统和方法
CN109272057A (zh) * 2018-11-21 2019-01-25 北京国网富达科技发展有限责任公司 一种雷害冰灾的聚类分析方法、设备及系统
CN110021018A (zh) * 2019-04-12 2019-07-16 电子科技大学 一种基于遥感数据提取森林火灾足迹的方法
CN110490608A (zh) * 2019-07-12 2019-11-22 招联消费金融有限公司 风险评估方法、装置、计算机设备和存储介质
CN110689218A (zh) * 2019-08-13 2020-01-14 平安科技(深圳)有限公司 风险用户识别方法、装置、计算机设备及存储介质
CN112052908A (zh) * 2020-09-17 2020-12-08 公安部交通管理科学研究所 一种交通事故地点聚类方法及系统
CN112527936A (zh) * 2020-12-16 2021-03-19 平安科技(深圳)有限公司 灾难密度的统计方法、装置、计算机设备以及存储介质

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116047546A (zh) * 2022-07-07 2023-05-02 北京玖天气象科技有限公司 基于多源卫星数据的山火监测方法
CN116047546B (zh) * 2022-07-07 2024-02-27 北京玖天气象科技有限公司 基于多源卫星数据的山火监测方法

Also Published As

Publication number Publication date
CN112527936A (zh) 2021-03-19

Similar Documents

Publication Publication Date Title
US11847705B2 (en) Systems and methods for surface segment data
WO2022126979A1 (zh) 灾难密度的统计方法、装置、计算机设备以及存储介质
US11715160B1 (en) Systems and methods for using unmanned aerial vehicles
Li et al. Air pollution and environmental injustice: Are the socially deprived exposed to more PM2. 5 pollution in Hong Kong?
Newnam et al. Do not blame the driver: A systems analysis of the causes of road freight crashes
Koper et al. A randomized test of initial and residual deterrence from directed patrols and use of license plate readers at crime hot spots
WO2008036381A2 (en) Method and system for global consolidated risk, threat and opportunity assessment
Gradeci et al. The use of insurance data in the analysis of Surface Water Flood events–A systematic review
Guignet et al. Contamination and incomplete information: Bounding implicit prices using high-profile leaks
Walsh et al. Contaminated sites and information in hedonic models: An analysis of a NJ property disclosure law
Neelawala et al. The impact of mining and smelting activities on property values: a study of Mount Isa city, Queensland, Australia
Kim et al. Do superfund sites affect local property values? Evidence from a spatial hedonic approach
Meyer et al. Using photography to assess housing damage and rebuilding progress for disaster recovery planning
Özcan et al. Investigation of spatiotemporal changes in the incidence of traffic accidents in Kahramanmaraş, Turkey, using GIS-based density analysis
Chand et al. Examining the macro-level factors affecting vehicle breakdown duration
Ashby et al. Concentrations of railway metal theft and the locations of scrap-metal dealers
Bhandary et al. Land use planning and wildfire risk mitigation: an analysis of wildfire-burned subdivisions using high-resolution remote sensing imagery and GIS data
Azad et al. Spatio-temporal study of the determinants of residential satisfaction in new york city during COVID-19 using crowdsourced data
Flage et al. Overall regional risk analysis of four Norwegian municipalities
Winson-Geideman et al. Non-spatial contagion in real estate markets: the case of Brookland Greens
Maghelal et al. Assessing blight and its economic impacts: A case study of Dallas, TX
Kim et al. Mapping the rescue equipment mobilization potential: Decision support tool for emergency management
Labonnote Stormwater-related databases–Review and recommendations
Babukova et al. Challenges ahead the creation of geo databases for Multi-risk assessment in Republic of Bulgaria
Wisinger Chemical hazardous sites and residential prices: Determinants of impact

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21904918

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21904918

Country of ref document: EP

Kind code of ref document: A1