CN111260215B - Risk early warning method and related device - Google Patents

Risk early warning method and related device Download PDF

Info

Publication number
CN111260215B
CN111260215B CN202010042347.8A CN202010042347A CN111260215B CN 111260215 B CN111260215 B CN 111260215B CN 202010042347 A CN202010042347 A CN 202010042347A CN 111260215 B CN111260215 B CN 111260215B
Authority
CN
China
Prior art keywords
risk
position information
cluster
neighborhood
determining
Prior art date
Legal status (The legal status 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 status listed.)
Active
Application number
CN202010042347.8A
Other languages
Chinese (zh)
Other versions
CN111260215A (en
Inventor
曾永理
赵喆
冯宝兴
刘言曌
尹钏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Property and Casualty Insurance Company of China Ltd
Original Assignee
Ping An Property and Casualty Insurance Company of China Ltd
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 Ping An Property and Casualty Insurance Company of China Ltd filed Critical Ping An Property and Casualty Insurance Company of China Ltd
Priority to CN202010042347.8A priority Critical patent/CN111260215B/en
Publication of CN111260215A publication Critical patent/CN111260215A/en
Application granted granted Critical
Publication of CN111260215B publication Critical patent/CN111260215B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION 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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Biology (AREA)
  • Game Theory and Decision Science (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Development Economics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Educational Administration (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Traffic Control Systems (AREA)
  • Alarm Systems (AREA)

Abstract

The embodiment of the invention discloses a risk early warning method and a related device, which are suitable for risk management and control. The method comprises the following steps: acquiring a plurality of risk events and risk position information of the plurality of risk events, and classifying the risk position information of the plurality of risk events according to event types to obtain a plurality of risk position information sets; determining a risk position information cluster based on a clustering algorithm, and determining a risk area corresponding to the risk position information cluster; determining the service type of the service handled by the target user and the target event type corresponding to the service type, and determining a first target risk area corresponding to the target event type; when the position information of the target user is located in the first target risk area, a first early warning message is generated and sent to the target user so as to perform risk early warning on the target user. By adopting the embodiment of the invention, the risk event can be comprehensively early-warned while higher early-warning accuracy is ensured, and the user experience is improved.

