CN117746643A - Vehicle abnormal problem identification method, device, medium and electronic equipment - Google Patents

Vehicle abnormal problem identification method, device, medium and electronic equipment Download PDF

Info

Publication number
CN117746643A
CN117746643A CN202311788210.7A CN202311788210A CN117746643A CN 117746643 A CN117746643 A CN 117746643A CN 202311788210 A CN202311788210 A CN 202311788210A CN 117746643 A CN117746643 A CN 117746643A
Authority
CN
China
Prior art keywords
license plate
identification
vehicle type
data set
vehicle
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202311788210.7A
Other languages
Chinese (zh)
Inventor
涂贤明
汤剑
郭庆锋
付平
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tongdun Technology Co ltd
Original Assignee
Tongdun Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tongdun Technology Co ltd filed Critical Tongdun Technology Co ltd
Priority to CN202311788210.7A priority Critical patent/CN117746643A/en
Publication of CN117746643A publication Critical patent/CN117746643A/en
Pending legal-status Critical Current

Links

Landscapes

  • Devices For Checking Fares Or Tickets At Control Points (AREA)
  • Traffic Control Systems (AREA)

Abstract

The method can acquire a corresponding vehicle type identification data set and a historical exit data set aiming at an exit license plate identifier in vehicle exit data, wherein the vehicle type identification data set is obtained based on visual image statistics shot by a vehicle type identifier, and because a vehicle type represented by the visual image is truly and credible, accurate judgment on an actual vehicle type can be realized, whether a target vehicle type corresponding to the actual vehicle type and the exit license plate identifier is matched or not can be further determined, if the target vehicle type is not matched with the exit license plate identifier, the abnormal problem corresponding to the exit license plate identifier can be judged, and compared with the related technology of judging the abnormal problem only through toll gate data and portal data, the method can realize higher abnormal problem judging accuracy in an ETC passing mode.

