CN111429329B - Method and device for monitoring network car booking behavior - Google Patents
Method and device for monitoring network car booking behavior Download PDFInfo
- Publication number
- CN111429329B CN111429329B CN202010201689.XA CN202010201689A CN111429329B CN 111429329 B CN111429329 B CN 111429329B CN 202010201689 A CN202010201689 A CN 202010201689A CN 111429329 B CN111429329 B CN 111429329B
- Authority
- CN
- China
- Prior art keywords
- determining
- order
- passengers
- monitoring
- characteristic 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 175
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000006399 behavior Effects 0.000 claims abstract description 91
- 238000001514 detection method Methods 0.000 claims abstract description 69
- 230000001788 irregular Effects 0.000 claims abstract description 29
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 15
- 230000001680 brushing effect Effects 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims description 43
- 238000013507 mapping Methods 0.000 claims description 29
- 238000012790 confirmation Methods 0.000 claims description 23
- 230000002159 abnormal effect Effects 0.000 claims description 22
- 238000013139 quantization Methods 0.000 claims description 16
- 238000005201 scrubbing Methods 0.000 claims description 8
- 238000012806 monitoring device Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 230000008859 change Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 238000004590 computer program Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 6
- 238000013473 artificial intelligence Methods 0.000 description 5
- 230000008447 perception Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000004378 air conditioning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000001052 transient effect Effects 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Strategic Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- Marketing (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Probability & Statistics with Applications (AREA)
- Human Computer Interaction (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a method and a device for monitoring network car booking behaviors, wherein the method comprises the following steps: acquiring a monitoring image shot by a camera in the vehicle-mounted end; determining the number of travel passengers by using a target detection algorithm for the monitoring image, and acquiring order state information, wherein the order state information comprises whether a travel order exists at present; and determining whether a monitoring result of the irregular driving behavior exists or not according to the number of the passengers on the trip and the order state information. The method provided by the invention can monitor the behaviors of the driver such as order brushing, bus use, overload and the like, and can utilize a relevant reward and punishment system to restrict and standardize the network car booking market, thereby ensuring the safety of drivers and passengers and improving the service provided by the network car booking.
Description
Technical Field
The invention belongs to the technical field of communication, and particularly relates to a method and a device for monitoring a network taxi appointment behavior.
Background
In recent years, with the rapid development of the mobile internet industry, the new industry state of the traditional transportation and internet-integrated industry is developed vigorously, so that the network car booking service (for short, the network car booking) is just an important mode for users to go out, the users issue a travel order request to the network car booking platform, and the network car booking platform assigns corresponding vehicles to provide travel service for the users according to the issued orders, wherein the orders comprise information such as a traveling route and the number of passengers, so that the network car booking can meet the use demands of the users in different travel scenes, the scale of the users is continuously and stably increased, the network car booking can rapidly occupy a large number of user markets in a short time, and great convenience is brought to the users to go out.
The net car reservation brings convenience to users, irregular driving behaviors of some drivers also happen occasionally, and certain lucky drivers have the problems of private bus use, overload running or bill swiping through false GPS positioning by avoiding the platform rule, so that the benefit of passengers is infringed, and the market order is influenced. For example, some drivers use a virtual positioning software to virtually position a moving vehicle in real time to finally achieve the purpose of order-reading, and under the background that the online car-booking market gradually tends to be standardized, the irregular driving behaviors are not monitored and solved in time.
The current each net car appointment platform does not have good method to the control of this kind of driving action of irregularity, and the main solution is to compensate for the passenger earlier, punishs the driver again, and nevertheless the reality is low to driving action detection efficiency of irregularity, can only handle after the problem takes place a period, can not accomplish to prevent suffering in the bud.
The existing technical means are methods for judging whether the vehicle has irregular driving behaviors by comparing and monitoring whether the current driving position of the network car booking and the driving position of the order are consistent, but a driver can still escape from supervision by modifying the current positioning information, and various types of illegal behaviors are easy to exist due to the fact that the driver of the network car booking is located in a scattered region, most analysis modes are difficult to perform for real-time monitoring outside the order and under the condition that the driver does not have the order, errors often occur in the method for analyzing the order, and direct evidence cannot be obtained when the network car booking abnormally runs, so a direct and effective solution is not provided for monitoring the irregular driving behaviors.
Disclosure of Invention
The invention provides a method and a device for monitoring network car booking behaviors, which are used for solving the problems that the irregular driving behaviors of the network car booking cannot be monitored in time and the irregular driving behaviors of the network car booking cannot obtain direct evidence.
The invention provides a method for monitoring a network taxi appointment behavior, which comprises the following steps:
acquiring a monitoring image shot by a camera in the vehicle-mounted end;
determining the number of travel passengers by using a target detection algorithm for the monitoring image, and acquiring order state information, wherein the order state information comprises whether a travel order exists at present;
and determining whether a monitoring result of the irregular driving behavior exists or not according to the number of the passengers on the trip and the order state information.
Optionally, determining whether a monitoring result of irregular driving behavior exists according to the number of passengers on the trip and the order state information, including at least one of the following steps:
if the number of the trip passengers is larger than the maximum number of passengers carried by the vehicle-mounted terminal and an order currently exists, determining that the abnormal driving behavior suspected of overload exists;
if the number of the travel passengers is larger than 0 and no travel order exists at present, determining that the non-standard driving behavior of private use of the bus exists;
and if the number of the trip passengers is 0 and a trip order currently exists, determining whether the abnormal driving behavior suspected of scrubbing the order exists or not by combining at least one of monitoring images, car door opening and closing information, trip time related information and trip position related information at different moments collected before the trip order is finished.
Optionally, determining whether the non-normative driving behavior of the suspected scrub is present comprises:
mapping at least one of the monitoring images, the car door opening and closing information, the travel time related information and the travel position related information at different moments into corresponding first feature data, second feature data, third feature data and fourth feature data according to corresponding rules;
and making a decision to obtain the probability of the suspected bill brushing according to at least one of the first characteristic data, the second characteristic data, the third characteristic data and the fourth characteristic data.
Optionally, the making a decision according to at least one of the first feature data, the second feature data, the third feature data, and the fourth feature data to obtain the probability of the suspected scrub sheet includes:
and inputting at least one of the first characteristic data, the second characteristic data, the third characteristic data and the fourth characteristic data into a decision model to obtain the probability of the existence of the suspected bill swiping, wherein the decision model takes the first characteristic data, the second characteristic data, the third characteristic data and the fourth characteristic data which are marked as whether the single swiping line exists as input, and takes the output mark as a target to train the network model so as to obtain the result.
Optionally, mapping the monitored image to corresponding first feature data according to a corresponding rule, including:
determining the proportion of the changed pixel points to the total pixel points in the monitoring image according to the monitoring image at the order receiving moment and the monitoring image at the time of confirming the getting-on moment, and determining the proportion of the changed pixel points to the total pixel points in the monitoring image according to the monitoring image at the time of confirming the getting-on moment and the monitoring image at the time of finishing the order, so as to determine the first characteristic data.
Optionally, mapping the vehicle door opening and closing information to corresponding second feature data according to a corresponding rule, including:
and determining the door opening and closing times according to the door opening and closing information, and mapping the comparison result of the door opening and closing times and a plurality of times threshold values to be second characteristic data.
