CN112633580A - Drunk driving vehicle early warning method, device, equipment and medium based on artificial intelligence - Google Patents
Drunk driving vehicle early warning method, device, equipment and medium based on artificial intelligence Download PDFInfo
- Publication number
- CN112633580A CN112633580A CN202011578763.6A CN202011578763A CN112633580A CN 112633580 A CN112633580 A CN 112633580A CN 202011578763 A CN202011578763 A CN 202011578763A CN 112633580 A CN112633580 A CN 112633580A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- data
- drunk driving
- target vehicle
- driving
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 23
- 238000012544 monitoring process Methods 0.000 claims abstract description 103
- 238000001514 detection method Methods 0.000 claims description 28
- 230000007613 environmental effect Effects 0.000 claims description 27
- 238000004590 computer program Methods 0.000 claims description 25
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 abstract description 2
- 230000006399 behavior Effects 0.000 description 13
- 238000012549 training Methods 0.000 description 7
- 238000007726 management method Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000035622 drinking Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Operations Research (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Primary Health Care (AREA)
- Computational Linguistics (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medical Informatics (AREA)
- Computer Security & Cryptography (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Traffic Control Systems (AREA)
Abstract
The application relates to the technical field of big data, in particular to a drunk driving vehicle early warning method, device, equipment and medium based on artificial intelligence, comprising the following steps: acquiring vehicle data of a target vehicle entering a preset monitoring area; acquiring current running track data of a target vehicle when the target vehicle leaves a preset monitoring area and environment data of the preset monitoring area; generating a drunk driving grade index of the target vehicle; acquiring a preset drunk driving grade index threshold; judging whether the target vehicle is a drunk driving vehicle or not according to a preset drunk driving grade index threshold value and a drunk driving grade index of the target vehicle, and carrying out early warning on the drunk driving vehicle when the target vehicle is judged to be the drunk driving vehicle. By adopting the method, the intelligent drunk driving early warning level can be improved. In addition, the invention also relates to a block chain technology, and all the vehicle data, the current driving track data, the environment data, the drunk driving level index of the target vehicle and the preset drunk driving level index threshold value can be stored in the block chain.
Description
Technical Field
The application relates to the technical field of big data, in particular to a drunk driving vehicle early warning method, device, equipment and medium based on artificial intelligence.
Background
In daily life of people, traffic accidents happen occasionally. According to statistics, the probability of traffic accidents of a driver driving after drinking is 16 times that of the driver driving without drinking. Aiming at serious traffic illegal behaviors such as drunk driving, drunk driving and the like, the traffic illegal behaviors need to be intercepted in time and related punishment is carried out.
In a traditional mode, a traffic management department usually performs duty on duty, and performs alcohol detection on past vehicle drivers aiming at a drunk driving high-incidence place (determined according to past experience) to judge whether drunk driving behaviors exist or not.
However, the alcohol detection is performed manually on the passing vehicle drivers, the processing process is not intelligent enough, and the coverage rate is low.
Disclosure of Invention
Therefore, it is necessary to provide an artificial intelligence-based drunk driving vehicle early warning method, device, equipment and medium capable of improving the drunk driving early warning intelligence level in order to solve the technical problems.
An artificial intelligence-based drunk driving vehicle early warning method comprises the following steps:
acquiring vehicle data of a target vehicle entering a preset monitoring area;
acquiring current running track data of a target vehicle when the target vehicle leaves a preset monitoring area and environment data of the preset monitoring area;
generating a drunk driving grade index of the target vehicle based on the current driving track data, the environment data and the vehicle data;
acquiring a preset drunk driving grade index threshold;
judging whether the target vehicle is a drunk driving vehicle or not according to a preset drunk driving grade index threshold value and a drunk driving grade index of the target vehicle, and carrying out early warning on the drunk driving vehicle when the target vehicle is judged to be the drunk driving vehicle.
In one embodiment, before acquiring vehicle data of a target vehicle entering a preset monitoring area, the method further includes:
acquiring monitoring data of a preset monitoring area;
determining the stay time of each initial vehicle entering a preset monitoring area according to the monitoring data;
judging whether the stay time of each initial vehicle is greater than or equal to a preset time threshold;
and when the stay time is determined to be greater than or equal to the preset time threshold, determining that the initial vehicle is the target vehicle, and acquiring vehicle data of the target vehicle.
In one embodiment, generating the drunk driving level index of the target vehicle based on the current driving track data, the environment data and the vehicle data comprises:
acquiring historical driving track data of a target vehicle;
judging whether the target vehicle runs normally or not according to the historical running track data and the current running track data;
and when the target vehicle is determined to be abnormally driven, generating a drunk driving level index of the target vehicle based on the environmental data and the vehicle data.
In one embodiment, the historical travel track data includes a plurality of historical travel track segments, and the current travel track data includes a plurality of current travel track segments;
judging whether the target vehicle normally runs or not according to the historical running track data and the current running track data, wherein the judging step comprises the following steps:
judging whether each historical travel track segment in the historical travel track data is consistent with each current travel track segment in the current travel track data;
counting the number of track segments of which the historical travel track segments are consistent with the current travel track segments in the historical travel track data and the current travel track data;
judging whether the number of the track segments is greater than or equal to a preset number threshold value or not;
when the number of the track segments is smaller than a preset number threshold value, determining that the target vehicle is abnormal in running;
and when the number of the track segments is greater than or equal to the preset number threshold value, determining that the target vehicle runs normally.
In one embodiment, generating the drunk driving level index of the target vehicle based on the environmental data and the vehicle data comprises:
and inputting the environmental data and the vehicle data into a pre-trained drunk driving index estimation model, and outputting drunk driving grade indexes of corresponding target vehicles through the drunk driving index estimation model.
In one embodiment, the early warning of drunk driving of a vehicle comprises:
generating early warning information based on vehicle data of drunk driving vehicles;
determining the position information and the driving direction of the drunk driving vehicle according to the current driving track data of the drunk driving vehicle;
and sending the early warning information to a detection terminal corresponding to the position information and the driving direction so as to intercept and early warn the drunk driving vehicle.
In one embodiment, the method further includes:
and uploading at least one of the vehicle data, the current driving track data, the environment data, the drunk driving grade index of the target vehicle and a preset drunk driving grade index threshold value to a block chain node for storage.
The utility model provides a drunk driving vehicle early warning device based on artificial intelligence, the device includes:
the vehicle data acquisition module is used for acquiring vehicle data of a target vehicle entering a preset monitoring area;
the system comprises an acquisition module, a monitoring module and a monitoring module, wherein the acquisition module is used for acquiring current running track data and environmental data of a preset monitoring area when a target vehicle runs away from the preset monitoring area;
the drunk driving grade index generating module is used for generating drunk driving grade indexes of the target vehicle based on the current driving track data, the environment data and the vehicle data;
the index threshold value acquisition module is used for acquiring a preset drunk driving grade index threshold value;
the early warning module is used for judging whether the target vehicle is a drunk driving vehicle or not according to a preset drunk driving grade index threshold value and drunk driving grade indexes of the target vehicle, and carrying out early warning on the drunk driving vehicle when the target vehicle is judged to be the drunk driving vehicle.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the method of any of the above embodiments when the processor executes the computer program.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of any of the above embodiments.
According to the drunk driving vehicle early warning method, the drunk driving vehicle early warning device and the drunk driving vehicle early warning medium based on the artificial intelligence, vehicle data of a target vehicle entering a preset monitoring area are obtained, then current driving track data of each target vehicle driving away from the preset monitoring area and environment data of the preset monitoring area are collected, drunk driving grade indexes of the target vehicle are generated based on each current driving track data, the environment data and the vehicle data, further, whether each target vehicle is drunk driving is judged according to a preset drunk driving grade index threshold value and each drunk driving grade index, and when the target vehicle is judged to be drunk driving, the drunk driving vehicle is early warned. Therefore, whether drunk driving behaviors exist in the target vehicle or not can be estimated and early-warned based on the collected data, and the intelligent level of drunk driving early warning is improved. In addition, pre-estimation early warning can be carried out on a plurality of target vehicles through the method, and the coverage rate of drunk driving early warning is improved.
Drawings
FIG. 1 is a diagram illustrating an exemplary embodiment of an artificial intelligence-based drunk driving vehicle warning method;
FIG. 2 is a schematic flow chart illustrating an artificial intelligence-based drunk driving vehicle warning method according to an embodiment;
FIG. 3 is a schematic flow chart illustrating an artificial intelligence-based drunk driving vehicle warning method in another embodiment;
FIG. 4 is a schematic flow chart illustrating a drunk driving vehicle warning method based on artificial intelligence in yet another embodiment;
FIG. 5 is a flowchart illustrating the determination of the drunk driving level indicator in one embodiment;
FIG. 6 is a block diagram of an embodiment of an artificial intelligence-based drunk driving vehicle warning device;
FIG. 7 is a diagram illustrating an internal structure of a computer device according to an embodiment.
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.
The drunk driving vehicle early warning method based on artificial intelligence can be applied to the application environment shown in the figure 1. Wherein the terminal 102 communicates with the server 104 via a network. The terminal collects vehicle data of a target vehicle entering a preset monitoring area, and then sends the vehicle data to the server 104. After the vehicle data of the target vehicle entering the preset monitoring area is acquired, the server 104 may acquire current driving track data of the target vehicle when the target vehicle is driven away from the preset monitoring area and environment data of the preset monitoring area, and then generate a drunk driving level index of the target vehicle based on the current driving track data, the environment data and the vehicle data. Further, the server 104 may obtain a preset drunk driving level index threshold, determine whether the target vehicle is a drunk driving vehicle according to the preset drunk driving level index threshold and a drunk driving level index of the target vehicle, and perform early warning on the drunk driving vehicle when it is determined that the target vehicle is the drunk driving vehicle. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, an artificial intelligence-based drunk driving vehicle early warning method is provided, which is described by taking the server in fig. 1 as an example, and includes the following steps:
step S202, vehicle data of a target vehicle entering a preset monitoring area is acquired.
The preset monitoring area refers to an area where an electronic fence is preset, and may refer to a drunk driving high-speed area, such as a bar, a KTV, a large gear, a restaurant centralized area, and the like.
Specifically, the electronic fence is a monitoring device combined by a gate and an electronic police, the gate is an entrance with a defense and inspection facility, and the electronic police is used for collecting the traffic data of vehicles at the gate and communicating with a traffic control department database.
In this embodiment, the supervision department can enter the fence position of the electronic fence and the card port information and the like around the fence into the system when setting the electronic fence, so as to monitor the passing vehicles.
In this embodiment, the fence position of the electronic fence refers to a geographic position where the electronic fence is located, and may further include a size of a preset monitoring area determined by the electronic fence. The card slot information is information such as position information and card slot number where the card slot is located in the electronic fence.
The target vehicle is a vehicle entering a preset monitoring area and meeting preset conditions. The preset condition is a preset determination condition, and may be, for example, a vehicle stop time, a number of times that drunk driving is detected after the vehicle passes through the preset monitoring area, and the like.
The vehicle data may include the license plate number, the brand, the owner identity, and the like of the vehicle, and may further include the stay time of the vehicle in the monitoring area, the drunk driving history data of the vehicle, and the like.
In this embodiment, the server may define the start and stop time of the electronic fence, that is, the constraint time, only the vehicles entering the electronic fence within the constraint time range are checked, and the vehicles not at the constraint time are not checked, for example, if the drunk driving high-speed period is from 9 pm to 2 am, the server may set the constraint time of the electronic fence to be from 9 pm to 2 am in the next day, and perform real-time monitoring on the vehicles entering the electronic fence in the time period.
In this embodiment, the server monitors the vehicle entering the preset monitoring area, determines that the vehicle with the drunk driving suspicion is the target vehicle after the determination, and obtains vehicle data corresponding to the target vehicle, for example, license plate number information of the target vehicle may be obtained by a fence electronic police, and data such as owner identity of the corresponding target vehicle is downloaded from a vehicle management station server. Meanwhile, the server can also determine the stay time of the target vehicle in the electronic fence according to the time of the target vehicle entering and leaving the fence, which is detected by the gate.
And step S204, acquiring current running track data and environmental data of the preset monitoring area when the target vehicle runs away from the preset monitoring area.
The driving track data refers to driving data of the target vehicle when the target vehicle drives away from the preset monitoring area.
In this embodiment, a monitoring level may be set at an intersection near the preset monitoring area to collect the driving data of the target vehicle when the target vehicle drives away from the preset monitoring area.
The environmental data refers to whether important activities, weather and meteorological environments, density of surrounding running vehicles and other related data exist in the accessories of the preset monitoring area.
In this embodiment, the server may obtain real-time environmental data through various sensors or from various large websites, for example, obtain weather data of the current time from a weather website, obtain data of vehicles driving at intersections from a vehicle management database, and obtain data of whether a new shop is opened, a sales promotion event or a yearly celebration event exists in a preset monitoring area from various event websites.
And step S206, generating a drunk driving grade index of the target vehicle based on the current driving track data, the environment data and the vehicle data.
The drunk driving level index is an index for indicating that drunk driving behaviors exist in the target vehicle. Specifically, the drunk driving level index may be a probability value, i.e., a probability that drunk driving exists in the target vehicle.
In this embodiment, after acquiring the vehicle data, the current driving trajectory data, and the corresponding environment data of each target vehicle, the server may determine the drunk driving level index of the corresponding target vehicle based on the acquired current driving trajectory data, environment data, and vehicle data, for example, to obtain the probability that the target vehicle may have drunk driving, which is 80%, 50%, and the like.
And step S208, acquiring a preset drunk driving level index threshold value.
The preset drunk driving level index threshold value can be an empirical value or a threshold value obtained through big data statistical analysis and used for drunk driving judgment.
In an embodiment, the server may adjust or update the preset drunk driving level index threshold periodically or aperiodically, for example, when drunk driving early warning is obviously higher or lower at a certain time, the preset drunk driving level index threshold may be adjusted and updated according to real-time drunk driving behavior data.
Step S210, judging whether the target vehicle is a drunk driving vehicle or not according to a preset drunk driving level index threshold value and a drunk driving level index of the target vehicle, and carrying out early warning on the drunk driving vehicle when the target vehicle is judged to be the drunk driving vehicle.
In this embodiment, after the server obtains the preset drunk driving level index threshold, the drunk driving level index threshold of the corresponding target vehicle may be determined by the preset drunk driving level index threshold.
For example, when the drunk driving level index corresponding to the target vehicle is greater than or equal to the preset drunk driving index threshold, the server may determine that the target vehicle is a drunk driving vehicle. At this time, the server can generate early warning information and send the early warning information to a traffic police department so as to early warn the drunk driving vehicle, remind the traffic police department to deploy and control interception measures, and perform interception detection so as to further determine whether the target vehicle is drunk driving. When the server determines that the drunk driving level index corresponding to the target vehicle is smaller than the preset drunk driving index threshold value, the target vehicle can be judged to be a non-drunk driving vehicle, the vehicle is excluded, and no further early warning is carried out on the vehicle.
In this embodiment, when determining that the target vehicle is a drunk driving vehicle, the server may further generate prompt information such as a short message, and send the prompt information to the mobile terminal of the owner of the target vehicle to remind the owner of the target vehicle not to drive the vehicle after drinking.
According to the drunk driving vehicle early warning method based on artificial intelligence, vehicle data of target vehicles entering a preset monitoring area are obtained, then current driving track data of the target vehicles driving away from the preset monitoring area and environment data of the preset monitoring area are collected, drunk driving grade indexes of the target vehicles are generated based on the current driving track data, the environment data and the vehicle data, further, whether the target vehicles drink the drunk driving vehicles or not is judged according to preset drunk driving grade index thresholds and the drunk driving grade indexes, and when the target vehicles are judged to be drunk driving vehicles, early warning is carried out on the drunk driving vehicles. Therefore, whether drunk driving behaviors exist in the target vehicle or not can be estimated and early-warned based on the collected data, and the intelligent level of drunk driving early warning is improved. In addition, pre-estimation early warning can be carried out on a plurality of target vehicles through the method, and the coverage rate of drunk driving early warning is improved.
In one embodiment, referring to fig. 3, before acquiring vehicle data of a target vehicle entering a preset monitoring area, the method may further include:
step S302, acquiring monitoring data of a preset monitoring area.
The monitoring data refers to data for monitoring a preset monitoring area, for example, data collected by the aforementioned gate, electronic police, and the like.
In this embodiment, the server may access the database of the traffic management department through a network request to acquire the monitoring data of the preset monitoring area, or the server may also send a data acquisition request, so that the server of the traffic management department feeds back the monitoring data corresponding to the request according to the request.
And step S304, determining the stay time of each initial vehicle entering the preset monitoring area according to the monitoring data.
In this embodiment, after the server obtains the monitoring data, statistics may be performed on the monitored stay time of each initial vehicle in the preset monitoring area, for example, referring to fig. 4, the server determines the time difference as the stay time of the corresponding initial vehicle in the preset monitoring area by calculating the time difference between the initial vehicle entering the preset monitoring area and leaving the preset monitoring area, that is, T2-T1.
And step S306, judging whether the stay time of each initial vehicle is greater than or equal to a preset time threshold.
In this embodiment, after the initial vehicle arrives at the preset monitoring area, the initial vehicle may only pass by, or pick up or step on, that is, the vehicle may not have drunk driving behavior, the server may set the preset time threshold, and screen out a part of the vehicles that may not have drunk driving behavior through the preset time threshold.
Specifically, the server compares the stay time of each initial vehicle with a preset time threshold, and determines that the initial vehicle with the stay time less than the preset time threshold is a normal vehicle, that is, the drunk driving behavior is not possible, and the initial vehicle with the stay time greater than or equal to the preset time threshold is a target vehicle, which is likely to have the drunk driving behavior.
And step S308, when the stay time is determined to be greater than or equal to the preset time threshold, determining that the initial vehicle is the target vehicle, and acquiring the vehicle data of the target vehicle.
In this embodiment, after determining the target vehicles, the server may correspondingly obtain vehicle data of each target vehicle, such as the aforementioned data of license plate number, vehicle brand, owner identity, and duration of stay, and perform subsequent processing.
In the embodiment, the monitoring data of the preset monitoring area is acquired, then the staying time of each initial vehicle entering the preset monitoring area is determined according to the monitoring data, whether the staying time of each initial vehicle is greater than or equal to the preset time threshold value is judged, the initial vehicle with the staying time greater than or equal to the preset time threshold value is further determined as the target vehicle, and the vehicle data of each target vehicle is acquired, so that part of vehicles which are unlikely to have drunk driving behaviors can be removed, the acquisition amount of the vehicle data can be reduced, the data resources can be saved, the occupation of the vehicle data on the resource space of the server can be reduced, and the operation stability of the server can be guaranteed.
In one embodiment, referring to fig. 5, generating the drunk driving level index of the target vehicle based on the current driving trajectory data, the environment data and the vehicle data may include:
in step S502, the history travel track data of the target vehicle is acquired.
The historical travel track data refers to travel track data of the target vehicle before the target vehicle is driven away from the preset monitoring area, and may be travel track data of the target vehicle when the target vehicle is driven into the preset monitoring area, for example.
And step S504, judging whether the target vehicle normally runs or not according to the historical running track data and the current running track data.
In this embodiment, the server may obtain historical travel track data of the target vehicle and current travel track data of the target vehicle that has traveled away from the preset monitoring area through a monitoring level or an electronic police station provided at a road intersection or the like, and compare the current travel track data with the historical travel track data to determine whether the target vehicle has traveled normally, for example, determine through a travel track, a travel speed, and the like.
In step S506, when it is determined that the target vehicle is traveling abnormally, a drunk driving level index of the target vehicle is generated based on the environmental data and the vehicle data.
In this embodiment, when the server determines that the traveling track of the target vehicle is normal, the server may determine that the target vehicle is a non-drunk driving vehicle and reject the target vehicle.
Further, when the server determines that the traveling track of the target vehicle is not normal, the server may generate a drunk driving level index of the target vehicle based on the environmental data and the vehicle data corresponding to the target vehicle, and perform further processing.
In the above embodiment, the historical travel track data of the target vehicle is acquired, whether the target vehicle is normally traveling is judged according to the historical travel track data and the current travel track data, and the drunk driving level index of the target vehicle is generated based on the environmental data and the vehicle data when the target vehicle is abnormally traveling, so that the target vehicle can be eliminated according to the historical travel track data and the current travel track data, the number of the target vehicles which need to be further judged subsequently can be reduced, data resources can be saved, and the processing efficiency is improved.
In one embodiment, the historical travel track data includes a plurality of historical travel track segments, and the current travel track data includes a plurality of current travel track segments.
The track segment may refer to a travel track per unit time, for example, a travel track per unit time of 5 seconds, or may also refer to a travel track per unit travel distance, for example, a travel track per unit time of 1 meter.
In this embodiment, determining whether the target vehicle normally travels according to the historical travel track data and the current travel track data may include: judging whether each historical travel track segment in the historical travel track data is consistent with each current travel track segment in the current travel track data; counting the number of track segments of which the historical travel track segments are consistent with the current travel track segments in the historical travel track data and the current travel track data; judging whether the number of the track segments is greater than or equal to a preset number threshold value or not; when the number of the track segments is smaller than a preset number threshold value, determining that the target vehicle is abnormal in running; and when the number of the track segments is greater than or equal to the preset number threshold value, determining that the target vehicle runs normally.
In the present embodiment, the server determines the historical travel track data and the current travel track data, and determining whether the target vehicle travels normally may be a comparison determination of each of a plurality of track segments of the group travel track data to determine whether each track segment is consistent.
In this embodiment, after the server traverses each travel track segment and performs the comparison and determination, the number N of track segments of the travel track segment whose determination result is consistent may be counted1。
Further, the server determines the number of track segments N1Whether it is greater than or equal to a preset number threshold NF。
Specifically, when the server determines the number of track segments N1Less than a predetermined number threshold NFIf the target vehicle is not normally driven, the server may determine that the historical driving track data is inconsistent with the current driving track data, and then the server may further determine the target vehicle.
In this embodiment, when the server determines the number of track segments N1Greater than or equal to a preset number threshold NFIf so, the server may determine that the historical travel track data is consistent with the current travel track data, that is, the target vehicle travels normally, and then the server may determine that the target vehicle is a non-drunk-driving vehicle.
In the embodiment, the historical driving track data and the current driving track data are compared, and whether the target vehicle is normally driven is determined, so that whether the target vehicle is drunk driving or not can be accurately determined from the angle of the driving track of the vehicle, and the accuracy and the intelligent level of determination can be improved.
In one embodiment, generating the drunk driving level index of the target vehicle based on the environmental data and the vehicle data may include: and inputting the environmental data and the vehicle data into a pre-trained drunk driving index estimation model, and outputting drunk driving grade indexes of corresponding target vehicles through the drunk driving index estimation model.
The drunk driving index generation model is a model for judging whether the target vehicle is suspected to be drunk driving, and can be a neural network model based on deep learning.
In this embodiment, the server may pre-construct an initial drunk driving index generation model, train and test the constructed initial drunk driving index generation model through the acquired training data, and perform drunk driving index rating evaluation according to the present application after the test is completed. The training data may include, but is not limited to, information related to the historical drunk driving data (such as license plate number, vehicle brand, owner identity, etc.) and vehicle stay time, and environmental data.
In this embodiment, with continuing reference to fig. 4, the server may further convert the training data into data labels corresponding to the data, and perform model training according to the training data and the data labels corresponding to the training data, for example, an age label, a vehicle brand label, a drunk driving time period label, a driving track label, a vehicle owner local label, a weather condition label, a month label, a heavy event day, and the like.
Similarly, when the drunk driving grade index prediction is performed by the server according to the trained drunk driving index generation model, the environment data and the vehicle data can be converted into corresponding data labels, and then the drunk driving index generation model is input and prediction is performed.
Optionally, the data for training the drunk driving index generation model may further include data of month, week, working day time, non-working day time, other time, age group, gender, vehicle brand, vehicle attribution, driving track, activity day, and the like, and before the server evaluates the drunk driving level index of the target vehicle, the server may also obtain data of corresponding month, week, working day time, non-working day time, other time, age group, gender, vehicle brand, vehicle attribution, driving track, activity day, and the like, and input the data into the drunk driving index generation model to obtain the drunk driving level index of the corresponding target vehicle.
In the embodiment, the drunk driving grade index of the target vehicle is evaluated through the pre-trained drunk driving index generation model, and the model can improve the data processing efficiency and the judgment accuracy, so that the drunk driving grade index evaluation accuracy and the judgment efficiency can be improved.
In one embodiment, the warning of drunk driving of the vehicle may include: generating early warning information based on vehicle data of drunk driving vehicles; determining the position information and the driving direction of the drunk driving vehicle according to the current driving track data of the drunk driving vehicle; and sending the early warning information to a detection terminal corresponding to the position information and the driving direction so as to intercept and early warn the drunk driving vehicle.
In this embodiment, when determining that the target vehicle is a drunk driving vehicle, the server may generate the warning information according to the acquired vehicle data, for example, generate the warning information corresponding to the target vehicle according to a license plate number, a vehicle color, and a vehicle model in the vehicle data, where the generated warning information may include data such as the license plate number, the vehicle color, and the vehicle model.
Further, the server can determine the position of the drunk driving vehicle and the driving direction of the drunk driving vehicle according to the current driving track data of the drunk driving vehicle.
In this embodiment, the server may acquire the detection terminals existing in the traveling direction of the drunk-driving vehicle, and acquire the position information of each detection terminal. Then, the server determines a target detection terminal to which the early warning information is to be sent according to the position information of each detection terminal, for example, the detection terminal A is closest to the drunk driving vehicle, however, when the warning message is sent, the detection terminal a may not intercept the drunk driving vehicle when being deployed, the detection terminal C is located far away from the drunk driving vehicle, and a plurality of branched intersections exist between the distance position of the detection terminal C and the current position of the drunk driving vehicle, the detection terminal C is not necessarily able to intercept the drunk driving vehicle, the detection terminal B is located between the detection terminal a and the detection terminal C, through the above comparison, the server can determine that the detection terminal B is the most suitable terminal for intercepting the drunk-driving vehicle, the server can send the early warning information to the detection terminal B, warn to intercept and deploy, and detect drunk driving.
Alternatively, with continued reference to fig. 4, the server may also determine the driving direction of the drunk driving vehicle directly according to the historical track data, and perform deployment control.
In this embodiment, the detection terminal may also feed back the detection result to the server, that is, feed back the result of whether the drunk driving vehicle really has drunk driving behavior to the server.
In this embodiment, at a predetermined time interval, for example, one month or one quarter, the server may count the result fed back by the detection terminal and compare and analyze the result with the estimated result to determine the estimated accuracy.
Further, the server can update each drunk driving index generation model and each threshold value data according to a result fed back by the detection terminal, so that the accuracy of the threshold value condition and the drunk driving index generation model is improved.
In the embodiment, the early warning information is generated, the position information and the driving direction of the drunk driving vehicle are determined, and then the early warning information is sent to the detection terminal of the position information corresponding to the driving direction to warn the drunk driving vehicle, so that the early warning is more targeted, and the accuracy of the early warning is improved.
In one embodiment, the method may further include: and uploading at least one of the vehicle data, the current driving track data, the environment data, the drunk driving grade index of the target vehicle and a preset drunk driving grade index threshold value to a block chain node for storage.
The blockchain refers to a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A Block chain (Block chain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data Block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next Block.
Specifically, the blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
In this embodiment, the server may upload and store one or more of the vehicle data, the current driving track data, the environment data, the drunk driving level index of the target vehicle, and the preset drunk driving level index threshold in the node of the block chain, so as to ensure privacy and security of the data.
In the above embodiment, at least one of the vehicle data, the current driving track data, the environment data, the drunk driving level index of the target vehicle and the preset drunk driving level index threshold is uploaded to the block chain and stored in the node of the block chain, so that the privacy of the data stored in the block chain link point can be guaranteed, and the safety of the data can be improved.
It should be understood that although the various steps in the flowcharts of fig. 2-5 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-5 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 6, there is provided an artificial intelligence-based drunk driving vehicle warning apparatus including: the system comprises a vehicle data acquisition module 100, a collection module 200, a drunk driving level index generation module 300, an index threshold acquisition module 400 and an early warning module 500, wherein:
the vehicle data acquiring module 100 is configured to acquire vehicle data of a target vehicle entering a preset monitoring area.
The collection module 200 is configured to collect current driving track data of the target vehicle when the target vehicle leaves the preset monitoring area and environment data of the preset monitoring area.
The drunk driving level index generating module 300 is configured to generate a drunk driving level index of the target vehicle based on the current driving track data, the environment data, and the vehicle data.
And an index threshold value obtaining module 400, configured to obtain a preset drunk driving level index threshold value.
The early warning module 500 is configured to determine whether the target vehicle is a drunk driving vehicle according to a preset drunk driving level index threshold and a drunk driving level index of the target vehicle, and perform early warning on the drunk driving vehicle when the target vehicle is determined to be the drunk driving vehicle.
In one embodiment, the apparatus may further include:
and a monitoring data acquiring module, configured to acquire the monitoring data of the preset monitoring area before the vehicle data acquiring module 100 acquires the vehicle data of the target vehicle entering the preset monitoring area.
And the stay time calculation module is used for determining the stay time of each initial vehicle entering the preset monitoring area according to the monitoring data.
And the judging module is used for judging whether the stay time of each initial vehicle is greater than or equal to a preset time threshold.
And the target vehicle determining module is used for determining that the initial vehicle is the target vehicle and acquiring vehicle data of the target vehicle when the stay time is determined to be greater than or equal to the preset time threshold.
In one embodiment, the drunk driving level index generating module 300 may include:
and the historical driving track data acquisition submodule is used for acquiring the historical driving track data of the target vehicle.
And the driving judgment submodule is used for judging whether the target vehicle normally drives according to the historical driving track data and the current driving track data.
And the drunk driving grade index generating submodule is used for generating drunk driving grade indexes of the target vehicle based on the environmental data and the vehicle data when the target vehicle is determined to be abnormally driven.
In one embodiment, the historical driving trace data may include a plurality of historical driving trace segments, and the current driving trace data may include a plurality of current driving trace segments.
In this embodiment, the driving determination sub-module may include:
and the track segment judging unit is used for judging whether each historical driving track segment in the historical driving track data is consistent with each current driving track segment in the current driving track data.
And the track number counting unit is used for counting the number of track segments of which the historical travel track segments are consistent with the current travel track segments in the historical travel track data and the current travel track data.
And the judging unit is used for judging whether the number of the track segments is greater than or equal to a preset number threshold value.
The first determination unit is used for determining that the target vehicle is abnormally driven when the number of the track segments is smaller than a preset number threshold value.
And the second determination unit is used for determining that the target vehicle normally runs when the track segment number is greater than or equal to the preset number threshold.
In one embodiment, the drunk driving level index generation sub-module is further configured to input the environmental data and the vehicle data into a drunk driving index estimation model trained in advance, and output a drunk driving level index corresponding to the target vehicle through the drunk driving index estimation model.
In one embodiment, the early warning module 500 may include:
and the early warning information generation submodule is used for generating early warning information based on the vehicle data of the drunk driving vehicle.
And the position information and driving direction determining submodule is used for determining the position information and the driving direction of the drunk driving vehicle according to the current driving track data of the drunk driving vehicle.
And the sending submodule is used for sending the early warning information to the detection terminal corresponding to the position information and the driving direction so as to intercept and early warn drunk driving vehicles.
In one embodiment, the apparatus may further include:
and the storage submodule is used for uploading at least one of the vehicle data, the current driving track data, the environment data, the drunk driving grade index of the target vehicle and a preset drunk driving grade index threshold value to the block chain node for storage.
For specific limitations of the drunk driving vehicle early warning device based on artificial intelligence, reference may be made to the above limitations of the drunk driving vehicle early warning method based on artificial intelligence, and details are not repeated here. All modules in the drunk driving vehicle early warning device based on artificial intelligence can be completely or partially realized through software, hardware and a combination of the software and the hardware. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing vehicle data, current driving track data, environment data, drunk driving grade indexes of target vehicles and preset drunk driving grade index threshold value data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to realize an artificial intelligence-based drunk driving vehicle early warning method.
Those skilled in the art will appreciate that the architecture shown in fig. 7 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, there is provided a computer device comprising a memory storing a computer program and a processor implementing the following steps when the processor executes the computer program: acquiring vehicle data of a target vehicle entering a preset monitoring area; acquiring current running track data of a target vehicle when the target vehicle leaves a preset monitoring area and environment data of the preset monitoring area; generating a drunk driving grade index of the target vehicle based on the current driving track data, the environment data and the vehicle data; acquiring a preset drunk driving grade index threshold; judging whether the target vehicle is a drunk driving vehicle or not according to a preset drunk driving grade index threshold value and a drunk driving grade index of the target vehicle, and carrying out early warning on the drunk driving vehicle when the target vehicle is judged to be the drunk driving vehicle.
In one embodiment, before the processor executes the computer program to acquire the vehicle data of the target vehicle entering the preset monitoring area, the following steps may be further implemented: acquiring monitoring data of a preset monitoring area; determining the stay time of each initial vehicle entering a preset monitoring area according to the monitoring data; judging whether the stay time of each initial vehicle is greater than or equal to a preset time threshold; and when the stay time is determined to be greater than or equal to the preset time threshold, determining that the initial vehicle is the target vehicle, and acquiring vehicle data of the target vehicle.
In one embodiment, the processor, when executing the computer program, is configured to generate a drunk driving level index of the target vehicle based on the current driving trajectory data, the environmental data and the vehicle data, and may include: acquiring historical driving track data of a target vehicle; judging whether the target vehicle runs normally or not according to the historical running track data and the current running track data; and when the target vehicle is determined to be abnormally driven, generating a drunk driving level index of the target vehicle based on the environmental data and the vehicle data.
In one embodiment, the historical travel track data includes a plurality of historical travel track segments, and the current travel track data includes a plurality of current travel track segments.
In this embodiment, the processor, when executing the computer program, for determining whether the target vehicle normally travels according to the historical travel track data and the current travel track data, may include: judging whether each historical travel track segment in the historical travel track data is consistent with each current travel track segment in the current travel track data; counting the number of track segments of which the historical travel track segments are consistent with the current travel track segments in the historical travel track data and the current travel track data; judging whether the number of the track segments is greater than or equal to a preset number threshold value or not; when the number of the track segments is smaller than a preset number threshold value, determining that the target vehicle is abnormal in running; and when the number of the track segments is greater than or equal to the preset number threshold value, determining that the target vehicle runs normally.
In one embodiment, the processor, when executing the computer program, is configured to generate a drunk driving level indicator of the target vehicle based on the environmental data and the vehicle data, and may include: and inputting the environmental data and the vehicle data into a pre-trained drunk driving index estimation model, and outputting drunk driving grade indexes of corresponding target vehicles through the drunk driving index estimation model.
In one embodiment, the processor, when executing the computer program, implements early warning for drunk driving of the vehicle, and may include: generating early warning information based on vehicle data of drunk driving vehicles; determining the position information and the driving direction of the drunk driving vehicle according to the current driving track data of the drunk driving vehicle; and sending the early warning information to a detection terminal corresponding to the position information and the driving direction so as to intercept and early warn the drunk driving vehicle.
In one embodiment, the processor, when executing the computer program, may further implement the following steps: and uploading at least one of the vehicle data, the current driving track data, the environment data, the drunk driving grade index of the target vehicle and a preset drunk driving grade index threshold value to a block chain node for storage.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: acquiring vehicle data of a target vehicle entering a preset monitoring area; acquiring current running track data of a target vehicle when the target vehicle leaves a preset monitoring area and environment data of the preset monitoring area; generating a drunk driving grade index of the target vehicle based on the current driving track data, the environment data and the vehicle data; acquiring a preset drunk driving grade index threshold; judging whether the target vehicle is a drunk driving vehicle or not according to a preset drunk driving grade index threshold value and a drunk driving grade index of the target vehicle, and carrying out early warning on the drunk driving vehicle when the target vehicle is judged to be the drunk driving vehicle.
In one embodiment, the computer program when executed by the processor may further implement the following steps before acquiring the vehicle data of the target vehicle entering the preset monitoring area: acquiring monitoring data of a preset monitoring area; determining the stay time of each initial vehicle entering a preset monitoring area according to the monitoring data; judging whether the stay time of each initial vehicle is greater than or equal to a preset time threshold; and when the stay time is determined to be greater than or equal to the preset time threshold, determining that the initial vehicle is the target vehicle, and acquiring vehicle data of the target vehicle.
In one embodiment, the computer program when executed by the processor for implementing the method for generating a drunk driving level index of a target vehicle based on current driving trajectory data, environmental data and vehicle data may include: acquiring historical driving track data of a target vehicle; judging whether the target vehicle runs normally or not according to the historical running track data and the current running track data; and when the target vehicle is determined to be abnormally driven, generating a drunk driving level index of the target vehicle based on the environmental data and the vehicle data.
In one embodiment, the historical travel track data includes a plurality of historical travel track segments, and the current travel track data includes a plurality of current travel track segments.
In this embodiment, the computer program, when executed by the processor, for determining whether the target vehicle normally travels according to the historical travel track data and the current travel track data, may include: judging whether each historical travel track segment in the historical travel track data is consistent with each current travel track segment in the current travel track data; counting the number of track segments of which the historical travel track segments are consistent with the current travel track segments in the historical travel track data and the current travel track data; judging whether the number of the track segments is greater than or equal to a preset number threshold value or not; when the number of the track segments is smaller than a preset number threshold value, determining that the target vehicle is abnormal in running; and when the number of the track segments is greater than or equal to the preset number threshold value, determining that the target vehicle runs normally.
In one embodiment, the computer program when executed by the processor for implementing the generating the drunk driving level indicator of the target vehicle based on the environmental data and the vehicle data may include: and inputting the environmental data and the vehicle data into a pre-trained drunk driving index estimation model, and outputting drunk driving grade indexes of corresponding target vehicles through the drunk driving index estimation model.
In one embodiment, the computer program when executed by the processor implements early warning of drunk driving of the vehicle may include: generating early warning information based on vehicle data of drunk driving vehicles; determining the position information and the driving direction of the drunk driving vehicle according to the current driving track data of the drunk driving vehicle; and sending the early warning information to a detection terminal corresponding to the position information and the driving direction so as to intercept and early warn the drunk driving vehicle.
In one embodiment, the computer program when executed by the processor may further implement the steps of: and uploading at least one of the vehicle data, the current driving track data, the environment data, the drunk driving grade index of the target vehicle and a preset drunk driving grade index threshold value to a block chain node for storage.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. An early warning method for drunk driving vehicles based on artificial intelligence is characterized by comprising the following steps:
acquiring vehicle data of a target vehicle entering a preset monitoring area;
acquiring current running track data of the target vehicle when the target vehicle drives away from the preset monitoring area and environment data of the preset monitoring area;
generating a drunk driving level index of the target vehicle based on the current driving track data, the environment data and the vehicle data;
acquiring a preset drunk driving grade index threshold;
and judging whether the target vehicle is a drunk driving vehicle or not according to the preset drunk driving grade index threshold and the drunk driving grade index of the target vehicle, and warning the drunk driving vehicle when the target vehicle is judged to be the drunk driving vehicle.
2. The method of claim 1, wherein prior to obtaining vehicle data for a target vehicle entering a preset monitoring area, further comprising:
acquiring monitoring data of a preset monitoring area;
determining the stay time of each initial vehicle entering the preset monitoring area according to the monitoring data;
judging whether the stay time of each initial vehicle is greater than or equal to a preset time threshold;
and when the stay time is determined to be greater than or equal to the preset time threshold, determining that the initial vehicle is a target vehicle, and acquiring vehicle data of the target vehicle.
3. The method of claim 1, wherein generating the drunk driving level indicator for the target vehicle based on the current driving trajectory data, the environmental data, and the vehicle data comprises:
acquiring historical driving track data of the target vehicle;
judging whether the target vehicle runs normally or not according to the historical running track data and the current running track data;
and when the target vehicle is determined to be abnormally driven, generating a drunk driving level index of the target vehicle based on the environmental data and the vehicle data.
4. The method according to claim 3, wherein the historical travel track data includes a plurality of historical travel track segments, and the current travel track data includes a plurality of current travel track segments;
the judging whether the target vehicle normally runs or not according to the historical running track data and the current running track data comprises the following steps:
judging whether each historical driving track segment in the historical driving track data is consistent with each current driving track segment in the current driving track data;
counting the number of track segments of which the historical travel track segments are consistent with the current travel track segments in the historical travel track data and the current travel track data;
judging whether the number of the track segments is greater than or equal to a preset number threshold value or not;
when the number of the track segments is smaller than the preset number threshold value, determining that the target vehicle is abnormal in running;
and when the number of the track segments is greater than or equal to the preset number threshold value, determining that the target vehicle runs normally.
5. The method of claim 3, wherein generating the drunk driving level indicator for the target vehicle based on the environmental data and the vehicle data comprises:
and inputting the environmental data and the vehicle data into a pre-trained drunk driving index estimation model, and outputting drunk driving grade indexes corresponding to the target vehicle through the drunk driving index estimation model.
6. The method of claim 1, wherein the pre-warning the drunk-driving vehicle comprises:
generating early warning information based on the vehicle data of the drunk driving vehicle;
determining the position information and the driving direction of the drunk driving vehicle according to the current driving track data of the drunk driving vehicle;
and sending the early warning information to a detection terminal corresponding to the position information and the driving direction so as to intercept and early warn the drunk driving vehicle.
7. The method according to any one of claims 1 to 6, further comprising:
uploading at least one of the vehicle data, the current driving track data, the environment data, the drunk driving level index of the target vehicle and the preset drunk driving level index threshold value to a block chain node for storage.
8. The utility model provides a drunk driving vehicle early warning device based on artificial intelligence, its characterized in that, the device includes:
the vehicle data acquisition module is used for acquiring vehicle data of a target vehicle entering a preset monitoring area;
the acquisition module is used for acquiring current running track data when the target vehicle drives away from the preset monitoring area and environment data of the preset monitoring area;
the drunk driving grade index generating module is used for generating drunk driving grade indexes of the target vehicle based on the current driving track data, the environment data and the vehicle data;
the index threshold value acquisition module is used for acquiring a preset drunk driving grade index threshold value;
and the early warning module is used for judging whether the target vehicle is a drunk driving vehicle or not according to the preset drunk driving grade index threshold and the drunk driving grade index of the target vehicle, and carrying out early warning on the drunk driving vehicle when the target vehicle is judged to be the drunk driving vehicle.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011578763.6A CN112633580A (en) | 2020-12-28 | 2020-12-28 | Drunk driving vehicle early warning method, device, equipment and medium based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011578763.6A CN112633580A (en) | 2020-12-28 | 2020-12-28 | Drunk driving vehicle early warning method, device, equipment and medium based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112633580A true CN112633580A (en) | 2021-04-09 |
Family
ID=75326012
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011578763.6A Pending CN112633580A (en) | 2020-12-28 | 2020-12-28 | Drunk driving vehicle early warning method, device, equipment and medium based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112633580A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113433574A (en) * | 2021-06-09 | 2021-09-24 | 深圳前海微众银行股份有限公司 | Method and device for processing driving track |
| CN115100861A (en) * | 2022-06-22 | 2022-09-23 | 公安部交通管理科学研究所 | Drunk driving vehicle identification method |
| CN117495384A (en) * | 2023-11-07 | 2024-02-02 | 广州准捷电子科技有限公司 | KTV face brushing payment method based on AI face recognition technology |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104408932A (en) * | 2014-11-03 | 2015-03-11 | 河海大学常州校区 | Drunk driving vehicle detection system based on video monitoring |
| CN106571028A (en) * | 2016-10-18 | 2017-04-19 | 北京科技大学 | Vehicle driving state analysis method and device for driver drunk driving identification |
| US20170215783A1 (en) * | 2015-09-08 | 2017-08-03 | Boe Technology Group Co., Ltd. | Method for determining target of alcohol test, driving safety device and system, server |
| CN108091136A (en) * | 2017-12-14 | 2018-05-29 | 阜阳裕晟电子科技有限公司 | A kind of drunk driving vehicle detecting system based on video monitoring |
| CN108242181A (en) * | 2016-12-27 | 2018-07-03 | 中国移动通信有限公司研究院 | A kind of information early warning processing method and server |
| CN109146914A (en) * | 2018-06-20 | 2019-01-04 | 上海市政工程设计研究总院（集团）有限公司 | A kind of drink-driving behavior method for early warning of the highway based on video analysis |
| CN110286667A (en) * | 2019-07-03 | 2019-09-27 | 上运车物联网科技（深圳）有限公司 | Abnormal driving condition intelligent control method and Intelligent terminal for Internet of things |
| CN111460518A (en) * | 2020-02-19 | 2020-07-28 | 山东爱城市网信息技术有限公司 | Block chain-based drunk driving behavior detection control method, device and medium |
-
2020
- 2020-12-28 CN CN202011578763.6A patent/CN112633580A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104408932A (en) * | 2014-11-03 | 2015-03-11 | 河海大学常州校区 | Drunk driving vehicle detection system based on video monitoring |
| US20170215783A1 (en) * | 2015-09-08 | 2017-08-03 | Boe Technology Group Co., Ltd. | Method for determining target of alcohol test, driving safety device and system, server |
| CN106571028A (en) * | 2016-10-18 | 2017-04-19 | 北京科技大学 | Vehicle driving state analysis method and device for driver drunk driving identification |
| CN108242181A (en) * | 2016-12-27 | 2018-07-03 | 中国移动通信有限公司研究院 | A kind of information early warning processing method and server |
| CN108091136A (en) * | 2017-12-14 | 2018-05-29 | 阜阳裕晟电子科技有限公司 | A kind of drunk driving vehicle detecting system based on video monitoring |
| CN109146914A (en) * | 2018-06-20 | 2019-01-04 | 上海市政工程设计研究总院（集团）有限公司 | A kind of drink-driving behavior method for early warning of the highway based on video analysis |
| CN110286667A (en) * | 2019-07-03 | 2019-09-27 | 上运车物联网科技（深圳）有限公司 | Abnormal driving condition intelligent control method and Intelligent terminal for Internet of things |
| CN111460518A (en) * | 2020-02-19 | 2020-07-28 | 山东爱城市网信息技术有限公司 | Block chain-based drunk driving behavior detection control method, device and medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113433574A (en) * | 2021-06-09 | 2021-09-24 | 深圳前海微众银行股份有限公司 | Method and device for processing driving track |
| CN113433574B (en) * | 2021-06-09 | 2024-02-06 | 深圳前海微众银行股份有限公司 | Driving track processing method and device |
| CN115100861A (en) * | 2022-06-22 | 2022-09-23 | 公安部交通管理科学研究所 | Drunk driving vehicle identification method |
| CN117495384A (en) * | 2023-11-07 | 2024-02-02 | 广州准捷电子科技有限公司 | KTV face brushing payment method based on AI face recognition technology |
| CN117495384B (en) * | 2023-11-07 | 2024-04-26 | 广州准捷电子科技有限公司 | KTV face brushing payment method based on AI face recognition technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11397993B2 (en) | Electronic logging and track identification system for mobile telematics devices, and corresponding method thereof | |
| CN112633580A (en) | Drunk driving vehicle early warning method, device, equipment and medium based on artificial intelligence | |
| US10977945B1 (en) | Vehicular driver warnings | |
| US20170124660A1 (en) | Telematics Based Systems and Methods for Determining and Representing Driving Behavior | |
| CN110060484B (en) | Road passenger traffic violation real-time early warning system and method based on block chain | |
| CN110490608B (en) | Risk assessment method and device, computer equipment and storage medium | |
| WO2015160900A1 (en) | Assessing asynchronous authenticated data sources for use in driver risk management | |
| Yu et al. | LSTM-based intrusion detection system for VANETs: a time series classification approach to false message detection | |
| CN112530163B (en) | Traffic accident prediction method, traffic accident prediction device, electronic device, and storage medium | |
| CN109800984B (en) | Driving level evaluation method, driving level evaluation device, computer device, and storage medium | |
| CN206684779U (en) | A kind of vehicle insurance management service system based on ADAS intelligent vehicle mounted terminals | |
| CN109360417B (en) | Dangerous driving behavior identification and pushing method and system based on block chain | |
| CN115662148B (en) | Early warning method, device, equipment and medium for road abnormal event | |
| CN111091215A (en) | Vehicle identification method and device, computer equipment and storage medium | |
| US20230054889A1 (en) | Automatically tracking a trajectory of a vehicle | |
| EP3774478A1 (en) | Vehicular motion assessment method | |
| Ucar et al. | Differential deviation based abnormal driving behavior detection | |
| CN110533930B (en) | Traffic data processing method and device, computer equipment and storage medium | |
| CN111325999A (en) | Vehicle driving assistance method, device, computer device, and storage medium | |
| CN116312023B (en) | Guiding parking method, guiding parking device, guiding parking equipment and storage medium | |
| CN116189107A (en) | Unmanned aerial vehicle expressway monitoring method, unmanned aerial vehicle and storage medium | |
| Han et al. | Transformer-based modeling of abnormal driving events for freeway crash risk evaluation | |
| CN114358395A (en) | Attendance checking prediction method and device | |
| CN110751567A (en) | Vehicle information processing method, device, computer equipment and storage medium | |
| CN113888302A (en) | Risk early warning method and system for automobile financial vehicle loan |
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 |