CN113486128A

CN113486128A - Method, device, equipment and storage medium for displaying disaster black spot information

Info

Publication number: CN113486128A
Application number: CN202110608322.4A
Authority: CN
Inventors: 刘锦健; 张琛; 刘峰; 李子旺; 余浩然; 何沛钊; 杨飞彬
Original assignee: Peoples Insurance Company of China
Current assignee: Peoples Insurance Company of China
Priority date: 2021-06-01
Filing date: 2021-06-01
Publication date: 2021-10-08

Abstract

The embodiment of the invention discloses a method for displaying disaster-prone black spot information, which aims to solve the problem that the prior art can not provide disaster-prone black spot information associated with a geographical position based on the information of the geographical position. The method comprises the following steps: acquiring target geographical position information; the method comprises the steps that target geographical position information is input into a pre-established high disaster risk early warning model, and an output result of the high disaster risk early warning model is obtained; outputting the result at least comprises: geographical position information of the disaster-prone black spots and risk attribute information of the disaster-prone black spots; and displaying the output result on a disaster black spot information display interface of the client. The embodiment of the invention also provides a device for displaying the disaster black spot information, electronic equipment and a storage medium.

Description

Method, device, equipment and storage medium for displaying disaster black spot information

Technical Field

The present application relates to the technical field of recommendation of black spot information, and in particular, to a method and an apparatus for displaying disaster black spot information, an electronic device, and a storage medium.

Background

In areas where natural disasters frequently occur, a large number of buildings, land and living facilities are damaged every year, certain economic losses are brought to the public, along with continuous improvement of an early warning mechanism, all large information clients, WeChat public numbers and the like can send reminding notices of the arrival of large disasters to the public before the natural disasters arrive, but the notices can only provide the public with conventional early warning information about the disasters, such as the arrival time and occurrence areas of the disasters.

At present, for insurance services, aiming at disaster early warning, the prior art can only provide a claim settlement flow including cautions and after insurance, and cannot realize providing disaster black spot information associated with a geographic position based on information of the geographic position according to the personal demands of users, particularly car owners.

The disaster-prone black spot information may be geographical location information, disaster-suffering situation information, disaster-suffering reason, risk level, and the like corresponding to a place where a major natural disaster has occurred, is occurring, or is about to occur.

Disclosure of Invention

The embodiment of the application provides a method for displaying disaster-prone black spot information, which is used for solving the problem that the disaster-prone black spot information associated with a geographical position cannot be provided based on the information of the geographical position in the prior art.

The embodiment of the application also provides a device, equipment and a storage medium for displaying the disaster black spot information.

The embodiment of the application adopts the following technical scheme:

in a first aspect, a method for displaying disaster black spot information includes:

acquiring target geographical position information;

inputting the target geographical position information into a pre-established big disaster risk early warning model to obtain an output result of the big disaster risk early warning model; the output result at least comprises: geographical location information of the disaster black points and risk attribute information of the disaster black points, wherein the distances between the geographical location information and the target geographical location information are arranged according to a preset sequencing rule;

displaying the output result on a disaster black spot information display interface of the client;

the disaster risk early warning model comprises: mapping relation between the target recording cluster and the information of the geographic position of the insurance client; the target recording cluster includes: the distance between the geographic position and the geographic position of the insurance application client is smaller than a record cluster formed by records of historical insurance cases with a specified distance threshold;

the historical emergency case comprises: historical case of occurrence caused by disaster; the single historical accident case record at least comprises: and the geographic position information of the disaster black points and the risk attribute information of the disaster black points of the historical case are caused.

In a second aspect, an embodiment of the present application provides a method for displaying disaster black spot information, including:

acquiring target geographical position information;

sending the target geographical position information to a server;

receiving an output result which is sent by a server and obtained by taking the target geographical position information as the input of a disaster risk early warning model; the output result at least comprises: geographical location information of the disaster black points and risk attribute information of the disaster black points, wherein the distances between the geographical location information and the target geographical location information are arranged according to a preset sequencing rule;

In a third aspect, an embodiment of the present invention provides an apparatus for providing disaster black spot information, where the apparatus includes:

the geographic position information acquisition module is used for acquiring target geographic position information;

the geographical position information input module is used for inputting the target geographical position information into a pre-established disaster risk early warning model to obtain an output result of the disaster risk early warning model; the output result at least comprises: geographical location information of the disaster black points and risk attribute information of the disaster black points, wherein the distances between the geographical location information and the target geographical location information are arranged according to a preset sequencing rule;

the output result display module is used for displaying the output result on a disaster black spot information display interface of the client;

In a fourth aspect, an embodiment of the present invention provides a device for displaying disaster black spot information, including:

the target geographic position information sending module is used for sending the target geographic position information to a server;

the target geographic position information receiving module is used for receiving an output result which is sent by the server and obtained by taking the target geographic position information as the input of the disaster risk early warning model; the output result at least comprises: geographical location information of the disaster black points and risk attribute information of the disaster black points, wherein the distances between the geographical location information and the target geographical location information are arranged according to a preset sequencing rule;

In a fifth aspect, an embodiment of the present invention provides an electronic device, including:

the display method comprises a processor, a memory and a computer program which is stored on the memory and can run on the processor, wherein when the computer program is executed by the processor, the steps of the display method for the disaster black spot information provided by the embodiment are realized.

A processor, a memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to implement any one of the methods for displaying disaster black spot information as described above.

In a sixth aspect, an embodiment of the present invention provides a storage medium, including:

when the instructions in the storage medium are executed by a processor of the electronic device, the electronic device is enabled to execute any one of the methods for displaying disaster black spot information.