Optionally, mapping the travel time related information into corresponding third feature data according to a corresponding rule, including:
determining order receiving time, boarding confirmation time and order ending time of a travel order according to travel time related information, and determining a first time difference T by using the order receiving time and the boarding confirmation time1Determining a second time difference T using the time of arrival confirmation and the time of order completion2;
Determining the mean value of the first time difference of the network car booking platform according to order receiving time, boarding time confirmation and order ending time in different travel orders acquired by the network car booking platformAnd the variance value sigma1And determining the mean value of the second time differenceAnd the variance value sigma2;
According to a first time difference T1Mean value of first time differenceVariance value sigma1Preset weight w0And deviation b0Determining a first time difference processing resultAccording to the second time difference T2Mean value of the second time differenceVariance value sigma2Preset weight w0And deviation b0Determining a second time difference processing result
And determining third characteristic data according to the first time difference processing result and the second time difference processing result.
Optionally, mapping the travel position related information to corresponding fourth feature data according to a corresponding rule, including:
determining a pick-up position, a confirmed boarding position and an order ending position of a trip order according to the travel position related information, determining a first distance difference by using the pick-up position and the confirmed boarding position through a Manhattan distance formula, and determining a second distance difference by using the confirmed boarding position and the order ending position through the Manhattan distance formula;
and respectively comparing the first distance difference and the second distance difference of the travel order with a plurality of distance thresholds, then carrying out quantization processing, and determining fourth characteristic data according to the quantization results of the first distance difference and the second distance difference.
A second aspect of the invention provides a monitoring device for network appointment behaviour, the device comprising a memory for storing instructions;
and the processor is used for reading the instructions in the memory and realizing the monitoring method for the network appointment behavior provided by any one of the first aspect of the invention.
Optionally, the processor is configured to determine whether there is a monitoring result of irregular driving behavior according to the number of passengers on the trip and the order status information, and includes at least one of the following steps:
if the number of the trip passengers is larger than the maximum number of passengers carried by the vehicle-mounted terminal and an order currently exists, determining that the abnormal driving behavior suspected of overload exists;
if the number of the travel passengers is larger than 0 and no travel order exists at present, determining that the non-standard driving behavior of private use of the bus exists;
and if the number of the trip passengers is 0 and a trip order currently exists, determining whether the abnormal driving behavior suspected of scrubbing the order exists or not by combining at least one of monitoring images, car door opening and closing information, trip time related information and trip position related information at different moments collected before the trip order is finished.
Optionally, the processor is configured to determine whether there is an irregular driving behavior of suspected billing, including:
mapping at least one of the monitoring images, the car door opening and closing information, the travel time related information and the travel position related information at different moments into corresponding first feature data, second feature data, third feature data and fourth feature data according to corresponding rules;
and according to the first characteristic data and at least one of the second characteristic data, the third characteristic data and the fourth characteristic data, making a decision to obtain the probability of the suspected bill brushing.
Optionally, the processor is configured to make a decision according to the first feature data and at least one of the second feature data, the third feature data, and the fourth feature data to obtain the probability of the suspected scrub sheet, including:
and inputting the first characteristic data and at least one of the second characteristic data, the third characteristic data and the fourth characteristic data into a decision model to obtain the probability of the existence of the suspected bill swiping, wherein the decision model takes the first characteristic data, the second characteristic data, the third characteristic data and the fourth characteristic data which are marked as whether the single swiping line exists as input, and takes the output mark as a target to train the network model so as to obtain the result.
Optionally, the processor is configured to map the monitored images to corresponding first feature data according to a corresponding rule, and includes:
determining the proportion of the changed pixel points to the total pixel points in the monitoring image according to the monitoring image at the order receiving moment and the monitoring image at the time of confirming the getting-on moment, and determining the proportion of the changed pixel points to the total pixel points in the monitoring image according to the monitoring image at the time of confirming the getting-on moment and the monitoring image at the time of finishing the order, so as to determine the first characteristic data.
Optionally, the processor is configured to map the door opening and closing information to corresponding second feature data according to a corresponding rule, and includes:
and determining the door opening and closing times according to the door opening and closing information, and mapping the comparison result of the door opening and closing times and a plurality of times threshold values to be second characteristic data.
Optionally, the processor is configured to map the travel time related information into corresponding third feature data according to a corresponding rule, and includes:
determining order receiving time, boarding confirmation time and order ending time of a travel order according to travel time related information, and determining a first time difference T by using the order receiving time and the boarding confirmation time1Determining a second time difference T using the time of arrival confirmation and the time of order completion2;
Determining the mean value of the first time difference of the network car booking platform according to the order receiving time, the confirmed getting-on time and the order ending time in different travel orders collected by the network car booking platformAnd the variance value sigma1And determining the mean value of the second time differenceAnd the variance value sigma2;
According to a first time difference T1Mean value of first time differenceVariance value sigma1Preset weight w0And deviation b0Determining a first time difference processing resultAccording to the second time difference T2Mean value of the second time differenceVariance value sigma2Preset weight w0And deviation b0Determining a second time difference processing result
And determining third characteristic data according to the first time difference processing result and the second time difference processing result.
Optionally, the processor is configured to map the travel position related information into corresponding fourth feature data according to a corresponding rule, and the mapping includes:
determining a pick-up position, a confirmed boarding position and an order ending position of a trip order according to the travel position related information, determining a first distance difference by using the pick-up position and the confirmed boarding position through a Manhattan distance formula, and determining a second distance difference by using the confirmed boarding position and the order ending position through the Manhattan distance formula;
and respectively comparing the first distance difference and the second distance difference of the travel order with a plurality of distance thresholds, then carrying out quantization processing, and determining fourth characteristic data according to the quantization results of the first distance difference and the second distance difference.
The invention provides a monitoring device for network car booking behavior, which comprises the following modules:
the monitoring image acquisition module is used for acquiring a monitoring image shot by a camera in the vehicle-mounted end;
the passenger number determining module is used for determining the number of travelling passengers by using a target detection algorithm for the monitoring image and acquiring order state information, wherein the order state information comprises whether a travelling order exists at present;
and the monitoring result determining module is used for determining whether a monitoring result of irregular driving behavior exists according to the number of the passengers on the trip and the order state information.
Optionally, the monitoring result determining module is configured to determine whether a monitoring result of irregular driving behavior exists according to the number of passengers on the trip and the order state information, and includes at least one of the following steps:
if the number of the trip passengers is larger than the maximum number of passengers carried by the vehicle-mounted terminal and an order currently exists, determining that the abnormal driving behavior suspected of overload exists;
if the number of the travel passengers is larger than 0 and no travel order exists at present, determining that the non-standard driving behavior of the private use of the bus exists;
and if the number of the trip passengers is 0 and a trip order currently exists, determining whether the abnormal driving behavior suspected of scrubbing the order exists or not by combining at least one of monitoring images, car door opening and closing information, trip time related information and trip position related information at different moments collected before the trip order is finished.
Optionally, the monitoring result determining module is configured to determine whether there is an irregular driving behavior of a suspected scrub list, and includes:
mapping at least one of the monitoring images, the car door opening and closing information, the travel time related information and the travel position related information at different moments into corresponding first feature data, second feature data, third feature data and fourth feature data according to corresponding rules;
and according to the first characteristic data and at least one of the second characteristic data, the third characteristic data and the fourth characteristic data, making a decision to obtain the probability of the suspected bill brushing.
Optionally, the monitoring result determining module is configured to make a decision according to the first feature data and at least one of the second feature data, the third feature data, and the fourth feature data to obtain the probability of the suspected bill-brushing, and includes:
and inputting at least one of the first characteristic data, the second characteristic data, the third characteristic data and the fourth characteristic data into a decision model to obtain the probability of the existence of the suspected bill swiping, wherein the decision model takes the first characteristic data, the second characteristic data, the third characteristic data and the fourth characteristic data which are marked as whether the single swiping line exists as input, and takes the output mark as a target to train the network model so as to obtain the result.
Optionally, the monitoring result determining module is configured to map the monitored image to corresponding first feature data according to a corresponding rule, and includes:
determining the proportion of the changed pixel points to the total pixel points in the monitoring image according to the monitoring image at the order receiving moment and the monitoring image at the time of confirming the getting-on moment, and determining the proportion of the changed pixel points to the total pixel points in the monitoring image according to the monitoring image at the time of confirming the getting-on moment and the monitoring image at the time of finishing the order, so as to determine the first characteristic data.
Optionally, the monitoring result determining module is configured to map the vehicle door opening and closing information to corresponding second feature data according to a corresponding rule, and includes:
and determining the door opening and closing times according to the door opening and closing information, and mapping the comparison result of the door opening and closing times and a plurality of times threshold values to be second characteristic data.
Optionally, the monitoring result determining module is configured to map the travel time related information into corresponding third feature data according to a corresponding rule, and includes:
determining order receiving time, boarding confirmation time and order ending time of a travel order according to travel time related information, and determining a first time difference T by using the order receiving time and the boarding confirmation time1Determining a second time difference T using the time of arrival confirmation and the time of order completion2;
Determining the mean value of the first time difference of the network car booking platform according to the order receiving time, the confirmed getting-on time and the order ending time in different travel orders collected by the network car booking platformAnd the variance value sigma1And determining the mean value of the second time differenceAnd the variance value sigma2;
According to a first time difference T1Mean value of first time differenceVariance value sigma1Preset weight w0And deviation b0Determining a first time difference processing resultAccording to the second time difference T2Mean value of the second time differenceVariance value sigma2Preset weight w0And deviation b0Determining a second time difference processing result
And determining third characteristic data according to the first time difference processing result and the second time difference processing result.
Optionally, the monitoring result determining module is configured to map the travel position related information into corresponding fourth feature data according to a corresponding rule, and includes:
determining a pick-up position, a confirmed boarding position and an order ending position of a trip order according to the travel position related information, determining a first distance difference by using the pick-up position and the confirmed boarding position through a Manhattan distance formula, and determining a second distance difference by using the confirmed boarding position and the order ending position through the Manhattan distance formula;
and respectively comparing the first distance difference and the second distance difference of the travel order with a plurality of distance thresholds, then carrying out quantization processing, and determining fourth characteristic data according to the quantization results of the first distance difference and the second distance difference.
A fourth aspect of the present invention provides a computer medium, wherein the computer readable storage medium stores computer instructions, and the computer instructions, when executed by a processor, implement any one of the monitoring methods for network appointment behavior provided in the first aspect of the present invention.
The method for monitoring the network car booking behaviors can monitor the behaviors of a driver such as order brushing, bus use, overload and the like, and can restrict and standardize the network car booking market by utilizing a relevant reward and punishment system, so that the safety of drivers and passengers is guaranteed and the service provided by the network car booking is improved.
Drawings
FIG. 1 is a schematic view of a monitoring system for online taxi appointment activities;
FIG. 2 is a flow chart of a method for monitoring a network taxi appointment;
FIG. 3 is a complete flow chart of a method for monitoring network taxi appointment activities;
fig. 4 is a block diagram of a monitoring apparatus for online taxi appointment activities;
fig. 5 is a block diagram of a monitoring device for network appointment activities.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
For convenience of understanding, terms referred to in the embodiments of the present invention are explained below:
(1) an intelligent double-recording acquisition terminal DVR (digital Video recorder), also called digital Video recorder, adopts hard disk Video recording compared with the traditional analog Video recorder, so is often called hard disk Video recorder, also called DVR, is a set of computer system for image storage processing, and has the functions of long-time Video recording, sound recording, remote monitoring and control of images/voice;
(2) the Vehicle-mounted information entertainment equipment IVI (In-Vehicle information) is Vehicle-mounted comprehensive information processing equipment which is formed by adopting a Vehicle-mounted special central processing unit and based on a Vehicle body bus system and internet service. The IVI can realize a series of applications including three-dimensional navigation, real-time road conditions, IPTV, auxiliary driving, fault detection, vehicle information, vehicle body control, mobile office, wireless communication, online-based entertainment functions, TSP (short message service) service and the like, and greatly improves the vehicle electronization, networking and intelligentization levels;
(3) the vehicle background terminal IOV (Internet Of vehicles) is one type Of vehicle networking equipment, vehicle-mounted equipment on a vehicle effectively utilizes dynamic information Of all vehicles in an information network platform through a wireless communication technology, different functional services are provided during vehicle operation, the vehicle background terminal can provide guarantee for the distance between the vehicles, reduce the probability Of vehicle collision accidents, help vehicle owners to navigate in real time, and improve the efficiency Of traffic operation through communication with other vehicles and network systems;
(4) TBOX (telematics BOX) is used as a wireless gateway, and provides a remote communication interface for the whole vehicle through functions of 4G/5G remote wireless communication, GPS satellite positioning, acceleration sensor, CAN communication and the like, and services including vehicle data acquisition, vehicle track recording, vehicle fault monitoring, vehicle remote inquiry and control (locking and unlocking, air conditioning control, vehicle window control, transmitter torque limitation, engine starting and stopping), driving behavior analysis, hotspot sharing and the like are provided.
The application provides a monitoring system of net car booking action utilizes peculiar mobile unit configuration and specific target detection algorithm real-time supervision net car booking in passenger's number, for the condition such as bus is private, the vehicle overloads, the passenger loses article, and according to on-vehicle information entertainment equipment IVI, acquire order state information, whether have net car booking to brush the line for according to order state information and further definite one-tenth of the interior number of people of car, further standardizes net car booking operation order, improves user experience.
The system is specifically shown in fig. 1, and includes the following devices: as an optional implementation, the system also comprises a DVR intelligent double-recording acquisition terminal 101, an IVI vehicle-mounted information entertainment device 102, an AI-BOX artificial intelligence perception terminal 103 and an IOV vehicle background terminal 104, and as an optional implementation, the system also comprises a T-BOX intelligent remote control terminal 105;
the DVR intelligent double-recording acquisition terminal 101 comprises a vehicle-mounted end built-in camera for shooting the driving and taking situation in a vehicle, the AI-BOX artificial intelligence sensing terminal 103 is used for processing images and videos sent by the vehicle-mounted end built-in camera, judging the number of passengers in the vehicle, acquiring the vehicle travel order situation from the IVI vehicle-mounted information entertainment device 102, determining whether overload behavior and bus private behavior exist according to the vehicle travel order situation and the number of passengers in the vehicle, and further acquiring order state information from the IVI vehicle-mounted information entertainment device 102 when judging that the current vehicle has the suspected behavior of refreshing orders, and the method comprises the following steps: the IOV vehicle background terminal 104 is used for receiving a monitoring result of the irregular driving behavior obtained by the overload, the billing and the private behavior of the bus determined by the AI-BOX artificial intelligent sensing terminal 103 by combining the order, the number of passengers in the vehicle and the like, and storing the monitoring area image of the irregular driving behavior and the order information. The DVR intelligent double-recording acquisition terminal 101, the IVI vehicle-mounted information entertainment equipment 102, the AI-BOX artificial intelligence perception terminal 103 and the IOV vehicle background terminal 104 can be integrated in the T-BOX intelligent remote control terminal 105, or can be distributed in different positions of the vehicle to carry out data connection through a network;
after the vehicle is started, shooting the internal information of the vehicle through a built-in camera of a vehicle-mounted end in the DVR, acquiring a monitoring area image, wherein the monitoring area image mainly comprises a main driving area image, a secondary driving area image and a gap area image between seats, and determining the number of passengers in a trip according to the target number of each area.
Example 1
The invention provides a method for monitoring network car booking behaviors, which comprises the following steps as shown in figure 2:
step S201, acquiring a monitoring image shot by a camera in a vehicle-mounted end;
the vehicle-mounted end built-in camera of the network car is used for shooting the images in the car, for example, the vehicle-mounted end built-in camera of the network car is usually installed at the position of the center of a windshield of the car, and the effect of shooting various information coverage in the car by the camera at the position is better.
Step S202, determining the number of travel passengers by using a target detection algorithm for the monitoring image, and acquiring order state information, wherein the order state information comprises whether a travel order exists at present;
the AI-BOX artificial intelligence perception terminal receives a vehicle interior image shot by a vehicle-mounted end built-in camera, as an optional implementation mode, a monitoring image shot by the vehicle-mounted end built-in camera can be divided into a plurality of areas according to area division configuration information so as to improve the effect of shooting passengers in the vehicle, for example, the monitoring image shot by the vehicle-mounted end built-in camera is divided into a first image area without a shielding object and a second image area with the shielding object outside the first image area, the number of the passengers in the vehicle is determined according to the monitoring image, so that the shot area to which a driver belongs can be filtered from the first image area, and different areas can be divided according to the arrangement position of the camera, the focal length of the camera, the arrangement in the vehicle and the like according to the mode of dividing the image areas; the first image area refers to an area which can be completely shot by a built-in camera at the vehicle-mounted end, the second image area is an area which cannot completely shot the rear row of the vehicle with the shielding due to the shielding of the vehicle seat, and the detection accuracy can be improved by using different algorithms for different detection areas;
as an optional implementation manner, global face detection is performed on the first image region, the method for global face detection may employ a deep neural network to perform face detection, determine the number of targets existing in the first image region, and determine the number of passengers in the first region according to the number of targets existing in the first image region;
since the number of passengers in the vehicle is required to exclude the face of the driver, the position of the driver is not detected in the first image area, or the face characteristics of the driver are stored in the face detection algorithm in advance, so that when the driver is detected by the global face, the face information of the driver is not mistakenly judged as the target in the first image area.
For the second image area with the shelter, the second image area can be divided into a plurality of target detection areas, specifically, each area is divided according to the default passenger seating area behind the shelter, for example, the vehicle is a vehicle accommodating five persons at most, the rear row area is divided into 3 parts on average, each sheltered part with seat shelter is defined as a target detection area, and the specific dividing mode is not limited to the method provided by the embodiment;
carrying out local face detection on a target detection area and extracting local face probability, and determining whether a target exists in the target detection area or not through the local face probability; detecting the human body posture of the target detection area and extracting the human body posture probability, and determining whether a target exists in the target detection area or not according to the human body posture probability; the moving target detection is carried out on the target detection area and the probability of the moving target is determined, whether the moving target exists in the target detection area can be determined through the probability of the moving target, the characteristic description of the whole target can be further enriched through the determination of the moving target, and the accuracy of the local face probability and the human body posture detection on the target detection probability is enhanced;
judging whether a target exists in the target detection area or not according to the local human face characteristic and local human face probability of the target detection area, the human body posture characteristic and the regional change characteristic moving target probability, summarizing target detection results of all the target detection areas, and determining the number of passengers in the vehicle in the second image area;
as an optional second image region determining manner, a local face probability, a human body posture probability and a moving target probability of a target detection region may be input into a target detection model to obtain a target existence probability, when the target existence probability is greater than a probability threshold, it is determined that a target exists in the target detection region, the target detection model is obtained by taking the local face probability, the human body posture probability and the moving target probability of an image for marking whether the target exists as input, and performing network model training with the output target existence probability as a target, and the network model includes a regressor; inputting local face features, human body posture features and regional change features of target detection regions into a target detection model, and determining the target quantity of each target detection region, wherein the target detection model is obtained by taking the local face features, the human body posture features and the regional change features as input and taking the target condition of an image corresponding to the output features as a target to perform network model training, and the network model comprises a regressor;
and determining the number of passengers in the second image area according to the number of the targets in each target detection area, and determining the number of passengers going out according to the number of the passengers in the first image area and the number of the passengers in the second image area.
The AI-BOX artificial intelligence perception terminal obtains order state information from the IVI vehicle-mounted information entertainment equipment, wherein the order state information comprises whether a travel order exists at present, specifically, the order state information is the order information about the coming or going of the network taxi appointment, and also comprises driver information, a travel order number, a vehicle traveling route and the like.
Step S203, determining whether a monitoring result of irregular driving behaviors exists according to the number of the trip passengers and the order state information.
Determining whether a monitoring result of irregular driving behavior exists according to the number of the passengers on the trip and the order state information, wherein the monitoring result comprises at least one of the following steps:
if the number of the trip passengers is larger than the maximum number of passengers carried by the vehicle-mounted end and an order currently exists, determining that the abnormal driving with suspected overload exists;
specifically, when the number of passengers traveling is about the maximum number of passengers (including no driver) of the vehicle and the order information about going out or traveling currently exists, it is determined that the abnormal driving suspected of being overloaded exists, and the monitored area image of the abnormal driving behavior suspected of being overloaded and the order information are stored in the IOV vehicle background terminal.
If the number of the travel passengers is larger than 0 and no travel order exists at present, determining that the non-standard driving behavior of private use of the bus exists;
specifically, when a travel passenger exists in the network vehicle and order information about going to be or going out does not exist at present, it is determined that an irregular driving behavior for private use of the bus exists, and the monitoring area image of the irregular driving behavior for private use of the bus and the order information are stored in the IOV vehicle background terminal.
And if the number of the trip passengers is 0 and a trip order currently exists, determining whether the abnormal driving behavior suspected of scrubbing the order exists or not by combining at least one of monitoring images, car door opening and closing information, trip time related information and trip position related information at different moments collected before the trip order is finished.
The monitoring images at different moments can include: acquiring monitoring images at any time point between starting and ending of a travel order, determining a foreground area between the monitoring images by using a frame difference method according to image differences between the monitoring images so as to better determine the number of changed pixel points, and calculating first characteristic data according to the proportion of the changed pixel points to total pixel points in the total monitoring images;
the door opening and closing information can be obtained by detecting the opening and closing times and the opening and closing duration of a door by a door sensor of the vehicle or detecting the opening and closing state of the door by a camera device outside the vehicle;
the travel time related information includes: after a passenger issues a travel order, the driver receives time information of the order, the time information when the driver confirms that the passenger receives the order and the time information when the passenger confirms that the passenger finishes getting off the order, wherein the time information is acquired in a mode that the time information of each moment of the order is determined by acquiring the time of equipment of a current operation network appointment platform APP from the IVI vehicle-mounted information entertainment equipment;
the travel location related information includes: after the passenger issues the travel order, the driver receives the position information of the order, the position information when the driver confirms that the passenger receives the order, and the position information when the passenger confirms that the passenger finishes getting off the vehicle, wherein the position information can be obtained in a mode that the position information at each moment of the order is determined by obtaining the GPS position information of the equipment of the current operation network appointment platform APP from the IVI vehicle-mounted information entertainment equipment, or the GPS positioning position information of the current vehicle is obtained from the T-BOX intelligent remote control terminal, the specific positioning mode is not limited too much, and the detailed description is omitted.
Specifically, when no trip passenger exists in the network vehicle and the order information of the vehicle in trip exists, mapping at least one of the monitoring images, the door opening and closing information, the trip time related information and the trip position related information at different moments into corresponding first characteristic data, second characteristic data, third characteristic data and fourth characteristic data according to corresponding rules;
and according to the first characteristic data and at least one of the second characteristic data, the third characteristic data and the fourth characteristic data, making a decision to obtain the probability of the suspected bill brushing.
The decision of the data refers to that whether the non-standard behavior of the suspected bill swiping exists is judged by inputting a specific training model or a classification prediction algorithm according to the various types of feature data, for example, a regressor model is trained through relevant information of the bill swiping order, different weight values of the various types of feature data are given to the regressor model, the various types of feature data are input into the trained model, the probability of the suspected bill swiping obtained by weighting and summing the various types of feature data through the model is compared with a bill swiping probability threshold value, and whether the bill swiping behavior exists is determined.
As an optional implementation manner, mapping the monitored image to corresponding first feature data according to a corresponding rule includes:
determining the proportion of the changed pixel points to the total pixel points in the monitoring image according to the monitoring image at the order receiving moment and the monitoring image at the time of confirming the getting-on moment, and determining the proportion of the changed pixel points to the total pixel points in the monitoring image according to the monitoring image at the time of confirming the getting-on moment and the monitoring image at the time of finishing the order, so as to determine the first characteristic data.
The method comprises the steps that the changed pixel points are determined through a foreground area of a monitoring image, a frame difference method is a method for carrying out difference operation on two continuous frames of images of a video image to obtain a moving target contour, through obtaining two adjacent frames of images, when abnormal target movement occurs in a target detection area, a relatively obvious difference can occur between the two adjacent frames of images, the difference position is the foreground area, and the number of the changed pixel points is determined in the difference position;
the changed pixel points are determined according to the monitoring image foreground area extracted by the frame difference method, specifically, the changed pixel points account for the proportion of the total pixel points in the monitoring image, and the calculation steps are as follows:
wherein SDiff (i, j) is a variation score difference value obtained at a certain position (i, j) among the monitoring images, the position (i, j) can be any pixel point in the monitoring images, TH1 is a set threshold value, when the score difference value is larger than TH1, the score difference value of the pixel point is recorded as 1, otherwise, the score difference value is recorded as 0, Rows and Cols are the height and width of a target monitoring area in the vehicle,representing the number of changed pixel points in the monitoring image, area (SDiff) is the pixel area size of the monitoring image, F is the proportion of the pixel points in the monitoring image change to the total pixel points in the monitoring image, the position of a cab can be eliminated in the processing process, and the proportion of the pixel points of the monitoring image at the order receiving moment and the monitoring image change at the time of confirming the getting-on moment to the total pixel points in the monitoring image and the proportion of the pixel points of the monitoring image change at the time of confirming the getting-on moment and the monitoring image change at the order ending moment to the total pixel points in the monitoring image are respectively calculated to determine first characteristic data;
as an optional implementation manner, mapping the door opening and closing information to corresponding second feature data according to a corresponding rule includes:
and determining the door opening and closing times according to the door opening and closing information, and mapping the comparison result of the door opening and closing times and a plurality of times threshold values to be second characteristic data.
The opening and closing times of the vehicle doors are determined by detection sensors which are arranged in the vehicle doors, the sensors can be pressure sensors or electric contact sensors, information such as the opening and closing times of the vehicle doors is determined according to the change times of the measurement data of the sensors between the order taking and the stroke ending, or the opening and closing states of the vehicle doors are detected in real time through a camera device outside the vehicle, so that the information such as the opening and closing times of the vehicle doors is determined.
The method comprises the steps of obtaining the number of times of opening and closing the door in the process from the online taxi appointment driving order to the end of the travel from the IVI vehicle-mounted infotainment device, comparing the number of times of opening and closing the door with a plurality of times threshold values, and determining second characteristic data according to the number threshold value interval where the number of times of opening and closing the door is located and the number threshold value interval where the comparison result is located.
As an optional implementation manner, mapping the travel time related information to corresponding third feature data according to a corresponding rule includes:
determining order receiving time, boarding time confirmation and order ending time of a travel order according to travel time related information, and determining a first time difference T by using the order receiving time and the boarding time confirmation1Determining a second time difference T using the time of arrival confirmation and the time of order completion2;
Determining the mean value of the first time difference of the network car booking platform according to order receiving time, boarding time confirmation and order ending time in different travel orders acquired by the network car booking platformAnd the variance value sigma1And determining the mean value of the second time differenceAnd the variance value sigma2;
According to a first time difference T1Mean value of first time differenceVariance value sigma1Preset weight w0And deviation b0Determining a first time difference processing resultAccording to the second time difference T2Mean value of the second time differenceVariance value sigma2Preset weight w0And deviation b0Determining a second time difference processing result
And determining third characteristic data according to the first time difference processing result and the second time difference processing result.
As an optional implementation manner, mapping the travel position related information to corresponding fourth feature data according to a corresponding rule includes:
determining a pick-up position, a confirmed boarding position and an order ending position of a trip order according to the travel position related information, determining a first distance difference by using the pick-up position and the confirmed boarding position through a Manhattan distance formula, and determining a second distance difference by using the confirmed boarding position and the order ending position through the Manhattan distance formula;
and respectively comparing the first distance difference and the second distance difference of the travel order with a plurality of distance thresholds, then carrying out quantization processing, and determining fourth characteristic data according to the quantization results of the first distance difference and the second distance difference.
Calculating a difference value between an order receiving position of a travel order and a confirmed boarding position as a first distance difference, and calculating a difference value between the confirmed boarding position and an order ending position as a second distance difference, wherein the calculating steps are as follows:
MD=|SPos2.x-SPos1.x|+|SPos2.y-SPos1.y|
F=Quant(MD(SPos2,Spos1))
the MD is a Manhattan distance calculation formula, the Quant function is a distance quantization function, the first distance difference and the second distance difference are compared with a plurality of distance threshold values by combining order travel data collected from the platform, and different feature quantization values corresponding to the first distance difference and the second distance difference are mapped into fourth feature data according to a distance threshold interval in which the first distance difference and the second distance difference are located.
As an optional implementation manner, the making a decision according to the first feature data and at least one of the second feature data, the third feature data, and the fourth feature data to obtain the probability of the suspected scrub sheet includes:
and inputting the first characteristic data and at least one of the second characteristic data, the third characteristic data and the fourth characteristic data into a decision model to obtain the probability of the existence of the suspected bill swiping, wherein the decision model takes the first characteristic data, the second characteristic data, the third characteristic data and the fourth characteristic data which are marked as whether the single swiping line exists as input, and takes the output mark as a target to train the network model so as to obtain the result.
The network model is a regressor, and the decision model is a decision model obtained by taking at least one of first characteristic data, second characteristic data, third characteristic data and fourth characteristic data which are determined by monitoring images, door opening and closing information, travel time related information and travel position related information at different moments in a travel order with/without a billing behavior collected from a network appointment scene as input and performing network model training by taking output marks as targets;
the method for monitoring the network car booking behaviors can monitor the behaviors of a driver such as order brushing, bus use, overload and the like, and restricts and standardizes the network car booking market by using a relevant reward and punishment system, so that the safety of drivers and passengers is guaranteed and the service of the network car booking is improved.
The embodiment of the invention provides a complete flow chart of a monitoring method for a network taxi appointment behavior, which comprises the following steps as shown in fig. 3:
step S301, acquiring a monitoring image shot by a camera in the vehicle-mounted end;
step S302, determining the number of travel passengers by using a target detection algorithm for the monitoring image, and acquiring order state information, wherein the order state information comprises whether a travel order exists at present;
step S303, if the number of the trip passengers is larger than the maximum number of passengers carried by the vehicle-mounted terminal and an order currently exists, executing step S304, if the number of the trip passengers is larger than 0 and no trip order currently exists, executing step S305, and if the number of the trip passengers is 0 and a trip order currently exists, executing step S306;
step S304, determining that the abnormal driving behavior suspected of overload exists, and storing the monitoring area image and the order information of the abnormal driving behavior in the IOV vehicle background terminal;
step S305, determining that the abnormal driving behavior private to the bus exists, and storing the monitoring area image and the order information of the abnormal driving behavior in the IOV vehicle background terminal;
step S306, mapping at least one of the monitoring images, the door opening and closing information, the travel time related information and the travel position related information at different moments into corresponding first feature data, second feature data, third feature data and fourth feature data according to corresponding rules;
step S307, according to the first characteristic data and at least one of the second characteristic data, the third characteristic data and the fourth characteristic data, making a decision to obtain the probability of suspected bill brushing;
step S308, comparing the probability of suspected billing with a probability threshold value, determining that the unnormalized driving behavior of billing exists, and storing the monitoring area image and the order information of the unnormalized driving behavior in the background terminal of the IOV vehicle;
and step S309, sending the relevant information of the irregular driving behavior to the T-BOX intelligent remote control terminal.
As shown in fig. 4, the device 400 may generate a large difference due to different configurations or performances, and may include one or more processors (CPU) 401 (e.g., one or more processors), a memory 402, and one or more storage media 403 (e.g., one or more mass storage devices) for storing applications 404 or data 406. Memory 402 and storage medium 403 may be, among other things, transient storage or persistent storage. The program stored in the storage medium 403 may include one or more modules (not shown), and each module may include a series of instruction operations in the information processing apparatus. Further, the processor 401 may be configured to communicate with the storage medium 403 to execute a series of instruction operations in the storage medium 403 on the device 400.
The device 400 may also include one or more power supplies 409, one or more wired or wireless network interfaces 407, one or more input-output interfaces 408, and/or one or more operating systems 405, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc.
The device is used for realizing the following method:
acquiring a monitoring image shot by a camera in the vehicle-mounted end;
determining the number of travel passengers by using a target detection algorithm for the monitoring image, and acquiring order state information, wherein the order state information comprises whether a travel order exists at present;
and determining whether a monitoring result of the irregular driving behavior exists or not according to the number of the passengers on the trip and the order state information.
Optionally, the processor is configured to determine whether there is a monitoring result of irregular driving behavior according to the number of passengers on the trip and the order status information, and includes at least one of the following steps:
if the number of the trip passengers is larger than the maximum number of passengers carried by the vehicle-mounted terminal and an order currently exists, determining that the abnormal driving behavior suspected of overload exists;
if the number of the travel passengers is larger than 0 and no travel order exists at present, determining that the non-standard driving behavior of private use of the bus exists;
and if the number of the trip passengers is 0 and a trip order currently exists, determining whether the abnormal driving behavior suspected of scrubbing the order exists or not by combining at least one of monitoring images, car door opening and closing information, trip time related information and trip position related information at different moments collected before the trip order is finished.
Optionally, the processor is configured to determine whether there is an irregular driving behavior of suspected billing, including:
mapping at least one of the monitoring images, the car door opening and closing information, the travel time related information and the travel position related information at different moments into corresponding first feature data, second feature data, third feature data and fourth feature data according to corresponding rules;
and according to the first characteristic data and at least one of the second characteristic data, the third characteristic data and the fourth characteristic data, making a decision to obtain the probability of the suspected bill brushing.
Optionally, the processor is configured to make a decision according to the first feature data and at least one of the second feature data, the third feature data, and the fourth feature data to obtain the probability of the suspected scrub sheet, including:
and inputting the first characteristic data and at least one of the second characteristic data, the third characteristic data and the fourth characteristic data into a decision model to obtain the probability of existence of the suspected bill-brushing, wherein the decision model is obtained by taking the first characteristic data, the second characteristic data, the third characteristic data and the fourth characteristic data which are marked as whether a single-brushing line exists as input and taking output marks as targets to train a network model to obtain the probability of existence of the bill-brushing.
Optionally, the processor is configured to map the monitored images to corresponding first feature data according to a corresponding rule, and includes:
determining the proportion of the changed pixel points to the total pixel points in the monitoring image according to the monitoring image at the order receiving moment and the monitoring image at the time of confirming the getting-on moment, and determining the proportion of the changed pixel points to the total pixel points in the monitoring image according to the monitoring image at the time of confirming the getting-on moment and the monitoring image at the time of finishing the order, so as to determine the first characteristic data.
Optionally, the processor is configured to map the vehicle door opening and closing information to corresponding second feature data according to a corresponding rule, and includes:
and determining the door opening and closing times according to the door opening and closing information, and mapping the comparison result of the door opening and closing times and a plurality of times threshold values to be second characteristic data.
Optionally, the processor is configured to map the travel time related information into corresponding third feature data according to a corresponding rule, and includes:
determining order receiving time, boarding confirmation time and order ending time of a travel order according to travel time related information, and determining a first time difference T by using the order receiving time and the boarding confirmation time1Determining a second time difference T using the time of arrival confirmation and the time of order completion2;
Determining the mean value of the first time difference of the network car booking platform according to the order receiving time, the confirmed getting-on time and the order ending time in different travel orders collected by the network car booking platformAnd the variance value sigma1And determining the mean value of the second time differenceAnd the variance value sigma2;
According to a first time difference T1Mean value of first time differenceVariance value sigma1Preset weight w0And deviation b0Determining a first time difference processing resultAccording to the second time difference T2Mean value of the second time differenceVariance value sigma2Preset weight w0And deviation b0Determining a second time difference processing result
And determining third characteristic data according to the first time difference processing result and the second time difference processing result.
Optionally, the processor is configured to map the travel position related information into corresponding fourth feature data according to a corresponding rule, and the mapping includes:
determining a pick-up position, a confirmed boarding position and an order ending position of a trip order according to the travel position related information, determining a first distance difference by using the pick-up position and the confirmed boarding position through a Manhattan distance formula, and determining a second distance difference by using the confirmed boarding position and the order ending position through the Manhattan distance formula;
and respectively comparing the first distance difference and the second distance difference of the travel order with a plurality of distance thresholds, then carrying out quantization processing, and determining fourth characteristic data according to the quantization results of the first distance difference and the second distance difference.
The embodiment of the invention provides a monitoring device for network taxi appointment behaviors, which comprises the following modules as shown in fig. 5:
a monitoring image acquisition module 501, configured to acquire a monitoring image captured by a camera in the vehicle-mounted terminal;
a passenger number determining module 502, configured to determine the number of traveling passengers by using a target detection algorithm for the monitoring image, and acquire order state information, where the order state information includes whether a traveling order exists currently;
a monitoring result determining module 503, configured to determine whether there is a monitoring result of irregular driving behavior according to the number of passengers on the trip and the order state information.
Optionally, the monitoring result determining module 503 is configured to determine whether there is a monitoring result of irregular driving behavior according to the number of passengers on the trip and the order status information, and includes at least one of the following steps:
if the number of the trip passengers is larger than the maximum number of passengers carried by the vehicle-mounted terminal and an order currently exists, determining that the abnormal driving behavior suspected of overload exists;
if the number of the travel passengers is larger than 0 and no travel order exists at present, determining that the non-standard driving behavior of private use of the bus exists;
and if the number of the trip passengers is 0 and a trip order currently exists, determining whether the abnormal driving behavior suspected of scrubbing the order exists or not by combining at least one of monitoring images, car door opening and closing information, trip time related information and trip position related information at different moments collected before the trip order is finished.
Optionally, the monitoring result determining module 503 is configured to determine whether the abnormal driving behavior of the suspected scrub list exists, and includes:
mapping at least one of the monitoring images, the car door opening and closing information, the travel time related information and the travel position related information at different moments into corresponding first feature data, second feature data, third feature data and fourth feature data according to corresponding rules;
and according to the first characteristic data and at least one of the second characteristic data, the third characteristic data and the fourth characteristic data, making a decision to obtain the probability of the suspected bill brushing.
Optionally, the monitoring result determining module 503 is configured to make a decision according to the first feature data and at least one of the second feature data, the third feature data, and the fourth feature data to obtain the probability of the suspected billing existence, and includes:
and inputting at least one of the first characteristic data, the second characteristic data, the third characteristic data and the fourth characteristic data into a decision model to obtain the probability of the existence of the suspected bill swiping, wherein the decision model takes the first characteristic data, the second characteristic data, the third characteristic data and the fourth characteristic data which are marked as whether the single swiping line exists as input, and takes the output mark as a target to train the network model so as to obtain the result.
Optionally, the monitoring result determining module 503 is configured to map the monitored image into corresponding first feature data according to a corresponding rule, and includes:
determining the proportion of the changed pixel points to the total pixel points in the monitoring image according to the monitoring image at the order receiving moment and the monitoring image at the time of confirming the getting-on moment, and determining the proportion of the changed pixel points to the total pixel points in the monitoring image according to the monitoring image at the time of confirming the getting-on moment and the monitoring image at the time of finishing the order, so as to determine the first characteristic data.
Optionally, the monitoring result determining module 503 is configured to map the vehicle door opening and closing information into corresponding second feature data according to a corresponding rule, and includes:
and determining the door opening and closing times according to the door opening and closing information, and mapping the comparison result of the door opening and closing times and a plurality of times threshold values to be second characteristic data.
Optionally, the monitoring result determining module 503 is configured to map the travel time related information into corresponding third feature data according to a corresponding rule, and includes:
determining order receiving time, boarding confirmation time and order ending time of a travel order according to travel time related information, and determining a first time difference T by using the order receiving time and the boarding confirmation time1Determining a second time difference T using the time of arrival confirmation and the time of order completion2;
Determining the mean value of the first time difference of the network car booking platform according to the order receiving time, the confirmed getting-on time and the order ending time in different travel orders collected by the network car booking platformAnd the variance value sigma1And determining the mean value of the second time differenceAnd the variance value sigma2;
According to a first time difference T1Mean value of first time differenceVariance value sigma1Preset weight w0And deviation b0Determining a first time difference processing resultAccording to the second time difference T2Mean value of the second time differenceVariance value sigma2Preset weight w0And deviation b0Determining a second time difference processing result
And determining third characteristic data according to the first time difference processing result and the second time difference processing result.
Optionally, the monitoring result determining module 503 is configured to map the travel position related information into corresponding fourth feature data according to a corresponding rule, and includes:
determining a pick-up position, a confirmed boarding position and an order ending position of a trip order according to the travel position related information, determining a first distance difference by using the pick-up position and the confirmed boarding position through a Manhattan distance formula, and determining a second distance difference by using the confirmed boarding position and the order ending position through the Manhattan distance formula;
and respectively comparing the first distance difference and the second distance difference of the travel order with a plurality of distance thresholds, then carrying out quantization processing, and determining fourth characteristic data according to the quantization results of the first distance difference and the second distance difference.
An embodiment of the present invention provides a computer medium, where the computer-readable storage medium stores computer instructions, and the computer instructions, when executed by a processor, implement any one of the monitoring methods for network appointment behavior provided in embodiment 1 of the present invention.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (11)
1. A method for monitoring a network appointment behavior, the method comprising:
acquiring a monitoring image shot by a camera in a vehicle-mounted end, wherein the monitoring image comprises a first image area without a shielding object and a second image area with the shielding object;
determining the number of travel passengers by using a target detection algorithm for the monitoring image, and acquiring order state information, wherein the order state information comprises whether a travel order exists at present;
determining whether a monitoring result of irregular driving behaviors exists or not according to the number of the travel passengers and the order state information;
the method for determining the number of passengers in a trip by using the target detection algorithm on the monitoring image comprises the following steps:
based on a deep neural network, carrying out global face detection on the first image area, determining the number of targets existing in the first image area, and determining the number of passengers in the first image area according to the number of the targets, wherein the number of the passengers in the first image area is the number of the passengers excluding the face of the driver;
dividing the second image area into a plurality of target detection areas, determining the local face probability of each target detection area based on local face detection, determining the human posture probability of each target detection area based on human posture detection, determining the moving target probability of each target detection area based on moving target detection, and determining whether a target exists in each target detection area according to the local face probability, the human posture probability and the moving target probability;
summarizing the target detection results of the plurality of target detection areas, and determining the number of passengers in the second image area;
and determining the number of travelling passengers according to the number of passengers in the first image area and the number of passengers in the second image area.
2. The method of claim 1, wherein determining whether there is a monitoring result of irregular driving behavior according to the number of passengers on the trip and order status information comprises at least one of the following steps:
if the number of the trip passengers is larger than the maximum number of passengers carried by the vehicle-mounted terminal and an order currently exists, determining that the abnormal driving behavior suspected of overload exists;
if the number of the travel passengers is larger than 0 and no travel order exists at present, determining that the non-standard driving behavior of the private use of the bus exists;
and if the number of the trip passengers is 0 and a trip order currently exists, determining whether the abnormal driving behavior suspected of scrubbing the order exists or not by combining at least one of monitoring images, car door opening and closing information, trip time related information and trip position related information at different moments collected before the trip order is finished.
3. The method of claim 2, wherein determining whether the non-normative driving behavior suspected of scrubbing the bill is present comprises:
mapping at least one of the monitoring images, the vehicle door opening and closing information, the travel time related information and the travel position related information at different moments into corresponding first characteristic data, second characteristic data, third characteristic data and fourth characteristic data according to corresponding rules;
and making a decision to obtain the probability of the suspected bill brushing according to at least one of the first characteristic data, the second characteristic data, the third characteristic data and the fourth characteristic data.
4. The method of claim 3, wherein the determining the probability of the suspected scrub ticket based on at least one of the first, second, third and fourth characteristics comprises:
and inputting at least one of the first characteristic data, the second characteristic data, the third characteristic data and the fourth characteristic data into a decision model to obtain the probability of the existence of the suspected bill swiping, wherein the decision model takes the first characteristic data, the second characteristic data, the third characteristic data and the fourth characteristic data which are marked as whether the single swiping line exists as input, and takes the output mark as a target to train the network model so as to obtain the result.
5. The method of claim 3, wherein mapping the monitored images to corresponding first feature data according to corresponding rules comprises:
determining the proportion of the changed pixel points to the total pixel points in the monitoring image according to the monitoring image at the order receiving moment and the monitoring image at the time of confirming the getting-on moment, and determining the proportion of the changed pixel points to the total pixel points in the monitoring image according to the monitoring image at the time of confirming the getting-on moment and the monitoring image at the time of finishing the order, so as to determine the first characteristic data.
6. The method of claim 3, wherein mapping the door opening and closing information to corresponding second characteristic data according to a corresponding rule comprises:
and determining the door opening and closing times according to the door opening and closing information, and mapping the comparison result of the door opening and closing times and a plurality of times threshold values to be second characteristic data.
7. The method according to claim 3, wherein mapping the travel time related information to corresponding third feature data according to a corresponding rule comprises:
determining order receiving time, boarding time confirmation and order ending time of a travel order according to travel time related information, and determining a first time difference T by using the order receiving time and the boarding time confirmation1Determining a second time difference T using the time of arrival confirmation and the time of order completion2;
Determining the mean value of the first time difference of the network car booking platform according to the order receiving time, the confirmed getting-on time and the order ending time in different travel orders collected by the network car booking platformAnd the variance value sigma1And determining the mean value of the second time differenceDifference value sigma2;
According to a first time difference T1Mean value of first time differenceVariance value sigma1Preset weight w0And deviation b0Determining a first time difference processing resultAccording to a second time difference T2Mean value of the second time differenceVariance value sigma2Preset weight w0And deviation b0Determining a second time difference processing result
And determining third characteristic data according to the first time difference processing result and the second time difference processing result.
8. The method according to claim 3, wherein mapping the travel position related information to corresponding fourth feature data according to a corresponding rule comprises:
determining a pick-up position, a confirmed boarding position and an order ending position of a trip order according to the travel position related information, determining a first distance difference by using the pick-up position and the confirmed boarding position through a Manhattan distance formula, and determining a second distance difference by using the confirmed boarding position and the order ending position through the Manhattan distance formula;
and respectively comparing the first distance difference and the second distance difference of the travel order with a plurality of distance thresholds, then carrying out quantization processing, and determining fourth characteristic data according to the quantization results of the first distance difference and the second distance difference.
9. A monitoring device for online taxi appointment behaviors is characterized by comprising a memory, a monitoring module and a control module, wherein the memory is used for storing instructions;
a processor for reading the instructions in the memory to implement the method for monitoring the network appointment behavior according to any one of claims 1 to 8.
10. A monitoring device for network booking behavior is characterized by comprising the following modules:
the monitoring image acquisition module is used for acquiring a monitoring image shot by a camera in the vehicle-mounted end, wherein the monitoring image comprises a first image area without a shielding object and a second image area with the shielding object;
the passenger number determining module is used for determining the number of travelling passengers by using a target detection algorithm for the monitoring image and acquiring order state information, wherein the order state information comprises whether a travelling order exists at present;
the monitoring result determining module is used for determining whether a monitoring result of irregular driving behavior exists according to the number of the trip passengers and the order state information;
the method for determining the number of passengers in a trip by using the target detection algorithm on the monitoring image comprises the following steps:
based on a deep neural network, carrying out global face detection on the first image area, determining the number of targets existing in the first image area, and determining the number of passengers in the first image area according to the number of the targets, wherein the number of the passengers in the first image area is the number of the passengers excluding the face of the driver;
dividing the second image area into a plurality of target detection areas, determining the local face probability of each target detection area based on local face detection, determining the human posture probability of each target detection area based on human posture detection, determining the moving target probability of each target detection area based on moving target detection, and determining whether a target exists in each target detection area according to the local face probability, the human posture probability and the moving target probability;
summarizing the target detection results of the plurality of target detection areas, and determining the number of passengers in the second image area;
and determining the number of travelling passengers according to the number of passengers in the first image area and the number of passengers in the second image area.
11. A computer medium, wherein the computer readable storage medium stores computer instructions, and the computer instructions when executed by a processor implement a method for monitoring network appointment behavior according to any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010201689.XA CN111429329B (en) | 2020-03-20 | 2020-03-20 | Method and device for monitoring network car booking behavior |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010201689.XA CN111429329B (en) | 2020-03-20 | 2020-03-20 | Method and device for monitoring network car booking behavior |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111429329A CN111429329A (en) | 2020-07-17 |
CN111429329B true CN111429329B (en) | 2022-06-07 |
Family
ID=71549709
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010201689.XA Active CN111429329B (en) | 2020-03-20 | 2020-03-20 | Method and device for monitoring network car booking behavior |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111429329B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112232259B (en) * | 2020-10-27 | 2022-06-07 | 南京领行科技股份有限公司 | Method, device and equipment for monitoring behaviors of taxi appointment drivers |
CN112926881A (en) * | 2021-03-29 | 2021-06-08 | 广州宸祺出行科技有限公司 | Detection method and system for preventing driver from swiping bill based on vehicle-mounted system |
CN113780854A (en) * | 2021-09-16 | 2021-12-10 | 广州宸祺出行科技有限公司 | Method and device for identifying online taxi booking driver idle running list brushing |
CN114999023A (en) * | 2022-05-25 | 2022-09-02 | 北京畅行信息技术有限公司 | Behavior detection method, behavior detection device, storage medium, and vehicle-mounted terminal |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106960247A (en) * | 2017-03-24 | 2017-07-18 | 中国联合网络通信集团有限公司 | The net about monitoring method of car order, apparatus and system |
CN108717784A (en) * | 2018-05-21 | 2018-10-30 | 杭州优行科技有限公司 | Net about vehicle monitoring and managing method, device and computer readable storage medium |
CN108876522A (en) * | 2018-06-01 | 2018-11-23 | 深圳市零度智控科技有限公司 | Vehicle monitoring method, device and computer readable storage medium |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109146217A (en) * | 2017-06-19 | 2019-01-04 | 北京嘀嘀无限科技发展有限公司 | Safety travel appraisal procedure, device, server, computer readable storage medium |
-
2020
- 2020-03-20 CN CN202010201689.XA patent/CN111429329B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106960247A (en) * | 2017-03-24 | 2017-07-18 | 中国联合网络通信集团有限公司 | The net about monitoring method of car order, apparatus and system |
CN108717784A (en) * | 2018-05-21 | 2018-10-30 | 杭州优行科技有限公司 | Net about vehicle monitoring and managing method, device and computer readable storage medium |
CN108876522A (en) * | 2018-06-01 | 2018-11-23 | 深圳市零度智控科技有限公司 | Vehicle monitoring method, device and computer readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN111429329A (en) | 2020-07-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111429329B (en) | Method and device for monitoring network car booking behavior | |
US11067409B2 (en) | Distributed data processing systems for processing remotely captured sensor data | |
CN111460938B (en) | Vehicle driving behavior real-time monitoring method and device | |
US11361556B2 (en) | Deterioration diagnosis device, deterioration diagnosis system, deterioration diagnosis method, and storage medium for storing program | |
CN104730949A (en) | Affective user interface in an autonomous vehicle | |
KR20140031435A (en) | Diagnostic system and method for the analysis of driving behavior | |
KR20200078274A (en) | Method and system for evaluating safety operation index using vehicle driving information collection device | |
JP7398404B2 (en) | Car sharing management server and computer program | |
CN112700473B (en) | Carriage congestion degree judging system based on image recognition | |
CN116453345A (en) | Bus driving safety early warning method and system based on driving risk feedback | |
KR20220126203A (en) | Control apparatus, system, vehicle, and control method | |
TWI820471B (en) | Vehicle driving risk assessment system | |
CN116894501B (en) | Internet of vehicles (IOT) -based network appointment vehicle management system and method | |
CN115798182B (en) | Intelligent safety management method and system for motorcycle | |
CN111382617B (en) | Driver identification method and device | |
Sukegawa et al. | Estimation of Drivers' Cognitive Load Through Foot Placement Analysis in a Car-Sharing Service | |
JP2024068577A (en) | Traffic control device | |
CN117746329A (en) | Subway passenger getting-off intention recognition method and device | |
CN117010684A (en) | Method for determining passenger flow guiding strategy | |
CN112241688A (en) | Carriage congestion degree detection method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |