CN114511249A

CN114511249A - Grid partitioning method and device, electronic equipment and storage medium

Info

Publication number: CN114511249A
Application number: CN202210234384.8A
Authority: CN
Inventors: 朱泽超; 孙甜
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2022-03-09
Filing date: 2022-03-09
Publication date: 2022-05-17

Abstract

The embodiment of the application provides a grid partitioning method and device, electronic equipment and a storage medium, and belongs to the technical field of artificial intelligence. The method comprises the following steps: acquiring target map data; the target map data includes an original region; carrying out mesh division on an original area according to a preset mesh span and a geographic coordinate system to obtain a target mesh; acquiring a target case generated by each target grid; extracting position information of the target case to obtain an initial longitude and latitude point set; clustering the initial longitude and latitude point sets through a preset case clustering model and case clustering labels to obtain a plurality of case type clusters and central grid points of the case type clusters; and carrying out routing inspection simulation according to the central grid point and pre-acquired administrator basic data to generate partition management data of the target grid. The method and the device for managing the target cases in the areas can improve the management and control efficiency of the target cases in each area.

Description

Grid partitioning method and device, electronic equipment and storage medium

Technical Field

The present application relates to the field of artificial intelligence technologies, and in particular, to a grid partitioning method and apparatus, an electronic device, and a storage medium.

Background

At present, when a case in a jurisdiction scope is managed and controlled, the site measurement of a manager usually depends on the experience of a business department, for example, management manpower is increased in a region with more target cases, and management manpower is reduced in a region with less target cases, which often causes unbalanced grid partition management, redundant manager, and the like. Therefore, the grid partition management method based on the experience of the business department for administrator allocation is often inefficient in managing and controlling the target cases in the scope of the jurisdiction. Therefore, how to provide a grid partitioning method, which can improve the efficiency of managing and controlling target cases in each area, is a technical problem to be solved urgently.

Disclosure of Invention

The embodiments of the present application mainly aim to provide a grid partitioning method, a grid partitioning device, an electronic device, and a storage medium, which aim to improve the management and control efficiency of target cases in each area.

In order to achieve the above object, a first aspect of an embodiment of the present application provides a grid partitioning method, where the method includes:

acquiring target map data; the target map data comprises an original region;

performing mesh division on the original region according to a preset mesh span and a geographic coordinate system to obtain a target mesh;

acquiring a target case generated by each target grid;

extracting position information of the target case to obtain an initial longitude and latitude point set;

clustering the initial longitude and latitude point set through a preset case clustering model and case clustering labels to obtain a plurality of case type clusters and central grid points of the case type clusters;

and carrying out routing inspection simulation according to the central grid point and pre-acquired administrator basic data to generate the partition management data of the target grid.

In some embodiments, the grid span includes a longitude span and a latitude span, and the step of performing grid division on the original region according to a preset grid span and a geographic coordinate system to obtain a target grid includes:

performing grid division on the original region according to a preset longitude span and a preset latitude span to obtain an initial grid;

and screening the initial grid according to the geographic coordinate system to obtain the target grid.

In some embodiments, the step of extracting the position information of the target case to obtain an initial longitude and latitude point set includes:

performing label classification processing on the entity characteristics of the target case through a preset sequence classifier and characteristic class labels to obtain position information characteristics corresponding to preset position labels;

and carrying out convolution processing on the position information characteristics through a convolution layer to obtain the initial longitude and latitude point set.

In some embodiments, the step of clustering the initial longitude and latitude point set by using a preset case clustering model and case clustering labels to obtain a plurality of case category clusters and center grid points of the case category clusters includes:

clustering initial longitude and latitude points in the initial longitude and latitude point set through a clustering algorithm of the case clustering model, preset weight parameters and the case clustering labels to obtain a plurality of case category clusters;

calculating the central longitude and latitude point of each case type cluster through a preset first function to obtain a central longitude and latitude point set;

screening the central longitude and latitude point set according to the weight parameters to obtain target longitude and latitude points;

and carrying out longitude and latitude identification on the target longitude and latitude points to obtain the central grid point.

In some embodiments, the step of performing tour simulation according to the central grid point and pre-acquired administrator basic data to generate partitioned management data of the target grid includes:

calculating a first distance value between each target case and the central grid point through a preset second function;

taking the maximum value of the first distance value as a target value;

counting the case number of the target case of the case type cluster through a preset third function to obtain the total number of the target cases;

and performing routing inspection simulation by using the target value, the total amount of the target cases and the administrator basic data to generate the partition management data.

In some embodiments, after the step of clustering the initial longitude and latitude point set by using a preset case clustering model and case clustering labels to obtain a plurality of case category clusters and center grid points of the case category clusters, the method further includes:

calculating a second distance value between each target case and the central grid point through a preset second function;

according to a preset case distribution priority, performing case distribution on a target case corresponding to a second distance value which is greater than or equal to a preset distance threshold value to obtain a case distribution data set;

and carrying out case distribution on the administrator of the target grid according to the case distribution data set.

In some embodiments, before the step of clustering the initial longitude and latitude point set by using a preset case clustering model and case clustering labels to obtain a plurality of case category clusters and center grid points of the case category clusters, the method further includes pre-training the case clustering model, and specifically includes:

obtaining sample map data, wherein the sample map data includes a sample region;

meshing the sample region according to the grid span and the geographic coordinate system to obtain a sample grid;

acquiring a sample case of each sample grid;

inputting the longitude and latitude data of the sample case into an initial model;

calculating the estimated time value of each sample grid through the initial model and a preset reference grid;

and optimizing the loss function of the initial model according to the estimated time value so as to update the initial model and obtain the case clustering model.

To achieve the above object, a second aspect of the embodiments of the present application provides a mesh partitioning apparatus, including:

the target map acquisition module is used for acquiring target map data; the target map data comprises an original region;

the grid division module is used for carrying out grid division on the original area according to a preset grid span and a geographic coordinate system to obtain a target grid;

the target case acquisition module is used for acquiring target cases generated by each target grid;

the position information extraction module is used for extracting the position information of the target case to obtain an initial longitude and latitude point set;

the clustering module is used for clustering the initial longitude and latitude point set through a preset case clustering model and case clustering labels to obtain a plurality of case type clusters and central grid points of the case type clusters;

and the simulation analysis module is used for carrying out routing inspection simulation according to the central grid point and pre-acquired administrator basic data to generate the partition management data of the target grid.

In order to achieve the above object, a third aspect of the embodiments of the present application provides an electronic device, which includes a memory, a processor, a program stored on the memory and executable on the processor, and a data bus for implementing connection communication between the processor and the memory, wherein the program, when executed by the processor, implements the method of the first aspect.

To achieve the above object, a fourth aspect of the embodiments of the present application proposes a storage medium, which is a computer-readable storage medium for computer-readable storage, and stores one or more programs, which are executable by one or more processors to implement the method of the first aspect.

The grid partitioning method, the grid partitioning device, the electronic equipment and the storage medium are used for obtaining target map data; the target map data includes an original region; carrying out grid division on the original region according to a preset grid span and a geographic coordinate system to obtain a target grid, and conveniently carrying out grid management on the original region; and then, acquiring a target case of each target grid, and extracting the position information of the target case to obtain an initial longitude and latitude point set. The initial longitude and latitude point sets are clustered through a preset case clustering model and case clustering labels to obtain a plurality of case type clusters and center grid points of the case type clusters, each target case can be clustered according to the target grid where the target case is located and the type of the target case to obtain a plurality of case type clusters, and therefore case distribution efficiency is improved. And finally, carrying out routing inspection simulation according to the central grid point and pre-acquired administrator basic data to generate partition management data of the target grid, and being capable of pertinently allocating different administrators to different case type clusters, thereby improving the management and control efficiency and management and control rationality of the target cases.

Drawings

FIG. 1 is a flowchart of a grid partitioning method provided in an embodiment of the present application;

FIG. 2 is a flowchart of step S102 in FIG. 1;

FIG. 3 is a flowchart of step S104 in FIG. 1;

FIG. 4 is another flowchart of a grid partitioning method provided in an embodiment of the present application;

fig. 5 is a flowchart of step S105 in fig. 1;

FIG. 6 is another flowchart of a grid partitioning method provided in an embodiment of the present application;

FIG. 7 is a flowchart of step S106 in FIG. 1;

FIG. 8 is a schematic structural diagram of a grid partitioning apparatus provided in an embodiment of the present application;

fig. 9 is a schematic hardware structure diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

It should be noted that although functional blocks are partitioned in a schematic diagram of an apparatus and a logical order is shown in a flowchart, in some cases, the steps shown or described may be performed in a different order than the partitioning of blocks in the apparatus or the order in the flowchart. The terms first, second and the like in the description and in the claims, and the drawings described above, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only and is not intended to be limiting of the application.

First, several terms referred to in the present application are resolved:

artificial Intelligence (AI): is a new technical science for researching and developing theories, methods, technologies and application systems for simulating, extending and expanding human intelligence; artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produces a new intelligent machine that can react in a manner similar to human intelligence, and research in this field includes robotics, language recognition, image recognition, natural language processing, and expert systems, among others. The artificial intelligence can simulate the information process of human consciousness and thinking. Artificial intelligence is also a theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results.

Natural Language Processing (NLP): NLP uses computer to process, understand and use human language (such as chinese, english, etc.), and belongs to a branch of artificial intelligence, which is a cross discipline between computer science and linguistics, also commonly called computational linguistics. Natural language processing includes parsing, semantic analysis, discourse understanding, and the like. Natural language processing is commonly used in the technical fields of machine translation, character recognition of handwriting and print, speech recognition and text-to-speech conversion, information intention recognition, information extraction and filtering, text classification and clustering, public opinion analysis and viewpoint mining, and relates to data mining, machine learning, knowledge acquisition, knowledge engineering, artificial intelligence research, linguistic research related to language calculation and the like related to language processing.

Information Extraction (NER): and extracting the fact information of entities, relations, events and the like of specified types from the natural language text, and forming a text processing technology for outputting structured data. Information extraction is a technique for extracting specific information from text data. The text data is composed of specific units, such as sentences, paragraphs and chapters, and the text information is composed of small specific units, such as words, phrases, sentences and paragraphs or combinations of these specific units. The extraction of noun phrases, names of people, names of places, etc. in the text data is text information extraction, and of course, the information extracted by the text information extraction technology can be various types of information.

And (3) supervision and learning: supervised learning refers to the process of adjusting the parameters of a classifier to achieve required performance by using a set of samples of known classes, and is also called supervised training or teacher learning. The process of adjusting the parameters of the classifier to achieve the required performance using a set of samples of known classes is also known as supervised training or teachers learning. Supervised learning is a machine learning task that infers a function from labeled training data. The training data includes a set of training examples. In supervised learning, each instance consists of an input object (usually a vector) and a desired output value (also called a supervisory signal). Supervised learning algorithms analyze the training data and produce an inferred function that can be used to map out new instances. An optimal solution would allow the algorithm to correctly determine class labels for those instances that are not visible. This requires that the learning algorithm be formed in a "rational" manner from a point of view of the training data to a point of view that is not visible.

The Geographic Coordinate System (Geographic Coordinate System) is a Coordinate System that defines the position of the earth surface using a three-dimensional spherical surface to realize the reference of the position of points on the earth surface by latitude and longitude. A geographic coordinate system comprises an angle measurement unit, the initial meridian and a reference ellipsoid. In a spherical system, the horizontal line is an equal latitude line or a latitude line. The vertical lines are isochronal lines or longitude lines. The geographic coordinate system may determine the location of any point on the earth. Firstly, the earth is abstracted into a regular ellipsoid which is close to the surface of the original natural earth and is called as a reference ellipsoid, and then a series of longitude lines and latitude lines are defined on the reference ellipsoid to form a graticule, so that the aim of describing the earth surface point location through the longitude and latitude is fulfilled. It should be noted that the longitude and latitude geographic coordinate system is not a plane coordinate system, because the degree is not a standard length unit, it is not possible to directly measure the area length with the longitude and latitude geographic coordinate system.

Latitude and longitude: generally divided into astronomical latitude and longitude, geodetic latitude and longitude, and geocentric latitude and longitude. The commonly used longitude and latitude are the measured angles from the geocenter to a point on the earth's surface. The angle is typically measured in degrees or percentages.

Euclidean distance (euclidean metric): also known as the euclidean metric, the euclidean distance is a commonly used distance definition that refers to the true distance between two points in an m-dimensional space, or the natural length of a vector (i.e., the distance of the point from the origin). The euclidean distance in two and three dimensions is the actual distance between two points.

Clustering: the process of dividing a collection of physical or abstract objects into classes composed of similar objects is called clustering. The cluster generated by clustering is a collection of a set of data objects that are similar to objects in the same cluster and distinct from objects in other clusters. "the groups of things and the groups of people" have a great number of classification problems in natural science and social science. Clustering analysis, also known as cluster analysis, is a statistical analysis method for studying (sample or index) classification problems. The clustering analysis originates from taxonomy, but clustering is not equal to classification. Clustering differs from classification in that the class into which the clustering is required to be divided is unknown. The clustering analysis content is very rich, and a system clustering method, an ordered sample clustering method, a dynamic clustering method, a fuzzy clustering method, a graph theory clustering method, a clustering forecasting method and the like are adopted.

Cluster center (cluster center): a special sample in cluster analysis. Which is used to represent a class to which other samples decide whether they belong by calculating the distance to it.

A classifier: the conventional task is to learn classification rules and classifiers using a given class, known training data, and then classify (or predict) unknown data. Logistic regression (logistic), SVM, etc. are commonly used to solve the two-class problem, for the multi-class problem (multi-class classification), such as recognizing handwritten numbers, it needs 10 classes, and it can also use logistic regression or SVM, just needs a plurality of two classes to compose multi-class, but this is easy to make mistakes and is not efficient, and the commonly used multi-class method is softmax.

The Long Short-Term Memory network (LSTM) is a time-cycle neural network, which is specially designed to solve the Long-Term dependence problem of the general RNN (cyclic neural network), and all RNNs have a chain form of repeated neural network modules. In the standard RNN, this repeated structure block has only a very simple structure, e.g. one tanh layer. LSTM is a neural network of the type that contains LSTM blocks (blocks) or other types of neural networks, which may be described in literature or other literature as intelligent network elements because it can remember values of varying lengths of time, with a gate in the block that can determine whether an input is important enough to be remembered and cannot be output.

Estimated Time of Arrival (ETA): are commonly used to inform someone of the expected time to arrive at the destination after taking a train, bus or flight. In addition, "ETA" may also be used to indicate the "estimated time of receipt" of a mailed letter, package, and the "estimated time of visit" for the appointment to meet.

Based on this, the embodiment of the application provides a grid partitioning method, a grid partitioning device, an electronic device and a storage medium, and aims to improve the management and control efficiency and management and control rationality of a target case.

The grid partitioning method, the grid partitioning device, the electronic device, and the storage medium provided in the embodiments of the present application are specifically described in the following embodiments, and first, the grid partitioning method in the embodiments of the present application is described.

The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.

The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.

The embodiment of the application provides a grid partitioning method, and relates to the technical field of artificial intelligence. The grid partitioning method provided by the embodiment of the application can be applied to a terminal, a server side and software running in the terminal or the server side. In some embodiments, the terminal may be a smartphone, tablet, laptop, desktop computer, or the like; the server side can be configured as an independent physical server, can also be configured as a server cluster or a distributed system formed by a plurality of physical servers, and can also be configured as a cloud server for providing basic cloud computing services such as cloud service, a cloud database, cloud computing, cloud functions, cloud storage, network service, cloud communication, middleware service, domain name service, security service, CDN (content distribution network) and big data and artificial intelligence platforms; the software may be an application or the like that implements a grid partitioning method, but is not limited to the above form.

The application is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

Fig. 1 is an alternative flowchart of a grid partitioning method provided in an embodiment of the present application, and the method in fig. 1 may include, but is not limited to, step S101 to step S106.

Step S101, obtaining target map data; the target map data includes an original region;

step S102, carrying out grid division on an original area according to a preset grid span and a geographic coordinate system to obtain a target grid;

step S103, acquiring a target case generated by each target grid;

step S104, extracting position information of the target case to obtain an initial longitude and latitude point set;

step S105, clustering the initial longitude and latitude point set through a preset case clustering model and case clustering labels to obtain a plurality of case type clusters and central grid points of the case type clusters;

and step S106, performing routing inspection simulation according to the central grid point and pre-acquired administrator basic data to generate partition management data of the target grid.

In steps S101 to S106 illustrated in the embodiment of the present application, a target grid is obtained by performing grid division on an original region according to a preset grid span and a geographic coordinate system, and grid management can be performed on the original region more conveniently. The initial longitude and latitude point sets are clustered through a preset case clustering model and case clustering labels to obtain a plurality of case type clusters, each target case can be clustered according to a target grid where the target case is located and the type of the target case to obtain a plurality of case type clusters and central grid points of the case type clusters, and therefore case distribution efficiency is improved. And finally, carrying out routing inspection simulation according to the central grid point and pre-acquired administrator basic data to generate partition management data of the target grid, and being capable of pertinently allocating different administrators to different case type clusters, thereby improving the management and control efficiency and management and control rationality of the target cases.

In step S101 of some embodiments, a web crawler may be written, and data crawling is performed purposefully after a data source is set, so as to obtain target map data, where the target map data includes an original area that needs to be administered in a car insurance accident jurisdiction; the target map data may be retrieved from a preset map database, or may be retrieved in other manners, which is not limited to this.

Referring to fig. 2, in some embodiments, step S102 may include, but is not limited to, step S201 to step S202:

step S201, performing grid division on an original area according to a preset longitude span and a preset latitude span to obtain an initial grid;

and step S202, screening the initial grids according to the geographic coordinate system to obtain target grids.

In step S201 of some embodiments, the target map may be a national map or a map area that needs to be subject to vehicle insurance accident administration. When the original area is divided according to the preset grid span and the geographic coordinate system, the preset grid span can be determined according to the fineness of data management. The grid span includes a longitude span and a latitude span. For example, according to the fineness of data management, the longitude span of a grid in the preset grid span is determined to be 0.001 degrees, the latitude spans are all 0.001 degrees, and equal-span grid division is performed on the original area to obtain an initial grid.

In step S202 of some embodiments, the actual coordinate position of each initial grid is identified according to the geographic coordinate system, the geographic form of each initial grid is identified by the GPS or the beidou system, and the initial grids corresponding to the overhead, high-speed, lake, etc. that cannot be marked by the station are removed to screen out the target grid. For example, the initial grids that do not meet the requirement (i.e., the initial grids that correspond to the high-rise, high-speed, lake, etc. and cannot be marked by station) are included in the same filter grid set, all the initial grids in the filter grid set are removed, and the initial grids that are not removed are used as final target grids.

In step S103 of some embodiments, data may be crawled through a web crawler or the like, and a target case corresponding to each grid map in a preset time period is obtained from a plurality of preset data sources, where the target case is mainly a car insurance case, for example, a traffic accident under various conditions such as drunk driving, and case information of the target case mainly includes occurrence time, occurrence location, occurrence frequency, longitude and latitude data, a physical distance between the target cases, and the like of the car insurance case.

Referring to fig. 3, in some embodiments, step S104 may include, but is not limited to, step S301 to step S302:

step S301, carrying out label classification processing on the entity characteristics of the target case through a preset sequence classifier and characteristic class labels to obtain position information characteristics corresponding to preset position labels;

step S302, carrying out convolution processing on the position information characteristics through the convolution layer to obtain an initial longitude and latitude point set.

Specifically, in step S301 of some embodiments, case features of the target case are labeled by using a pre-trained sequence classifier and feature class labels, so that the case features can be provided with preset labels, so as to improve the classification efficiency. Wherein the feature class labels include position labels, case class labels, etc., and the pre-trained sequence classifier can be a model based on a conditional random field algorithm (CRF) or a model based on a two-way long-term memory algorithm (bi-LSTM). For example, a sequence classifier can be constructed based on the bi-LSTM algorithm, where the input words wi and characters are embedded in a model based on the bi-LSTM algorithm, such that a single output layer is generated at the location where the outputs are connected, by left-to-right long-short memory and right-to-left long-short memory. The sequence classifier can directly transmit the input case characteristics to the softmax classifier through the output layer, a probability distribution is created on the preset part of speech category labels through the softmax classifier, the case characteristics are labeled and classified according to the probability distribution, and the position information characteristics corresponding to the position labels are identified from the case characteristics with a plurality of category labels.

In step S302 of some embodiments, the position information features are convolved by the convolution layer to obtain longitude and latitude data of each target case, and the longitude and latitude data are incorporated into the same set to obtain an initial longitude and latitude point set.

Referring to fig. 4, in some embodiments, before step S105, the method further includes pre-training the case clustering model, which specifically includes:

step S401, obtaining sample map data, wherein the sample map data comprises a sample area;

step S402, carrying out grid division on the sample area according to the grid span and the geographic coordinate system to obtain a sample grid;

step S403, obtaining a sample case of each sample grid;

step S404, inputting longitude and latitude data of the sample case into an initial model;

step S405, calculating the estimated time value of each sample grid through the initial model and a preset reference grid;

and S406, optimizing a loss function of the initial model according to the estimated time value to update the initial model to obtain a case clustering model.

In step S401 of some embodiments, data may be crawled purposefully by writing a web crawler after setting a data source, so as to obtain sample map data, where the sample map data includes sample areas that need to be administered by a vehicle insurance accident; the sample map data may be retrieved from a preset map database, or may be retrieved in other manners, which is not limited to this.

In step S402 of some embodiments, the sample map may be a national map or a map region that needs to be administered in the car insurance accident jurisdiction. When the sample area is divided according to the preset grid span and the geographic coordinate system, the preset grid span may be determined according to the fineness of data management. The grid span includes a longitude span and a latitude span. For example, according to the fineness of data management, the longitude spans of the grids in the preset grid spans are determined to be 0.001 degrees, the latitude spans are all 0.001 degrees, and the equal-span grid division is performed on the sample area to obtain the initial sample grid. Further, the actual coordinate position of each initial sample grid is identified according to a geographic coordinate system, the geographic form of each initial sample grid is identified through a GPS or a Beidou system, and the initial sample grids which correspond to the viaducts, the high-speed buildings, the lakes and the like and cannot be marked by the station positions are removed. For example, the initial sample grids that do not meet the requirements are included in the same grid set, the initial sample grids in the grid set are removed, and other initial sample grids that are not in the grid set are used as final sample grids.

In step S403 in some embodiments, data may be crawled by a web crawler or the like, and a sample case corresponding to each grid map in a preset time period is obtained from a plurality of preset data sources, where the sample case is mainly a car insurance case, for example, a traffic accident under various conditions such as drunk driving, and case information of the sample case mainly includes occurrence time, occurrence location, occurrence times, longitude and latitude data, a physical distance between target cases, and the like of the car insurance case. Further, the position feature extraction is performed on the sample case to obtain longitude and latitude data of the sample case, and the process of the position feature extraction is basically the same as the specific process of the step S104, and is not repeated here.

In step S404 of some embodiments, the latitude and longitude data of the sample case is input into an initial model, wherein the initial model is a textcnn model.

In step S405 of some embodiments, a distance value between each sample grid and the reference grid is calculated through a mysql function in the initial model, and an estimated time value of each sample grid is calculated according to a preset speed value, where the estimated time value mainly refers to an ETA duration of each sample grid, and a distance degree between the sample grid and the reference grid is identified through the ETA duration.

In step S406 of some embodiments, the estimated time value and the time threshold are compared, and according to the relationship between the estimated time value and the time threshold, model loss of the loss function of the initial model is propagated in the reverse direction to perform fine tuning on the model parameters, so that the estimated time value is smaller than the time threshold, and the updating of the initial model is stopped to obtain the final case clustering model.

Referring to fig. 5, in some embodiments, step S105 may further include, but is not limited to, step S501 to step S504:

step S501, clustering initial longitude and latitude points in an initial longitude and latitude point set through a clustering algorithm of a case clustering model, preset weight parameters and case clustering labels to obtain a plurality of case category clusters;

step S502, calculating the central longitude and latitude point of each case type cluster through a preset first function to obtain a central longitude and latitude point set;

step S503, screening the central longitude and latitude point set according to the weight parameters to obtain target longitude and latitude points;

and step S504, performing longitude and latitude identification on the target longitude and latitude point to obtain a central grid point.

In step S501 of some embodiments, each initial longitude and latitude point is clustered according to the case clustering labels and the weight parameters corresponding to each longitude and latitude point, so as to obtain a plurality of case category clusters. For example, the initial longitude and latitude point set is clustered into two clusters (namely two case categories) through a preset clustering label and a K-means clustering algorithm, wherein the two clusters are a case category cluster A and a case category cluster B respectively.

In step S502 of some embodiments, the center grid point of each case category cluster is calculated by a softmax function or a tanh function or the like. The central grid point is the cluster center of each case category cluster. For example, there are 3 initial longitude and latitude points in the case type cluster a, which are the initial longitude and latitude point P (40,75) of the mark weight parameter 10, the initial longitude and latitude point Q (42,80) of the mark weight parameter 11, and the initial longitude and latitude point R (44,85) of the mark weight parameter 12, and the mark weight parameter average and longitude and latitude average are performed on the P, Q, R three initial longitude and latitude points to obtain the center longitude and latitude point where the mark weight parameter is (10+11+12)/3 ═ 11, (40+42+44)/3 ═ 42), and the latitude is (75+80+85)/3 ═ 80, and the center longitude and latitude point is the longitude and latitude point (42,80) of the mark weight parameter 11. Through the process, the central longitude and latitude points of each case category cluster are collected to obtain a central longitude and latitude point set.

In step S503 of some embodiments, according to the magnitude of the weight parameter, the central longitude and latitude point with the largest central longitude and latitude point set labeled with the weight parameter is selected as the target central longitude and latitude point. For example: the central longitude and latitude point set comprises two central longitude and latitude points which are respectively a central longitude and latitude point M (35,90) marked with a weight parameter 15 and a central longitude and latitude point N (37,90) marked with a weight parameter 12, and the central longitude and latitude point M is a target central longitude and latitude point because the weight parameter 15 is the maximum weight parameter in the central longitude and latitude point set.

In step S504 of some embodiments, in order to reduce resource consumption of data calculation, two-dimensional longitude and latitude may be converted into one-dimensional data, for example, the longitude and latitude corresponding to the target longitude and latitude are converted into a Geohash value by using a Geohash algorithm to obtain a target code value, so that the central grid point is determined according to the position of the target code value. Specifically, the longitude and latitude are firstly changed into binary through a Geohash algorithm, and then the longitude and latitude are combined, namely the longitude occupies even digits, and the latitude occupies odd digits, so that a combined value is obtained. And coding the combined value according to Base32 to obtain a target coding value.

It should be explained that GeoHash is an address coding method, which can code longitude and latitude, code two-dimensional space longitude and latitude data into a character string, and convert the longitude and latitude from two-dimensional data into one-dimensional data, thereby realizing address position partition.

Referring to fig. 6, in some embodiments, after step S105, the method further includes, but is not limited to, steps S601 to S603:

step S601, calculating a second distance value between each target case and the central grid point through a preset second function;

step S602, according to a preset case distribution priority, performing case distribution on a target case corresponding to a second distance value which is greater than or equal to a preset distance threshold value to obtain a case distribution data set;

step S603, performing case allocation to the administrator of the target grid according to the case allocation dataset.

In step S601 of some embodiments, a second distance value between the target case and the central grid point is calculated according to the longitude and latitude coordinates of each target case and the central grid point through the mysql function.

In step S602 and step S603 of some embodiments, in order to improve the management and control efficiency, a case allocation priority may be preset, and a target case corresponding to a second distance value greater than or equal to a preset distance threshold is preferentially allocated to a manager closest to the target case, that is, a target case corresponding to a second distance value greater than or equal to the preset distance threshold is set to a corresponding case allocation object (i.e., a manager closest to the target case), and data such as an optimal path where the manager reaches an occurrence point of the target case is generated, so as to obtain corresponding case allocation data. And finally, according to case distribution data of the case distribution data set, case distribution is carried out on the administrator of the target grid, and a corresponding scheduling instruction is issued, so that the corresponding administrator can manage and control the series of target cases, and the management and control efficiency and management and control rationality of the target cases are improved.

Referring to fig. 7, in some embodiments, step S106 may further include, but is not limited to, step S701 to step S704:

step S701, calculating a first distance value between each target case and a central grid point through a preset second function;

step S702, taking the maximum value of the first distance value as a target value;

step S703, counting the case number of the target case of the case type cluster through a preset third function to obtain the total number of the target cases;

step S704, the target value, the total amount of the target cases and the basic data of the administrator are used for carrying out routing inspection simulation, and partition management data are generated.

In steps S701 and S702 of some embodiments, a first distance value between the target case and the central mesh point is calculated by the mysql function according to the longitude and latitude coordinates of each target case and the central mesh point. And screening the plurality of first distance values to take the maximum value of the first distance values as a target value.

In step S703 of some embodiments, the total number of cases of the target case in the case type cluster is obtained by counting the number of cases of the target case by a sum function.

In step S704 of some embodiments, the pre-obtained administrator basic data includes initial position information of an administrator, information of the number of administrator persons, and the like, and the case processing procedure is simulated and calculated by a monte carlo algorithm according to the target value, the preset distance value, the total number of cases, the preset case quantity threshold, and the initial position information of the administrator, so as to obtain case processing data, and thus the size of the target grid to which the target case belongs is finely adjusted according to the case processing data, so as to ensure that the case processing time is within the preset time range. Therefore, according to the finely adjusted case processing data and the initial position information of the administrator, administrator station data is generated, wherein the administrator station data comprises the path of the administrator to the case point, the station longitude and latitude when the administrator manages the target grid, and the like.

The method comprises the steps of obtaining target map data; the target map data includes an original region; carrying out grid division on the original region according to a preset grid span and a geographic coordinate system to obtain a target grid, and conveniently carrying out grid management on the original region; and then, acquiring a target case of each target grid, and extracting the position information of the target case to obtain an initial longitude and latitude point set. The initial longitude and latitude point sets are clustered through a preset case clustering model and case clustering labels to obtain a plurality of case type clusters and center grid points of the case type clusters, each target case can be clustered according to the target grid where the target case is located and the type of the target case to obtain a plurality of case type clusters, and therefore case distribution efficiency is improved. And finally, carrying out routing inspection simulation according to the central grid point and pre-acquired administrator basic data to generate partition management data of the target grid, and being capable of pertinently allocating different administrators to different case type clusters, thereby improving the management and control efficiency and management and control rationality of the target cases.

Referring to fig. 8, an embodiment of the present application further provides a grid partitioning apparatus, which can implement the grid partitioning method described above, and the apparatus includes:

a target map obtaining module 801, configured to obtain target map data; the target map data includes an original region;

a mesh division module 802, configured to perform mesh division on an original region according to a preset mesh span and a geographic coordinate system to obtain a target mesh;

a target case obtaining module 803, configured to obtain a target case generated by each target grid;

the position information extraction module 804 is used for extracting the position information of the target case to obtain an initial longitude and latitude point set;

a clustering module 805, configured to perform clustering processing on the initial longitude and latitude point sets through a preset case clustering model and case clustering labels to obtain a plurality of case category clusters and central grid points of the case category clusters;

and the simulation analysis module 806 is configured to perform routing inspection simulation according to the central grid point and pre-acquired administrator basic data, and generate partition management data of the target grid.

The specific implementation of the grid partitioning apparatus is substantially the same as the specific implementation of the grid partitioning method, and is not described herein again.

An embodiment of the present application further provides an electronic device, where the electronic device includes: a memory, a processor, a program stored on the memory and executable on the processor, and a data bus for enabling connection communication between the processor and the memory, the program, when executed by the processor, implementing the above-described grid partitioning method. The electronic equipment can be any intelligent terminal including a tablet computer, a vehicle-mounted computer and the like.

Referring to fig. 9, fig. 9 illustrates a hardware structure of an electronic device according to another embodiment, where the electronic device includes:

the processor 901 may be implemented by a general-purpose CPU (Central processing unit), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits, and is configured to execute a relevant program to implement the technical solution provided in the embodiment of the present application;

the memory 902 may be implemented in the form of a Read Only Memory (ROM), a static storage device, a dynamic storage device, or a Random Access Memory (RAM). The memory 902 may store an operating system and other application programs, and when the technical solution provided by the embodiments of the present specification is implemented by software or firmware, the relevant program codes are stored in the memory 902 and called by the processor 901 to execute the grid partitioning method of the embodiments of the present application;

an input/output interface 903 for implementing information input and output;

a communication interface 904, configured to implement communication interaction between the device and another device, where communication may be implemented in a wired manner (e.g., USB, network cable, etc.), and communication may also be implemented in a wireless manner (e.g., mobile network, WIFI, bluetooth, etc.);

a bus 905 that transfers information between various components of the device (e.g., the processor 901, the memory 902, the input/output interface 903, and the communication interface 904);

wherein the processor 901, the memory 902, the input/output interface 903 and the communication interface 904 enable a communication connection within the device with each other through a bus 905.

Embodiments of the present application further provide a storage medium, which is a computer-readable storage medium for computer-readable storage, and the storage medium stores one or more programs, and the one or more programs are executable by one or more processors to implement the above grid partitioning method.

The memory, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs as well as non-transitory computer executable programs. Further, the memory may include high speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory located remotely from the processor, and these remote memories may be connected to the processor through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The embodiments described in the embodiments of the present application are for more clearly illustrating the technical solutions of the embodiments of the present application, and do not constitute a limitation to the technical solutions provided in the embodiments of the present application, and it is obvious to those skilled in the art that the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems with the evolution of technology and the emergence of new application scenarios.

It will be appreciated by those skilled in the art that the solutions shown in fig. 1-7 are not intended to limit the embodiments of the present application and may include more or fewer steps than those shown, or some of the steps may be combined, or different steps may be included.

The above-described embodiments of the apparatus are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, i.e. may be located in one place, or may also be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

One of ordinary skill in the art will appreciate that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof.

The terms "first," "second," "third," "fourth," and the like in the description of the application and the above-described figures, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.

In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the above-described division of units is only one type of division of logical functions, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, which are essential or part of the technical solutions contributing to the prior art, or all or part of the technical solutions, may be embodied in the form of a software product stored in a storage medium, which includes multiple instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods of the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing programs, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

The preferred embodiments of the present application have been described above with reference to the accompanying drawings, and the scope of the claims of the embodiments of the present application is not limited thereby. Any modifications, equivalents and improvements that may occur to those skilled in the art without departing from the scope and spirit of the embodiments of the present application are intended to be within the scope of the claims of the embodiments of the present application.

Claims

1. A method of grid partitioning, the method comprising:

acquiring target map data; the target map data comprises an original region;

acquiring a target case generated by each target grid;

clustering the initial longitude and latitude point set through a preset case clustering model and a case clustering label to obtain a plurality of case type clusters and central grid points of the case type clusters;

2. The grid partitioning method according to claim 1, wherein the grid spans include longitude spans and latitude spans, and the step of performing grid partitioning on the original region according to a preset grid span and a geographic coordinate system to obtain a target grid includes:

3. The grid partitioning method according to claim 1, wherein said step of extracting location information of said target case to obtain an initial longitude and latitude point set comprises:

4. The grid partitioning method according to claim 1, wherein said step of clustering said initial longitude and latitude point sets by means of a preset case clustering model and case clustering labels to obtain a plurality of case category clusters and center grid points of said case category clusters comprises:

5. The grid partitioning method of claim 1, wherein said step of performing a routing inspection simulation based on said central grid point and pre-acquired administrator base data to generate partitioned management data for said target grid comprises:

taking the maximum value of the first distance value as a target value;

6. The grid partitioning method according to claim 1, wherein after said step of clustering said initial longitude and latitude point set by a preset case clustering model and case clustering labels to obtain a plurality of case category clusters and center grid points of said case category clusters, said method further comprises:

and carrying out case allocation on the administrator of the target grid according to the case allocation data set.

7. The grid partitioning method according to any one of claims 1 to 6, wherein before the step of performing clustering processing on the initial longitude and latitude point set through a preset case clustering model and case clustering labels to obtain a plurality of case category clusters and central grid points of the case category clusters, the method further comprises pre-training the case clustering model, specifically comprising:

obtaining a sample case of each sample grid;

8. A grid partitioning apparatus, the apparatus comprising:

9. An electronic device comprising a memory, a processor, a program stored on the memory and executable on the processor, and a data bus for enabling connection communication between the processor and the memory, the program, when executed by the processor, implementing the steps of the grid partitioning method of any one of claims 1 to 7.

10. A storage medium, the storage medium being a computer-readable storage medium for computer-readable storage, wherein the storage medium stores one or more programs, the one or more programs being executable by one or more processors to implement the steps of the grid partitioning method of any one of claims 1 to 7.