Description

Vehicle abnormal problem identification method, device, medium and electronic equipment
Technical Field
The present invention relates to the field of computer technology, and in particular, to a vehicle abnormality problem identification method, a vehicle abnormality problem identification device, a computer readable storage medium, and an electronic apparatus.
Background
An electronic toll collection (Electronic Toll Collection, ETC) portal is a modern highway toll collection system, and the aim of stopping vehicles to pay when passing through a toll station is fulfilled by adopting wireless communication and vehicle-mounted equipment technology. Based on the equipment erected on the ETC portal, the information such as license plate numbers, traffic events, traffic places, time stamps, number of traffic flows, traffic lanes and the like can be recorded, so that the real-time traffic of the expressway can be monitored, and the real-time traffic of the expressway can provide assistance for the early warning of the congestion of the expressway.
However, some malicious behaviors or technical errors cause problems in the related art, such as that an actual passing vehicle type is larger than a toll station transaction vehicle type, i.e., a cart-to-cart sign. This can result in the actual payment of the vehicle as it passes through the toll booth being lower than it should. For this problem, the existing solutions are: data acquired by toll station equipment and portal data are acquired, and whether an abnormal problem exists in a vehicle at the station is judged based on the data.
However, when a vehicle realizing automatic payment passing based on the ETC technology passes through a toll gate, the acquired data is registered data, and the registered data may be inaccurate based on subjective maliciousness, and meanwhile, portal data can only acquire information such as license plate numbers. Therefore, it is difficult to accurately determine the abnormality by only portal data. Along with the continuous popularization of ETC technology, an automatic payment passing mode is more and more widely applied, so how to accurately judge the abnormal problem of vehicles passing through the ETC mode becomes the problem to be solved currently.
It should be noted that the information disclosed in the foregoing background section is only for enhancing understanding of the background of the present application and thus may include information that does not form an existing solution known to those of ordinary skill in the art.
Disclosure of Invention
The invention aims to provide a vehicle abnormal problem identification method, a vehicle abnormal problem identification device, a computer readable storage medium and electronic equipment, corresponding vehicle type identification data sets and historical exit data sets can be acquired aiming at exit license plate identifications in vehicle exit data, wherein the vehicle type identification data sets are obtained based on visual image statistics shot by a vehicle type identifier, and because the visual image represents real and reliable vehicle types, accurate judgment of actual vehicle types can be realized, whether target vehicle types corresponding to the exit license plate identifications are matched or not can be determined, if the target vehicle types corresponding to the exit license plate identifications are not matched, abnormal problems corresponding to the exit license plate identifications can be determined, and compared with the related technology of judging the abnormal problems only through toll gate data and portal data, the method and the device are applicable to the abnormal problem judgment based on the vehicle type identification data sets and the historical exit data sets, can be applicable to the abnormal problem judgment of ETC traffic modes with high accuracy, and simultaneously can also be applicable to non-ETC traffic modes.
Other features and advantages of the present application will be apparent from the following detailed description, or may be learned in part by the practice of the application.
According to an aspect of the present application, there is provided a vehicle abnormality problem identification method, the method including:
responding to the detected vehicle exit data, and extracting an exit license plate identifier in the vehicle exit data;
determining an actual vehicle model corresponding to the export license plate identifier according to the vehicle model identification data set and the historical export data set corresponding to the export license plate identifier; the vehicle type recognition data set is obtained by statistics based on the recognition result of the visualized vehicle type recognizer;
if the actual vehicle type is not matched with the target vehicle type corresponding to the export license plate identifier, judging that the abnormal problem corresponding to the export license plate identifier exists.
In an exemplary embodiment of the present application, further comprising:
if the actual vehicle model is larger than the target vehicle model, judging that the actual vehicle model is not matched with the target vehicle model;
and, the anomaly problem includes a cart logo problem, determining that there is an anomaly problem corresponding to the exit license plate identification, including:
and judging that the large car logo and the small car logo corresponding to the export license plate identification exist.
In an exemplary embodiment of the present application, further comprising:
Fuzzy matching is carried out on the export license plate identification and the license plate identification in the card, so as to obtain a first matching result;
fuzzy matching is carried out on the export license plate identification and the identification license plate identification, and a second matching result is obtained;
if the first matching result and/or the second matching result represents successful matching, a vehicle type identification data set and a historical export data set corresponding to the export license plate identification are obtained.
In an exemplary embodiment of the present application, further comprising:
determining license plate identification in the card based on portal data acquired by portal equipment;
and determining and identifying the license plate identification based on the identification result of the vehicle type identifier.
In an exemplary embodiment of the present application, performing fuzzy matching on the exit license plate identifier and the license plate identifier in the card to obtain a first matching result, including:
converting the export license plate identifier into a first characteristic vector and converting the license plate identifier in the card into a second characteristic vector;
calculating cosine similarity of the first feature vector and the second feature vector based on a cosine similarity algorithm, and taking the cosine similarity as a first matching result;
and performing fuzzy matching on the export license plate identifier and the identification license plate identifier to obtain a second matching result, wherein the fuzzy matching comprises the following steps:
converting the identification license plate identifier into a third feature vector;
And calculating cosine similarity of the first feature vector and the third feature vector based on a cosine similarity algorithm, and taking the cosine similarity as a second matching result.
In an exemplary embodiment of the present application, further comprising:
data cleaning is carried out on the vehicle outlet data based on a preset cleaning rule; the preset cleaning rules are used for limiting judging conditions of illegal outlet data.
In an exemplary embodiment of the present application, further comprising:
determining a current single travel time range based on the outbound time and the inbound time corresponding to the exit license plate identification;
acquiring a vehicle type identification data set corresponding to the exit license plate identification in the current single travel time range;
and acquiring a historical export data set corresponding to the export license plate identifier within a specified historical time range.
In an exemplary embodiment of the present application, in a case where each data in the historical export data set corresponds to an automatic payment traffic mode, determining an actual vehicle model corresponding to the export license plate identifier according to the vehicle model identification data set corresponding to the export license plate identifier and the historical export data set includes:
calculating travel frequencies corresponding to all vehicle types in the vehicle type identification data set;
and determining the vehicle type corresponding to the highest travel frequency in the travel frequencies as the actual vehicle type corresponding to the exit license plate identifier.
In an exemplary embodiment of the present application, determining, in a case where each data in the historical egress data set corresponds to an automatic payment traffic mode and a non-automatic payment traffic mode, and in a case where each data in the historical egress data set corresponds to a non-automatic payment traffic mode, an actual vehicle model corresponding to the egress license plate identifier according to the vehicle model identification data set corresponding to the egress license plate identifier and the historical egress data set, includes:
extracting a specific historical data set corresponding to a non-automatic payment passing mode from the historical export data set, and calculating a class of trip frequency corresponding to each vehicle type in the specific historical data set;
calculating a class II trip frequency corresponding to each vehicle type in the vehicle type identification data set;
fusing one class of travel frequencies and two classes of travel frequencies of the same vehicle type into a target travel frequency to obtain target travel frequencies corresponding to all vehicle types;
and determining the vehicle type corresponding to the highest travel frequency in the target travel frequencies as the actual vehicle type corresponding to the exit license plate identifier.
In an exemplary embodiment of the present application, further comprising:
and updating the vehicle type identification data set and the historical export data set in response to the data continuously collected by the portal device, the vehicle type identifier and the toll station device.
According to an aspect of the present application, there is provided a vehicle abnormality recognition apparatus including:
the exit license plate identification determining unit is used for responding to the detected vehicle exit data and extracting an exit license plate identification in the vehicle exit data;
the actual vehicle type determining unit is used for determining an actual vehicle type corresponding to the export license plate identifier according to the vehicle type identification data set corresponding to the export license plate identifier and the historical export data set; the vehicle type recognition data set is obtained by statistics based on the recognition result of the visualized vehicle type recognizer;
the abnormal problem identification unit is used for judging that the abnormal problem corresponding to the export license plate identifier exists under the condition that the actual vehicle type is not matched with the target vehicle type corresponding to the export license plate identifier.
In an exemplary embodiment of the present application, further comprising:
the mismatch condition judging unit is used for judging that the actual vehicle type is not matched with the target vehicle type when the actual vehicle type is larger than the target vehicle type;
and, the abnormality problem includes a cart-to-cart-label problem, the abnormality problem identification unit determining that there is an abnormality problem corresponding to the exit license plate identification, including:
and judging that the large car logo and the small car logo corresponding to the export license plate identification exist.
In an exemplary embodiment of the present application, further comprising:
the fuzzy matching unit is used for performing fuzzy matching on the export license plate identification and the license plate identification in the card to obtain a first matching result;
the fuzzy matching unit is also used for performing fuzzy matching on the export license plate identification and the identification license plate identification to obtain a second matching result;
the data acquisition unit is used for acquiring a vehicle type identification data set and a historical export data set corresponding to the export license plate identification when the first matching result and/or the second matching result represents successful matching.
In an exemplary embodiment of the present application, further comprising:
the license plate identification determining unit is used for determining the license plate identification in the card based on portal data acquired by portal equipment; and determining and identifying the license plate identification based on the identification result of the vehicle type identifier.
In an exemplary embodiment of the present application, the fuzzy matching unit performs fuzzy matching on the exit license plate identifier and the license plate identifier in the card to obtain a first matching result, including:
converting the export license plate identifier into a first characteristic vector and converting the license plate identifier in the card into a second characteristic vector;
calculating cosine similarity of the first feature vector and the second feature vector based on a cosine similarity algorithm, and taking the cosine similarity as a first matching result;
And the fuzzy matching unit performs fuzzy matching on the export license plate identifier and the identification license plate identifier to obtain a second matching result, and the fuzzy matching unit comprises:
converting the identification license plate identifier into a third feature vector;
and calculating cosine similarity of the first feature vector and the third feature vector based on a cosine similarity algorithm, and taking the cosine similarity as a second matching result.
In an exemplary embodiment of the present application, further comprising:
the data cleaning unit is used for cleaning the data of the vehicle outlet based on a preset cleaning rule; the preset cleaning rules are used for limiting judging conditions of illegal outlet data.
In an exemplary embodiment of the present application, further comprising:
the time range determining unit is used for determining the current single travel time range based on the outbound time and the inbound time corresponding to the exit license plate identification;
the data acquisition unit is used for acquiring a vehicle type identification data set corresponding to the exit license plate identification in the current single travel time range;
the data acquisition unit is also used for acquiring a historical export data set corresponding to the export license plate identifier in a specified historical time range.
