CN115759332A - Drunk driving accident risk prediction method and device, computer equipment and storage medium - Google Patents
Drunk driving accident risk prediction method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN115759332A CN115759332A CN202211216108.5A CN202211216108A CN115759332A CN 115759332 A CN115759332 A CN 115759332A CN 202211216108 A CN202211216108 A CN 202211216108A CN 115759332 A CN115759332 A CN 115759332A
- Authority
- CN
- China
- Prior art keywords
- drunk driving
- time period
- accident
- dimensions
- data
- 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.)
- Pending
Links
Images
Abstract
The application provides a drunk driving accident risk prediction method and device, computer equipment and a storage medium, and relates to the technical field of computers. The method comprises the following steps: analyzing historical data of a plurality of drunk driving influence dimensions in a preset historical time period in a preset area to obtain accident occurrence weights of the plurality of drunk driving influence dimensions, wherein the accident occurrence weight of each drunk driving influence dimension is used for representing the correlation degree of each drunk driving influence dimension on the drunk driving accident; acquiring real-time data of a plurality of drunk driving influence dimensions in a first time period in a preset area; according to the accident occurrence weight of the drunk driving influence dimensions and the real-time data of the drunk driving influence dimensions, drunk driving risk indexes of future time periods after the first time period are determined, and the drunk driving risk indexes are used for representing the probability of drunk driving accidents in the future time periods in a preset area. The method and the device can improve the accuracy of drunk driving accident risk prediction and better prevent drunk driving accidents.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a drunk driving accident risk prediction method and device, computer equipment and a storage medium.
Background
The existing drunk driving accident risk prediction mainly comprises the steps of utilizing order data of a designated driving company to carry out statistical analysis on a starting point in the order data to generate a designated driving hotspot map, and predicting a high-incidence area of drunk driving accidents according to the designated driving hotspot map.
However, the existing data source is single, and the predicted high-incidence area of the drunk driving accident cannot be checked through the on-site drunk driving processing data, so that the prediction result is inaccurate, and the prevention of the drunk driving accident is not facilitated.
Disclosure of Invention
The invention aims to provide a drunk driving accident risk prediction method, a drunk driving accident risk prediction device, computer equipment and a storage medium, aiming at the defects in the prior art, so as to improve the accuracy of drunk driving accident risk prediction and better prevent drunk driving accidents.
In order to achieve the above purpose, the technical solutions adopted in the embodiments of the present application are as follows:
in a first aspect, an embodiment of the present application provides a method for predicting a risk of a drunk driving accident, where the method includes:
analyzing historical data of a plurality of drunk driving influence dimensions in a preset historical time period in a preset area to obtain accident occurrence weights of the plurality of drunk driving influence dimensions, wherein the accident occurrence weight of each drunk driving influence dimension is used for representing the correlation degree of each drunk driving influence dimension on the drunk driving accident;
acquiring real-time data of the plurality of drunk driving influence dimensions in a first time period in the preset area;
determining drunk driving risk indexes of future time periods after the first time period according to the accident occurrence weights of the drunk driving influence dimensions and the real-time data of the drunk driving influence dimensions, wherein the drunk driving risk indexes are used for representing the probability of drunk driving accidents in the future time periods in the preset area.
Optionally, the analyzing historical data of a plurality of drunk driving influence dimensions in a preset historical time period in a preset area to obtain accident occurrence weights of the plurality of drunk driving influence dimensions includes:
and performing correlation analysis on the historical data of the plurality of drunk driving influence dimensions according to the historical drunk driving accident data of the preset area in the preset historical time period to obtain accident occurrence weights of the plurality of drunk driving influence dimensions.
Optionally, the performing, according to the historical drunk driving accident data of the preset area in the preset historical time period, correlation analysis on the historical data of the plurality of drunk driving influence dimensions to obtain accident occurrence weights of the plurality of drunk driving influence dimensions includes:
and performing correlation analysis on the historical data of the plurality of drunk driving influence dimensions by adopting a Pearson correlation coefficient algorithm according to the historical drunk driving accident data of the preset area in the preset historical time period to obtain accident occurrence weights of the plurality of drunk driving influence dimensions.
Optionally, the performing, according to the historical drunk driving accident data of the preset area in the preset historical time period, correlation analysis on the historical data of the plurality of drunk driving influence dimensions to obtain accident occurrence weights of the plurality of drunk driving influence dimensions includes:
and performing correlation analysis on the historical data of the plurality of drunk driving influence dimensions by adopting a spearman rank test algorithm according to the historical drunk driving accident data of the preset area in the preset historical time period to obtain accident occurrence weights of the plurality of drunk driving influence dimensions.
Optionally, the method further includes:
and generating the drunk driving situation thermodynamic diagram in the preset range according to the drunk driving risk indexes of a plurality of regions in the preset range in the future time period.
Optionally, the method further includes:
and generating drunk driving intervention information of the plurality of areas according to the drunk driving risk indexes of the plurality of areas in the future time period.
Optionally, the plurality of drunk driving influence dimensions include at least two dimensions as follows: the method comprises the following steps of field measurement dimensionality, drunk driving identification dimensionality, designated driving service dimensionality, road position dimensionality, place dimensionality and section and fake special date dimensionality.
In a second aspect, an embodiment of the present application further provides a drunk driving accident risk prediction apparatus, where the apparatus includes:
the drunk driving influence dimension analysis module is used for analyzing historical data of a plurality of drunk driving influence dimensions in a preset historical time period in a preset area to obtain accident occurrence weights of the drunk driving influence dimensions, and the accident occurrence weight of each drunk driving influence dimension is used for representing the correlation degree of each drunk driving influence dimension on the drunk driving accident;
the real-time data acquisition module is used for acquiring real-time data of the plurality of drunk driving influence dimensions in the preset area in a first time period;
and the risk index calculation module is used for determining a drunk driving risk index of a future time period after the first time period according to the accident occurrence weights of the drunk driving influence dimensions and the real-time data of the drunk driving influence dimensions, and the drunk driving risk index is used for representing the probability of drunk driving accidents in the future time period in the preset area.
Optionally, the historical data analysis module is specifically configured to perform correlation analysis on the historical data of the multiple drunk driving influence dimensions according to the historical drunk driving accident data of the preset area in the preset historical time period, so as to obtain accident occurrence weights of the multiple drunk driving influence dimensions.
Optionally, the historical data analysis module is specifically configured to perform correlation analysis on the historical data of the multiple drunk driving influence dimensions by using a pearson correlation coefficient algorithm according to the historical drunk driving accident data of the preset area in the preset historical time period, so as to obtain accident occurrence weights of the multiple drunk driving influence dimensions.
Optionally, the historical data analysis module is further configured to perform correlation analysis on the historical data of the multiple drunk driving influence dimensions by using a spearman rank test algorithm according to historical drunk driving accident data of the preset region in the preset historical time period, so as to obtain accident occurrence weights of the multiple drunk driving influence dimensions.
Optionally, the apparatus further comprises:
and the thermodynamic diagram generation module is used for generating the drunk driving situation thermodynamic diagram in the preset range according to the drunk driving risk indexes of the plurality of regions in the preset range in the future time period.
Optionally, the apparatus further comprises:
and the intervention information generation module is used for generating drunk driving intervention information of the plurality of areas according to the drunk driving risk indexes of the plurality of areas in the future time period.
Optionally, the plurality of drunk driving influence dimensions include at least two dimensions as follows: the method comprises the following steps of field measurement dimensionality, drunk driving identification dimensionality, designated driving service dimensionality, road position dimensionality, place dimensionality and section and fake special date dimensionality.
In a third aspect, an embodiment of the present application further provides a computer device, including: a processor, a storage medium and a bus, wherein the storage medium stores program instructions executable by the processor, when a computer device runs, the processor and the storage medium communicate through the bus, and the processor executes the program instructions to execute the steps of the drunk driving accident risk prediction method according to any one of the first aspect.
In a fourth aspect, the present embodiments also provide a computer-readable storage medium, where a computer program is stored on the storage medium, and the computer program is executed by a processor to perform the steps of predicting the risk of a drunk driving accident according to any one of the first aspect.
The beneficial effect of this application is:
the application provides a drunk driving accident risk prediction method, a drunk driving accident risk prediction device, computer equipment and a storage medium, wherein the method comprises the following steps: analyzing historical data of a plurality of drunk driving influence dimensions in a preset historical time period in a preset area to obtain accident occurrence weights of the plurality of drunk driving influence dimensions, wherein the accident occurrence weight of each drunk driving influence dimension is used for representing the correlation of each drunk driving influence dimension on the drunk driving accident; acquiring real-time data of a plurality of drunk driving influence dimensions of a preset area in a first time period; according to the accident occurrence weight of the drunk driving influence dimensions and the real-time data of the drunk driving influence dimensions, drunk driving risk indexes of future time periods after the first time period are determined, and the drunk driving risk indexes are used for representing the probability of drunk driving accidents in the future time periods in a preset area. According to the method and the device, historical data are utilized to analyze the influence of the plurality of drunk driving influencing dimensions on the weight of accident occurrence, so that the accuracy of the probability of drunk driving accidents occurring in the future time period calculated according to the real-time data and the accident occurrence weight is higher, the drunk driving accidents can be better prevented according to the probability of drunk driving accidents occurring in the future time period, and dangerous events are prevented.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a schematic frame diagram of a drunk driving accident risk prediction platform provided in an embodiment of the present application;
fig. 2 is a schematic flow chart of a drunk driving accident risk prediction method provided in an embodiment of the present application;
fig. 3 is a schematic flowchart of another method for predicting the risk of drunk driving accidents according to the embodiment of the present application;
fig. 4 is a schematic diagram of pearson correlation coefficients provided in an embodiment of the present application;
fig. 5 is a thermodynamic diagram of a drunk driving mode provided by an embodiment of the present application;
fig. 6 is a schematic structural diagram of a drunk driving accident risk prediction device provided in an embodiment of the present application;
fig. 7 is a schematic diagram of an embodiment of a computer device provided in an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention.
Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In the description of the present application, it should be noted that if the terms "upper", "lower", etc. are used to indicate an orientation or a positional relationship based on an orientation or a positional relationship shown in the drawings or an orientation or a positional relationship which is usually placed when the product of the application is used, the description is merely for convenience of description and simplification of the application, but the indication or suggestion that the device or the element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, cannot be understood as a limitation of the application.
Furthermore, the terms "first," "second," and the like in the description and in the claims, as well as in the drawings, 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 invention described herein are capable of operation in sequences other than those illustrated or described herein. Moreover, 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 noted that the features of the embodiments of the present application may be combined with each other without conflict.
The drunk driving accident risk prediction method provided by the embodiment of the application is applied to a drunk driving accident risk prediction platform. Referring to fig. 1, a schematic frame diagram of a drunk driving accident risk prediction platform provided in an embodiment of the present application is shown, and as shown in fig. 1, the drunk driving accident risk prediction platform includes: the system comprises an interface management subsystem, a big data analysis subsystem and a display system.
The interface management subsystem is used for interfacing providers of data of multiple drunk driving influence dimensions, and the big data analysis subsystem is used for executing the drunk driving accident risk prediction method provided by the embodiment of the application to generate drunk driving risk indexes of all areas in a future time period. Wherein, the provider includes: each system and third party system in the management system, each system in the management system includes: drunk driving identification system, drunk driving measurement application program for field measurement, management six-in-one system and traffic management comprehensive application system of drunk driving identification center, the third party system comprises: a designated driving system and a map system.
Specifically, the drunk driving identification system is a medical system, managers pass through the drunk driving identification system nearby reservation drunk driving blood collection point, suspected drunk driving personnel go to drunk driving blood collection point in the time limit, identity information, face information that suspected drunk driving personnel advanced are verified by drunk driving blood collection point, blood sample collection is carried out to suspected drunk driving personnel, the blood that gathers is sealed, avoid suspected drunk driving personnel to lead to appraisal data low on the low side at blood sample collection link delay time, promote the accuracy of drunk driving identification. The blood sample is identified by the blood collection point, and the blood analysis result is sent to the drunk driving identification center, or the blood sample is directly sent to the drunk driving identification center for identification, and the drunk driving identification center uploads the blood analysis result to the drunk driving identification system.
The drunk driving measurement application program is used for measuring drunk driving of passing vehicles in a specified road section for managers, and uploading field drunk driving measurement data, inspection areas and inspection time to the comprehensive traffic management application system for storage.
A large amount of historical drunk driving data and drunk driving accident data are stored in the traffic management comprehensive application system, the drunk driving data comprise identity information, blood analysis results and the like of drunk driving personnel, and the drunk driving accident data also comprise the identity information, the blood analysis results and the like of the drunk driving accident personnel.
The designated driving system is used for providing designated driving order data and data for canceling designated driving orders so as to judge the number of people using designated driving services after drunk, and can also be used for pushing designated driving services for drunk driving personnel according to drunk driving data stored in the traffic management comprehensive application system so as to stop drunk driving behaviors from the source.
The map system is used for providing the position of the drinking place so as to generate drunk driving prevention propaganda suggestions and enhance drunk driving harm propaganda aiming at the drinking place, and drunk driving measuring points can be deployed at the periphery based on the position of the drinking place so as to measure drunk driving of passing vehicles.
The big data analysis subsystem adopts a preset analysis tool, and generates a model for predicting the drunk driving accident risk by analyzing the data of the plurality of drunk driving influence dimensions so as to predict the probability of drunk driving accidents in a preset area in a future time period. By way of example, the analysis tool may be a TensorFlow.
The interface management subsystem is also used for butting a credit investigation system so as to perform credit investigation and report on the drunk driving personnel for multiple times recorded in the traffic management comprehensive application system, so that the deterrence and punishment on the drunk driving personnel are increased.
The big data analysis subsystem is also used for analyzing the drunk driving track, the drunk driving age bracket and the gender according to the historical drunk driving data and drunk driving accident data acquired from the traffic management comprehensive application system, and visually displaying the analysis result through the display system. The drunk driving frequent road section can be determined according to the drunk driving track, a control reference basis is provided for a manager for drunk driving check, and drunk driving illegal propaganda on merchants and residents in the region is increased.
Based on the drunk driving accident risk prediction system, the embodiment of the application further provides a drunk driving accident risk prediction method. Please refer to fig. 2, which is a schematic flowchart of a method for predicting the risk of drunk driving accident according to an embodiment of the present application, and as shown in fig. 2, the method includes:
s10: analyzing historical data of a plurality of drunk driving influence dimensions in a preset historical time period in a preset area to obtain accident occurrence weights of the plurality of drunk driving influence dimensions, wherein the accident occurrence weight of each drunk driving influence dimension is used for representing the correlation degree of each drunk driving influence dimension on the drunk driving accident.
In this embodiment, the preset area may be an area within a preset range in a city, the preset area may be divided according to distribution conditions of drinking places in a map system, and the area within the preset range including a plurality of drunk driving accident locations may be determined as the preset area from drunk driving accident locations obtained from a traffic management integrated application system. The preset historical time period may be a frequent drunk driving time period, such as 5 pm to 2 am, or a weekend.
The method comprises the steps of docking with a plurality of data providers through an interface management subsystem, obtaining historical data of a plurality of drunk driving influence dimensions in a preset historical time period in a preset area, determining accident occurrence weights of the plurality of drunk driving influence dimensions by adopting a preset analysis method, and representing the correlation between each drunk driving influence dimension and a drunk driving accident by the accident occurrence weight.
In an optional embodiment, the plurality of drunk driving influence dimensions include at least two dimensions as follows: the method comprises the following steps of field measurement dimension, drunk driving identification dimension, designated driving service dimension, road position dimension, place dimension and holiday special date dimension.
In this embodiment, the data dimension for determining the existence of the correlation with the drunk driving accident through the correlation analysis includes: the method comprises the following steps of field measurement dimension, drunk driving identification dimension, designated driving service dimension, road position dimension, place dimension and holiday special date dimension. The data corresponding to the field measurement dimension comprises: the drinking ratio, the measurement place, the measurement time period and the arrangement condition of management personnel of on-site measurement, the drinking ratio is the proportion of the actual drunk driving number to the measured number, and the data corresponding to the drunk driving identification dimensionality comprises: the total number of people drinking, the blood alcohol content, the survey and treatment place and the like, wherein the blood alcohol content can be the average value or the mode of the blood alcohol content of the total number of people drinking in a preset historical time period in a preset area; the data corresponding to the designated driving service dimension comprises: the fixed number of the fixed numbers and the fixed number of the fixed numbers are cancelled; the data corresponding to the road position dimension comprises: vectorizing the road data; the data corresponding to the place dimension comprises: vectorizing location distribution data; the data corresponding to the false special date position comprises the following data: the number of actual drunk driving people on special dates is saved.
After historical data of a plurality of drunk driving influence dimensions are obtained, the historical data are cleaned, so that incomplete data are deleted, and the integrity of the data is guaranteed.
S20: the method comprises the steps of obtaining real-time data of a plurality of drunk driving influence dimensions in a preset area in a first time period.
In this embodiment, after determining the accident occurrence weights of a plurality of drunk driving influence dimensions of a preset region in a preset historical time period, dividing a current time period corresponding to the preset historical time period into a plurality of sub-time periods, where the first time period is a first sub-time period in the current time period, and acquiring real-time data of the plurality of drunk driving influence dimensions of the preset region in the first time period from a plurality of data providers.
S30: according to the accident occurrence weight of the drunk driving influence dimensions and the real-time data of the drunk driving influence dimensions, drunk driving risk indexes of future time periods after the first time period are determined, and the drunk driving risk indexes are used for representing the probability of drunk driving accidents in the future time periods in a preset area.
In this embodiment, a regression analysis model is constructed according to accident occurrence weights of a plurality of drunk driving influence dimensions, and real-time data of the plurality of drunk driving influence dimensions are input into the regression analysis model to determine the probability of drunk driving accidents in a preset region in a future time period, wherein the future time period is a sub-time period after a first sub-time period in the current time period.
For example, the Regression analysis model is a Logistic Regression (LR) analysis model for estimating a binary response probability of one or more prediction variables, and the influence of data of multiple influence dimensions on the drunk driving accident occurrence probability is estimated through the Logistic Regression analysis model. The following is a mathematical formula of the logistic regression analysis model provided in this embodiment:
wherein y = (0, 1) is the probability of occurrence of the whole drunk driving accident, and p is the occurrence of different drunk driving influence dimensions
Probability of drunk driving accident, x i (i =1,2, \8230;, n) is real-time data for a plurality of drunk-driving impact dimensions, a 0 Is a constant number, a i (i =1,2, \8230;, n) is a regression system, i.e. accident weight.
In an alternative embodiment, since the accident weight is determined by analyzing historical data, which is not necessarily applicable to the current situation, the accident weight may be adjusted according to the drinking ratio of the first time period as a loss function, so as to more accurately set the drunk driving risk index of the preset area in the future time period.
Specifically, if the drinking ratio of the first time period is smaller than the drinking ratio of the historical time period corresponding to the first time period in the preset historical time period, the number of drinkers in the first time period is obviously reduced relative to the historical data, and the accident occurrence weight of the field measurement dimension can be reduced; if the drinking ratio of the first time period is greater than that of the historical time period corresponding to the first time period in the preset historical time period, the number of drinkers in the first time period is obviously increased relative to the historical data, the accident occurrence weight of the on-site measurement dimension can be increased, and the calculation result of the logistic regression analysis model is more accurate.
According to the drunk driving accident risk prediction method provided by the embodiment, accident occurrence weights of a plurality of drunk driving influence dimensions are obtained by analyzing historical data of a plurality of drunk driving influence dimensions in a preset historical time period of a preset area, and the accident occurrence weight of each drunk driving influence dimension is used for representing the correlation of each drunk driving influence dimension on the drunk driving accident; acquiring real-time data of a plurality of drunk driving influence dimensions of a preset area in a first time period; according to the accident occurrence weight of the drunk driving influence dimensions and the real-time data of the drunk driving influence dimensions, drunk driving risk indexes of future time periods after the first time period are determined, and the drunk driving risk indexes are used for representing the probability of drunk driving accidents in the future time periods in a preset area. The above-described embodiment analyzes the weights that the plurality of drunk driving influence dimensions influence the occurrence of the accident by using the historical data, so that the accuracy of the probability of the drunk driving accident occurring in the future time period calculated according to the real-time data and the accident occurrence weight is higher, so that the drunk driving accident can be better prevented according to the probability of the drunk driving accident occurring in the future time period, and the occurrence of dangerous events can be prevented.
On the basis of the above embodiment, the embodiment of the application also provides another drunk driving accident risk prediction method. Referring to fig. 3, a schematic flow chart of another drunk driving accident risk prediction method provided in the embodiment of the present application is shown in fig. 3, where the method includes S11, S20, and S30, where S20 and S30 are the same as those in the embodiment described above, and are not described again here.
S11: according to historical drunk driving accident data of a preset area in a preset historical time period, correlation analysis is conducted on the historical data of the drunk driving influence dimensionality, and accident occurrence weights of the drunk driving influence dimensionality are obtained.
In this embodiment, since there are many historical data related to drunk driving, but not all historical data have an influence on drunk driving accidents, some historical data may not have a great relationship with drunk driving accidents, for example, occupation of drunk driving personnel. The method comprises the steps of carrying out correlation analysis on historical data related to drunk driving and obtained from a plurality of data providers, and determining a plurality of drunk driving influence dimensions related to drunk driving accidents.
And then, historical drunk driving accident data of a preset area in a preset historical time period are obtained, correlation analysis is carried out on the historical data of the drunk driving influence dimensions and the historical drunk driving accident data, and accident occurrence weight of the drunk driving influence dimension influencing the drunk driving accidents is determined.
In an optional embodiment, correlation analysis is performed on historical data of multiple drunk driving influence dimensions by adopting a pearson correlation coefficient algorithm according to historical drunk driving accident data of a preset area in a preset historical time period, so that accident occurrence weights of the multiple drunk driving influence dimensions are obtained.
In this embodiment, a Pearson correlation coefficient (Pearson correlation coefficient) algorithm is adopted to measure the linear correlation between the data of each drunk driving influence dimension and the drunk driving accident. For example, referring to fig. 4, a schematic diagram of pearson correlation coefficients provided for an embodiment of the present application is shown in fig. 4, where p represents pearson correlation coefficients, and p is a real number, where-1 ≦ p <0 represents negative correlation, where p = -1 has a negative correlation degree smaller than-1 is restricted to p restricted to 0, and 0 ≦ p 1 represents positive correlation, where p =1 has a positive correlation degree smaller than 0 is restricted to p restricted to 1, and p =0 represents no linear correlation.
In another optional embodiment, correlation analysis can be performed on historical data of multiple drunk driving influence dimensions by adopting a spearman rank test algorithm according to historical drunk driving accident data of a preset region in a preset historical time period, so that accident occurrence weights of the multiple drunk driving influence dimensions are obtained.
In this embodiment, the pearson correlation coefficient algorithm is suitable for measuring the linear correlation between the data of each drunk driving influence dimension and drunk driving accidents, but no linear correlation exists, which means no correlation, and for the data of the drunk driving influence dimension which is analyzed according to the pearson correlation coefficient algorithm and has no linear correlation, the spearman rank test algorithm can be adopted to perform correlation analysis again, so that the accident occurrence weights of a plurality of drunk driving influence dimensions are obtained.
It should be noted that, the correlation may be calculated by using a pearson correlation coefficient algorithm and a spearman rank test algorithm, and the correlation is determined jointly according to the calculation results of the pearson correlation coefficient algorithm and the spearman rank test algorithm, so as to reduce the error rate of the correlation calculation result.
S20: acquiring real-time data of a plurality of drunk driving influence dimensions in a first time period in a preset area;
s30: according to the accident occurrence weight of the drunk driving influence dimensions and the real-time data of the drunk driving influence dimensions, drunk driving risk indexes of future time periods after the first time period are determined, wherein the drunk driving risk indexes are used for representing the probability of drunk driving accidents in the future time periods in a preset area.
According to the embodiment, correlation analysis is performed on historical data of a plurality of drunk driving influence dimensions according to historical drunk driving accident data of a preset region in a preset historical time period to obtain accident occurrence weights of the plurality of drunk driving influence dimensions, so that the accuracy of the probability of drunk driving accidents in the future time period calculated according to the real-time data and the accident occurrence weights is higher, drunk driving accidents can be better prevented according to the probability of drunk driving accidents in the future time period, and dangerous events are prevented.
On the basis of the above embodiment, the embodiment of the present application further provides a drunk driving accident risk prediction method, which further includes:
and generating a drunk driving situation thermodynamic diagram in a preset range according to drunk driving risk indexes of a plurality of regions in the preset range in a future time period.
In this embodiment, the processes of S10 to S30 are executed to obtain the drunk driving risk indexes of a plurality of areas in the preset range in the future time period. The method comprises the steps of obtaining vector maps of a plurality of areas in a preset range through a map system, and marking drunk driving risk indexes of all the areas in the vector maps to generate drunk driving situation thermodynamic diagrams in the preset range.
For example, please refer to fig. 5, the drunk driving form thermodynamic diagram provided by the embodiment of the present application is shown in fig. 5, where drunk driving risk indexes of a plurality of regions in a preset range are different, a map system may be docked according to the drunk driving form thermodynamic diagram, distribution conditions of dining places in the regions with high drunk driving risk indexes are obtained, an alteration prompt is sent to merchants in each dining place through a drunk driving accident risk prediction platform, and the drunk driving easy place and a designated driving system are docked through an interface management subsystem to establish association between the drunk driving easy place and the designated driving system, so that the designated driving system may easily allocate more designated drivers to provide designated driving services in drunk driving.
Further, drunk driving intervention information of the multiple regions is generated according to drunk driving risk indexes of the multiple regions in a future time period.
In this embodiment, according to the drunk driving situation thermodynamic diagram within the preset range, the probability of drunk driving accidents occurring in the future time period in the multiple regions within the preset range is determined, so that drunk driving intervention information of the multiple regions is generated according to the probability of drunk driving accidents occurring in the future time period in different regions. The drunk driving intervention information is used for indicating arrangement conditions and drunk driving check frequency of managers carrying out drunk driving detection in multiple regions, for example, more managers are arranged in regions with high drunk driving accident probability, the drunk driving check frequency is improved, less managers are arranged in regions with low drunk driving accident probability, the drunk driving check frequency is reduced, and managers are guaranteed to be reasonably distributed.
The drunk driving data after drunk driving control is carried out by adopting the drunk driving intervention information provided by the embodiment is analyzed, drunk driving control reports of month, quarter and year are generated, and the drunk driving accident risk prediction method provided by the embodiment of the application is further optimized through the report data, so that the drunk driving control effect is improved.
In an optional embodiment, the characteristics of the drunk driving data can be analyzed, so that drunk driving propaganda and prevention suggestions can be generated according to the result. Wherein, the analysis of the characteristics of drunk driving data comprises: the drunk driving prevention method comprises the steps of carrying out drunk driving prevention propaganda in drunk driving frequent regions and places, carrying out drunk driving prevention propaganda on the drunk driving frequent region and the drunk driving frequent time period, sending reminding information for the drunk driving frequent time period, drunk driving frequent time period and drunk driving frequent special date to the drunk driving frequent population, and the like, so as to carry out targeted drunk driving prevention propaganda.
In an optional embodiment, the method further comprises the steps of obtaining an order of the designated driving service finished in advance through docking with the designated driving system, and performing key analysis on the order of the designated driving service finished in advance to avoid drunk driving behaviors of the last kilometer.
On the basis of the foregoing embodiments, the present application embodiment also provides a drunk driving accident risk prediction apparatus, please refer to fig. 6, which is a schematic structural diagram of the drunk driving accident risk prediction apparatus provided in the present application embodiment, and as shown in fig. 6, the apparatus includes:
the historical data analysis module 10 is configured to analyze historical data of a plurality of drunk driving influence dimensions in a preset historical time period in a preset region to obtain accident occurrence weights of the plurality of drunk driving influence dimensions, wherein the accident occurrence weight of each drunk driving influence dimension is used for representing the correlation degree of each drunk driving influence dimension on the occurrence of drunk driving accidents;
the real-time data acquisition module 20 is used for acquiring real-time data of a plurality of drunk driving influence dimensions in a first time period in a preset area;
and the risk index calculation module 30 is used for determining a drunk driving risk index of a future time period after the first time period according to the accident occurrence weights of the drunk driving influence dimensions and the real-time data of the drunk driving influence dimensions, wherein the drunk driving risk index is used for representing the probability of drunk driving accidents in the future time period in a preset area.
Optionally, the historical data analysis module 10 is specifically configured to perform correlation analysis on historical data of multiple drunk driving influence dimensions according to historical drunk driving accident data of a preset region in a preset historical time period, so as to obtain accident occurrence weights of the multiple drunk driving influence dimensions.
Optionally, the historical data analysis module is specifically configured to perform correlation analysis on historical data of multiple drunk driving influence dimensions by using a pearson correlation coefficient algorithm according to historical drunk driving accident data of a preset area in a preset historical time period, so as to obtain accident occurrence weights of the multiple drunk driving influence dimensions.
Optionally, the historical data analysis module 10 is further configured to perform correlation analysis on the historical data of the multiple drunk driving influence dimensions by using a spearman rank test algorithm according to historical drunk driving accident data of the preset region in a preset historical time period, so as to obtain accident occurrence weights of the multiple drunk driving influence dimensions.
Optionally, the apparatus further comprises:
the thermodynamic diagram generation module is used for generating the drunk driving situation thermodynamic diagram in the preset range according to drunk driving risk indexes of a plurality of regions in the preset range in a future time period.
Optionally, the apparatus further comprises:
and the intervention information generation module is used for generating drunk driving intervention information of the plurality of areas according to drunk driving risk indexes of the plurality of areas in a future time period.
Optionally, the multiple drunk driving influence dimensions include at least two of the following dimensions: the method comprises the following steps of field measurement dimensionality, drunk driving identification dimensionality, designated driving service dimensionality, road position dimensionality, place dimensionality and section and fake special date dimensionality.
The above-mentioned apparatus is used for executing the method provided by the foregoing embodiment, and the implementation principle and technical effect are similar, which are not described herein again.
These above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or one or more microprocessors, or one or more Field Programmable Gate Arrays (FPGAs), etc. For another example, when one of the above modules is implemented in the form of a Processing element scheduler code, the Processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).
Referring to fig. 7, a schematic diagram of an embodiment of a computer device according to an embodiment of the present disclosure is provided, where the computer device may be a computing device or a server with a computing processing function.
As shown in fig. 7, the computer apparatus 100 includes: a memory 101 and a processor 102. The memory 101 and the processor 102 are connected by a bus.
The memory 101 is used for storing programs, and the processor 102 calls the programs stored in the memory 101 to execute the above method embodiments. The specific implementation and technical effects are similar, and are not described herein again.
Optionally, the invention also provides a program product, for example a computer-readable storage medium, comprising a program which, when being executed by a processor, is adapted to carry out the above-mentioned method embodiments.
In the embodiments provided in the present invention, 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 division of the units is only one logical division, 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 position, or may be distributed on multiple 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 invention 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 may be implemented in the form of hardware, or in the form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer-readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a portable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other media capable of storing program codes.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and shall be covered by the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A drunk driving accident risk prediction method is characterized by comprising the following steps:
analyzing historical data of a plurality of drunk driving influence dimensions in a preset historical time period in a preset area to obtain accident occurrence weights of the plurality of drunk driving influence dimensions, wherein the accident occurrence weight of each drunk driving influence dimension is used for representing the correlation degree of each drunk driving influence dimension on the drunk driving accident;
acquiring real-time data of the plurality of drunk driving influence dimensions in a first time period in the preset area;
determining a drunk driving risk index of a future time period after the first time period according to the accident occurrence weights of the drunk driving influence dimensions and the real-time data of the drunk driving influence dimensions, wherein the drunk driving risk index is used for representing the probability of drunk driving accidents in the future time period in the preset area.
2. The method of claim 1, wherein analyzing historical data of a plurality of drunk driving influence dimensions of a preset area within a preset historical time period to obtain accident occurrence weights of the plurality of drunk driving influence dimensions comprises:
and performing correlation analysis on the historical data of the plurality of drunk driving influence dimensions according to the historical drunk driving accident data of the preset area in the preset historical time period to obtain accident occurrence weights of the plurality of drunk driving influence dimensions.
3. The method of claim 2, wherein the performing correlation analysis on the historical data of the plurality of drunk driving influence dimensions according to the historical drunk driving accident data of the preset area in the preset historical time period to obtain accident occurrence weights of the plurality of drunk driving influence dimensions comprises:
and performing correlation analysis on the historical data of the plurality of drunk driving influence dimensions by adopting a Pearson correlation coefficient algorithm according to the historical drunk driving accident data of the preset area in the preset historical time period to obtain accident occurrence weights of the plurality of drunk driving influence dimensions.
4. The method of claim 2, wherein the performing correlation analysis on the historical data of the plurality of drunk driving influence dimensions according to the historical drunk driving accident data of the preset area in the preset historical time period to obtain accident occurrence weights of the plurality of drunk driving influence dimensions comprises:
and performing correlation analysis on the historical data of the plurality of drunk driving influence dimensions by adopting a spearman rank test algorithm according to the historical drunk driving accident data of the preset region in the preset historical time period to obtain accident occurrence weights of the plurality of drunk driving influence dimensions.
5. The method of claim 1, further comprising:
and generating the drunk driving situation thermodynamic diagram in the preset range according to the drunk driving risk indexes of a plurality of regions in the preset range in the future time period.
6. The method of claim 5, further comprising:
and generating drunk driving intervention information of the plurality of regions according to the drunk driving risk indexes of the plurality of regions in the future time period.
7. The method of claim 1, wherein the plurality of drunk driving impact dimensions includes at least two of the following dimensions: the method comprises the following steps of field measurement dimension, drunk driving identification dimension, designated driving service dimension, road position dimension, place dimension and holiday special date dimension.
8. A drunk driving accident risk prediction device, characterized in that the device comprises:
the drunk driving influence dimension analysis module is used for analyzing historical data of a plurality of drunk driving influence dimensions in a preset historical time period in a preset area to obtain accident occurrence weights of the drunk driving influence dimensions, and the accident occurrence weight of each drunk driving influence dimension is used for representing the correlation degree of each drunk driving influence dimension on the drunk driving accident;
the real-time data acquisition module is used for acquiring real-time data of the plurality of drunk driving influence dimensions in the preset area in a first time period;
and the risk index calculation module is used for determining a drunk driving risk index of a future time period after the first time period according to the accident occurrence weights of the drunk driving influence dimensions and the real-time data of the drunk driving influence dimensions, and the drunk driving risk index is used for representing the probability of drunk driving accidents in the future time period in the preset area.
9. A computer device, comprising: a processor, a storage medium and a bus, the storage medium storing program instructions executable by the processor, the processor and the storage medium communicating via the bus when a computer device is running, the processor executing the program instructions to perform the steps of the drunk driving accident risk prediction method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that the storage medium has stored thereon a computer program which, when being executed by a processor, performs the steps of the drunk driving accident risk prediction according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211216108.5A CN115759332A (en) | 2022-09-30 | 2022-09-30 | Drunk driving accident risk prediction method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211216108.5A CN115759332A (en) | 2022-09-30 | 2022-09-30 | Drunk driving accident risk prediction method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115759332A true CN115759332A (en) | 2023-03-07 |
Family
ID=85350766
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211216108.5A Pending CN115759332A (en) | 2022-09-30 | 2022-09-30 | Drunk driving accident risk prediction method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115759332A (en) |
-
2022
- 2022-09-30 CN CN202211216108.5A patent/CN115759332A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101617349B1 (en) | Diagnostic system and method for the analysis of driving behavior | |
| Rasch et al. | What drives fraud in a credence goods market?–Evidence from a field study | |
| US20210110480A1 (en) | Intelligent machine sensing and machine learning-based commercial vehicle insurance risk scoring system | |
| KR20180105133A (en) | Systems, devices, methods and readable storage media for presenting auto insurance exploration missions | |
| Weng et al. | Real-time bus travel speed estimation model based on bus GPS data | |
| CN113539509A (en) | Method, device, terminal device and medium for predicting risk of new infectious disease | |
| Corro et al. | Comparison of overnight truck parking counts with GPS-derived counts for truck parking facility utilization analysis | |
| Scott et al. | The consequences of self‐reporting biases: Evidence from the crash preventability program | |
| Cetateanu et al. | A novel methodology for identifying environmental exposures using GPS data | |
| CN109791677A (en) | System and method for carrying out Geographic Reference and scoring to vehicle data in community | |
| US11506525B2 (en) | Method for verifying sensors in a sensor network, and sensor network | |
| US20230221134A1 (en) | Machine Learning Platform for Dynamic Device and Sensor Quality Evaluation | |
| CN115759332A (en) | Drunk driving accident risk prediction method and device, computer equipment and storage medium | |
| CN113327336B (en) | Method and device for identifying people-vehicle relationship and electronic equipment | |
| CN115034686A (en) | Job behavior quantification method and device, computer equipment and storage medium | |
| Tsai et al. | New pavement performance indicators using crack fundamental elements and 3D pavement surface data with multiple-timestamp registration for crack deterioration analysis and optimal treatment determination | |
| Hagen et al. | Modeling of parking violations using zero-inflated negative binomial regression: A case study for Berlin | |
| Cheng et al. | Evaluation of the impact of traffic volume on site ranking | |
| CN112053098B (en) | Order processing method, device, server and computer storage medium | |
| CN114331181A (en) | Vehicle driving behavior risk analysis method based on big data | |
| Basso et al. | Assessing factors influencing the occurrence of traffic conflicts: a vehicle-by-vehicle approach | |
| CN112581291A (en) | Risk assessment transaction detection method, device, equipment and storage medium | |
| CN108268988B (en) | Grain purchasing business management method and system | |
| CN110751567A (en) | Vehicle information processing method, device, computer equipment and storage medium | |
| US10825096B1 (en) | Systems and methods for water loss mitigation messaging |
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 |