The embodiment of the application adopts at least one technical scheme which can achieve the following beneficial effects:

the geographical position information of the disaster black points associated with the target geographical position and the risk attribute information of the disaster black points are obtained and displayed by inputting the target geographical position information into the disaster risk early warning model, so that the problem that the existing technology cannot provide the disaster black point information associated with the geographical position based on the geographical position information can be solved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:

fig. 1 is a schematic flowchart of a method for displaying disaster black spot information according to an embodiment of the present application;

fig. 2 is a schematic flowchart of a method for establishing a disaster risk early warning model according to a second embodiment of the present application;

fig. 3 is a schematic flowchart of another family insurance recommendation method provided in the second embodiment of the present application;

fig. 4 is a schematic view of an application interface of disaster black spot information according to a third embodiment of the present application;

fig. 5 is a schematic flowchart of a method for displaying disaster black spot information according to a fourth embodiment of the present application;

fig. 6 is a schematic structural diagram of a device for displaying disaster black spot information according to a fifth embodiment of the present application;

fig. 7 is a schematic structural diagram of another apparatus for displaying disaster black spot information according to a sixth embodiment of the present application;

fig. 8 is a schematic structural diagram of an electronic device according to a seventh embodiment of the present application.

Detailed Description

The first embodiment is as follows:

in order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.

In order to solve the problem that the disaster black spot information associated with the geographic position cannot be provided based on the information of the geographic position in the prior art, the embodiment of the application provides a method for displaying the disaster black spot information.

Referring to fig. 1, fig. 1 is a schematic flow chart of a method for displaying disaster black spot information according to an embodiment of the present invention. The disaster black spot information display method can be applied to a user terminal, and the method is executed through application software installed in the user terminal, wherein the user terminal can be a desktop computer, a notebook computer, a tablet personal computer or a mobile phone, an intelligent wearable device and the like. The method may also be applied to a server.

The disaster black spot described in the embodiment of the present invention may include, but is not limited to: the natural phenomena which bring serious harm to human survival or seriously damage human living environment, such as lightning stroke, flood, typhoon, storm surge, frost damage, hail disaster, tsunami, earthquake, volcano, landslide, debris flow, forest fire, cosmic radiation, red tide, tornado, flood, ground collapse, coastline change and the like.

The method is described below by taking the method as an example of being applied to a server.

The method comprises the following steps:

in step S11, the server obtains the target geographical location information.

The target geographical location information referred to herein is geographical location information that is an inquiry condition for "inquiring disaster black spot information associated with geographical location information".

In practical application scenarios, for example, the target geographic location information may include, but is not limited to, at least one of the following:

the vehicle insurance application geographic position of the vehicle insurance application client;

resident geographic location of the car insurance applicant;

current position information of the insurance application client;

and the geographic position information is input through the client and used for inquiring the disaster black spot information associated with the geographic position.

The insurance application geographical position information of the insurance application client can be understood as the geographical range of the insurance application for the vehicle (namely the application vehicle) purchased by the user. That is, only in the area represented by the geographic location information of the insurance application, when the insurance client takes out the insurance, the insurance will pay the insurance client. The vehicle insurance application geographical position information can be filled by the user during application and sent to the server for storage.

The resident geographical position information of the insurance application client can be understood as the information of the geographical position of the insurance application vehicle which is parked for a period of time. For the resident geographic location, for example, if the user always stops the insurance vehicle in a parking lot of a work unit on a weekday, the location of the parking lot is the resident geographic location; for example, after the user leaves work, the user always parks the insurance vehicle in a parking lot at a home address, and the location of the parking lot may be the resident geographic location. Whether the vehicle is a resident geographic location or not can be determined by the server according to a (Global Positioning System, GPS) coordinate periodically reported by the insurance vehicle and a reporting date of the coordinate. If the insured vehicle reports the same geographical position for a plurality of consecutive days (such as one month), the geographical position can be determined as a resident geographical position.

The current position information of the insurance application user can be understood as the GPS coordinates of the insurance application vehicle, which are acquired by the GPS module of the insurance application vehicle in real time. The GPS coordinate can be acquired by a GPS module of the vehicle to be insured and is sent to a client used by a vehicle insurance user, and then is sent to the server by the client; or the GPS module of the insurance vehicle can acquire the information and directly send the information to the server.

In one embodiment, the current location of the insurance application user may also be a GPS coordinate of the user/mobile phone obtained in real time by a client (such as a client facing the insurance company) installed on the mobile phone of the insurance application user.

The real-time acquisition may be performed by triggering a GPS module of the insurance vehicle or a client on the mobile phone of the user when the user needs to acquire the disaster black spot information.

The geographical location information input by the client and used for inquiring the disaster black spot information associated with the geographical location can be understood as the geographical location information manually input by the user in real time or the geographical location information input by the user in advance.

And step S12, the server inputs the acquired target geographical position information into a pre-established disaster risk early warning model to obtain an output result of the disaster risk early warning model.

Wherein the outputting the result at least comprises: the geographical position information of the disaster black points and the risk attribute information of the disaster black points, wherein the distance between the geographical position information and the target geographical position information is arranged according to a preset sequencing rule.

For the server, based on the output result, the output result may be pushed to the client on the mobile phone of the user, so that the client displays the output result on the interface (the specific implementation process may be shown in the subsequent step S13), thereby implementing notification of the specific location of the potential disaster black spot near the target geographic location of the user, and the risk attribute information of the potential disaster black spot, such as the disaster grade information, the type of the disaster black spot (such as flooding, strong wind, etc.), the degree of loss caused, or the potential cause of danger, etc., and being helpful to remind the vehicle insurance application client to transfer the vehicle in advance.

In the embodiment of the present invention, a typical disaster risk early warning model may include: and recording the mapping relation of the information of the geographic positions of the target cluster and the insurance application client.

Wherein the target recording cluster includes: and the distance between the geographic position and the geographic position of the insurance application client is smaller than the record cluster formed by the historical insurance cases with the specified distance threshold.

Historical emergence cases may include: historical case of occurrence of disaster. The single historical accident case record at least comprises: and the geographic position information of the disaster black points and the risk attribute information of the disaster black points of the historical case are caused.

In the embodiment of the invention, the target recording cluster is formed by the historical risk cases meeting the condition that the distance between the target recording cluster and the geographic position of the vehicle insurance application client is smaller than the specified distance threshold, and the information of the historical risk cases which are closer to or even overlapped with the geographic position of the vehicle insurance application user, including the geographic position information of the disaster black spot and the risk attribute information of the disaster black spot, when a disaster occurs, is considered to be more valuable to the user needing to obtain the disaster black spot information. In contrast, the information of the historical insurance case far away from the geographic position of the vehicle insurance application user has relatively low reference value for the user needing to obtain the information of the disaster black spots.

Based on the model, by inputting the target geographical location information into the model, the model can query and match the geographical location information of the disaster black spot causing the history case in the history risk case record in the mapping relation stored in the model according to the target geographical location information, so as to determine the geographical location information of the disaster black spot of which the distance to the target geographical location is less than the specified distance threshold. And determining a recording cluster where the historical case belonging to the geographical position information of the disaster black spot belongs, namely the target recording cluster.

After the model queries the geographical location information of the disaster-prone black points, the distance between which and the target geographical location information is smaller than the designated distance threshold, if the queried geographical location information is more than one, the queried geographical location information can be sorted according to a preset sorting rule, and then the sorted geographical location information and the risk attribute information of the disaster-prone black points contained in the historical risk case to which the geographical location information belongs are output.

Specifically, the above sort rule may include, for example: the distance from the target geographic location is sorted from near to far, and so on. The geographical position information of the disaster recovery black points and the risk attribute information of the disaster recovery black points are arranged according to a sorting mode from near to far, so that a user can know the distance relationship between the disaster recovery black points and the target geographical position at a glance when an output result is displayed on a disaster recovery black point information display interface of a client in the following, and a reasonable plan is made for driving and traveling of the user.

In an embodiment, the disaster risk early warning model may be established in the following manner:

selecting a set formed by selected historical insurance cases, namely the selected historical insurance cases, from the historical insurance cases, wherein the distance between the geographic position and the geographic position of the vehicle insurance applicant is smaller than a specified distance threshold value, and the set is a target record cluster;

and establishing a mapping relation between the target record cluster and the information of the geographic position of the insurance application client.

The established mapping relation is the disaster risk early warning model.

For example, the geographic location of the vehicle insurance applicant includes A, B, C, and in the historical risk cases 1 to 10, the distance between at least one of the historical risk cases 1, 2, 3, and A, B, C is smaller than the specified distance threshold (e.g., 10 km), so that the historical risk cases 1, 2, and 3 may be selected to form the target record cluster, and a mapping relationship between the target record cluster and the geographic location A, B, C is established as the disaster warning model.

The "vehicle insurance users" may refer to all or part of the vehicle insurance users who can be determined by the server to purchase vehicle insurance for the vehicle in the process of establishing the disaster risk early warning model.

And step S13, displaying the output result on a disaster black spot information display interface of the client.

As described above, the output result at least includes the geographical location information of the disaster recovery black points whose distances from the target geographical location information are arranged according to the predetermined sorting rule, and the risk attribute information of the disaster recovery black points.

By adopting the method provided by the embodiment of the invention, the geographical position information of the disaster black spot associated with the target geographical position and the risk attribute information of the disaster black spot are obtained and displayed by inputting the target geographical position information into the disaster risk early warning model, so that the problem that the existing technology can not provide the disaster black spot information associated with the geographical position based on the geographical position information can be solved.

Example two

In the second embodiment of the present application, a specific establishment method of the disaster early warning model is mainly introduced.

Referring to fig. 2, a schematic flow chart of a method for establishing a disaster risk early warning model according to the second embodiment of the present application specifically includes the following steps 121 to 124:

step 121, acquiring a plurality of historical case records;

wherein, the single history accident record at least comprises: and the geographic position information of the disaster black points and the risk attribute information of the disaster black points of the historical case are caused.

Since the historical risk occurrence case record is usually saved by the vehicle insurance claim settlement service system of the insurance company, in one embodiment, a valid (i.e. successfully occurring) historical risk occurrence case record can be obtained from the vehicle insurance claim settlement service system.

In a single historical incident record, this may typically include: the location of the accident (i.e., the geographical location of the black spot), the reason of the accident (i.e., the type of the black spot, such as storm, rainstorm, lightning strike, debris flow, etc.), the amount of the claim, the level of the black spot, etc.

Here, the information such as the type of the disaster black spot (the reason of the occurrence of the disaster), the amount of the payment, and the disaster level of the disaster black spot may be collectively referred to as the risk attribute information of the disaster black spot.

In an embodiment, when obtaining the historical risk occurrence case records from the vehicle insurance claim settlement service system, the type of disaster black spots (risk occurrence cause) may be used as a query keyword, and the historical risk occurrence case records successfully occurring in the vehicle insurance claim settlement service system for the risk occurrence cause in the last period of time (for example, the last five years) are queried and extracted as the plurality of historical risk occurrence case records.

The historical insurance case records in the vehicle insurance claim settlement service system can be stored correspondingly with the historical insurance case records by taking the insurance reasons and the insurance time as the key words of a single historical insurance case record. Based on the storage mode, historical risk case records can be conveniently inquired based on risk reasons.

In the embodiment of the present invention, the obtained plurality of historical risk occurrence case records may be directly used as the historical risk occurrence case records to be clustered, and then step 122 is executed; or, the history risk case records obtained by screening the history risk case records may be used as the history risk case records to be clustered, and then step 122 is executed.

The screening is carried out by considering that in the queried and extracted historical risk case records, the risk reasons of some historical risk cases are very rare and belong to events with small probability, and for users who want to know the information of the black spots in the disaster, the reference value of the events with small probability is not very high, but the subsequent clustering process consumes more processing resources due to the existence of the records of the historical risk cases. Therefore, in the embodiment of the application, the queried and extracted historical risk case records can be further screened, so that the subsequent processing amount is reduced, and the processing resources are saved.

The specific screening method is as follows:

the history accident record in the embodiment of the present application may be a text composed of a plurality of words. For the history insurance case record in the format, word segmentation processing can be carried out on the history insurance case record to obtain word segmentation results such as ' insurance location (namely the geographical position of the disaster black spot), ' payment amount ', ' type of the disaster black spot ', ' disaster level of the disaster black spot '.

The grading mode of the disaster severity blackspot can be as shown in table 1 below. For example, when the claim amount range is within 5 thousand yuan, the corresponding disaster black spot grade is one grade.

Table 1:

when performing word segmentation processing on the history adventure case records, in one embodiment, the word segmentation processing may be performed in an accurate mode of a Python jieba library.

The Python jieba library has three modes, which are respectively 1 and an accurate mode: the text is accurately separated, and redundancy does not exist; 2. full mode: all possible words in the text are scanned out, and redundancy exists; 3. search engine mode: and on the basis of the accurate mode, segmenting the long words again.

Cut(s) function, which can return an iterateable data type. In an accurate mode, if the historical risk case records ' 7.21.7.7.7.8.pond river people's way rainstorm, water-logging claim pay 5000 yuan, grade 1 ' are compared for word segmentation, word segmentation results can be obtained: 21 months 7 in 2019, Qiantangjiang, Min Lu, rainstorm, flooding, claim payment, 5000 Yuan, and grade 1.

After the word segmentation result is obtained, the database for storing the disaster-prone keyword, which is referred to as a disaster-prone keyword library in the embodiment of the present application, may be updated according to the word segmentation result. The disaster-causing keywords mentioned herein refer to words representing causes of direct damage to vehicles, such as flooding, water logging, water level, wading, water depth, water intake, tree falling, wind blowing, and the like.

The implementation process of updating the disaster keyword library according to the word segmentation result comprises the following steps:

counting the total number of words representing the reason of direct damage to the vehicle in the word segmentation results aiming at all the word segmentation results obtained by respectively segmenting the obtained plurality of historical risk case records;

according to the respective number of each vocabulary representing the reason causing direct damage to the vehicle and the total number obtained by statistics in the word segmentation result, calculating the occurrence frequency of each vocabulary, namely calculating the ratio of the respective number in the total number;

and updating the vocabulary with the prior appearance frequency (for example, the size of the appearance frequency is ranked at the top 60%) into the disaster keyword library according to the calculated appearance frequency.

In the embodiment of the present application, information stored in a disaster-prone keyword library may be as shown in table 2 below. In the column corresponding to WORD, WORDs representing the reason of direct damage to the vehicle, such as water immersion, water level, wading, etc., are stored.

Table 2:

serial number	TYPE	WORD	VALVE
				1	Carlpdis	Soaking in water	1
2	Carlpdis	Water level	1
				3	Carlpdis	Wading water	1
4	Carlpdis	Depth of water	1
				5	Carlpdis	Water logging	1
6	...	...	...

Based on the updated disaster keyword library, several history case records obtained by performing step 121 may be screened.

The specific screening process may include: for each acquired historical risk case record in the plurality of historical risk case records, respectively executing the following operations:

judging whether the word segmentation result of the historical risk occurrence case record contains a disaster-prone keyword stored in the updated disaster-prone keyword library or not based on the word segmentation result obtained by segmenting the historical risk occurrence case record and the updated disaster-prone keyword library;

if so, taking the historical risk case record as a screening result, and storing the word segmentation result of the historical risk case record into a database of the server, wherein the database is used for storing information of the historical risk case record;

if not, the word segmentation result of the history case record can be discarded.

In the database for storing information of historical risk occurrence case records, for example, the storage form of the word segmentation result of the historical risk occurrence case records may be as shown in table 3 below:

table 3:

the history emergent case records obtained by screening are used as history emergent case records to be clustered, and the method has the advantages that: the method and the device can reduce the number of historical case records to be clustered while ensuring the attention to the large disaster black points with high occurrence probability, thereby saving processing resources to a certain extent.

Step 122, based on the geographical position information of the disaster black points causing the historical risk cases, clustering the historical risk case records to be clustered by adopting a density-based clustering algorithm and a K-means clustering algorithm to obtain record clusters formed by the historical risk case records;

as described above, the history risk occurrence case records to be clustered may be the history risk occurrence case records obtained by performing step 121, or may be history risk occurrence case records obtained by screening the history risk occurrence case records by using the above-described screening manner based on the occurrence frequency of the keyword.

In a specific embodiment, step 122 can be implemented by the following method:

firstly, clustering geographical location information of disaster black points causing the history case to be clustered, which is contained in the history case record to be clustered, by using a density-based DBSCAN clustering algorithm, so as to obtain various categories formed by the geographical location information of the disaster black points. The geographical location information of the disaster black spot may include, but is not limited to, a longitude coordinate value and a latitude coordinate value of the disaster black spot;

secondly, determining the clustering center of each category obtained by clustering by using a K-means clustering algorithm so as to obtain a set formed by history case records respectively corresponding to each category of the determined clustering center, and taking the set as each record cluster.

In an actual scene, the geographical location information of the disaster black spots of different historical emergency cases may have a non-uniform form. For example, some geographical location information is in the form of a place name, such as the three-water area in the mountain of Buddha; some geographical location information is in the form of GPS coordinates, i.e., latitude and longitude coordinates. In order to facilitate clustering, in the embodiment of the invention, the geographical position information of the disaster black points causing the historical case of the accident can be converted according to a uniform form, for example, the geographical position information is converted into a form of longitude and latitude coordinates. And then, clustering operation is carried out based on the geographic position information in the form of longitude and latitude coordinates. For example, taking "san shui district in foshan city" as an example, the geographic location information may be converted into longitude and latitude coordinates of the central location of the district.

In one embodiment, the geographical location information of the disaster black points causing the historical case is clustered by using a density-based DBSCAN clustering algorithm to obtain each category formed by the geographical location information of the disaster black points; the geographical location information of the disaster black spot includes a longitude coordinate value and a latitude coordinate value of the disaster black spot, and includes: initializing a data set, and dividing clusters of the risk coordinate set by using a DBSCAN algorithm based on the initialized data set. When cluster division is performed, the scanning radius is set as follows: 0.2; density threshold value: 5; nearest neighbor distance metric parameter: sparse radius adjacency graphs.

The specific implementation process is as follows:

step one, initializing a data set.

Initializing a data set comprising:

assigning longitude coordinate values and latitude coordinate values of geographical location information of disaster black points causing the historical emergency cases (for convenience of description, the geographical location information of the historical disaster black points is abbreviated as historical black point geographical location information hereinafter) and types of the disaster black points (namely, the emergency types) to a records list, wherein the records list comprises a records _ result list, a points list and an amount variable, and initializing the records _ result list, the points list, the amount variable and the count variable. Wherein:

the records _ result list is constructed for storing the historical black spot geographical position information processed by the DBSCAN algorithm, namely storing the clustered historical black spot geographical position information of each category;

the points list is used for storing the historical black spot geographical position information processed by the DBSCAN algorithm and then processed by the Kmeans algorithm, namely storing the record clusters;

the initial value of the amount variable is set to 5 as the value of the number MinPts specified in the DBSCAN algorithm, while the original length of the records list is assigned to the variable count.

And step two, dividing the clusters of the risk coordinate set by using a DBSCAN algorithm. (preset scan radius: 0.2, density threshold: 5, nearest neighbor distance metric parameter: sparse radius adjacency graph.)

The concrete implementation process of the second step comprises the following steps:

2.0: when the length value of the records _ result list is smaller than the value of the variable count, 2.1 is executed, otherwise, two variable values of the posts (black point information list) and the records _ result list (the record data set marked with the black point sequence number) are returned.

2.1: establishing and initializing a lats longitude list and an lngs latitude list, wherein the lats list is used for storing longitude data of historical black point geographical position information to be clustered, and the lngs list is used for storing latitude data of the historical black point geographical position information to be clustered;

2.2: traversing the records list, and when detecting that longitude and latitude data in the records list do not respectively store the historical black point geographical location information in the lats list and the lngs list, respectively adding the longitude and latitude values of the historical black point geographical location information into the lats longitude list and the lngs latitude list.

2.3: processing data in a lats longitude list and a lngs latitude list by using a pd.DataFrame tool, and storing the processed data into a data set X;

and the data frame tool arranges the longitude and latitude data in the lats longitude list and the lngs latitude list into a matrix respectively, and the longitude and latitude data of one coordinate point is stored in any cell in the matrix.

2.4: and calculating the distance between the different historical black spot geographic positions corresponding to the longitude and latitude in the data set X by using a spherical calculation formula, wherein the distance is called a geodesic distance.

Specifically, in an embodiment, the geodesic distance may be calculated based on a pdist distance measurement method, a geodesic distance matrix including the calculated distance values is constructed based on the calculation result, further, the geodesic distance matrix is compressed by using a squarform function, and the compressed geodesic distance matrix is assigned to the variable distance _ matrix.

One of the calculation formulas that can be specifically used is as follows:

s is the geodesic distance;

r is the sphere radius of 6371 km;

α₁and alpha₂Two longitude data in a lats longitude list are obtained;

β₁and beta₂For lngs latitude list corresponding to alpha₁And alpha₂The two latitude data, for example, the correspondence described herein, refers to α₁And beta₁Longitude data and latitude data of historical black spot geographic position information, alpha₂And beta₂Longitude data and latitude data of historical black spot geographic location information.

2.5: the DBSCAN algorithm is initialized.

The specific initialization content includes:

the cluster number db is 0;

the scanning radius is r-0.2;

the density threshold is amount-5;

the measurement mode is as follows: sparse radius neighborhood map.

2.6: and calling the initialized DBSCAN algorithm for operation.

Specifically, the distance _ matrix is used as an algorithm input when the DBSCAN algorithm is called, an operation result of the DBSCAN algorithm is obtained, and the operation result is added to the data set X in a new column mode.

The obtained operation result comprises: and clustering the geodesic distances into different categories.

And traversing the data set X, and executing the steps 2.4-2.6 on all longitude data and latitude data in the X, so that clustering on all longitude data and latitude data in the data set X can be realized. The results obtained were: different categories of historical black spot geographic location information.

In the embodiment of the invention, a results dictionary and a damages list can be initialized. The results dictionary is used for storing an array formed by longitude data and latitude data of historical black point geographic position information; and the damages list is used for storing the risk types of the disaster black spots causing the historical risk cases.

In the process of respectively executing the steps 2.4-2.6 on all longitude data and latitude data in the X, every time the execution is completed, on one hand, an array is constructed and stored in a results dictionary based on the longitude data and the latitude data which are clustered, and on the other hand, the risk type corresponding to the array is correspondingly stored in a damages list.

And after the steps 2.4-2.6 are respectively executed on all longitude data and latitude data in the X, a results dictionary which stores the array and a data list of the risk type are obtained, and the following steps are further executed.

2.7: and determining the clustering center of each category by taking a coordinate data set formed by the coordinate data of each category (each cluster) obtained by clustering as the input of a Kmeans algorithm, randomly selecting the coordinate data serving as an initial clustering center from the coordinate set, and determining a set formed by historical risk case records respectively corresponding to each category of the determined clustering center as each record cluster in an iterative clustering center calculation mode.

When a Kmeans algorithm is adopted, the set iteration number constraint condition is as follows: the calculation was iterated 20 times.

EXAMPLE III

In the third embodiment, in order to facilitate that a user can conveniently and quickly select a risk according to the self requirement after acquiring the geographical location information of the displayed disaster black spot information and the risk attribute information of the disaster black spot, the method provided in the first embodiment of the present application can be further improved, so as to meet the requirement of the user.

Specifically, the further improvement comprises:

determining a vehicle insurance type insurance application suggestion matched with the risk attribute information according to the risk attribute information contained in the output result of the major disaster risk early warning model;

and displaying the insurance type insurance application suggestion at the client.

For example, if the risk attribute information includes the type of the disaster black spot, and the type is flooding, the server may select the vehicle insurance application suggestion mapped with the type according to a preset mapping relationship between the risk attribute information (including the type of the disaster black spot) of different disaster black spots and the vehicle insurance application suggestion, and send the selected vehicle insurance application suggestion to the client for display. Taking flooding as an example, the insurance application suggestions mapped to the type include: the insurance application is recommended to ensure the dangerous species of 'vehicle damage risk caused by flooding'.

Optionally, the displayed insurance application suggestion can be displayed on the client in the form of a 'clickable selection' control. Therefore, if a user clicks and selects a certain car insurance application suggestion, the insurance server of the insurance company can push the corresponding insurance purchase confirmation page to the client for display, and further guide the user to successfully purchase insurance based on the guide item displayed on the page.

Optionally, if the server determines that the user at the client has purchased the vehicle insurance currently, it may determine whether the vehicle insurance currently purchased by the user has a condition that cannot guarantee the loss caused by the disaster black points corresponding to the risk attribute information of the disaster black points according to the risk attribute information of the disaster black points included in the output result.

For example, if the car insurance that the user has purchased currently is a dangerous type for paying for the loss caused by "strong wind", and the output result includes the risk attribute information of the flood black spot of "flooding", this is the case that the loss caused by the "flood black spot corresponding to the risk attribute information of the flood black spot" cannot be guaranteed.

If it is determined that this situation exists, the server may determine a supplemental car insurance for the car insurance that has been purchased. The supplementary vehicle insurance satisfies the following conditions: the supplementary vehicle insurance can be ensured together with the purchased vehicle insurance, and the loss caused by the large disaster black points corresponding to the risk attribute information of the large disaster black points is ensured.

The information for supplementing the car insurance can be used as the content of the car insurance type insurance application suggestion and is sent to the client side by the server for display. The insurance type insurance application proposal containing the information of the supplementary insurance can also be called a 'customized insurance adding scheme' aiming at the user.

Based on the customized automobile insurance adding scheme, the user can fully know professional automobile insurance supplementing information, and the comprehensive property protection can be realized by performing targeted insurance application based on the information.

Please refer to fig. 3, which is a flowchart illustrating a family insurance recommendation method provided in the third embodiment of the present application, specifically including the following steps 1211 to 1213:

and 1211, determining the resident area type of the resident address of the insurance application client according to the resident information.

The resident message includes at least one of the following: the vehicle insurance application geographic position of the vehicle insurance application client, the geographic position of the house property of the vehicle insurance application client and the current position of the vehicle insurance application client.

The residential area type can be rural areas, commercial areas, ordinary urban residences and the like, the area type of the user resident address is determined based on the geographic position information, and for example, when the obtained user resident address is a Qinglong district in Guangdong city, the ordinary residential area type of the user can be known to be the ordinary urban residences.

Step 1212, determining a family property insurance application proposal matched with the type of the residential area according to the type of the residential area.

And searching resident information corresponding to the user, and if the user does not insusceptible to the designated insurance in the resident area, further searching a historical insurance case corresponding to the area according to the resident information corresponding to the user, thereby obtaining risk attribute information corresponding to the area and finally determining a family insurance insuring suggestion.

For example, a user has a house property in a Qinglong district in Guangdong City, and meanwhile, the user does not invest the household property in the Qinglong district and flood disasters occur in the area, so the system can recommend the user to purchase the household property such as the house property and the indoor property.

And step 1213, displaying the family property insurance proposal at the client.

As shown in fig. 4, the client displays the disaster black spot information around the target geographical location information, and recommends an insurable family insurance for the user, and after the user selects the corresponding insurance information, the user can click a one-key insurance button in the graph to purchase the corresponding insurance service.

Example four

In view of the same inventive concept as the above scheme, an embodiment of the present application further provides a method for displaying disaster black spot information, where the method uses a client as an execution main body to solve a problem that accurate disaster black spot information cannot be provided according to a geographical location in the prior art.

As shown in fig. 5, a flowchart is a specific implementation flow of a disaster black spot information display method according to a fourth embodiment of the present invention, where the method mainly includes the following steps:

step S21: acquiring target geographical position information;

step S22: sending the target geographical position information to a server;

step S23: receiving an output result which is sent by a server and obtained by taking the target geographical position information as the input of a disaster risk early warning model; the output result at least comprises: geographical location information of the disaster black points and risk attribute information of the disaster black points, wherein the distances between the geographical location information and the target geographical location information are arranged according to a preset sequencing rule;

step S24: and displaying the output result on a disaster black spot information display interface of the client.

The geographical position information of the disaster black spot near the target geographical position information and the risk attribute information of the disaster black spot are obtained and displayed by inputting the geographical position information of the target into the disaster risk early warning model, so that the problem that accurate disaster black spot information cannot be provided according to the geographical position of a user in the prior art can be solved.

EXAMPLE five

In view of the same inventive concept as the above solution, an embodiment of the present application further provides a device for displaying disaster black spot information, so as to solve the problem that the disaster black spot information associated with the geographical location cannot be provided based on the information of the geographical location in the prior art.

As shown in fig. 6, a schematic structural diagram of a disaster black spot information display device according to a fifth embodiment of the present invention is shown, where the device mainly includes: geographic position information acquisition module 61, geographic position information input module 62 and geographic position information display module 63, wherein:

a geographic position information obtaining module 61, configured to obtain target geographic position information;

a geographic position information input module 62, configured to input the target geographic position information into a pre-established disaster risk early warning model, so as to obtain an output result of the disaster risk early warning model; the output result at least comprises: geographical location information of the disaster black points and risk attribute information of the disaster black points, wherein the distances between the geographical location information and the target geographical location information are arranged according to a preset sequencing rule;

the output result display module 63 is configured to display the output result on a disaster black spot information display interface of the client;

In an optional implementation manner, if the user corresponding to the client is a car insurance applicant; then, the target geographical location information includes at least one of:

the resident geographic location of the car insurance applicant;

current position information of the insurance application client;

and the geographic position information is input through the client and used for inquiring the associated disaster black spot information.

In an optional implementation manner, the device for displaying disaster black spot information further includes:

the insurance application suggestion determining module is used for determining insurance type insurance application suggestions matched with the risk attribute information according to the risk attribute information;

and the insurance application suggestion display module is used for displaying the insurance type insurance application suggestions at the client.

In an alternative embodiment, the insurance type insurance application suggestion includes: and customizing the insurance adding scheme aiming at the insurance application client.

In an optional implementation manner, if the target geographic location information includes resident address information of the insurance applicant, the disaster-prone black spot information display device displays disaster-prone black spot information; then, the apparatus further comprises:

the resident area type determining module is used for determining the resident area type of the resident address of the insurance driver according to the resident information;

the insurance application suggestion determining module is used for determining the household property insurance application suggestions matched with the type of the residential area according to the type of the residential area;

and the family property insurance application suggestion display module displays the family property insurance application suggestions at the client.

In an optional embodiment, the disaster early warning model includes:

the historical emergence case acquisition module is used for acquiring a plurality of historical emergence case records; wherein, the single history accident record at least comprises: geographical position information of disaster-prone black points and risk attribute information of the disaster-prone black points of historical case cases;

the clustering module is used for clustering the plurality of historical risk case records by adopting a density-based clustering algorithm and a K-means clustering algorithm based on the geographical position information of the disaster black spots causing the historical risk cases so as to obtain each record cluster formed by the historical risk case records;

the vehicle insurance application client geographic position information acquisition module is used for acquiring the information of the geographic position of the vehicle insurance application client, wherein the geographic position of the vehicle insurance application client comprises the following steps: at least one of a resident geographic location and an insurance application geographic location of the insurance application client;

and the early warning model establishing module is used for establishing the disaster risk early warning model according to the information of the geographic position of the vehicle insurance clients and the record clusters.

In an optional implementation manner, the clustering the plurality of history risk case records based on the geographical location information of the disaster black spot causing the history risk case by using a density-based clustering algorithm and a K-means clustering algorithm to obtain each record cluster formed by the history risk case records specifically includes:

clustering the geographical position information of the disaster black points causing the historical case by using a density-based DBSCAN clustering algorithm to obtain various categories formed by the geographical position information of the disaster black points; the geographical position information of the disaster black spot comprises a longitude coordinate value and a latitude coordinate value of the disaster black spot;

and the clustering center determining module is used for determining the clustering centers of all the categories by utilizing a K-means clustering algorithm so as to obtain a set formed by historical risk case records respectively corresponding to all the categories for determining the clustering centers, and the set is used as each record cluster.

By adopting the device provided by the embodiment of the application, the geographical position information of the disaster black spot near the target geographical position information and the risk attribute information of the disaster black spot are obtained and displayed by inputting the target geographical position information into the disaster risk early warning model, so that the problem that the information of the disaster black spot associated with the geographical position cannot be provided based on the geographical position information in the prior art can be solved.

EXAMPLE six

As shown in fig. 8, a schematic structural diagram of a disaster black spot information display device according to an embodiment of the present invention is shown, where the device mainly includes: geographic position information acquisition module 81, target geographic position information sending module, 82, target geographic position information receiving module 83 and output result display module 84, wherein:

a geographic position information obtaining module 81, configured to obtain target geographic position information;

a target geographical position information sending module 82, configured to send the target geographical position information to a server;

a target geographic position information receiving module 83, configured to receive an output result obtained by using the target geographic position information as an input of the disaster risk early warning model and sent by the server; the output result at least comprises: geographical location information of the disaster black points and risk attribute information of the disaster black points, wherein the distances between the geographical location information and the target geographical location information are arranged according to a preset sequencing rule;

and an output result display module 84, configured to display the output result on a disaster black spot information display interface of the client.

The geographical position information of the disaster black spot near the target geographical position information and the risk attribute information of the disaster black spot are obtained and displayed by inputting the geographical position information of the target into the disaster risk early warning model, so that the problem that the prior art cannot provide accurate disaster black spot information according to the geographical position of a user can be solved.

EXAMPLE seven

A seventh embodiment of the present specification relates to an electronic apparatus, as shown in fig. 8. On the hardware level, the electronic device comprises a processor, and optionally an internal bus, a network interface, and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory, such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.

The processor, the network interface, and the memory may be connected to each other via an internal bus, which may be an ISA (Industry Standard Architecture) bus, a PCI (peripheral component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, FIG. 8 is shown with only a single double-headed arrow, but does not indicate only a single bus or a single type of bus.

And the memory is used for storing programs. In particular, the program may include program code comprising computer operating instructions. The memory may include both memory and non-volatile storage and provides instructions and data to the processor.

The processor reads a corresponding computer program from the nonvolatile memory to the memory and then runs the computer program to form the display device of the disaster black spot information on the logic level. The processor is used for executing the program stored in the memory and is specifically used for executing the following operations:

acquiring target geographical position information;

the disaster risk early warning model comprises: mapping relation of the target recording cluster and the information of the geographic position of the insurance application client; the target recording cluster includes: the distance between the geographic position and the geographic position of the insurance application client is smaller than a record cluster formed by historical insurance case records with a specified distance threshold;

In another alternative embodiment, the processor, executing the program stored in the memory, is specifically configured to:

acquiring target geographical position information;

sending the target geographical position information to a server;

The method for displaying the disaster black spot information provided in the present specification may be applied to a processor, or implemented by the processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present specification may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The steps of a method disclosed in connection with the embodiments of the present specification may be embodied directly in a hardware decoding processor, or in a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor.

An embodiment of the present specification further provides a computer-readable storage medium storing one or more programs, where the one or more programs include instructions, which, when executed by an electronic device including multiple application programs, enable the electronic device to perform a method for displaying disaster black spot information, and are specifically configured to perform:

acquiring target geographical position information;

In another alternative implementation, an embodiment of the present specification further provides a computer-readable storage medium storing one or more programs, where the one or more programs include instructions, which, when executed by an electronic device including multiple application programs, enable the electronic device to perform a method for displaying disaster black spot information, and are specifically configured to perform:

acquiring target geographical position information;

sending the target geographical position information to a server;

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the various elements may be implemented in the same one or more software and/or hardware implementations of the present description.

As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, apparatus, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The description has been presented with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

Claims

1. A method for displaying disaster black spot information is characterized by comprising the following steps:

acquiring target geographical position information;

2. The method of claim 1, wherein if the user corresponding to the client is an insurance application client; then, the target geographical location information includes at least one of:

the resident geographic location of the car insurance applicant;

current position information of the insurance application client;

3. The method of claim 2, wherein the method further comprises:

determining a vehicle insurance type insurance application suggestion matched with the risk attribute information according to the risk attribute information;

4. The method of claim 3, wherein the insurance type application recommendation comprises: and customizing the insurance adding scheme aiming at the insurance application client.

5. The method of any one of claims 2 to 4, wherein if the target geographic location information comprises resident address information of the insurance applicant; then, the method further comprises:

determining the resident area type of the resident address of the insurance application client according to the resident information;

determining a family property insurance application proposal matched with the type of the residential area according to the type of the residential area;

and displaying the family property insurance proposal at the client.

6. The method of claim 1, wherein the disaster risk early warning model is established by:

acquiring a plurality of historical risk-occurrence case records; wherein, the single history accident record at least comprises: geographical position information of disaster-prone black points and risk attribute information of the disaster-prone black points of historical case cases;

based on the geographical position information of the disaster black spots causing the historical risk cases, clustering the plurality of historical risk case records by adopting a density-based clustering algorithm and a K-means clustering algorithm to obtain record clusters formed by the historical risk case records;

obtaining information of a geographic position of an insurance application client, wherein the geographic position of the insurance application client comprises: at least one of a resident geographic location and an insurance application geographic location of the insurance application client;

and establishing the disaster risk early warning model according to the information of the geographical position of the vehicle insurance client and the record clusters.

7. The method according to claim 6, wherein said clustering said plurality of historical risk case records based on said geographical location information of disaster black spots causing said historical risk case, using a density-based clustering algorithm and a K-means clustering algorithm, to obtain record clusters formed by said historical risk case records, specifically comprises:

and determining the clustering centers of the categories by using a K-means clustering algorithm to obtain a set formed by historical risk case records respectively corresponding to the categories of which the clustering centers are determined as the record clusters.

8. A method for displaying disaster black spot information is characterized by comprising the following steps:

acquiring target geographical position information;

sending the target geographical position information to a server;

9. The utility model provides a display device of disaster recovery black spot information which characterized in that includes:

10. The apparatus of claim 9, wherein if the user corresponding to the client is a car insurance applicant; then, the target geographical location information includes at least one of:

the resident geographic location of the car insurance applicant;

current position information of the insurance application client;

11. The apparatus of claim 10, wherein the apparatus further comprises:

12. The apparatus of claim 11, wherein the insurance type application recommendation comprises: and customizing the insurance adding scheme aiming at the insurance application client.

13. The apparatus according to any one of claims 10 to 12, wherein if the target geographical location information includes resident address information of the insurance applicant; then, the apparatus further comprises:

14. The apparatus of claim 9, wherein the disaster risk early warning model is established by:

15. The apparatus according to claim 14, wherein said clustering said plurality of historical risk case records based on said geographical location information of disaster black spots causing said historical risk case using a density-based clustering algorithm and a K-means clustering algorithm to obtain record clusters formed by said historical risk case records comprises:

16. The utility model provides a display device of disaster recovery black spot information which characterized in that includes:

17. An electronic device, comprising:

a processor; a memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to implement the method for displaying disaster black spot information according to any one of claims 1 to 8.

18. A storage medium, wherein instructions of the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the disaster black spot information presentation method according to any one of claims 1 to 8.