In an exemplary embodiment of the present application, in a case where each data in the historical export data set corresponds to an automatic payment traffic mode, the actual vehicle type determining unit determines an actual vehicle type corresponding to the export license plate identifier according to the vehicle type identification data set corresponding to the export license plate identifier and the historical export data set, including:
Calculating travel frequencies corresponding to all vehicle types in the vehicle type identification data set;
and determining the vehicle type corresponding to the highest travel frequency in the travel frequencies as the actual vehicle type corresponding to the exit license plate identifier.
In an exemplary embodiment of the present application, in a case where each data in the historical egress data set corresponds to an automatic payment traffic mode and a non-automatic payment traffic mode, respectively, and in a case where each data in the historical egress data set corresponds to a non-automatic payment traffic mode, the actual vehicle model determining unit determines an actual vehicle model corresponding to the egress license plate identifier according to the vehicle model identification data set corresponding to the egress license plate identifier and the historical egress data set, including:
extracting a specific historical data set corresponding to a non-automatic payment passing mode from the historical export data set, and calculating a class of trip frequency corresponding to each vehicle type in the specific historical data set;
calculating a class II trip frequency corresponding to each vehicle type in the vehicle type identification data set;
fusing one class of travel frequencies and two classes of travel frequencies of the same vehicle type into a target travel frequency to obtain target travel frequencies corresponding to all vehicle types;
and determining the vehicle type corresponding to the highest travel frequency in the target travel frequencies as the actual vehicle type corresponding to the exit license plate identifier.
In an exemplary embodiment of the present application, further comprising:
and the data updating unit is used for responding to the data continuously collected by the portal equipment, the vehicle type identifier and the toll station equipment and updating the vehicle type identification data set and the historical export data set.
According to an aspect of the present application, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of any of the above.
According to an aspect of the present application, there is provided an electronic apparatus including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the method of any of the above via execution of executable instructions.
Exemplary embodiments of the present application may have some or all of the following benefits:
in the vehicle abnormal problem identification method provided by an example embodiment of the present application, corresponding vehicle type identification data sets and historical exit data sets may be obtained for exit license plate identifications in vehicle exit data, where the vehicle type identification data sets are obtained based on visual image statistics captured by a vehicle type identifier, and because a vehicle type represented by the visual image is truly and reliably represented, accurate determination of an actual vehicle type may be achieved, and further it may be determined whether a target vehicle type corresponding to the exit license plate identifications is matched or not, if not matched, it may be determined that an abnormal problem corresponding to the exit license plate identifications exists, and compared with a related technology that performs abnormal problem determination only through toll gate data and portal data, the method of determining abnormal problem by relying on the vehicle type identification data sets and the historical exit data sets may be applicable to an ETC traffic mode and perform high-accuracy abnormal problem determination, and may also be applicable to a non-ETC traffic mode.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application. It is apparent that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 schematically illustrates a flow chart of a vehicle anomaly issue identification method according to one embodiment of the present application;
FIG. 2 schematically illustrates a gantry diagram according to one embodiment of the present application;
FIG. 3 schematically illustrates a schematic diagram of a vehicle type identifier setup according to one embodiment of the present application;
FIG. 4 schematically illustrates a flow chart of a vehicle anomaly issue identification method according to another embodiment of the present application;
FIG. 5 schematically shows a block diagram of a vehicle abnormality issue recognition device in accordance with one embodiment of the present application;
fig. 6 schematically shows a schematic of a computer system suitable for use in implementing the electronic device of the embodiments of the present application.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the present application. One skilled in the relevant art will recognize, however, that the aspects of the application may be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known aspects have not been shown or described in detail to avoid obscuring aspects of the present application.
Furthermore, the drawings are only schematic illustrations of the present application and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor devices and/or microcontroller devices.
Referring to fig. 1, fig. 1 schematically shows a flowchart of a vehicle abnormality problem identification method according to an embodiment of the present application. As shown in fig. 1, the vehicle abnormality problem identification method may include: step S110 to step S130. The method may be implemented by a server/server cluster.
Step S110: and responding to the detected vehicle exit data, and extracting the exit license plate identification in the vehicle exit data.
Step S120: determining an actual vehicle model corresponding to the export license plate identifier according to the vehicle model identification data set and the historical export data set corresponding to the export license plate identifier; the vehicle type recognition data set is obtained through statistics based on the recognition result of the visualized vehicle type recognizer.
Step S130: if the actual vehicle type is not matched with the target vehicle type corresponding to the export license plate identifier, judging that the abnormal problem corresponding to the export license plate identifier exists.
By implementing the method shown in fig. 1, a corresponding vehicle type identification data set and a corresponding historical exit data set can be obtained for the exit license plate identifier in the vehicle exit data, wherein the vehicle type identification data set is obtained based on the statistics of the visual image shot by the vehicle type identifier, and because the visual image represents the real and reliable vehicle type, the accurate judgment of the actual vehicle type can be realized, whether the target vehicle type corresponding to the exit license plate identifier is matched or not can be further determined, if the target vehicle type is not matched with the exit license plate identifier, the abnormal problem corresponding to the exit license plate identifier can be determined, and compared with the related art of judging the abnormal problem only through toll gate data and portal data, the method and the device are applicable to the scheme of judging the abnormal problem by relying on the vehicle type identification data set and the historical exit data set, can be suitable for the ETC traffic mode and judging the abnormal problem with high accuracy, and meanwhile, can also be suitable for the non-ETC traffic mode.
Next, the above steps of the present exemplary embodiment will be described in more detail.
The ETC system is an unmanned automatic passing system for information exchange by means of wireless communication and consists of a vehicle automatic identification system, an information base management system and corresponding auxiliary equipment. After the vehicle is provided with an on-board unit/electronic tag/transponder (OBU), when the vehicle arrives at a toll station, a loop sensor under a lane senses that the vehicle passes through and transmits a signal to a roadside unit. The roadside unit sends an inquiry signal to the vehicle, and the OBU senses the microwave signal of the roadside unit and responds to report the vehicle information. The information base receives the vehicle information and matches with the registered vehicle information in the base according to the license plate number, the vehicle type and the like, thus completing the identification of the vehicle. If the identification is passed, the railing is lifted to allow the vehicle to pass, and the roadside unit completes communication with a highway Compound Pass Card (CPC)/IC card in the vehicle-mounted unit, so that the fee deduction operation is completed. If the identification is not passed, the card-running alarm gives an alarm until the vehicle exits the loop sensor.
With the development of ETC, the existing way to pass through a highway toll station includes the following two ways: 1. an automatic toll-collecting traffic mode; 2. a non-automatic toll collection mode. In the automatic toll collection passing mode, the vehicle can realize a series of operations such as automatic vehicle information identification and payment based on the communication between the OBU installed by the vehicle and the roadside unit, and the vehicle can pass through a toll station in a shortcut without entering a manual toll collection channel. In the non-automatic toll collection and passing mode, the vehicle can enter a manual toll collection channel, a toll collector can swipe vehicle running data (such as vehicle type, time, license plate number and the like) into a toll booth system based on a CPC card provided by a vehicle owner, and charge the current vehicle according to the vehicle data recorded by the CPC card, and the vehicle can pass through the toll booth after paying.
However, the development of ETC may also cause a series of problems, and some subjects may register smaller vehicle types for the vehicle based on subjective maliciousness, to avoid paying fees by using ETC holes, or use the same OBU on different vehicles, or may cause a registered vehicle type of the vehicle to be larger than an actual vehicle type due to working errors of related personnel/automation systems during the vehicle registration process, which may bring unnecessary cost loss to the vehicle owners. Before ETC complements the vulnerability, a scheme for identifying such abnormal problems should be designed as soon as possible, avoiding the loss caused by ETC vulnerability.
In the process of determining abnormal problems (such as car logo problems, etc.), the related art generally relies on toll station data and data collected by portal equipment.
Wherein the toll station data comes from a manual toll collection channel.
Wherein the portal (as in fig. 2) is a device erected on the expressway, and any number of portals can be arranged between two toll stations according to requirements. A portal apparatus is an apparatus that is configured on a portal, which may be used for different purposes based on different needs. For example, the portal device may be a device for collecting license plate numbers and traffic flows, a device for detecting vehicle speeds, or a device for other purposes. In this application, a portal apparatus refers to an apparatus that acquires a license plate number by taking an image.
Obviously, when a vehicle passes through a toll station in an automatic toll collection way, the acquired vehicle type of the vehicle is not necessarily accurate, and meanwhile, because the portal equipment can only acquire a license plate number, the problem that the vehicle passing through the toll station in the automatic toll collection way is abnormal is judged based on the related technology, and the problem that the judgment accuracy is not high exists.
In order to solve the problems in the related art, the method and the device consider that images acquired by the vehicle type identifier erected on the portal can be utilized, and meanwhile, historical data are combined to realize an abnormal problem judgment scheme with higher accuracy.
As an alternative embodiment, the following steps may be performed prior to step S110: data cleaning is carried out on the vehicle outlet data based on a preset cleaning rule; the preset cleaning rules are used for limiting judging conditions of illegal outlet data.
Therefore, the influence of redundant data on the abnormal problem judging process can be reduced, and the abnormal problem judging efficiency is improved.
In particular, in the present application, the vehicle exit data may originate from a toll station system, and the toll station system may record vehicle exit data collected in real time by each toll station, where the vehicle exit data refers to traffic data recorded by one toll station and related to the vehicle after the vehicle passes through the toll station.
The vehicle outlet data may include, but is not limited to, the following fields: site coding, charging mode, amount, passing Identification (ID), export license plate identification, license plate color and outbound time. Among them, for license plate identification, it may also be called license plate number, for example, threAXXXXX_1.
Optionally, the data cleaning is performed on the vehicle outlet data based on a preset cleaning rule, and the specific implementation manner may be: obtaining a road company outlet data flow meter (ots_chg_rt_exit_jour_result_dt) according to a preset time interval (e.g. 48 h), sorting the road company outlet data flow meter into a vehicle outlet data set, wherein the vehicle outlet data set can contain any number of vehicle outlet data, and for any vehicle outlet data, the abnormal problem can be judged based on the steps shown in fig. 1 and the embodiment thereof; further, the plurality of vehicle outlet data may be subjected to data cleaning based on the determination condition of the illegal outlet data defined by the preset cleaning rule (e.g., the first character of the license plate mark is not abbreviated as provincial number, the number of license plate mark characters is insufficient (this may be caused by shielding the license plate)), so as to obtain the vehicle outlet data which can be subjected to the abnormality determination.
In step S110, in response to the detected vehicle outlet data, an outlet license plate identification in the vehicle outlet data is extracted.
Specifically, after the data cleaning is completed, the exit license plate identification in the vehicle exit data can be extracted in response to the vehicle exit data. The exit license plate identification refers to a license plate number detected by a toll station when a vehicle passes through the toll station. Alternatively, the license plate identifier may be other than a license plate number, and as technology and society evolves, it may be another form of entity that is used as a unique representation of a vehicle.
As an alternative embodiment, further comprising: determining license plate identification in the card based on portal data acquired by portal equipment; and determining and identifying the license plate identification based on the identification result of the vehicle type identifier.
Therefore, the multi-dimensional license plate identification (namely, the license plate identification in the card and the identification license plate identification) can be obtained and used for comparing with the export license plate identification, so that the vehicle export data needing to be subjected to abnormal problem judgment is determined, the abnormal problem judgment on the whole vehicle export data is avoided, and the calculation resources can be saved.
Specifically, since any number of portals can be assumed between two toll stations, and any number of portal devices can be provided on one portal, a plurality of pieces of portal data can be collected by the portal devices in the journey between two toll stations for the same vehicle, but no matter how many pieces of portal data are, license plate identifications recorded in these portal data are generally the same. In one case, there may be a problem that the license plates of the fake-licensed vehicle are inconsistent, so license plate identifications recorded in the plurality of portal data may be different.
The portal devices configured may be the same type of portal device, or may be different types of portal devices, for example, (the portal device VA for identifying the license plate of the vehicle head, and the portal device VB for identifying the license plate of the vehicle tail). Portal data collected by the portal device may be implemented in any form of character strings, text, images, video, and the like, and the embodiment of the present application is not limited.
Referring to fig. 3, fig. 3 schematically illustrates a schematic diagram of a vehicle type identifier setting mode according to an embodiment of the present application. Fig. 3 shows a partial road layout between two toll stations, and fig. 3 specifically includes an up road including 2 traffic lanes and 1 emergency lane, and a down road including 2 traffic lanes and 1 emergency lane. An upstream gantry 310 and an upstream gantry 320 may be provided on an upstream road, and a downstream gantry 330 and a downstream gantry 340 may be provided on a downstream road.
As an example, the configuration of the upstream portal 310 and the downstream portal 330 is the same, and each of the 2 license plate image recognition devices (i.e., the portal device VA for recognizing license plates of the vehicle described above), the 1 license plate image recognition device (i.e., the portal device VB for recognizing license plates of the vehicle described above), and the 3 portal vehicle type recognition devices (i.e., the vehicle type recognizer for recognizing vehicle types) is configured. The configuration of the uplink portal 320 and the downlink portal 340 is the same, and 2 license plate image recognition devices and 1 license plate image recognition device are configured.
Based on the above, the license plate identification in the card is determined based on portal data acquired by portal equipment, and the specific implementation mode can be as follows: determining license plate identifiers recorded in portal data acquired by any portal equipment as license plate identifiers in the card; or determining the license plate identifier with the highest occurrence frequency in portal data acquired by portal equipment as the license plate identifier in the card. Similarly, the license plate identification is determined based on the identification result of the vehicle type identifier, and the specific implementation mode can be as follows: determining license plate identifiers recorded in images acquired by any vehicle type identifier as identification license plate identifiers; or determining the license plate identification with the highest occurrence frequency in the images acquired by the vehicle type identifiers as the identification license plate identification.
The license plate identification, the license plate identification in the card and the export license plate identification are all license plate identifications with the same word length from different acquisition devices. If any two different conditions exist among the identification license plate identification, the in-card license plate identification and the export license plate identification, the conditions are possibly caused by adjacent channel interference, inconsistent card labels and the like. If the license plate identifications, the license plate identifications in the card and the export license plate identifications are consistent with each other, the license plate identifications can be caused by ETC issuing errors, multiple cards of one vehicle and the like. The technical purpose of the present application is to identify the problems recorded in the latter case.
As an alternative embodiment, further comprising: fuzzy matching is carried out on the export license plate identification and the license plate identification in the card, so as to obtain a first matching result; fuzzy matching is carried out on the export license plate identification and the identification license plate identification, and a second matching result is obtained; if the first matching result and/or the second matching result represents successful matching, a vehicle type identification data set and a historical export data set corresponding to the export license plate identification are obtained.
Therefore, the vehicle type identification data set and the historical export data set of the export license plate identification can be obtained under the condition that the identification license plate identification and the license plate identification in the card are matched with the export license plate identification, the execution of an abnormal problem identification process on the export license plate identification without abnormal problem identification is avoided, and the waste of calculation resources can be avoided.
Specifically, when the export license plate identifier and the license plate identifier in the card are subjected to fuzzy matching, and when the export license plate identifier and the identification license plate identifier are subjected to fuzzy matching, the adopted fuzzy matching algorithm can be selected according to actual requirements, and the embodiment of the application is not limited to the fuzzy matching algorithm.
The first matching result and the second matching result can be realized in the same data form, and if the first matching result and/or the second matching result represents successful matching, the vehicle type identification data set and the historical export data set corresponding to the export license plate identification can be obtained. And when the first matching result is detected to be larger than a first preset threshold (e.g. 0.85), judging that the first matching result represents successful matching. And when the second matching result is detected to be larger than a second preset threshold (e.g., 0.85), judging that the second matching result represents successful matching. The first preset threshold value and the second preset threshold value can be equal or unequal, and the values of the first preset threshold value and the second preset threshold value can be configured in a personalized way according to actual demands.
In addition, it should be noted that the algorithm used to calculate the first matching result and the second matching result may be the same algorithm or different algorithms, which is not limited in the embodiment of the present application.
As an optional embodiment, performing fuzzy matching on the exit license plate identifier and the license plate identifier in the card to obtain a first matching result, including: converting the export license plate identifier into a first characteristic vector and converting the license plate identifier in the card into a second characteristic vector; calculating cosine similarity of the first feature vector and the second feature vector based on a cosine similarity algorithm, and taking the cosine similarity as a first matching result;
and performing fuzzy matching on the export license plate identifier and the identification license plate identifier to obtain a second matching result, wherein the fuzzy matching comprises the following steps: converting the identification license plate identifier into a third feature vector; and calculating cosine similarity of the first feature vector and the third feature vector based on a cosine similarity algorithm, and taking the cosine similarity as a second matching result.
Therefore, considering that the identification accuracy of the license plate identifications is not necessarily high, the first matching result and the second matching result can be calculated based on a cosine similarity algorithm, and further a result which can tolerate an error range and is used for representing whether the two license plate identifications are in fuzzy matching or not is obtained.
Specifically, the cosine similarity algorithm can be expressed as: when the cosine similarity algorithm is applied to the application, a and B in Cosine Similarity (a, B) may respectively represent two different feature vectors that need to be substituted into the cosine similarity algorithm formula, and i represents an i-th element in the feature vectors.
Substituting a and B into a first feature vector (e.g., {1,2,1,0,1,1,2,0 }) and a second feature vector (e.g., {1,2,1,1,0,1,1,1 }) respectively when calculating the first matching result; when calculating the second matching result, the first feature vector and the third feature vector (e.g., {1,2,1,1,0,1,1,0 }) are substituted for a and B, respectively. Taking the first feature vector and the second feature vector as examples, the first matching result
In step S120, determining an actual vehicle model corresponding to the exit license plate identifier according to the vehicle model identification data set corresponding to the exit license plate identifier and the historical exit data set; the vehicle type recognition data set is obtained through statistics based on the recognition result of the visualized vehicle type recognizer.
Specifically, the vehicle type identification data set and the history exit data set are both data sets including a plurality of pieces of data, except that each piece of data included in the vehicle type identification data set is data identified by the vehicle type identifier in a single, current trip corresponding to the exit license plate identifier, and each piece of data included in the history exit data set may be from a plurality of devices in any period of history (e.g., within 3 months, within half a year, etc.).
The vehicle type identifier can be started in real time and used for identifying the vehicle type based on the acquired images, and one or more images in the images can be intercepted to be used as the vehicle type identification basis when the vehicle type is identified. After the vehicle type identifier collects the image, the vehicle type identifier can identify information such as license plate identification, vehicle type and the like in the image and generate the information into corresponding vehicle type identification data, and the vehicle type identification data can be stored in a vehicle type identifier flow table (dwd _gateway_data_pass_dt), wherein the vehicle type identifier flow table comprises the following fields: time, license plate representation, license plate color, and side picture address identification. For a single trip of the exit license plate identification, multiple pieces of vehicle model identification data may be corresponding. In addition, the historical exit data set may also be referred to as a vehicle representation (ods_increment_vehicle_portrait_dt), which includes, but is not limited to, the following fields: the license plate identification, the vehicle type and the vehicle type, and the data in the historical export data set can come from portal equipment and toll station equipment.
As an alternative embodiment, further comprising: determining a current single travel time range based on the outbound time and the inbound time corresponding to the exit license plate identification; acquiring a vehicle type identification data set corresponding to the exit license plate identification in the current single travel time range; and acquiring a historical export data set corresponding to the export license plate identifier within a specified historical time range.
Therefore, a historical exit data set for describing the travel condition of the vehicle corresponding to the exit license plate identifier in a period of time and a vehicle type identification data set in the current journey (namely, the current single journey) can be obtained, so that the subsequent abnormal problem judgment can be performed, more accurate judgment results can be obtained, and the judgment mode can be applied to not only ETC (electronic toll collection) but also non-ETC (electronic toll collection) modes, and can be provided with a wide application range and higher judgment precision compared with the related technologies.
Specifically, the vehicle corresponding to the exit license plate identifier enters from one toll station and leaves from the other toll station, this process is called a current single journey, the time when the vehicle enters from one toll station is inbound time, the time when the vehicle leaves from the other toll station is inbound time, and the outbound time and the inbound time can form a current single journey time range.
The method and the device can extract the vehicle type identification data which belongs to the current single travel time range and corresponds to the exit license plate identification from the vehicle type identifier flow water meter, further obtain a vehicle type identification data set (the table 1 below comprises 7 pieces of vehicle type identification data), further obtain a historical exit data set (the table 2 below comprises 25 pieces of historical exit data) which corresponds to the exit license plate identification within a specified historical time range (for example, within 3 months from the current time); the specified historical time range can be configured in a personalized way according to requirements, and the embodiment of the application is not limited.
Identifying date Identifying a timestamp Vehicle model identification License plate identification
20230717 83821 3 Su AXXXXX_1
20230717 85518 6 Su AXXXXX_1
20230717 93841 6 Su AXXXXX_1
20230717 102749 6 Su AXXXXX_1
20230717 110238 2 Su AXXXXX_1
20230717 111827 6 Su AXXXXX_1
20230717 113822 6 Su AXXXXX_1
TABLE 1
/>
/>
TABLE 2
As an optional embodiment, in the case that each data in the historical export data set corresponds to an automatic payment traffic mode, determining an actual vehicle model corresponding to the export license plate identifier according to the vehicle model identification data set corresponding to the export license plate identifier and the historical export data set, includes: calculating travel frequencies corresponding to all vehicle types in the vehicle type identification data set; and determining the vehicle type corresponding to the highest travel frequency in the travel frequencies as the actual vehicle type corresponding to the exit license plate identifier.
Therefore, when all data in the historical export data set corresponds to an automatic payment passing mode, the actual vehicle type is determined only based on the travel frequency corresponding to each vehicle type in the vehicle type identification data set, and the calculation efficiency of the actual vehicle type can be improved.
Specifically, the outbound mode at least includes: automatic toll collection (ETC) and non-automatic toll collection (CPC). The trip frequency corresponding to each vehicle type in the vehicle type identification data set is calculated, and the specific implementation mode is as follows: based on the expression Counting travel frequencies T corresponding to all vehicle types in the vehicle type identification data set; wherein a refers to a vehicle model, and Sigma a refers to the vehicle modelNumber of occurrences of Sigma n 1 refers to the vehicle type recognition data amount. Taking table 1 as an example, the travel frequencies corresponding to each vehicle type are respectively: travel frequency of vehicle model 6 is->The travel frequency of the vehicle model 3 is +.>Travel frequency of vehicle model 2 is
As an alternative embodiment, in a case where each data in the historical egress data set corresponds to an automatic payment traffic mode and a non-automatic payment traffic mode, respectively, and in a case where each data in the historical egress data set corresponds to a non-automatic payment traffic mode, determining an actual vehicle model corresponding to the egress license plate identifier according to the vehicle model identification data set corresponding to the egress license plate identifier and the historical egress data set, includes: extracting a specific historical data set corresponding to a non-automatic payment passing mode from the historical export data set, and calculating a class of trip frequency corresponding to each vehicle type in the specific historical data set; calculating a class II trip frequency corresponding to each vehicle type in the vehicle type identification data set; fusing one class of travel frequencies and two classes of travel frequencies of the same vehicle type into a target travel frequency to obtain target travel frequencies corresponding to all vehicle types; and determining the vehicle type corresponding to the highest travel frequency in the target travel frequencies as the actual vehicle type corresponding to the exit license plate identifier.
Therefore, the travel frequencies corresponding to the vehicle types corresponding to the non-automatic payment passing mode can be obtained, the actual vehicle types are determined based on the travel frequencies and the travel frequencies corresponding to the vehicle types in the vehicle type identification data set, and the fact that the vehicle types registered when handling the OBU card are read when ETC passing exit charge is considered, and lie reporting exists is considered, so that the accuracy of the determined actual vehicle types can be improved depending on the travel frequencies corresponding to the vehicle types under the non-automatic payment passing mode.
Specifically, taking tables 1 and 2 as an example, in table 2, it is apparent that both of the automatic payment traffic mode and the non-automatic payment traffic mode are contained, then a specific history data set corresponding to the non-automatic payment traffic mode, that is, history exit data corresponding to CPC, among the history exit data sets, may be extracted as a specific history data set containing 12 pieces of history exit data.
On the basis, the travel frequency P of the class corresponding to each vehicle type in the specific historical data set can be calculated a The number of occurrences of the same vehicle model in a specific historical data set in the CPC traffic mode is denoted by a, the specific historical data set corresponds to a specific period (e.g., 3 months nearest to the current time), the specific period can be customized according to actual requirements, each vehicle model can correspond to a different count (x), and sum (a) represents the data volume of the specific historical data set. That is, the travel frequency of the model 6 is calculated as Travel frequency of vehicle model 3The travel frequency of the vehicle type 2 is +.>Wherein, although table 2 does not contain historical export data corresponding to model 2, in order to improve the accuracy of actual model, P may be calculated 2 A predetermined value (e.g., 1) is assigned to the molecule of (a).
Furthermore, two types of travel frequencies corresponding to each vehicle type in the vehicle type identification data set can be calculated, and since the travel frequencies of each vehicle type in the vehicle type identification data set are calculated in the previous embodiment, the two types of travel frequencies are used for distinguishing the previous embodiment, and the two types of travel frequencies corresponding to each vehicle type in the vehicle type identification data set substantially refer to the travel frequencies of each vehicle type in the vehicle type identification data set. Namely, the second class travel frequency of the vehicle model 6 is obtainedThe second class trip frequency of the vehicle type 3 is +.>The second class trip frequency of the vehicle type 2 is +.>
Furthermore, the first class travel frequency and the second class travel frequency of the same vehicle model can be fused (e.g., multiplied) to be the target travel frequency, so as to obtain the target travel frequency corresponding to each vehicle model. Continuing to use the above example, fusing the first class trip frequency and the second class trip frequency of the vehicle model 6 into the target trip frequencyFusing one class of trip frequency and two class of trip frequency of the vehicle model 3 into a target trip frequency +. >Fusing one class of trip frequency and two class of trip frequency of the vehicle type 2 into a target trip frequency +.>
Furthermore, the highest trip frequency of the trip frequencies of the targets can be setThe corresponding model (e.g., model 6) is determined to be the actual model corresponding to the exit license plate identifier.
In step S130, if the actual vehicle type does not match the target vehicle type corresponding to the exit license plate identifier, it is determined that there is an abnormal problem corresponding to the exit license plate identifier.
Specifically, the abnormal problem may include any problem (such as a cart logo problem) that belongs to the distinguishing scope of the application at present or in the future, besides the cart logo problem in the following alternative embodiments, and the embodiment of the application is not limited.
As an alternative embodiment, further comprising: if the actual vehicle model is larger than the target vehicle model, judging that the actual vehicle model is not matched with the target vehicle model; and, the anomaly problem includes a cart logo problem, determining that there is an anomaly problem corresponding to the exit license plate identification, including: and judging that the large car logo and the small car logo corresponding to the export license plate identification exist.
Therefore, accurate cart and car logo problem judgment is achieved.
Specifically, when the actual vehicle model is larger than the target vehicle model, the automatic fee collection of the vehicle through the toll booth is lower than the amount that the vehicle should collect.
As an alternative embodiment, further comprising: and updating the vehicle type identification data set and the historical export data set in response to the data continuously collected by the portal device, the vehicle type identifier and the toll station device.
Therefore, the instantaneity of the vehicle type identification data set and the historical export data set can be improved, and the judgment accuracy of the abnormal problems can be improved.
Specifically, the data continuously collected by the portal device, the vehicle type identifier and the toll station device comprises: the new portal data continuously collected by the portal equipment, the new vehicle type identification data continuously collected by the vehicle type identifier and the new vehicle outlet data continuously collected by the toll station equipment can be stored in a designated database. The method and the device can store the data continuously collected by the portal equipment, the vehicle type identifier and the toll station equipment according to unit time (such as 24 h).
For example, if the current time is 2023-1-4, the data continuously collected by the door frame device, the vehicle type identifier, and the toll station device of 2023-1-3 may be stored as table 1 (T-1), the data continuously collected by the door frame device, the vehicle type identifier, and the toll station device of 2023-1-2 may be stored as table 2 (T-2), the data continuously collected by the door frame device, the vehicle type identifier, and the toll station device of 2023-1-1 may be stored as table 3 (T-3), and so on. Based on the above, the vehicle type identification data set and the historical export data set are updated on time according to the stored data according to the appointed updating time, so that the vehicle type identification data set and the historical export data set can be ensured to have instantaneity.
Referring to fig. 4, fig. 4 schematically shows a flowchart of a vehicle abnormality problem identification method according to another embodiment of the present application. As shown in fig. 4, the vehicle abnormality problem identification method may include: step S410 to step S430.
Step S410: and updating the vehicle type identification data set and the historical export data set in response to the data continuously collected by the portal device, the vehicle type identifier and the toll station device.
Step S412: data cleaning is carried out on the vehicle outlet data based on a preset cleaning rule; the preset cleaning rules are used for limiting judging conditions of illegal outlet data.
Step S414: and responding to the detected vehicle exit data, and extracting the exit license plate identification in the vehicle exit data.
Step S416: determining license plate identification in the card based on portal data acquired by portal equipment; and determining and identifying the license plate identification based on the identification result of the vehicle type identifier.
Step S418: converting the export license plate identifier into a first characteristic vector and converting the license plate identifier in the card into a second characteristic vector; calculating cosine similarity of the first feature vector and the second feature vector based on a cosine similarity algorithm, and taking the cosine similarity as a first matching result; converting the identification license plate identifier into a third feature vector; and calculating cosine similarity of the first feature vector and the third feature vector based on a cosine similarity algorithm, and taking the cosine similarity as a second matching result.
Step S420: judging whether the first matching result and the second matching result represent successful matching. If yes, go to step S422; if not, step S430 is performed.
Step S422: determining a current single travel time range based on the outbound time and the inbound time corresponding to the exit license plate identification; acquiring a vehicle type identification data set corresponding to the exit license plate identification in the current single travel time range; and acquiring a historical export data set corresponding to the export license plate identifier within a specified historical time range.
Step S424: under the condition that all data in the historical export data set correspond to an automatic payment passing mode, calculating travel frequencies corresponding to all vehicle types in the vehicle type identification data set; and determining the vehicle type corresponding to the highest travel frequency in the travel frequencies as the actual vehicle type corresponding to the exit license plate identifier. Under the condition that each data in the historical export data set corresponds to an automatic payment passing mode and a non-automatic payment passing mode respectively, and under the condition that each data in the historical export data set corresponds to the non-automatic payment passing mode, extracting a specific historical data set corresponding to the non-automatic payment passing mode in the historical export data set, and calculating a class of trip frequency corresponding to each vehicle type in the specific historical data set; calculating a class II trip frequency corresponding to each vehicle type in the vehicle type identification data set; fusing one class of travel frequencies and two classes of travel frequencies of the same vehicle type into a target travel frequency to obtain target travel frequencies corresponding to all vehicle types; and determining the vehicle type corresponding to the highest travel frequency in the target travel frequencies as the actual vehicle type corresponding to the exit license plate identifier.
Step S426: and judging whether the actual vehicle type is larger than a target vehicle type corresponding to the exit license plate identification. If yes, go to step S428; if not, the process is ended.
Step S428: and judging that the large car logo and the small car logo corresponding to the export license plate identification exist.
Step S430: and judging that the exit license plate identification does not belong to the large car and small car logo problem judging range. Further, the flow is ended.
It should be noted that, the steps S410 to S430 correspond to the steps and embodiments shown in fig. 1, and for the specific implementation of the steps S410 to S430, please refer to the steps and embodiments shown in fig. 1, and the description thereof is omitted here.
It can be seen that, implementing the method shown in fig. 4, corresponding vehicle type identification data set and historical exit data set can be obtained for the exit license plate identifier in the vehicle exit data, wherein the vehicle type identification data set is obtained based on the statistics of the visual image shot by the vehicle type identifier, and because the visual image represents the real and credible vehicle type, the accurate judgment of the actual vehicle type can be realized, and further, whether the actual vehicle type is matched with the target vehicle type corresponding to the exit license plate identifier or not can be determined, if the actual vehicle type is not matched with the target vehicle type, the abnormal problem corresponding to the exit license plate identifier can be determined, and compared with the related technology of judging the abnormal problem only through toll station data and portal data, the method and the device are applicable to the ETC traffic mode and the high-accuracy abnormal problem judgment, and meanwhile, the method and the device are applicable to the non-ETC traffic mode.
Referring to fig. 5, fig. 5 schematically shows a block diagram of a vehicle abnormality issue recognition apparatus according to an embodiment of the present application. The vehicle abnormality problem recognition device 500 corresponds to the method shown in fig. 1, and as shown in fig. 5, the vehicle abnormality problem recognition device 500 includes:
an exit license plate identification determining unit 501, configured to respond to the detected vehicle exit data, and extract an exit license plate identification in the vehicle exit data;
an actual vehicle type determining unit 502, configured to determine an actual vehicle type corresponding to the exit license plate identifier according to the vehicle type identification data set corresponding to the exit license plate identifier and the historical exit data set; the vehicle type recognition data set is obtained by statistics based on the recognition result of the visualized vehicle type recognizer;
an abnormal problem identification unit 503, configured to determine that an abnormal problem corresponding to the export license plate identifier exists in a case where the actual vehicle type does not match the target vehicle type corresponding to the export license plate identifier.
As can be seen, implementing the apparatus shown in fig. 5, a corresponding vehicle type identification data set and a historical exit data set can be obtained for the exit license plate identifier in the vehicle exit data, where the vehicle type identification data set is obtained based on the statistics of the visual image captured by the vehicle type identifier, and because the vehicle type represented by the visual image is true and reliable, accurate determination of the actual vehicle type can be implemented, and further, whether the actual vehicle type is matched with the target vehicle type corresponding to the exit license plate identifier or not can be determined, if the actual vehicle type is not matched with the target vehicle type corresponding to the exit license plate identifier, it can be determined that an abnormal problem corresponding to the exit license plate identifier exists, and compared with the related art that the abnormal problem determination is performed only by the toll station data and the portal data, the method and the apparatus of the present application rely on the vehicle type identification data set and the historical exit data set to perform the abnormal problem determination scheme, can be applied to the etc. and perform the high-accuracy abnormal problem determination in the passing manner, and simultaneously, and the method of the present invention can also be applied to the non-ETC passing manner.
In an exemplary embodiment of the present application, further comprising:
the mismatch condition judging unit is used for judging that the actual vehicle type is not matched with the target vehicle type when the actual vehicle type is larger than the target vehicle type;
and, the abnormality problem includes a cart-to-cart-label problem, and the abnormality problem identification unit 503 determines that there is an abnormality problem corresponding to the exit license plate identification, including:
and judging that the large car logo and the small car logo corresponding to the export license plate identification exist.
Therefore, by implementing the alternative embodiment, accurate cart and car logo problem judgment can be realized.
In an exemplary embodiment of the present application, further comprising:
the fuzzy matching unit is used for performing fuzzy matching on the export license plate identification and the license plate identification in the card to obtain a first matching result;
the fuzzy matching unit is also used for performing fuzzy matching on the export license plate identification and the identification license plate identification to obtain a second matching result;
the data acquisition unit is used for acquiring a vehicle type identification data set and a historical export data set corresponding to the export license plate identification when the first matching result and/or the second matching result represents successful matching.
Therefore, by implementing the alternative embodiment, the vehicle type identification data set and the historical export data set of the export license plate identification can be obtained under the condition that the identification license plate identification and the in-card license plate identification are matched with the export license plate identification, so that the execution of an abnormal problem identification flow on the export license plate identification without abnormal problem identification is avoided, and the waste of computing resources can be avoided.
In an exemplary embodiment of the present application, further comprising:
the license plate identification determining unit is used for determining the license plate identification in the card based on portal data acquired by portal equipment; and determining and identifying the license plate identification based on the identification result of the vehicle type identifier.
Therefore, by implementing the alternative embodiment, the multi-dimensional license plate identification (namely, the license plate identification in the card and the identification license plate identification) can be obtained for comparison with the export license plate identification, so that the vehicle export data needing to be subjected to abnormal problem judgment is determined, the abnormal problem judgment on the whole vehicle export data is avoided, and the calculation resources can be saved.
In an exemplary embodiment of the present application, the fuzzy matching unit performs fuzzy matching on the exit license plate identifier and the license plate identifier in the card to obtain a first matching result, including:
converting the export license plate identifier into a first characteristic vector and converting the license plate identifier in the card into a second characteristic vector;
calculating cosine similarity of the first feature vector and the second feature vector based on a cosine similarity algorithm, and taking the cosine similarity as a first matching result;
and the fuzzy matching unit performs fuzzy matching on the export license plate identifier and the identification license plate identifier to obtain a second matching result, and the fuzzy matching unit comprises:
Converting the identification license plate identifier into a third feature vector;
and calculating cosine similarity of the first feature vector and the third feature vector based on a cosine similarity algorithm, and taking the cosine similarity as a second matching result.
Therefore, by implementing the alternative embodiment, considering that the identification accuracy of the license plate identifications is not necessarily high, the first matching result and the second matching result can be calculated based on the cosine similarity algorithm, and further, the result used for representing whether the two license plate identifications are in fuzzy matching or not and having an allowable error range can be obtained.
In an exemplary embodiment of the present application, further comprising:
the data cleaning unit is used for cleaning the data of the vehicle outlet based on a preset cleaning rule; the preset cleaning rules are used for limiting judging conditions of illegal outlet data.
It can be seen that, implementing this alternative embodiment, the influence of redundant data on the abnormal problem discriminating process can be reduced, thereby being beneficial to improving the abnormal problem discriminating efficiency.
In an exemplary embodiment of the present application, further comprising:
the time range determining unit is used for determining the current single travel time range based on the outbound time and the inbound time corresponding to the exit license plate identification;
the data acquisition unit is used for acquiring a vehicle type identification data set corresponding to the exit license plate identification in the current single travel time range;
The data acquisition unit is also used for acquiring a historical export data set corresponding to the export license plate identifier in a specified historical time range.
Therefore, by implementing the alternative embodiment, a historical exit data set for describing the travel situation of the vehicle corresponding to the exit license plate identifier in a period of time and a vehicle type identification data set in the current journey (namely, the current single journey) can be obtained, so that the subsequent abnormal problem judgment can be performed, more accurate judgment results can be obtained, and the judgment mode can be applied to not only ETC traffic modes but also non-ETC traffic modes, and compared with the related art, the method has a wide application range and higher judgment precision.
In an exemplary embodiment of the present application, in a case where each data in the historical export data set corresponds to an automatic payment traffic mode, the actual vehicle type determining unit 502 determines an actual vehicle type corresponding to the export license plate identifier according to the vehicle type identification data set corresponding to the export license plate identifier and the historical export data set, including:
calculating travel frequencies corresponding to all vehicle types in the vehicle type identification data set;
and determining the vehicle type corresponding to the highest travel frequency in the travel frequencies as the actual vehicle type corresponding to the exit license plate identifier.
Therefore, by implementing the optional embodiment, when each data in the historical exit data set corresponds to the automatic payment passing mode, the actual vehicle type is determined only based on the travel frequency corresponding to each vehicle type in the vehicle type identification data set, and the calculation efficiency of the actual vehicle type can be improved.
In an exemplary embodiment of the present application, in a case where each data in the historical egress data set corresponds to an automatic payment traffic mode and a non-automatic payment traffic mode, respectively, and in a case where each data in the historical egress data set corresponds to a non-automatic payment traffic mode, the actual vehicle model determining unit 502 determines an actual vehicle model corresponding to the egress license plate identifier according to the vehicle model identification data set corresponding to the egress license plate identifier and the historical egress data set, including:
extracting a specific historical data set corresponding to a non-automatic payment passing mode from the historical export data set, and calculating a class of trip frequency corresponding to each vehicle type in the specific historical data set;
calculating a class II trip frequency corresponding to each vehicle type in the vehicle type identification data set;
fusing one class of travel frequencies and two classes of travel frequencies of the same vehicle type into a target travel frequency to obtain target travel frequencies corresponding to all vehicle types;
And determining the vehicle type corresponding to the highest travel frequency in the target travel frequencies as the actual vehicle type corresponding to the exit license plate identifier.
Therefore, by implementing the alternative embodiment, a class of travel frequency corresponding to each vehicle type corresponding to the non-automatic payment passing mode can be obtained, the actual vehicle type is determined based on the class of travel frequency and the class of travel frequency corresponding to each vehicle type in the vehicle type identification data set, and the situation that the vehicle type registered when handling the OBU card is read and reported when ETC passing exit charge is considered, so that the accuracy of the determined actual vehicle type can be improved depending on the class of travel frequency corresponding to each vehicle type in the non-automatic payment passing mode.
In an exemplary embodiment of the present application, further comprising:
and the data updating unit is used for responding to the data continuously collected by the portal equipment, the vehicle type identifier and the toll station equipment and updating the vehicle type identification data set and the historical export data set.
Therefore, by implementing the alternative embodiment, the instantaneity of the vehicle type identification data set and the historical export data set can be improved, and the judgment accuracy of the abnormal problem can be improved.
It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functions of two or more modules or units described above may be embodied in one module or unit, in accordance with embodiments of the present application. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.
Since each functional module of the vehicle abnormality problem recognition device according to the exemplary embodiment of the present application corresponds to a step of the exemplary embodiment of the vehicle abnormality problem recognition method described above, for details not disclosed in the embodiment of the device of the present application, reference is made to the embodiment of the vehicle abnormality problem recognition method described above.
Referring to fig. 6, fig. 6 shows a schematic diagram of a computer system suitable for implementing the electronic device of the embodiments of the present application.
It should be noted that, the computer system 600 of the electronic device shown in fig. 6 is only an example, and should not impose any limitation on the functions and the application scope of the embodiments of the present application.
As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for system operation are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other through a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, mouse, etc.; an output portion 607 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The drive 610 is also connected to the I/O interface 605 as needed. Removable media 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed as needed on drive 610 so that a computer program read therefrom is installed as needed into storage section 608.
In particular, according to embodiments of the present application, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network through the communication portion 609, and/or installed from the removable medium 611. The computer program, when executed by a Central Processing Unit (CPU) 601, performs the various functions defined in the methods and apparatus of the present application.
As another aspect, the present application also provides a computer-readable medium that may be contained in the electronic device described in the above embodiment; or may exist alone without being incorporated into the electronic device. The computer-readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to implement the methods described in the above embodiments.
It should be noted that the computer readable medium shown in the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units involved in the embodiments of the present application may be implemented by means of software, or may be implemented by means of hardware, and the described units may also be provided in a processor. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.

Claims (13)

1. A vehicle abnormality recognition method, characterized by comprising:
responding to the detected vehicle exit data, and extracting an exit license plate identifier in the vehicle exit data;
determining an actual vehicle model corresponding to the export license plate identifier according to a vehicle model identification data set and a historical export data set corresponding to the export license plate identifier; the vehicle type recognition data set is obtained by statistics based on the recognition result of the visualized vehicle type recognizer;
if the actual vehicle type is not matched with the target vehicle type corresponding to the export license plate identifier, judging that the abnormal problem corresponding to the export license plate identifier exists.
2. The method as recited in claim 1, further comprising:
if the actual vehicle model is larger than the target vehicle model, judging that the actual vehicle model is not matched with the target vehicle model;
and, the anomaly problem includes a cart small scale problem, determining that there is an anomaly problem corresponding to the exit license plate identification, including:
and judging that the large car logo problem corresponding to the export license plate identification exists.
3. The method as recited in claim 1, further comprising:
fuzzy matching is carried out on the export license plate identification and the license plate identification in the card, and a first matching result is obtained;
fuzzy matching is carried out on the export license plate identification and the identification license plate identification, and a second matching result is obtained;
and if the first matching result and/or the second matching result represents successful matching, acquiring the vehicle type identification data set and the historical export data set corresponding to the export license plate identifier.
4. A method according to claim 3, further comprising:
determining license plate identifications in the card based on portal data acquired by portal equipment;
and determining the identification license plate identification based on the identification result of the vehicle type identifier.
5. The method of claim 3, wherein performing fuzzy matching on the exit license plate identifier and the in-card license plate identifier to obtain a first matching result comprises:
converting the export license plate identifier into a first characteristic vector and converting the license plate identifier in the card into a second characteristic vector;
calculating cosine similarity of the first feature vector and the second feature vector based on a cosine similarity algorithm, and taking the cosine similarity as a first matching result;
and performing fuzzy matching on the export license plate identifier and the identification license plate identifier to obtain a second matching result, wherein the fuzzy matching comprises the following steps:
converting the identification license plate identifier into a third feature vector;
and calculating cosine similarity of the first feature vector and the third feature vector based on the cosine similarity algorithm, and taking the cosine similarity as a second matching result.
6. The method as recited in claim 1, further comprising:
data cleaning is carried out on the vehicle outlet data based on a preset cleaning rule; the preset cleaning rules are used for limiting judging conditions of illegal outlet data.
7. The method as recited in claim 1, further comprising:
determining a current single travel time range based on the outbound time and the inbound time corresponding to the exit license plate identifier;
Acquiring the vehicle type identification data set corresponding to the exit license plate identifier in the current single travel time range;
and acquiring the historical export data set corresponding to the export license plate identifier within a specified historical time range.
8. The method of claim 1, wherein, in the case where each data in the historical egress data set corresponds to an automatic payment traffic pattern, determining an actual vehicle model corresponding to the egress license plate identifier from a vehicle model identification data set corresponding to the egress license plate identifier and the historical egress data set, comprises:
calculating travel frequencies corresponding to all vehicle types in the vehicle type identification data set;
and determining the vehicle model corresponding to the highest travel frequency in the travel frequencies as the actual vehicle model corresponding to the exit license plate identifier.
9. The method of claim 1, wherein determining an actual vehicle model corresponding to the outlet license plate identification from a vehicle model identification data set corresponding to the outlet license plate identification and a historical outlet data set, in the case where each data in the historical outlet data set corresponds to an automatic payment traffic mode and a non-automatic payment traffic mode, respectively, and in the case where each data in the historical outlet data set corresponds to the non-automatic payment traffic mode, comprises:
Extracting a specific historical data set corresponding to the non-automatic payment passing mode from the historical exit data set, and calculating a class of trip frequency corresponding to each vehicle type in the specific historical data set;
calculating a class II trip frequency corresponding to each vehicle type in the vehicle type identification data set;
fusing one class of travel frequencies and two classes of travel frequencies of the same vehicle type into a target travel frequency to obtain target travel frequencies corresponding to all vehicle types;
and determining the vehicle model corresponding to the highest travel frequency in the target travel frequencies as the actual vehicle model corresponding to the exit license plate identifier.
10. The method according to any one of claims 1-9, further comprising:
and updating the vehicle type identification data set and the historical export data set in response to data continuously collected by the portal device, the vehicle type identifier and the toll station device.
11. A vehicle abnormality recognition device, characterized by comprising:
the system comprises an exit license plate identification determining unit, a license plate identification determining unit and a license plate identification determining unit, wherein the exit license plate identification determining unit is used for responding to detected vehicle exit data and extracting an exit license plate identification in the vehicle exit data;
the actual vehicle type determining unit is used for determining an actual vehicle type corresponding to the export license plate identifier according to the vehicle type identification data set and the historical export data set corresponding to the export license plate identifier; the vehicle type recognition data set is obtained by statistics based on the recognition result of the visualized vehicle type recognizer;
The abnormal problem identification unit is used for judging that the abnormal problem corresponding to the export license plate identifier exists under the condition that the actual vehicle type is not matched with the target vehicle type corresponding to the export license plate identifier.
12. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the method of any of claims 1-10.
13. An electronic device, comprising:
a processor; and
a memory for storing executable instructions of the processor;
wherein the processor is configured to perform the method of any of claims 1-10 via execution of the executable instructions.
CN202311788210.7A 2023-12-22 2023-12-22 Vehicle abnormal problem identification method, device, medium and electronic equipment Pending CN117746643A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311788210.7A CN117746643A (en) 2023-12-22 2023-12-22 Vehicle abnormal problem identification method, device, medium and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311788210.7A CN117746643A (en) 2023-12-22 2023-12-22 Vehicle abnormal problem identification method, device, medium and electronic equipment

Publications (1)

Publication Number Publication Date
CN117746643A true CN117746643A (en) 2024-03-22

Family

ID=90283107

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311788210.7A Pending CN117746643A (en) 2023-12-22 2023-12-22 Vehicle abnormal problem identification method, device, medium and electronic equipment

Country Status (1)

Country Link
CN (1) CN117746643A (en)

Similar Documents

Publication Publication Date Title
US20130132166A1 (en) Smart toll network for improving performance of vehicle identification systems
CN110751828B (en) Road congestion measuring method and device, computer equipment and storage medium
CN110264734A (en) A kind of vehicle on highway auditing system and its working method
CN110443904B (en) Missed fee detection method, device, server and storage medium
CN111105514B (en) Vehicle fee deduction method, device, system, equipment and storage medium
CN104732205A (en) System for checking expressway toll evasion
CN104867192A (en) Automobile driving path identification system based on automotive electronic identification, and method thereof
CN111369801B (en) Vehicle identification method, device, equipment and storage medium
CN110728759B (en) ETC portal transaction success rate detection method and device, computing equipment and medium
KR20090069943A (en) Highway passage money collection system using vehicle-number and model recognition
CN117746643A (en) Vehicle abnormal problem identification method, device, medium and electronic equipment
CN113674442B (en) Non-inductive passing method, device, electronic equipment and computer readable storage medium
CN114023085B (en) Intersection signal timing parameter inference method based on bayonet detection data
CN114038075B (en) New generation lane charge auditing integrated system
KR20090077114A (en) System for checking an unpaid car of the toll road and controlling method for the same
CN114780591A (en) Calculation method and system for detecting travel license plate recognition error
WO2017169012A1 (en) Identification information determination device, identification information determination system, computer program, and identification information determination method
CN111369790B (en) Vehicle passing record correction method, device, equipment and storage medium
CN113962331A (en) ETC portal system fault reason identification method and system
CN116305735B (en) Computer data remote management system and method based on Internet of things
CN117373259B (en) Expressway vehicle fee evasion behavior identification method, device, equipment and storage medium
CN117218852A (en) Method and device for analyzing whether vehicle is suspected to be in or out, electronic equipment and medium
KR20130077922A (en) Electronic toll collecting system and method thereof
CN113096257A (en) High-speed toll vehicle type matching method based on cloud platform
CN108182805A (en) A kind of vehicle on highway method for managing and monitoring that biradical modeling is doubted based on letter

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