Description

Risk early warning method and related device
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a risk early warning method and related devices.
Background
With the continuous progress of society, people who go out to work, travel, walk, and the like to conduct outdoor activities are increasing. But often suffer from a series of risk events such as natural disasters or traffic accidents outdoors, thereby affecting travel experience or bringing an intolerable loss to the user. The traditional risk early warning mode is usually only used for carrying out risk early warning on one or one type of risk event, and can not be used for carrying out early warning on multiple types of risk events at the same time, so that the effect is single. In addition, the traditional risk early warning mode often adopts modes such as historical experience, construction of a prediction model and the like to realize risk early warning, and early warning accuracy is low.
Therefore, how to perform omnibearing early warning on a risk event on the premise of ensuring higher early warning accuracy becomes a problem to be solved.
Disclosure of Invention
The embodiment of the invention provides a risk early warning method and a related device, which can ensure higher early warning accuracy and simultaneously carry out omnibearing early warning on a risk event, thereby improving user experience.
In a first aspect, an embodiment of the present invention provides a risk early warning method, including:
acquiring a plurality of risk events and risk position information of the plurality of risk events, and classifying the risk position information of the plurality of risk events according to event types to obtain a plurality of risk position information sets, wherein one event type corresponds to one risk position information set;
Determining a risk position information cluster from each risk position information set based on a clustering algorithm, and determining a risk region corresponding to the risk position information cluster based on each risk position information in the risk position information cluster to obtain a risk region corresponding to each event type;
determining the service type of the service handled by the target user and the target event type corresponding to the service type, and determining a first target risk area corresponding to the target event type based on a risk position information cluster corresponding to the target event type;
and determining the position information of the target user, generating a first early warning message when the position information of the target user is positioned in the first target risk area, and sending the first early warning message to the target user so as to perform risk early warning on the target user.
With reference to the first aspect, in one possible implementation manner, determining the risk location information cluster from each risk location information set based on the clustering algorithm includes:
determining distance parameters and quantity parameters corresponding to each risk position information set;
selecting risk position information i from the risk position information of each risk position information set, and determining a neighborhood N of the risk position information i by taking the risk position information i as a circle center and the distance parameter as a radius i ；
When the neighborhood N i When the number of the risk position information is not less than the number parameter, the neighborhood N is determined i Is determined as a cluster C to be processed 1 ；
Determining the cluster C to be processed 1 Neighborhood of other risk position information except the risk position information i, and determining a first target neighborhood with the number of the risk position information not smaller than the number parameter from the neighborhood of other risk position information;
the first target neighborhood and the cluster C to be processed are processed 1 Merging to obtain a cluster C to be processed 2 Up to cluster C to be treated n Is not in contact with the cluster C to be processed n When the first target neighborhood is merged, the cluster C to be processed is processed n And determining the first risk position information cluster, wherein n is an integer greater than or equal to 1.
With reference to the first aspect, in a possible implementation manner, the method further includes:
when the neighborhood N i When the number of risk position information is smaller than the number parameter, selecting risk position information j from the risk position information of each risk position information set;
determining a neighborhood N of the risk position information j by taking the risk position information j as a circle center and the distance parameter as a radius j And judging the neighborhood N j Whether the number of risk location information is smaller than the number parameter.
With reference to the first aspect, in a possible implementation manner, the method further includes:
dividing the cluster C to be processed from each risk position information set n Other risk location informationSelecting risk position information x from the information, and determining the neighborhood N of the risk position information x x ；
When the neighborhood N x Neutralization and the cluster C to be treated n When the number of other risk position information except the same risk position information is not less than the number parameter, the neighborhood N is determined x Is determined as a cluster D to be processed 1 ；
Determining the cluster D to be processed 1 Neighborhood of other risk location information than the risk location information x, and from the cluster D to be processed 1 Determining the cluster C to be processed from the neighborhood of other risk position information except the risk position information x n The number of other risk position information except the same risk position information is not less than the second target neighborhood of the number parameter;
the second target neighborhood and the cluster to be processed D are processed 1 Merging to obtain a cluster D to be processed 2 Up to cluster D to be processed m Is not in contact with the cluster D to be processed m When the second target neighborhood is merged, the cluster D to be processed is processed m And determining as a second risk position information cluster, wherein m is an integer greater than or equal to 1.
With reference to the first aspect, in a possible implementation manner, the method further includes:
when the neighborhood N x Neutralization and the cluster C to be treated n When the number of other risk location information except the same risk location information is smaller than the number parameter, the clusters C to be processed are selected from each risk location information set n Selecting risk position information y from other risk position information;
determining a neighborhood N of the risk position information y by taking the risk position information z as a circle center and the distance parameter as a radius y And judging the neighborhood N y Neutralization and the cluster C to be treated n Whether the number of other risk location information other than the same risk location information is smaller than the number parameter.
With reference to the first aspect, in one possible implementation manner, the risk location information includes a longitude and a latitude of a risk location corresponding to the risk location information; the determining the risk area corresponding to the risk location information cluster based on each risk location information in the risk location information cluster includes:
determining the average longitude and the average latitude of the longitude of the risk place corresponding to each risk position information in the risk position information cluster;
Determining a risk radius based on the longitude and latitude of a risk place corresponding to each risk position information in the risk position information cluster;
and determining a risk area corresponding to the risk position information cluster based on the average longitude, the average latitude and the risk radius.
With reference to the first aspect, in a possible implementation manner, the method further includes:
acquiring the journey information of the target user, and determining a second target risk area containing any one or more sections of journey information in the journey information;
and generating a second early warning message based on the event type corresponding to the second target risk area, and sending the second early warning message to the target user before the target user reaches any second target risk area so as to perform risk early warning on the target user.
In a second aspect, an embodiment of the present invention provides a risk early warning device, including:
the system comprises an acquisition module, a storage module and a storage module, wherein the acquisition module is used for acquiring a plurality of risk events and risk position information of the plurality of risk events, and classifying the risk position information of the plurality of risk events according to event types to obtain a plurality of risk position information sets, wherein one event type corresponds to one risk position information set;
The determining module is used for determining a risk position information cluster from each risk position information set based on a clustering algorithm, and determining a risk area corresponding to the risk position information cluster based on each risk position information in the risk position information cluster so as to obtain a risk area corresponding to each event type;
the determining module is used for determining the service type of the service handled by the target user and the target event type corresponding to the service type, and determining a first target risk area corresponding to the target event type based on a risk position information cluster corresponding to the target event type;
and the early warning module is used for determining the position information of the target user, generating a first early warning message when the position information of the target user is positioned in the first target risk area, and sending the first early warning message to the target user so as to perform risk early warning on the target user.
With reference to the second aspect, in one possible implementation manner, the determining module includes a neighborhood determining unit and a first determining unit;
the neighborhood determining unit is configured to:
determining distance parameters and quantity parameters corresponding to each risk position information set;
Selecting risk position information i from the risk position information of each risk position information set, and determining a neighborhood N of the risk position information i by taking the risk position information i as a circle center and the distance parameter as a radius i ；
The first determining unit is configured to:
when the neighborhood N i When the number of the risk position information is not less than the number parameter, the neighborhood N is determined i Is determined as a cluster C to be processed 1 ；
Determining the cluster C to be processed 1 Neighborhood of other risk position information except the risk position information i, and determining a first target neighborhood with the number of the risk position information not smaller than the number parameter from the neighborhood of other risk position information;
the first target neighborhood and the cluster C to be processed are processed 1 Merging to obtain a cluster C to be processed 2 Up to cluster C to be treated n Is not in contact with the cluster C to be processed n When the first target neighborhood is merged, the first target neighborhood is mergedCluster C to be processed n And determining the first risk position information cluster, wherein n is an integer greater than or equal to 1.
With reference to the second aspect, in a possible implementation manner, the determining module further includes:
an acquisition unit for, when the neighborhood N is the same as i When the number of risk position information is smaller than the number parameter, selecting risk position information j from the risk position information of each risk position information set;
The neighborhood determining unit is further configured to determine a neighborhood N of the risk location information j using the risk location information j as a center and the distance parameter as a radius j And judging the neighborhood N j Whether the number of risk location information is smaller than the number parameter.
With reference to the second aspect, in a possible implementation manner, the neighborhood determining unit is further configured to:
dividing the cluster C to be processed from each risk position information set n Selecting risk position information x from other risk position information, and determining neighborhood N of the risk position information x x ；
The above determining module further includes a second determining unit, further configured to:
when the neighborhood N x Neutralization and the cluster C to be treated n When the number of other risk position information except the same risk position information is not less than the number parameter, the neighborhood N is determined x Is determined as a cluster D to be processed 1 ；
Determining the cluster D to be processed 1 Neighborhood of other risk location information than the risk location information x, and from the cluster D to be processed 1 Determining the cluster C to be processed from the neighborhood of other risk position information except the risk position information x n The number of other risk position information except the same risk position information is not less than the second target neighborhood of the number parameter;
The second target neighborhood and the cluster to be processed D are processed 1 Merging to obtain a waiting placeCluster D 2 Up to cluster D to be processed m Is not in contact with the cluster D to be processed m When the second target neighborhood is merged, the cluster D to be processed is processed m And determining as a second risk position information cluster, wherein m is an integer greater than or equal to 1.
With reference to the second aspect, in a possible implementation manner, the acquiring unit is further configured to:
when the neighborhood N x Neutralization and the cluster C to be treated n When the number of other risk location information except the same risk location information is smaller than the number parameter, the clusters C to be processed are selected from each risk location information set n Selecting risk position information y from other risk position information;
the neighborhood determining unit is further configured to determine a neighborhood N of the risk location information y using the risk location information z as a center and the distance parameter as a radius y And judging the neighborhood N y Neutralization and the cluster C to be treated n Whether the number of other risk location information other than the same risk location information is smaller than the number parameter.
With reference to the second aspect, in one possible implementation manner, the risk location information includes a longitude and a latitude of a risk location corresponding to the risk location information; the determining module is used for:
Determining the average longitude and the average latitude of the longitude of the risk place corresponding to each risk position information in the risk position information cluster;
determining a risk radius based on the longitude and latitude of a risk place corresponding to each risk position information in the risk position information cluster;
and determining a risk area corresponding to the risk position information cluster based on the average longitude, the average latitude and the risk radius.
With reference to the second aspect, in one possible implementation manner, the foregoing early warning module is further configured to:
acquiring the journey information of the target user, and determining a second target risk area containing any one or more sections of journey information in the journey information;
and generating a second early warning message based on the event type corresponding to the second target risk area, and sending the second early warning message to the target user before the target user reaches any second target risk area so as to perform risk early warning on the target user.
In a third aspect, an embodiment of the present invention provides an apparatus, including a processor and a memory, the processor and the memory being interconnected. The memory is for storing a computer program supporting the device for performing the method as provided by the first aspect and/or any of the possible implementation manners of the first aspect, the computer program comprising program instructions, the processor being configured for invoking the program instructions for performing the method as provided by the first aspect and/or any of the possible implementation manners of the first aspect.
In a fourth aspect, embodiments of the present invention provide a computer readable storage medium storing a computer program for execution by a processor to implement the method provided by the first aspect and/or any one of the possible implementation manners of the first aspect.
In the embodiment of the invention, the risk area corresponding to each event type can be obtained by classifying the acquired risk position information of the plurality of risk events according to the event type to determine the risk area corresponding to each event type, so that risk early warning can be carried out on users aiming at all event types, and the applicability is better. Meanwhile, the risk areas obtained through the clustering algorithm are more reasonably divided, and the accuracy of risk early warning based on the risk areas corresponding to each event type can be improved. In addition, the target risk area for carrying out risk early warning on the user is determined through the service type of the service handled by the user, the early warning requirements on different users can be met, redundant and useless early warning messages are prevented from being received by the user, and the user experience is further improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a risk early warning method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a scenario for determining a risk location information cluster according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of another scenario for determining a risk location information cluster according to an embodiment of the present invention;
FIG. 4 is a schematic view of a scenario for determining a risk area according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a scenario for risk early warning for a user according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a risk early warning device according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an apparatus according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The risk early warning method (for convenience of description, the method provided by the embodiment of the invention can be abbreviated) provided by the embodiment of the invention can be suitable for risk early warning of various enterprises in various fields aiming at various types of risks. Referring to fig. 1, fig. 1 is a flow chart of a risk early warning method provided by an embodiment of the present invention. In fig. 1, the method provided by the embodiment of the present invention may include the following steps S101 to S104.
S101, acquiring a plurality of risk events and risk position information of the plurality of risk events, and classifying the risk position information of the plurality of risk events according to event types to obtain a plurality of risk position information sets.
In some possible implementations, multiple risk events may be acquired from multiple sources based on multiple acquisition modes. For example, a plurality of natural disaster events may be obtained from weather websites, weather departments, news stories, etc., where the natural disaster events include, but are not limited to, floods, fires, storms, debris flows, landslide, avalanches, earthquakes, and waterlogging, etc., and may be specifically determined based on actual application scenarios without limitation. The system can also obtain a plurality of risk events such as traffic jams, vehicle rollover, vehicle collision, rear-end collision and the like from traffic departments, news and other sources, and can be specifically determined based on actual application scenes without limitation. The public security organization can acquire a plurality of risk events such as theft, robbery and the like, or can acquire a plurality of risk events such as high-altitude falling objects, road collapse and the like which endanger personal and property safety from various sources of society, and the risk events can be determined specifically based on actual application scenes without limitation. Since risk early warning needs to be performed on the various risk events, after the plurality of risk events are acquired, risk position information (occurrence place of the risk event) of each risk event in the plurality of risk events needs to be acquired, and then the risk position information of the plurality of risk events is classified according to corresponding event types to obtain a plurality of risk position information sets. That is, risk event information of the same type of risk event is classified into one wind position information set, i.e., one event type corresponds to one risk position information set. It should be specifically noted that the above-mentioned range division of event types may be determined based on the actual application scenario, which is not limited herein. For example, the risk location information of the plurality of risk events may be classified according to event types such as natural disasters, traffic accidents, social security, etc., so as to obtain a plurality of risk location information sets, or may be classified according to event types such as floods, earthquakes, rear-end collisions, high-altitude falling objects, etc., so as to obtain a plurality of risk location information sets, and for risk early warning planning of different enterprises in different fields, different event type classification manners may be adopted, which will not be described herein again.
S102, determining a risk position information cluster from each risk position information set based on a clustering algorithm, and determining a risk region corresponding to the risk position information cluster based on each risk position information in the risk position information cluster to obtain a risk region corresponding to each event type.
In some possible embodiments, for each risk location information set, since there are multiple risk location information in the set and the distribution of the risk location information is not uniform, a portion of multiple risk location information with more concentrated distribution needs to be selected from the risk location information set, that is, a risk location information cluster is determined from the risk location information set, and then a risk area of an event type corresponding to the risk location information set is determined based on the risk location information cluster, where the risk area is based on a high-occurrence area of a risk event of the event type. Wherein, determining the risk location information cluster from the risk location information set can be realized based on a clustering algorithm. For convenience of description, a method for determining a risk area will be described by taking any risk location information set as an example. Specifically, when clustering one risk location information set to obtain a risk location information cluster, determining a distance parameter and a quantity parameter when clustering the risk location information set based on an event type corresponding to the risk location information set, a distribution condition of each risk location information in the risk location information set, a distance condition between each risk location information and an actual application scene, wherein the distance parameter and the quantity parameter are used for determining whether each risk location information set in the risk location information set is risk location information in the finally obtained risk location information cluster. After determining the distance parameters and the number parameters corresponding to the risk position information set, one risk position information i can be arbitrarily selected from the risk position information of the risk position information set, and the neighborhood N of the risk position information i is determined by taking the risk position information i as a circle center and the distance parameters corresponding to the risk position information set as a radius i And for neighborhood N of risk location information i i The number of risk location information included in the list (including risk locationInformation i) makes a judgment. When the risk position information i is in the neighborhood N i When the number of the risk position information is not less than the number parameter corresponding to the risk position information set, the neighborhood N of the risk position information i can be selected at the moment i Is determined as a cluster C to be processed 1 When the neighborhood N of the risk position information i i When the number of risk position information is smaller than the number parameter corresponding to the risk position information set, at the moment, any one risk position information j needs to be selected from the risk position information set, and the neighborhood N of the risk position information j is determined by taking the risk position information j as a circle center and the distance parameter corresponding to the risk position information set as a radius j . In the neighborhood N for determining the risk position information j j Then, the neighborhood N of the risk position information j can be determined again j Whether the number of risk location information (including risk location information j) is less than the number parameter corresponding to the set of risk location information. And the same is repeated until the risk position information of which the number of the risk position information in the neighborhood is not less than the number parameter corresponding to the risk position information set is determined from the risk position information set. Assuming neighborhood N of the risk location information i i The number of the risk position information is not less than the corresponding number parameter of the risk position information set, namely the neighborhood N of the risk position information i i Is determined as a cluster C to be processed 1 Thereafter, the cluster C to be processed can be determined 1 Neighborhood of other risk location information except the risk location information i (taking the risk location information as a circle center and the distance parameter corresponding to the risk location information set as a radius). Judging the number of risk position information in the neighborhood of each risk position information at this time, and determining the neighborhood of which the number of risk position information is not smaller than the number parameter corresponding to the risk position information set as a first target neighborhood, namely when the cluster C to be processed 1 When the number of risk location information in the neighborhood of any one risk location information is not smaller than the number parameter corresponding to the risk location information set, each risk location information in the neighborhood can be attributed to the finally obtained risk location information cluster. Based on the implementation manner, when based on the cluster C to be processed 1 ObtainingWhen each first target neighborhood of (a), each first target neighborhood and the cluster C to be processed can be selected 1 Merging to obtain a cluster C to be processed 2 And from the resulting cluster C to be processed 2 Re-determining a plurality of first target neighborhoods in the neighborhood of each risk position information in the cluster C to re-determine the plurality of first target neighborhoods and the cluster C to be processed 2 Merging, and so on until a cluster to be processed (e.g., cluster C to be processed n ) The neighborhood of each risk position information (except the risk position information corresponding to each first target neighborhood in the combination process) does not have a cluster C to be processed n When the first target neighborhood is merged, the cluster C to be processed is processed n And determining a first risk position information cluster corresponding to the risk position information set, wherein n is an integer greater than or equal to 1.
For example, referring to fig. 2, fig. 2 is a schematic diagram of a scenario for determining a risk location information cluster according to an embodiment of the present invention. In fig. 2, the risk location information i is any risk location information selected from a risk location information set, and in this case, the neighborhood N of the risk location information i may be determined by using the risk location information i as a center and a distance parameter corresponding to the risk location information set as a radius i . Assuming that the distance parameter corresponding to the risk location information set is 4, the neighborhood N of the risk location information i can be found in fig. 2 i The number of risk position information in the system is also 4, namely the neighborhood N of the risk position information i i The number of the risk position information is not less than 4, and the neighborhood N of the risk position information i can be obtained i Is determined as a cluster C to be processed 1 . At this time, the clusters C to be processed can be respectively used 1 And the risk position information a, the risk position information b and the risk position information c except the risk position information i are used as circle centers, the distance parameter 4 is used as a radius to obtain a neighborhood corresponding to the risk position information a, a neighborhood corresponding to the risk position information b and a neighborhood corresponding to the risk position information c, and the number of the risk position information in the neighborhood corresponding to the risk position information a, the neighborhood corresponding to the risk position information b and the neighborhood corresponding to the risk position information c is respectively determined. As shown in fig. 2, the number of risk location information in the neighborhood corresponding to the risk location information a is 3, and the risk isThe number of risk position information in the neighborhood corresponding to the position information b and the number of risk position information in the neighborhood corresponding to the risk position information c are both 4, and the number parameter corresponding to the risk position information set is assumed to be 4, at this time, the neighborhood corresponding to the risk position information b and the neighborhood corresponding to the risk position information c can be determined to be the first target neighborhood, and the two first target neighborhoods and the neighborhood N of the risk position information i can be determined i (pending cluster C) 1 ) Merging to obtain a cluster C to be processed 2 。
Referring to fig. 3 again, fig. 3 is another schematic diagram of a scenario for determining a risk location information cluster according to an embodiment of the present invention. In FIG. 3, the clusters C are treated 1 In the method, risk position information d, risk position information e, risk position information f and risk position information g except the risk position information i, the risk position information a, the risk position information b and the risk position information c are used as circle centers, the distance parameter 4 is used as a radius to obtain a neighborhood corresponding to the risk position information d, a neighborhood corresponding to the risk position information e, a neighborhood corresponding to the risk position information f and a neighborhood corresponding to the risk position information g, and the number of risk position information in the neighborhood corresponding to the risk position information d, the neighborhood corresponding to the risk position information e, the neighborhood corresponding to the risk position information f and the neighborhood corresponding to the risk position information g are respectively determined. As shown in fig. 3, the number of risk position information in the neighborhood corresponding to the risk position information g and the neighborhood corresponding to the risk position information f is 3, the number of risk position information in the neighborhood corresponding to the risk position information d and the neighborhood corresponding to the risk position information e is 4, and since the number parameter corresponding to the risk position information set is 4, the neighborhood corresponding to the risk position information d and the neighborhood corresponding to the risk position information e can be determined to be the first target neighborhood at this time, and two first target neighborhoods and the cluster C to be processed are determined 2 Merging to obtain a cluster C to be processed 3 . And so on, in FIG. 3, cluster C is to be processed 3 The number of the neighborhood corresponding to the risk position information r, the neighborhood corresponding to the risk position information s and the neighborhood corresponding to the risk position information t is smaller than 4, and the neighborhood corresponding to the risk position information r, the neighborhood corresponding to the risk position information s and the risk position information t are describedThe neighborhood corresponding to the information t is not the first target neighborhood, and the cluster C to be processed 3 Risk position information with the number of risk position information in the neighborhood not less than 4 is not existed, and the cluster C to be processed can be processed at the moment 3 And determining the first risk position information cluster.
In some possible embodiments, since the distribution of the risk location information in each risk location information set is not uniform, after the first risk location information cluster is determined from one risk location information set based on the implementation manner, the number of risk location information in the neighborhood of all multiple risk location information in the risk location information set may not be determined, where the same risk location information combination needs to be divided by the pending cluster C n One or more risk location information clusters are determined in other risk location information outside the (first risk location information cluster). Specifically, the cluster C to be processed can be removed from the risk location information set n Selecting any one risk position information x from other risk position information, and determining a neighborhood N of the risk position information x by taking the risk position information x and the same distance parameter as radius x And determining the neighborhood N of the risk position information x x The number of the medium risk position information and the cluster C to be processed n Is the same risk location information. When the neighborhood N of the risk position information x is x Cluster C for neutralization and treatment n When the number of other risk position information except the same risk position information is not less than the number parameter, the neighborhood N of the risk position information x is determined x Is determined as a cluster D to be processed 1 . Further, the above-mentioned cluster to be processed D can be determined 1 Neighborhood of other risk location information than the risk location information x, and from the above-mentioned cluster to be processed D 1 Determining the cluster C except the cluster C to be processed in the neighborhood of other risk position information except the risk position information x n The number of other risk position information except the same risk position information is not smaller than the second target neighborhood of the quantity parameter. Similarly, the determined second target neighborhood can be compared with the cluster D to be processed 1 Merging to obtain a cluster D to be processed 2 Up to the above-mentioned cluster D to be processed m Is not in contact with the cluster D to be processed m When the second target neighborhood is merged, the cluster D to be processed is processed m And determining as a second risk position information cluster, wherein m is an integer greater than or equal to 1. If the risk location information set has risk location information in which the neighborhood is not determined and the number of risk location information in the neighborhood is determined, one or more risk location information clusters may be determined from other risk location information in the risk location information set except the first risk location information cluster and the second risk location information cluster based on the implementation manner, and the specific implementation manner is not described herein.
S103, determining the service type of the service handled by the target user and the target event type corresponding to the service type, and determining a first target risk area corresponding to the target event type based on the risk position information cluster corresponding to the target event type.
In some possible embodiments, after determining a plurality of risk location information clusters from each risk location information set, for enterprises and institutions with numerous clients, it is required to determine which event types of risk event early warning is performed on the users, so as to provide targeted risk early warning for different users. Specifically, for a target user, the service type of the service handled by the target user can be determined, and then the target event type corresponding to the service type can be determined. For example, for a user in the car insurance industry, the event type related to the car insurance business handled by the user may be a risk event of a traffic accident class, and for an agricultural organization, the risk event related to the agricultural class handled by the user may be a flood, a heavy rain, etc. In addition, for event types which can relate to all users, such as high-altitude objects, no matter what service is handled by the target user, risk early warning can be carried out on the target user based on the event types. In short, if the target user handles only one service, the target event type corresponding to the service type of the service may be one or multiple target event types. Similarly, if the target user handles multiple services, the service types of the multiple services may be the same service type, and thus, the paper may also correspond to a target event type. Thus, the specific implementation of determining the target event type corresponding to the service type of the service handled by the target user may be determined based on the actual application scenario, and is not limited in this regard.
In some possible embodiments, after determining the target event type, one or more first target risk areas corresponding to the target event type may be further determined based on one or more risk location information clusters corresponding to the target event type. Specifically, taking a case that the service type of the service transacted by the target user corresponds to only one target event type as an example, a risk position information cluster corresponding to the target event type can be determined first, and then the longitude and latitude of the risk location corresponding to each risk position information can be determined from the risk position information cluster. At this time, an average longitude of longitudes of the risk sites corresponding to the respective risk position information in the risk position information cluster may be determined as a longitude of a center position of the first target risk area, and an average latitude of longitudes of the risk sites corresponding to the respective risk position information in the risk position information cluster may be determined as a latitude of a center position of the first target risk area. After determining the central position of the first target risk area, determining the distance between every two risk places corresponding to each risk position information based on the longitude and latitude of the risk place corresponding to each risk position information in the risk position information cluster, and determining the first target risk area corresponding to the target event type based on the determined central position of the first target risk area and the diameter by taking the longest distance as the diameter of the risk area. For example, please refer to fig. 4, fig. 4 is a schematic diagram of a scenario for determining a risk area according to an embodiment of the present invention. The risk location set shown in fig. 4 is a set of risk locations corresponding to respective risk location information in the risk location information cluster, and each risk location has an independent longitude and latitude. Therefore, the center position of the risk area can be determined based on the average longitude and the average latitude obtained by the implementation mode. If the distance 1 shown in fig. 4 is the longest distance between risk sites corresponding to the respective risk location information, the distance 1 may be used as the diameter of the risk area to determine the risk area shown in fig. 4 based on the risk radius obtained by the diameter.
In some possible embodiments, the process of determining the risk location information cluster based on the risk location information set may be regarded as a screening process of risk location information, so as to screen effective risk location information meeting the risk early warning requirement. Therefore, when determining the risk areas based on the risk position information clusters, each risk position information in the risk position information clusters can be clustered again under the condition that the number parameter corresponding to the risk position information clusters can be determined to be a distance parameter, so that one or more first target risk areas corresponding to the target event can be determined, and the specific clustering mode is not limited and is not repeated. It should be specifically noted that the method for determining the risk area based on the risk location information cluster is only a few possible embodiments, and may be specifically determined based on data statistics and actual application scenarios, which is not limited herein.
S104, determining the position information of the target user, and when the position information of the target user is located in the first target risk area, generating a first early warning message and sending the first early warning message to the target user so as to perform risk early warning on the target user.
In some possible embodiments, once the first target risk area is determined based on the service type of the service handled by the target user, the location of the target user may be obtained through the terminal used by the user. When the location information of the target user is located in the first target risk area, the target user is located in a high-occurrence zone of a risk event of an event type. At this time, a first early warning message may be generated and sent to the target user to perform risk early warning on the target user. Optionally, the trip information of the target user may also be obtained (for example, the trip navigation of the target user and the planned route that is set by the target user in advance through other modes, which is not limited herein), and a second target risk area containing any one or more pieces of trip information in the trip information of the target user is determined, that is, one or more second target risk areas that the target user will pass through are determined, so that before the target user does not pass through the second target risk areas, a second early warning message is generated in advance based on event types corresponding to each second target risk area, and the second early warning message is sent to the target user to perform risk early warning on the target user.
Specifically, referring to fig. 5, fig. 5 is a schematic view of a scenario of risk early warning for a user according to an embodiment of the present invention. As shown in fig. 5, after determining a target event type corresponding to a service type based on the service type of a service handled by a target user, three risk areas corresponding to the target event type, namely, a risk area 1, a risk area 2, and a risk area 3, may be determined. The graph in fig. 5 is trip information of the target user, and it is not difficult to find out after comparing the trip information of the target user with the risk area 1, the risk area 2, and the risk area 3, wherein the risk area 1 contains one trip information (trip information 1) of the trip information of the target user, the risk area 2 contains one trip information (trip information 2) of the trip information of the target user, and the risk area 3 contains one trip information (trip information 3) of the trip information of the target user. That is, the target user may pass through the risk areas 1, 2 and 3, so that risk early warning can be performed on the target user when the target user is at a certain distance from one of the risk areas, so that the user can make an emergency response or reasonably plan the journey in time, and after the target user re-plans the journey, the planned journey information of the target user is obtained again, and risk early warning is performed on the target user according to the planned journey information. It should be specifically noted that, for risk areas corresponding to different event types, the time for sending the early warning message to the target user may be determined according to the event type. For example, for a risk event of a natural disaster type, once the position information of the target user reaches the early warning condition, an early warning message may be sent to the target user before the natural disaster comes, for a risk event of a traffic accident type, an early warning message may be sent to the target user when the position information of the target user is located in a risk area, and the early warning message may be specifically determined based on an actual application scenario, which is not limited herein.
In some possible embodiments, when sending the early warning message to the target user, different sending modes can be adopted based on different event types. For example, for a risk event of a natural disaster type, a short message may be passed. And the client side informs the message and the like to send the early warning message to the target user. For the risk event of the traffic accident type, the position information of the target user can be obtained in real time, and the early warning message can be broadcast to the target user in real time through voice. For more urgent event types, such as an earthquake, an early warning message can be sent to the user in a mode of making a call to the user. The sending mode of the early warning message corresponding to the specific event type can be determined based on the actual application scene.
In some possible embodiments, when determining the event type based on the service type of the service handled by the target user, the user type of the target user may be determined by the service type of the service handled by the target user, and when performing risk early warning in a risk area corresponding to the event type determined by the service type, early warning messages with different contents may be sent to the target user for different user types, and the specific content may be determined for a long time based on practical application, which is not limited herein. For example, for risk early warning of an insurance enterprise, if it is determined that a target user is a risk event disposal person of the enterprise according to a user type of the target user, relevant risk information and risk locations corresponding to various risk location information in the risk area can be sent to the target user, so that the target user can dispose risk events in the risk area in time, or work locations of the risk event disposal person can be reasonably arranged, so as to improve risk event disposal efficiency of the risk event disposal person. For another example, for the target user with the user type as the key user, the early warning message sent to the target user may further provide the target user with related information of other risk areas adjacent to the current risk area in addition to the risk information of the current risk area, so that the target user reasonably schedules the personal trip.
In the embodiment of the invention, the risk area corresponding to each event type can be obtained by classifying the acquired risk position information of the plurality of risk events according to the event type to determine the risk area corresponding to each event type, so that risk early warning can be carried out on users aiming at all event types, and the applicability is better. Meanwhile, the risk areas obtained through the clustering algorithm are more reasonably divided, and the accuracy of risk early warning based on the risk areas corresponding to each event type can be improved. In addition, the target risk area for carrying out risk early warning on the user is determined through the service type of the service handled by the user, the early warning requirements on different users can be met, redundant and useless early warning messages are prevented from being received by the user, and the user experience is further improved.
Referring to fig. 6, fig. 6 is a schematic structural diagram of a risk early warning device according to an embodiment of the present invention. The risk early warning device 1 provided by the embodiment of the invention comprises:
an obtaining module 11, configured to obtain a plurality of risk events and risk location information of the plurality of risk events, and classify the risk location information of the plurality of risk events according to event types to obtain a plurality of risk location information sets, where one event type corresponds to one risk location information set;
The determining module 12 is configured to determine a risk location information cluster from each risk location information set based on a clustering algorithm, and determine a risk area corresponding to the risk location information cluster based on each risk location information in the risk location information cluster, so as to obtain a risk area corresponding to each event type;
the determining module 12 is configured to determine a service type of a service handled by a target user and a target event type corresponding to the service type, and determine a first target risk area corresponding to the target event type based on a risk location information cluster corresponding to the target event type;
and the early warning module 13 is configured to determine location information of the target user, and when the location information of the target user is located in the first target risk area, generate a first early warning message and send the first early warning message to the target user to perform risk early warning on the target user.
In some possible embodiments, the determining module 12 includes a neighborhood determining unit 121 and a first determining unit 122;
the neighborhood determining unit 121 is configured to:
determining distance parameters and quantity parameters corresponding to each risk position information set;
Selecting risk position information i from the risk position information of each risk position information set, and determining a neighborhood N of the risk position information i by taking the risk position information i as a circle center and the distance parameter as a radius i ；
The first determining unit 122 is configured to:
when the neighborhood N i When the number of the risk position information is not less than the number parameter, the neighborhood N is determined i Is determined as a cluster C to be processed 1 ；
Determining the cluster C to be processed 1 Neighborhood of other risk position information except the risk position information i, and determining a first target neighborhood with the number of the risk position information not smaller than the number parameter from the neighborhood of other risk position information;
the first target neighborhood and the cluster C to be processed are processed 1 Merging to obtain a cluster C to be processed 2 Up to cluster C to be treated n Is not in contact with the cluster C to be processed n When the first target neighborhood is merged, the cluster C to be processed is processed n And determining the first risk position information cluster, wherein n is an integer greater than or equal to 1.
In some possible embodiments, the determining module 12 further includes:
the obtaining unit 123 is further configured to, when the neighborhood N is i When the number of risk position information is smaller than the number parameter, selecting risk position information j from the risk position information of each risk position information set;
The neighborhood determination unit 121 is further configured to determine, with the risk location information j as a center and the distance parameter as a radiusDefining the neighborhood N of the risk position information j j And judging the neighborhood N j Whether the number of risk location information is smaller than the number parameter.
In some possible embodiments, the neighborhood determination unit 121 is further configured to:
dividing the cluster C to be processed from each risk position information set n Selecting risk position information x from other risk position information, and determining neighborhood N of the risk position information x x ；
The above determination module further includes a second determination unit 124, which is further configured to:
when the neighborhood N x Neutralization and the cluster C to be treated n When the number of other risk position information except the same risk position information is not less than the number parameter, the neighborhood N is determined x Is determined as a cluster D to be processed 1 ；
Determining the cluster D to be processed 1 Neighborhood of other risk location information than the risk location information x, and from the cluster D to be processed 1 Determining the cluster C to be processed from the neighborhood of other risk position information except the risk position information x n The number of other risk position information except the same risk position information is not less than the second target neighborhood of the number parameter;
The second target neighborhood and the cluster to be processed D are processed 1 Merging to obtain a cluster D to be processed 2 Up to cluster D to be processed m Is not in contact with the cluster D to be processed m When the second target neighborhood is merged, the cluster D to be processed is processed m And determining as a second risk position information cluster, wherein m is an integer greater than or equal to 1.
In some possible embodiments, the above-mentioned obtaining unit 123 is further configured to:
when the neighborhood N x Neutralization and the cluster C to be treated n When the number of other risk location information except the same risk location information is smaller than the number parameter, the clusters C to be processed are selected from each risk location information set n Selecting risk position information y from other risk position information;
the neighborhood determining unit 121 is further configured to determine a neighborhood N of the risk location information y using the risk location information z as a center and the distance parameter as a radius y And judging the neighborhood N y Neutralization and the cluster C to be treated n Whether the number of other risk location information other than the same risk location information is smaller than the number parameter.
In some possible embodiments, the risk location information includes a longitude and a latitude of a risk location corresponding to the risk location information; the determining module 12 is configured to:
Determining the average longitude and the average latitude of the longitude of the risk place corresponding to each risk position information in the risk position information cluster;
determining a risk radius based on the longitude and latitude of a risk place corresponding to each risk position information in the risk position information cluster;
and determining a risk area corresponding to the risk position information cluster based on the average longitude, the average latitude and the risk radius.
In some possible embodiments, the foregoing early warning module 13 is further configured to:
acquiring the journey information of the target user, and determining a second target risk area containing any one or more sections of journey information in the journey information;
and generating a second early warning message based on the event type corresponding to the second target risk area, and sending the second early warning message to the target user before the target user reaches any second target risk area so as to perform risk early warning on the target user.
In a specific implementation, the apparatus may execute, through its built-in modules and/or units, an implementation as provided in the steps of fig. 1 above. For example, the foregoing may be used in an implementation manner, and specific reference may be made to the implementation manner provided by each step, which is not described herein.
In the embodiment of the invention, the risk area corresponding to each event type can be obtained by classifying the acquired risk position information of the plurality of risk events according to the event type to determine the risk area corresponding to each event type, so that risk early warning can be carried out on users aiming at all event types, and the applicability is better. Meanwhile, the risk areas obtained through the clustering algorithm are more reasonably divided, and the accuracy of risk early warning based on the risk areas corresponding to each event type can be improved. In addition, the target risk area for carrying out risk early warning on the user is determined through the service type of the service handled by the user, the early warning requirements on different users can be met, redundant and useless early warning messages are prevented from being received by the user, and the user experience is further improved.
Referring to fig. 7, fig. 7 is a schematic structural diagram of an apparatus according to an embodiment of the present invention. As shown in fig. 7, the apparatus 1000 in this embodiment may include: processor 1001, network interface 1004, and memory 1005, and in addition, the above device 1000 may further include: a user interface 1003, and at least one communication bus 1002. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display (Display), a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface, among others. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1004 may be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as at least one disk memory. The memory 1005 may also optionally be at least one storage device located remotely from the processor 1001. As shown in fig. 7, an operating system, a network communication module, a user interface module, and a device control application may be included in a memory 1005, which is a type of computer-readable storage medium.
In the apparatus 1000 shown in fig. 7, the network interface 1004 may provide a network communication function; while user interface 1003 is primarily used as an interface for providing input to a user; and the processor 1001 may be used to invoke a device control application stored in the memory 1005 to implement:
in some possible embodiments, the processor 1001 is configured to:
acquiring a plurality of risk events and risk position information of the plurality of risk events, and classifying the risk position information of the plurality of risk events according to event types to obtain a plurality of risk position information sets, wherein one event type corresponds to one risk position information set;
determining a risk position information cluster from each risk position information set based on a clustering algorithm, and determining a risk region corresponding to the risk position information cluster based on each risk position information in the risk position information cluster to obtain a risk region corresponding to each event type;
determining the service type of the service handled by the target user and the target event type corresponding to the service type, and determining a first target risk area corresponding to the target event type based on a risk position information cluster corresponding to the target event type;
And determining the position information of the target user, generating a first early warning message when the position information of the target user is positioned in the first target risk area, and sending the first early warning message to the target user so as to perform risk early warning on the target user.
In some possible embodiments, the processor 1001 is configured to:
determining distance parameters and quantity parameters corresponding to each risk position information set;
selecting risk position information i from the risk position information of each risk position information set, and determining a neighborhood N of the risk position information i by taking the risk position information i as a circle center and the distance parameter as a radius i ；
When the neighborhood N i When the number of the risk position information is not less than the number parameter, the neighborhood N is determined i Is determined as a cluster C to be processed 1 ；
Determining the cluster C to be processed 1 Neighborhood of other risk location information than the risk location information i, and from the aboveDetermining a first target neighborhood with the number of the risk position information not smaller than the number parameter from the neighborhood of other risk position information;
the first target neighborhood and the cluster C to be processed are processed 1 Merging to obtain a cluster C to be processed 2 Up to cluster C to be treated n Is not in contact with the cluster C to be processed n When the first target neighborhood is merged, the cluster C to be processed is processed n And determining the first risk position information cluster, wherein n is an integer greater than or equal to 1.
In some possible embodiments, the processor 1001 is further configured to:
when the neighborhood N i When the number of risk position information is smaller than the number parameter, selecting risk position information j from the risk position information of each risk position information set;
determining a neighborhood N of the risk position information j by taking the risk position information j as a circle center and the distance parameter as a radius j And judging the neighborhood N j Whether the number of risk location information is smaller than the number parameter.
In some possible embodiments, the processor 1001 is further configured to:
dividing the cluster C to be processed from each risk position information set n Selecting risk position information x from other risk position information, and determining neighborhood N of the risk position information x x ；
When the neighborhood N x Neutralization and the cluster C to be treated n When the number of other risk position information except the same risk position information is not less than the number parameter, the neighborhood N is determined x Is determined as a cluster D to be processed 1 ；
Determining the cluster D to be processed 1 Neighborhood of other risk location information than the risk location information x, and from the cluster D to be processed 1 Determining the cluster C to be processed from the neighborhood of other risk position information except the risk position information x n Other risk location information than the same risk location informationThe number of the information is not smaller than the second target neighborhood of the number parameter;
the second target neighborhood and the cluster to be processed D are processed 1 Merging to obtain a cluster D to be processed 2 Up to cluster D to be processed m Is not in contact with the cluster D to be processed m When the second target neighborhood is merged, the cluster D to be processed is processed m And determining as a second risk position information cluster, wherein m is an integer greater than or equal to 1.
In some possible embodiments, the processor 1001 is further configured to:
when the neighborhood N x Neutralization and the cluster C to be treated n When the number of other risk location information except the same risk location information is smaller than the number parameter, the clusters C to be processed are selected from each risk location information set n Selecting risk position information y from other risk position information;
determining a neighborhood N of the risk position information y by taking the risk position information z as a circle center and the distance parameter as a radius y And judging the neighborhood N y Neutralization and the cluster C to be treated n Whether the number of other risk location information other than the same risk location information is smaller than the number parameter.
In some possible embodiments, the risk location information includes a longitude and a latitude of a risk location corresponding to the risk location information; the processor 1001 is configured to:
determining the average longitude and the average latitude of the longitude of the risk place corresponding to each risk position information in the risk position information cluster;
determining a risk radius based on the longitude and latitude of a risk place corresponding to each risk position information in the risk position information cluster;
and determining a risk area corresponding to the risk position information cluster based on the average longitude, the average latitude and the risk radius.
In some possible embodiments, the processor 1001 is further configured to:
acquiring the journey information of the target user, and determining a second target risk area containing any one or more sections of journey information in the journey information;
and generating a second early warning message based on the event type corresponding to the second target risk area, and sending the second early warning message to the target user before the target user reaches any second target risk area so as to perform risk early warning on the target user.
It should be appreciated that in some possible embodiments, the processor 1001 may be a central processing unit (central processing unit, CPU), which may also be other general purpose processors, digital signal processors (digital signal processor, DSP), application specific integrated circuits (application specific integrated circuit, ASIC), off-the-shelf programmable gate arrays (field-programmable gate array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The memory may include read only memory and random access memory and provide instructions and data to the processor. A portion of the memory may also include non-volatile random access memory. For example, the memory may also store information of the device type.
In a specific implementation, the device 1000 may execute, through each functional module built in the device, an implementation provided by each step in fig. 1, and specifically, the implementation provided by each step may be referred to, which is not described herein again.
In the embodiment of the invention, the risk area corresponding to each event type can be obtained by classifying the acquired risk position information of the plurality of risk events according to the event type to determine the risk area corresponding to each event type, so that risk early warning can be carried out on users aiming at all event types, and the applicability is better. Meanwhile, the risk areas obtained through the clustering algorithm are more reasonably divided, and the accuracy of risk early warning based on the risk areas corresponding to each event type can be improved. In addition, the target risk area for carrying out risk early warning on the user is determined through the service type of the service handled by the user, the early warning requirements on different users can be met, redundant and useless early warning messages are prevented from being received by the user, and the user experience is further improved.
The embodiment of the present invention further provides a computer readable storage medium, where a computer program is stored and executed by a processor to implement the method provided by each step in fig. 1, and specifically, the implementation manner provided by each step may be referred to, which is not described herein.
The computer readable storage medium may be the task processing device provided in any one of the foregoing embodiments or an internal storage unit of the foregoing device, for example, a hard disk or a memory of an electronic device. The computer readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash card (flash card) or the like, which are provided on the electronic device. The computer readable storage medium may also include a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (randomaccess memory, RAM), or the like. Further, the computer-readable storage medium may also include both an internal storage unit and an external storage device of the electronic device. The computer-readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.
The terms first, second and the like in the claims and in the description and drawings are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus. Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the invention. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments. The term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The foregoing disclosure is illustrative of the present invention and is not to be construed as limiting the scope of the invention, which is defined by the appended claims.

Claims (10)

1. A risk early warning method, the method comprising:
acquiring a plurality of risk events and risk position information of the plurality of risk events, and classifying the risk position information of the plurality of risk events according to event types to obtain a plurality of risk position information sets, wherein one event type corresponds to one risk position information set;
Determining distance parameters and quantity parameters corresponding to each risk position information set;
from each risk location of each set of risk location informationSelecting risk position information from information
Figure QLYQS_1
And with the risk location information +.>
Figure QLYQS_2
Determining the risk position information for the circle center and the distance parameter for the radius>
Figure QLYQS_3
Neighborhood of->
Figure QLYQS_4
；
When the neighborhood is in
Figure QLYQS_5
When the number of risk location information is not smaller than the number parameter, the neighborhood is +.>
Figure QLYQS_6
Determination of the cluster to be treated->
Figure QLYQS_7
；
Determining the cluster to be processed
Figure QLYQS_8
Except for the risk location information->
Figure QLYQS_9
Other risk position information neighborhood outside, and determining a first target neighborhood with the number of risk position information not smaller than the number parameter from the neighborhood of other risk position information;
the first target neighborhood and the cluster to be processed are processed
Figure QLYQS_10
Combining to obtain the treated cluster->
Figure QLYQS_11
Up to the cluster to be treated->
Figure QLYQS_12
Does not exist with the cluster to be treated +.>
Figure QLYQS_13
When the first target neighborhood is merged, the cluster to be processed is +.>
Figure QLYQS_14
Determining as a risk location information cluster, wherein +.>
Figure QLYQS_15
Is an integer greater than or equal to 1;
determining a risk area corresponding to the risk position information cluster based on each risk position information in the risk position information cluster to obtain a risk area corresponding to each event type;
Determining a service type of a service handled by a target user and a target event type corresponding to the service type, and determining a first target risk area corresponding to the target event type based on a risk position information cluster corresponding to the target event type;
and determining the position information of the target user, and when the position information of the target user is positioned in the first target risk area, generating a first early warning message and sending the first early warning message to the target user so as to perform risk early warning on the target user.
2. The method according to claim 1, wherein the method further comprises:
when the neighborhood is in
Figure QLYQS_16
When the number of risk location information is smaller than the number parameter, each risk location from each risk location information setThe information is selected from risk position information +.>
Figure QLYQS_17
；
With the risk location information
Figure QLYQS_18
The distance parameter is used as a circle center, and the risk position information is determined by using the distance parameter as a radius>
Figure QLYQS_19
Neighborhood of->
Figure QLYQS_20
And judging the neighborhood->
Figure QLYQS_21
Whether the number of risk location information is smaller than the number parameter;
and the same is repeated until the risk position information of which the number of the risk position information in the neighborhood is not less than the number parameter corresponding to the risk position information set is determined from the risk position information set.
3. The method according to claim 1, wherein the method further comprises:
dividing the clusters to be processed from each risk location information set
Figure QLYQS_22
The risk position information is selected from other risk position information>
Figure QLYQS_23
And determining said risk location information +.>
Figure QLYQS_24
Neighborhood of->
Figure QLYQS_25
；
When the neighborhood is in
Figure QLYQS_26
Is divided from the cluster to be treated +.>
Figure QLYQS_27
When the number of other risk position information except the same risk position information is not less than the number parameter, the neighborhood is added>
Figure QLYQS_28
Determination of the cluster to be treated->
Figure QLYQS_29
;
Determining the cluster to be processed
Figure QLYQS_30
Except for the risk location information->
Figure QLYQS_31
Neighborhood of other risk location information outside and from the cluster to be processed +.>
Figure QLYQS_32
Except for the risk location information->
Figure QLYQS_33
Determining the risk position information except the cluster to be processed in the neighborhood of other risk position information>
Figure QLYQS_34
The number of other risk position information except the same risk position information is not smaller than the second target neighborhood of the quantity parameter;
the second target neighborhood and the cluster to be processed are processed
Figure QLYQS_35
Combining to obtain the treated cluster->
Figure QLYQS_36
Up to the cluster to be treated->
Figure QLYQS_37
Does not exist with the cluster to be treated +.>
Figure QLYQS_38
When the second target neighborhood is merged, the cluster to be processed is +.>
Figure QLYQS_39
And determining as a risk position information cluster, wherein m is an integer greater than or equal to 1.
4. A method according to claim 3, characterized in that the method further comprises:
when the neighborhood is in
Figure QLYQS_40
Is divided from the cluster to be treated +.>
Figure QLYQS_41
When the number of other risk location information except the same risk location information is smaller than the number parameter, the risk location information is selected from the risk location information sets except the cluster to be processed>
Figure QLYQS_42
The risk position information is selected from other risk position information>
Figure QLYQS_43
；
With the risk location information
Figure QLYQS_44
The distance parameter is used as a circle center, and the risk position information is determined by using the distance parameter as a radius>
Figure QLYQS_45
Neighborhood of->
Figure QLYQS_46
And judging the neighborhood->
Figure QLYQS_47
Is divided from the cluster to be treated +.>
Figure QLYQS_48
Whether the number of other risk location information than the same risk location information is smaller than the number parameter.
5. The method of claim 1, wherein the risk location information includes a longitude and latitude of a risk location to which the risk location information corresponds; the determining the risk area corresponding to the risk location information cluster based on each risk location information in the risk location information cluster includes:
determining the average longitude and the average latitude of the longitude of the risk place corresponding to each risk position information in the risk position information cluster;
Determining a risk radius based on the longitude and latitude of a risk place corresponding to each risk position information in the risk position information cluster;
and determining a risk area corresponding to the risk position information cluster based on the average longitude, the average latitude and the risk radius.
6. The method according to claim 1, wherein the method further comprises:
acquiring the journey information of the target user, and determining a second target risk area containing any one or more sections of journey information in the journey information;
and generating a second early warning message based on the event type corresponding to the second target risk area, and sending the second early warning message to the target user before the target user reaches any second target risk area so as to perform risk early warning on the target user.
7. A risk early warning device, the device comprising:
the system comprises an acquisition module, a storage module and a storage module, wherein the acquisition module is used for acquiring a plurality of risk events and risk position information of the plurality of risk events, and classifying the risk position information of the plurality of risk events according to event types to obtain a plurality of risk position information sets, wherein one event type corresponds to one risk position information set;
The determining module is used for determining distance parameters and quantity parameters corresponding to each risk position information set; selecting risk location information from the individual risk location information of each set of risk location information
Figure QLYQS_50
And with the risk location information +.>
Figure QLYQS_58
Determining the risk position information for the circle center and the distance parameter for the radius>
Figure QLYQS_60
Neighborhood of->
Figure QLYQS_52
The method comprises the steps of carrying out a first treatment on the surface of the When the neighborhood is->
Figure QLYQS_55
When the number of risk location information is not smaller than the number parameter, the neighborhood is +.>
Figure QLYQS_62
Determination of the cluster to be treated->
Figure QLYQS_63
The method comprises the steps of carrying out a first treatment on the surface of the Determining the cluster to be treated->
Figure QLYQS_49
Except for the risk location information->
Figure QLYQS_54
Other risk position information neighborhood outside, and determining a first target neighborhood with the number of risk position information not smaller than the number parameter from the neighborhood of other risk position information; the first target neighborhood and the cluster to be processed are treated +>
Figure QLYQS_57
Combining to obtain the treated cluster->
Figure QLYQS_59
Up to the cluster to be treated->
Figure QLYQS_51
Does not exist with the cluster to be treated +.>
Figure QLYQS_53
When the first target neighborhood is merged, the cluster to be processed is +.>
Figure QLYQS_56
Determining as a risk location information cluster, wherein +.>
Figure QLYQS_61
Is an integer greater than or equal to 1;
the determining module is used for determining the service type of the service handled by the target user and the target event type corresponding to the service type, and determining a first target risk area corresponding to the target event type based on a risk position information cluster corresponding to the target event type;
And the early warning module is used for determining the position information of the target user, generating a first early warning message when the position information of the target user is positioned in the first target risk area, and sending the first early warning message to the target user so as to perform risk early warning on the target user.
8. The risk warning device of claim 7, wherein,
the determining module is further configured to: dividing the clusters to be processed from each risk location information set
Figure QLYQS_77
The risk position information is selected from other risk position information>
Figure QLYQS_66
And determining said risk location information +.>
Figure QLYQS_75
Neighborhood of->
Figure QLYQS_67
The method comprises the steps of carrying out a first treatment on the surface of the When the neighborhood is->
Figure QLYQS_69
Is divided from the cluster to be treated +.>
Figure QLYQS_71
When the number of other risk position information except the same risk position information is not less than the number parameter, the neighborhood is added>
Figure QLYQS_76
Determination of the cluster to be treated->
Figure QLYQS_72
Determining the cluster to be treated>
Figure QLYQS_74
Except for the risk location information->
Figure QLYQS_64
Other risk locations thanNeighborhood of information and from the cluster to be processed +.>
Figure QLYQS_68
Except for the risk location information->
Figure QLYQS_78
Determining the risk position information except the cluster to be processed in the neighborhood of other risk position information>
Figure QLYQS_80
The number of other risk position information except the same risk position information is not smaller than the second target neighborhood of the quantity parameter; associating said second target neighborhood with said cluster to be treated +. >
Figure QLYQS_79
Combining to obtain the treated cluster->
Figure QLYQS_81
Up to the cluster to be treated->
Figure QLYQS_65
Does not exist with the cluster to be treated +.>
Figure QLYQS_70
When the second target neighborhood is merged, the cluster to be processed is +.>
Figure QLYQS_73
And determining as a risk position information cluster, wherein m is an integer greater than or equal to 1.
9. The risk early warning device is characterized by comprising a processor and a memory, wherein the processor and the memory are connected with each other;
the memory is for storing a computer program comprising program instructions, the processor being configured to invoke the program instructions to perform the method of any of claims 1 to 6.
10. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program, which is executed by a processor to implement the method of any one of claims 1 to 6.
CN202010042347.8A 2020-01-15 2020-01-15 Risk early warning method and related device Active CN111260215B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010042347.8A CN111260215B (en) 2020-01-15 2020-01-15 Risk early warning method and related device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010042347.8A CN111260215B (en) 2020-01-15 2020-01-15 Risk early warning method and related device

Publications (2)

Publication Number Publication Date
CN111260215A CN111260215A (en) 2020-06-09
CN111260215B true CN111260215B (en) 2023-06-20

Family

ID=70953039

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010042347.8A Active CN111260215B (en) 2020-01-15 2020-01-15 Risk early warning method and related device

Country Status (1)

Country Link
CN (1) CN111260215B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113920690B (en) * 2020-07-07 2023-03-21 中国联合网络通信集团有限公司 Disaster early warning method and equipment
CN112131382B (en) * 2020-08-20 2024-05-10 彭涛 Method and device for identifying high-rise areas of civil problems and electronic equipment
CN112330332B (en) * 2021-01-05 2021-05-07 南京智闪萤科技有限公司 Methods, computing devices, and media for identifying fraud risk with respect to node tasks
CN113486128A (en) * 2021-06-01 2021-10-08 中国人民财产保险股份有限公司 Method, device, equipment and storage medium for displaying disaster black spot information
CN115687599B (en) * 2022-09-29 2023-10-31 恒生电子股份有限公司 Service data processing method and device, electronic equipment and storage medium

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016121828A1 (en) * 2015-01-29 2016-08-04 株式会社ジェイティービー Risk information distribution device and risk information distribution method
CN106291503A (en) * 2016-08-31 2017-01-04 西南交通大学 A kind of radar-probing system Density Clustering method for early warning
CN109543870A (en) * 2018-05-28 2019-03-29 云南大学 A kind of electric power line pole tower lightning stroke method for early warning keeping embedded mobile GIS based on neighborhood
CN110322671A (en) * 2019-06-12 2019-10-11 平安科技（深圳）有限公司 A kind of alarm information processing method and device

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8805707B2 (en) * 2009-12-31 2014-08-12 Hartford Fire Insurance Company Systems and methods for providing a safety score associated with a user location

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016121828A1 (en) * 2015-01-29 2016-08-04 株式会社ジェイティービー Risk information distribution device and risk information distribution method
CN106291503A (en) * 2016-08-31 2017-01-04 西南交通大学 A kind of radar-probing system Density Clustering method for early warning
CN109543870A (en) * 2018-05-28 2019-03-29 云南大学 A kind of electric power line pole tower lightning stroke method for early warning keeping embedded mobile GIS based on neighborhood
CN110322671A (en) * 2019-06-12 2019-10-11 平安科技（深圳）有限公司 A kind of alarm information processing method and device

Also Published As

Publication number Publication date
CN111260215A (en) 2020-06-09

Similar Documents

Publication Publication Date Title
CN111260215B (en) Risk early warning method and related device
US10599491B2 (en) Storing and verifying the integrity of event related data
US9521517B2 (en) Utilizing information about mobile communication devices with respect to an area of interest
US10423688B1 (en) Notifying entities of relevant events
US8874071B2 (en) Method and apparatus for prioritizing and routing emergent activity reporting
Pine Technology and emergency management
CN109996193B (en) Short message sending method, device, system and equipment based on intelligent communication platform
US10779152B2 (en) Communication between responders
Kaiser et al. An emergency evacuation planning model for special needs populations using public transit systems
Sovacool et al. Social media and disasters: human security, environmental racism, and crisis communication in Hurricane Irma response
US9125008B2 (en) Providing information about mobile communication devices
Ceccato et al. The geography of pickpocketing at bus stops: An analysis of grid cells
Tomsen et al. Evacuation planning in the Auckland Volcanic Field, New Zealand: a spatio-temporal approach for emergency management and transportation network decisions
US11250362B2 (en) Machine learning based decentralized business planning system
CN117496669A (en) Method and device for disaster early warning and emergency information targeted release and closed-loop management
Grasic et al. Classification of incoming calls for the capital city of Slovenia smart city 112 public safety system using open Internet of Things data
Esposito Amideo et al. An integrated user‐system approach for shelter location and evacuation routing
US10602338B2 (en) Emergency authorization to access data on proximate computing devices
Yang et al. Demo abstract: SmartSAT-a customizable secure app for San Antonio transit pilot project
US20210081477A1 (en) Filtering signals during major events
US10708749B1 (en) Validating and supplementing emergency call information removing private information
Odufuwa et al. Women and the use of public transport in Nigerian traditional city-ibadan
US20210012114A1 (en) Segmenting video stream frames
Pau et al. Emergency messaging to general public via public wireless networks
Elazab et al. Location Based Approach for Messaging Services.

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant