CN110415512B

CN110415512B - Vehicle information management method, device and storage medium

Info

Publication number: CN110415512B
Application number: CN201810398323.9A
Authority: CN
Inventors: 董则恒
Original assignee: Hangzhou Hikvision Digital Technology Co Ltd
Current assignee: Hangzhou Hikvision Digital Technology Co Ltd
Priority date: 2018-04-28
Filing date: 2018-04-28
Publication date: 2021-04-27
Anticipated expiration: 2038-04-28
Also published as: CN110415512A

Abstract

The invention discloses a vehicle information management method, a vehicle information management device and a storage medium, and belongs to the technical field of big data processing. The method comprises the following steps: and determining a plurality of vehicle files according to the N data sources, and searching the vehicle file of the same vehicle corresponding to the target vehicle file from the stored vehicle files. And updating the attribute value of the attribute A in the searched vehicle file according to the attribute statistical type of the attribute A for any attribute A in the plurality of attributes included in the target vehicle file. In the invention, when the data sources are different, the determined information types of the vehicles are also different, and excessive human resources are not needed, thus being beneficial to the popularization of the vehicle information management method. In addition, the statistical type of the attributes in the vehicle files comprises an accumulated attribute and a time limit attribute, and after a plurality of vehicle files are determined according to the N data sources, the searched vehicle files can be correspondingly updated according to the attribute statistical type corresponding to the attribute A, so that the flexibility of vehicle information management is improved.

Description

Vehicle information management method, device and storage medium

Technical Field

The invention relates to the technical field of big data processing, in particular to a vehicle information management method, a vehicle information management device and a storage medium.

Background

With the increasing number of vehicles, information of different vehicles needs to be managed to form a vehicle file system so that relevant departments can quickly refer to information of a certain vehicle. For example, a traffic authority may refer to violation information for a vehicle via a vehicle profile system.

In the related art, when information management needs to be performed on vehicles, information of each vehicle is collected in a manual mode, the information of each vehicle is distinguished according to corresponding license plate numbers, and then the information of the vehicle corresponding to each license plate number is input in a manual mode to obtain a vehicle file system. For example, a worker of a vehicle management department manually registers information of each vehicle, the registered information may include license plate numbers, drunk driving times, red light running times, illegal parking times and the like, the information of each vehicle is manually entered into a computer, and the information of different vehicles is distinguished according to the license plate numbers to obtain a vehicle file system. Subsequently, if a traffic management department needs to look up the drunk driving times of a certain vehicle, the vehicle file system is inquired according to the license plate number of the vehicle.

Because the information of each vehicle is collected manually in the method, the type of the recorded information of the vehicles is possibly single, the labor cost is high, and the popularization and the application of the vehicle file system are not facilitated.

Disclosure of Invention

In order to solve the problems of the related art, embodiments of the present invention provide a vehicle information management method, apparatus, and storage medium. The technical scheme is as follows:

in a first aspect, a vehicle information management method is provided, the method including:

determining a plurality of vehicle files according to N data sources, wherein each vehicle file comprises a plurality of attributes of the same vehicle and an attribute value of each attribute, each attribute is used for describing driving characteristics of the corresponding vehicle or characteristics of the vehicle, the data in the N data sources are acquired in a first preset time period before the current time, and N is a positive integer greater than or equal to 1;

searching a vehicle file of the same vehicle corresponding to a target vehicle file from the stored vehicle files, wherein the target vehicle file is one of the plurality of vehicle files;

for any attribute A in the plurality of attributes included in the target vehicle file, if the attribute statistical type corresponding to the attribute A is an accumulated attribute, combining the attribute value of the attribute A in the target vehicle file into the found attribute value of the attribute A in the vehicle file, wherein the accumulated attribute refers to the corresponding attribute used for describing the characteristic of the vehicle before the current time;

if the attribute statistical type corresponding to the attribute A is a time limit attribute, combining the attribute value of the attribute A in the target vehicle file into the found attribute value of the attribute A in the vehicle file, and deleting the attribute value which does not belong to a second preset time period in the combined attribute value of the attribute A, wherein the time limit attribute refers to that the corresponding attribute is used for describing the characteristics of the vehicle in the second preset time period before the current time, and the duration of the second preset time period is longer than that of the first preset time period.

Optionally, the determining a plurality of vehicle profiles from the N data sources includes:

acquiring N data sources;

determining at least one attribute of each vehicle present in each data source and an attribute value of each of the at least one attribute, based on a plurality of pieces of data included in each data source;

and combining the attributes of all vehicles appearing in the N types of data sources according to the mode of combining the attributes of the same vehicle to obtain a plurality of vehicle files, wherein each vehicle file comprises a plurality of attributes of the same vehicle and the attribute value of each attribute.

Optionally, each data in the plurality of data included in each data source corresponds to a set of license plate numbers and license plate colors, and the set of license plate numbers and license plate colors are used for identifying a vehicle;

the determining at least one attribute of each vehicle present in each data source and an attribute value of each of the at least one attribute, based on a plurality of pieces of data included in each data source, includes:

classifying a plurality of pieces of data included by each data source according to the difference of the license plate number and the license plate color to obtain a plurality of data sets corresponding to each data source, wherein each data set corresponds to one vehicle;

at least one attribute of the vehicle corresponding to each data set and an attribute value of each attribute are determined from the data included in each data set.

Optionally, there is an attribute of which the type is a dictionary attribute in the plurality of attributes included in each vehicle record, where the dictionary attribute means that the corresponding attribute includes a plurality of dictionaries, each dictionary is an instance of the corresponding attribute, and each dictionary corresponds to a dictionary value, and the dictionary value is used to describe the number of occurrences of the corresponding dictionary;

the determining at least one attribute of each vehicle present in each data source based on the plurality of pieces of data included in each data source includes:

determining all dictionaries corresponding to each vehicle appearing in each data source and the appearance times of each dictionary according to a plurality of pieces of data included in each data source;

and classifying dictionaries belonging to the same attribute in all dictionaries corresponding to each vehicle appearing in each data source to obtain a plurality of dictionary sets corresponding to each vehicle, wherein the attribute corresponding to the dictionary included in each dictionary set is an attribute of the corresponding vehicle, and the dictionary value of each dictionary included in each dictionary set is the attribute value of the corresponding attribute.

Optionally, the merging the attributes of all vehicles appearing in the N types of data sources in a manner of merging the attributes of the same vehicle to obtain a plurality of vehicle profiles includes:

determining a plurality of attribute sets, wherein each attribute set comprises all attributes of the same vehicle appearing in the N data sources and the attribute value of each attribute;

and removing the attribute which repeatedly appears in each attribute set and the attribute value of the attribute which repeatedly appears, and generating a vehicle file of the corresponding vehicle according to each attribute set after removal.

Optionally, the N data sources include at least one of a data source corresponding to a license plate recognition database, a data source corresponding to a vehicle management database, a data source corresponding to a cloud analysis database, and a data source corresponding to a study and judgment database, the license plate recognition database includes a plurality of pieces of license plate recognition data, each piece of license plate recognition data includes at least one of license plate number information and license plate color information recognized by a camera from a photographed license plate picture, photographing time information when the camera photographs the license plate picture, and position information of a corresponding vehicle when the camera photographs the license plate picture, each piece of vehicle management database data in the vehicle management database includes at least one of license plate information, vehicle owner information, manufacturer information, vehicle inspection information, and vehicle size information of the corresponding vehicle, and the cloud analysis data in the cloud analysis database refers to data obtained by a server analyzing a video picture acquired by the camera for the vehicle, the judgment data in the judgment database refers to data determined by a vehicle judgment algorithm.

Optionally, the plurality of attributes includes static attributes, statistical attributes, and behavioral attributes;

the static attributes comprise at least one of fixed attributes, license plate attributes, vehicle management library attributes, secondary recognition vehicle attributes and model attributes, the fixed attributes are used for identifying corresponding vehicles, the license plate attributes are used for describing license plate information of the corresponding vehicles, the vehicle attributes are used for describing at least one of brand information, annual payment information and appearance information of the corresponding vehicles, the secondary recognition vehicle attributes are attributes of information of the corresponding vehicles obtained after collected video pictures of the corresponding vehicles are analyzed and recognized, and the model attributes refer to models obtained by learning information of the corresponding vehicles through preset learning models;

the statistical attributes comprise at least one of activity attributes and secondary recognition behavior attributes, the activity attributes are used for describing activity information of the corresponding vehicle in time and/or space dimensions, and the secondary recognition behavior attributes refer to attributes about personnel information in the vehicle obtained after analyzing the collected video pictures of the corresponding vehicle;

the behavior attributes are used to describe driving behavior of the corresponding vehicle.

In a second aspect, there is provided a vehicle information management apparatus, the apparatus including:

the vehicle profile determining module is used for determining a plurality of vehicle profiles according to N data sources, each vehicle profile comprises a plurality of attributes of the same vehicle and an attribute value of each attribute, each attribute is used for describing driving characteristics of the corresponding vehicle or characteristics of the vehicle, the data included in the N data sources are data collected in a first preset time period before the current time, and N is a positive integer greater than or equal to 1;

the searching module is used for searching a vehicle file of the same vehicle corresponding to a target vehicle file from the stored vehicle files, wherein the target vehicle file is one of the plurality of vehicle files;

a first merging module, configured to, for any attribute a in the multiple attributes included in the target vehicle profile, merge an attribute value of the attribute a in the target vehicle profile into a found attribute value of the attribute a in the vehicle profile if the attribute statistical type corresponding to the attribute a is an accumulated attribute, where the accumulated attribute is an attribute used for describing a feature of a vehicle before a current time;

and a second merging module, configured to merge the attribute value of the attribute a in the target vehicle file into the found attribute value of the attribute a in the vehicle file if the attribute statistical type corresponding to the attribute a is a time limit attribute, and delete an attribute value not within a second preset time period in the merged attribute values of the attribute a, where the time limit attribute refers to that the corresponding attribute is used to describe a feature of the vehicle within the second preset time period before the current time, and a duration of the second preset time period is longer than a duration of the first preset time period.

Optionally, the determining module includes:

an acquisition unit for acquiring N data sources;

a determination unit configured to determine at least one attribute of each vehicle appearing in each data source and an attribute value of each attribute of the at least one attribute, based on a plurality of pieces of data included in each data source;

and the merging unit is used for merging the attributes of all vehicles appearing in the N types of data sources according to the mode of merging the attributes of the same vehicle to obtain a plurality of vehicle files, and each vehicle file comprises a plurality of attributes of the same vehicle and an attribute value of each attribute.

the determining unit is specifically configured to:

Optionally, the merging unit is specifically configured to:

In a third aspect, there is provided a vehicle information management apparatus, the apparatus including:

a processor;

a memory for storing processor-executable instructions;

wherein the processor is configured to perform the steps of any of the methods of the first aspect described above.

In a fourth aspect, a computer-readable storage medium is provided, having instructions stored thereon, which when executed by a processor, implement the steps of any of the methods of the first aspect described above.

According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product containing instructions which, when run on a computer, cause the computer to perform the steps of any of the methods described above in the first aspect.

The technical scheme provided by the embodiment of the invention has the following beneficial effects:

in the embodiment of the invention, a plurality of vehicle files are determined according to N data sources, and the vehicle file of the same vehicle corresponding to the target vehicle file is searched from the stored vehicle files, wherein the target vehicle file is one of the plurality of vehicle files. And for any attribute A in the plurality of attributes included in the target vehicle file, if the attribute statistical type corresponding to the attribute A is the accumulated attribute, combining the attribute value of the attribute A in the target vehicle file into the searched attribute value of the attribute A in the vehicle file. And if the attribute statistical type corresponding to the attribute A is the time limit attribute, combining the attribute values of the attribute A in the target vehicle file into the found attribute values of the attribute A in the vehicle file, and deleting the attribute values which do not belong to the second preset time period in the combined attribute values of the attribute A. In the embodiment of the invention, the vehicle file of each vehicle is determined according to the N data sources, and when the data sources are different, the information types of the determined vehicles are also different, so that the information included in the determined vehicle file is relatively comprehensive, excessive human resources are not required to be spent, and the popularization of the vehicle information management method is facilitated. In addition, the statistical type of the attributes in the vehicle files comprises an accumulated attribute and a time limit attribute, and after a plurality of vehicle files are determined according to the N data sources, the searched vehicle files can be correspondingly updated according to the attribute statistical type corresponding to the attribute A, so that the flexibility of vehicle information management is improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1 is a flow chart of a vehicle information management method according to an embodiment of the present invention;

fig. 2 is a block diagram of a vehicle information management apparatus according to an embodiment of the present invention;

fig. 3 is a block diagram of another vehicle information management apparatus according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

Before explaining the embodiments of the present invention in detail, terms related to the embodiments of the present invention will be described.

And the attribute is used for describing the driving characteristics of the corresponding vehicle or the characteristics of the vehicle. For example, the license plate number of the vehicle is an attribute of the vehicle, the color of the vehicle is an attribute of the vehicle, and the number of times that the vehicle passes through a certain gate in a certain period of time may also be an attribute of the vehicle.

And accumulating the attributes, namely the corresponding attributes are used for describing the characteristics of the vehicle before the current time. For example, if the attribute is the number of times that the vehicle is driven by the owner without wearing the seat belt, the attribute is all the times that the vehicle is driven by the owner without wearing the seat belt before the current time.

The time limit attribute refers to that the corresponding attribute is the characteristic of the vehicle in a certain time period. For example, the number of times that the vehicle enters the city within the last 7 days is the time limit attribute.

Dictionary attribute means that an attribute includes a plurality of dictionaries, each dictionary is an instance of the attribute, and each dictionary corresponds to a dictionary value, and the dictionary value is used for describing the occurrence number of the corresponding dictionary. For example, the attribute "vehicle brand year money" of a certain vehicle includes a plurality of dictionaries, which are 2017, 2016, 2015, and 2014, and the corresponding dictionary values are 2, 0, 10, and 1, respectively, that is, for this vehicle, the counted number of times the vehicle brand year money is 2017 is 2, the counted number of times the vehicle brand year money is 2016 is 0, the counted number of times the vehicle brand year money is 2015 is 10, and the counted number of times the vehicle brand year money is 2014 is 1.

The following explains the vehicle information management method provided by the embodiment of the present invention in detail.

Fig. 1 is a flowchart of a vehicle information management method according to an embodiment of the present invention, and as shown in fig. 1, the method includes the following steps:

step 101, determining a plurality of vehicle files according to N data sources, wherein each vehicle file comprises a plurality of attributes of the same vehicle and an attribute value of each attribute, each attribute is used for describing driving characteristics of the corresponding vehicle or characteristics of the vehicle, the data included in the N data sources are data collected in a first preset time period before the current time, and N is a positive integer greater than or equal to 1.

Specifically, step 101 may be implemented by the following three steps:

step 1011: n data sources are obtained, wherein N is a positive integer greater than or equal to 1, and each data source comprises a plurality of pieces of data.

In the embodiment of the invention, in order to realize the comprehensive information management of the vehicle, the information of the vehicle is acquired from N data sources. That is, for each data source, the data source includes a plurality of pieces of data each describing a characteristic of a vehicle.

The first preset time period is a preset time period, and the first preset time period is 1 day, 2 days or 3 days and the like. For example, if the first preset time period is 1 day, the N data sources are N data sources counted within 1 day before the current time.

In one possible implementation, the N data sources include at least one of a data source corresponding to the card identification database, a data source corresponding to the vehicle management database, a data source corresponding to the cloud analysis database, and a data source corresponding to the study and judgment database. For example, N is 4, that is, the four acquired data sources are a data source corresponding to the card identification database, a data source corresponding to the vehicle management database, a data source corresponding to the cloud analysis database, and a data source corresponding to the study and judgment database.

The above four data sources are only used for illustration, and in practical applications, any data source for describing the characteristics of the vehicle may be used as the data source in step 1011, and the embodiment of the present invention is not limited in detail here.

The license plate identification database comprises a plurality of pieces of license plate identification data, and each piece of license plate identification data comprises at least one of license plate number information and license plate color information which are identified by a camera from a shot license plate picture, shooting time information when the camera shoots the license plate picture and position information of a corresponding vehicle when the camera shoots the license plate picture.

Each piece of vehicle management library data in the vehicle management library comprises at least one of license plate information, owner information, manufacturer information, vehicle inspection information and vehicle size information of the corresponding vehicle. The license plate information may include whether a license plate of a corresponding vehicle is a grade license plate. The manufacturer information may include a manufacturer name or a manufacturer name of the corresponding vehicle. The vehicle inspection information may include an initial registration date, a latest scheduled inspection date, an inspection validity expiration date, and a forced scrapping expiration date. The vehicle dimension information may include vehicle profile length, vehicle profile width, and vehicle profile height information.

In practical applications, the vehicle management library data in the vehicle management library may be any data registered by the vehicle in the vehicle management, and is not limited to the aforementioned license plate information, owner information, manufacturer information, vehicle inspection information, and vehicle size information. For example, the vehicle management library data may further include identity information of an owner of the corresponding vehicle registered in the vehicle management library, or engine number information of the corresponding vehicle, and the like.

The cloud analysis data in the cloud analysis database refers to data obtained by analyzing video pictures acquired by the camera for the vehicle by the server. For example, the cloud analysis data may be whether the vehicle is a local vehicle, whether the vehicle is a yellow-label vehicle, a brand of the vehicle, a color of the vehicle, a brand year of the vehicle, whether a pendant is on the vehicle, a current position of the vehicle, whether a primary driver fastens a safety belt, whether a secondary driver fastens a safety belt, whether a child is in a front row, whether a skylight is occupied, whether the primary driver is using a mobile phone, and the like. That is, in practical application, the cloud analysis data may be any data analyzed by the server for the video pictures collected by the camera.

The judgment data in the judgment database refers to data determined by a vehicle judgment algorithm, for example, the judgment data includes data describing whether the vehicle is a fake-plate vehicle and/or a fake-plate vehicle. Of course, the judgment data may also be information of other vehicles determined by a judgment algorithm, and is not limited herein.

In addition, it should be noted that, for each data source, each piece of data in the plurality of pieces of data included in each data source corresponds to a set of license plate numbers and license plate colors, and the set of license plate numbers and license plate colors are used to identify one vehicle. That is, for any piece of data included in each data source, the piece of data corresponds to a set of license plate numbers and license plate colors, and the piece of data is used to describe a feature of the vehicle to which the license plate numbers and license plate colors correspond.

For example, the card identification database includes a plurality of card identification data, each card identification data corresponding to a set of license plate numbers and license plate colors. For a plurality of vehicle management library data in the vehicle management library, each vehicle management library data corresponds to a group of license plate numbers and license plate colors. For a plurality of pieces of cloud analysis data in the cloud analysis database, each piece of cloud analysis data corresponds to a set of license plate numbers and license plate colors. For a plurality of pieces of judging data in the judging database, each piece of judging data corresponds to a group of license plate numbers and license plate colors.

Step 1012: according to the plurality of pieces of data included in each data source, at least one attribute of each vehicle appearing in each data source and an attribute value of each attribute of the at least one attribute are determined, each attribute being used for describing a driving feature of the corresponding vehicle or a feature of the vehicle itself.

As can be seen from step 1011, each data in the plurality of data included in each data source corresponds to a group of license plate numbers and license plate colors, and the group of license plate numbers and license plate colors are used to identify one vehicle, so step 1012 can be specifically implemented by the following two steps:

(1) and classifying the plurality of data included by each data source according to the difference of the license plate number and the license plate color to obtain a plurality of data sets in each data source, wherein each data set corresponds to one vehicle.

For example, for a plurality of pieces of cloud analysis data in the cloud analysis database, each piece of cloud analysis data corresponds to one group of license plate numbers and license plate colors, and therefore the plurality of pieces of cloud analysis data can be classified according to the difference between the license plate numbers and the license plate colors to obtain a plurality of data sets, each data set includes at least one piece of cloud analysis data, and the license plate numbers and the license plate colors corresponding to the cloud analysis data included in each data set are the same, that is, the cloud analysis data included in each data set is the cloud analysis data describing the same vehicle.

Since the cloud analysis data included in each data set is cloud analysis data describing the same vehicle, for each data set, at least one attribute of the corresponding vehicle and an attribute value of each attribute may be analyzed according to the data included in the data set, and specifically, the at least one attribute of the corresponding vehicle and the attribute value of each attribute may be analyzed through the following step (2).

For convenience of description, the attributes of the vehicle provided by the embodiment of the present invention are explained herein.

In an embodiment of the present invention, the attributes of the vehicle include static attributes, statistical attributes, and behavior attributes.

The static attributes comprise at least one of fixed attributes, license plate attributes, vehicle management library attributes, secondary recognition vehicle attributes and model attributes.

Specifically, the fixed attribute is used to identify the corresponding vehicle, for example, the fixed attribute may be a license plate number and a license plate color of the corresponding vehicle. The vehicle attribute is used for describing at least one of brand information, annuity information and appearance information of the corresponding vehicle, for example, the vehicle attribute includes a vehicle brand, a vehicle annuity, a vehicle color, a vehicle depth and a vehicle picture of the corresponding vehicle. The license plate attributes are used for describing license plate information of the corresponding vehicle, for example, the license plate attributes include a license plate attribution, a license plate type and a license plate state of the corresponding vehicle.

The attribute of the car management library refers to an attribute analyzed according to data in the car management library, for example, the attribute of the car management library may include whether a license plate is registered, whether a vehicle is a mortgage vehicle, information of a car owner, a vehicle identification code, whether an imported vehicle is, an engine number, a car body color, a car body size, manufacturer information, car inspection information, and the like.

The secondary identification vehicle attribute is an attribute about information of the vehicle obtained after the collected video image of the corresponding vehicle is analyzed and identified, for example, the secondary identification vehicle attribute includes the number of times that the corresponding vehicle is a yellow-labeled vehicle, whether dangerous goods exist and whether hanging decorations exist. The yellow-mark vehicle refers to a vehicle with the exhaust emission passing the emission threshold, and the emission threshold is set by a relevant part.

The model attribute refers to a model obtained by learning information of a corresponding vehicle through a preset learning model. The preset learning model is a network model previously trained by training data, and is not described in detail herein.

Second, the statistical attribute includes at least one of an activity attribute and a secondary recognition behavior attribute.

In particular, the activity attributes are used to describe activity information of the corresponding vehicle in a temporal and/or spatial dimension. For example, the activity attribute includes the number of times that the corresponding vehicle passes through the target region range within a third preset time period, the number of times that the corresponding vehicle passes through the target region range within each fourth preset time period included in the third preset time period, the number of times that the corresponding vehicle passes through each gate within the target region range within the third preset time period, and the number of times that the corresponding vehicle passes through each region within the target region range within the third preset time period.

Wherein, the third preset time period and the fourth preset time period are preset time periods, the third preset time period may be 7 days, 15 days, 30 days or the like, and the fourth preset time period may be 1 hour, 2 hours, 3 hours or the like. For example, if the fourth preset time period is 1 hour, the third preset time period is 7 days, and the target region range is xxv, the activity attribute includes the number of times that the corresponding vehicle has passed xxv within the last 7 days, the number of times that the corresponding vehicle has passed xxv within each hour within the last 7 days, the number of times that the corresponding vehicle has passed each gate within xxv within the last 7 days, and the number of times that the corresponding vehicle has passed each region of xxv within the last 7 days.

The secondary recognition behavior attribute refers to an attribute about the information of the person in the vehicle, which is obtained after analyzing the collected video picture of the corresponding vehicle. For example, the secondary recognition behavior attribute includes at least one of the number of times that the sun visor is opened by the primary/secondary driver at night, the number of times that the safety belt is not fastened by the primary/secondary driver, the number of times that the telephone is made by the primary driver, the number of times that the child is in the front row, and the number of times that the person stands in the skylight.

In addition, the behavior attributes are used to describe the driving behavior of the corresponding vehicle. For example, the behavior attributes include the number of violations, the number of fake plate decks, the number of departure/entrance into a city, the number of night driving, the position information of foothold, and the driving track information. The foothold refers to a position point where the parking time of the corresponding vehicle exceeds a parking time threshold value. The parking time threshold is a preset time period, for example, the parking time threshold is 4 hours, and then the foothold refers to a position point corresponding to the parking time of the vehicle exceeding 4 hours.

The classification of the attributes of the vehicle is only one implementation manner, and in practical applications, the attributes of the vehicle may be counted according to other classification manners.

(2) At least one attribute of the vehicle corresponding to each data set and an attribute value of each attribute are determined from the data included in each data set.

Specifically, for any data set, according to the vehicle attributes appearing in the step (1), analyzing the data included in the data set to obtain at least one attribute of the vehicle corresponding to the data set and an attribute value of each attribute.

In addition, in the embodiment of the present invention, among the plurality of attributes included in the vehicle profile of each vehicle, there is an attribute whose type is a dictionary attribute, in which the corresponding attribute includes a plurality of dictionaries, each dictionary is an instance of the corresponding attribute, and each dictionary corresponds to a dictionary value describing the number of occurrences of the corresponding dictionary.

In this case, the implementation manner of step 1012 may specifically be: determining all dictionaries corresponding to each vehicle and the occurrence frequency of each dictionary in each data source; and classifying the dictionaries belonging to the same attribute in all the dictionaries corresponding to each vehicle to obtain a plurality of dictionary sets, wherein the attribute corresponding to each dictionary set is an attribute of the corresponding vehicle, and the dictionary value of each dictionary in each dictionary set is the attribute value of the corresponding attribute.

For example, after counting a plurality of data included in any data source, the number of occurrences of the dictionary "year of 2017" corresponding to a certain vehicle is 1, the number of occurrences of the dictionary "year of 2016" is 0, the number of occurrences of the dictionary "year of 2015" is 10, the number of occurrences of the dictionary "vehicle color yellow" is 10, the number of occurrences of the dictionary "vehicle color green" is 1, and the number of occurrences of the dictionary "vehicle color red" is 0.

The dictionary "year of year is 2017", the dictionary "year of year is 2016" and the dictionary "year of year is 2015" correspond to the same attribute: the vehicle brand year money, the dictionary "the vehicle color is yellow", the dictionary "the vehicle color is green" and the dictionary "the vehicle color is red" correspond to the same attribute: the color of the vehicle. That is, for this vehicle, the attribute "vehicle brand year money" includes 3 dictionaries: the dictionary has the dictionary values of 1 time, 0 time and 10 times respectively, wherein the dictionary has the annual payment of 2017, the dictionary has the annual payment of 2016 and the dictionary has the annual payment of 2015. The attribute "vehicle color" includes three dictionaries: the dictionary "the vehicle color is yellow", the dictionary "the vehicle color is green", and the dictionary "the vehicle color is red", and the dictionary values corresponding to these three dictionaries are 10 times, 1 time, and 0 time, respectively.

It should be noted that step 1012 is to perform the operation of step 1012 for each of the N data sources, that is, for any one of the N data sources, at least one attribute of each vehicle appearing in the data source and an attribute value of each attribute in the at least one attribute are determined through step 1012.

Step 1013: and combining the attributes of all vehicles appearing in the N types of data sources according to the mode of combining the attributes of the same vehicle to obtain a plurality of vehicle files, wherein each vehicle file comprises a plurality of attributes of the same vehicle and the attribute value of each attribute.

Since step 1012 is performed for each data source, that is, at least one attribute of each vehicle corresponding to each data source can be obtained through step 1012 for each data source. After each data source is processed, since different data sources may include attributes of the same vehicle, it is necessary to merge the attributes of the respective vehicles corresponding to the various data sources.

The implementation manner of step 1013 may specifically be: determining a plurality of attribute sets, wherein each attribute set comprises all attributes of the same vehicle appearing in N data sources and the attribute value of each attribute, eliminating the attribute appearing repeatedly in each attribute set and the attribute value of the attribute appearing repeatedly, and generating a vehicle file of the corresponding vehicle according to each attribute set after elimination.

The following description will be given by taking an example of how to merge attributes, where the following example also merges attribute values corresponding to the merged attributes according to the above method when merging the attributes.

For example, the N data sources are data source 1, data source 2, and data source 3, respectively. The attributes of each vehicle obtained from the data source 1 are shown in table 1 below. Wherein at least one property of the vehicle 1 is available from the data source 1: attribute 1, attribute 2, attribute 3. Obtaining at least one property of the vehicle 2: attribute 1, attribute 3, attribute 4. Obtaining at least one property of the vehicle 3: attribute 1, attribute 2, attribute 3. Obtaining at least one property of the vehicle 4: attribute 1, attribute 2, attribute 3. Obtaining at least one attribute of the vehicle 5: attribute 3, attribute 4, attribute 6.

TABLE 1

The attributes of each vehicle obtained from the data source 2 are shown in table 2 below. Wherein at least one property of the vehicle 1 is available from the data source 2: attribute 1, attribute 2, attribute 4. Obtaining at least one property of the vehicle 3: attribute 5, attribute 3, attribute 4. Obtaining at least one property of the vehicle 4: attribute 1, attribute 6, attribute 3. Obtaining at least one attribute of the vehicle 5: attribute 5, attribute 6, attribute 7. Obtaining at least one attribute of the vehicle 6: attribute 3, attribute 4, attribute 6.

TABLE 2

The attributes of each vehicle obtained from the data source 3 are shown in table 3 below. Wherein at least one property of the vehicle 1 is available from the data source 3: attribute 8, attribute 9, attribute 3. Obtaining at least one property of the vehicle 2: attribute 1, attribute 3, attribute 4. Obtaining at least one property of the vehicle 4: attribute 9, attribute 2, attribute 3. Obtaining at least one attribute of the vehicle 5: attribute 1, attribute 9, attribute 3. Obtaining at least one attribute of the vehicle 6: attribute 4, attribute 5, attribute 6.

TABLE 3

The attribute list shown in table 4 below may be used to normalize the attributes in the three tables, i.e., count the attributes belonging to the same vehicle.

The attributes corresponding to the vehicle 1 are: attributes 1, 2, and 3 corresponding to the data source 1, attributes 1, 2, and 4 corresponding to the data source 2, and attributes 8, 9, and 3 corresponding to the data source 3.

The attributes corresponding to the vehicle 2 are: attributes 1, 3, and 4 corresponding to the data source 1, and attributes 1, 3, and 4 corresponding to the data source 3.

The corresponding attributes of the vehicle 3 are: attribute 1, attribute 2, and attribute 3 corresponding to the data source 1, and attribute 5, attribute 3, and attribute 4 corresponding to the data source 2.

The corresponding attributes of the vehicle 4 are: attributes 1, 2, and 3 corresponding to the data source 1, attributes 1, 6, and 3 corresponding to the data source 2, and attributes 9, 2, and 3 corresponding to the data source 3.

The corresponding attributes of the vehicle 5 are: attributes 3, 4, and 6 corresponding to the data source 1, attributes 5, 6, and 7 corresponding to the data source 2, and attributes 1, 9, and 3 corresponding to the data source 3.

The corresponding attributes of the vehicle 6 are: attributes 3, 4, and 6 corresponding to the data source 2, and attributes 4, 5, and 6 corresponding to the data source 3.

TABLE 4

It can be found from the attributes corresponding to the vehicles that there may be more than two same attributes for a certain vehicle, and the repeated attributes are eliminated. At this time, the attributes of each vehicle are obtained as shown in table 5 below.

TABLE 5

As shown in table 5, after removing the repeated attributes, the attributes in the attribute set corresponding to each vehicle are different from each other, and a vehicle profile corresponding to each vehicle can be generated from the attribute set corresponding to each vehicle and the attribute value of each attribute in the attribute set.

Step 102, a vehicle file of the same vehicle corresponding to the target vehicle file is searched from the stored vehicle files, wherein the target vehicle file is one of the plurality of vehicle files.

In the embodiment of the present invention, in order to increase the speed of processing N data sources, only data sources in a certain time period are processed each time, and then the determined vehicle profile may be updated periodically according to the updated data sources. That is, the data included in each data source is the data collected in the first preset time period before the current time, so that the vehicle attribute in the vehicle file obtained in step 101 is the vehicle attribute in a certain time period, and therefore, the stored vehicle file needs to be updated according to the vehicle file obtained in step 101. Specifically, when the stored vehicle file is updated, the vehicle file of the same vehicle corresponding to the target vehicle file needs to be searched from the stored vehicle file, so as to update the searched vehicle file according to the target vehicle file.

In a possible implementation manner, when a license plate number and a license plate color are used to identify a vehicle, step 102 may specifically be: and determining the license plate number and the license plate color of the corresponding vehicle of the target vehicle file, selecting the vehicle file with the license plate number and the license plate color consistent with the determined license plate number and the determined license plate color from the stored vehicle file, wherein the selected vehicle file is the vehicle file of the same vehicle corresponding to the target vehicle file.

When the found vehicle profile is determined through step 102, the found vehicle profile may be updated according to the target vehicle profile. In the embodiment of the invention, a corresponding attribute statistical type is set for each attribute, and the attribute statistical type comprises an accumulated attribute and a time limit attribute. The accumulated attribute refers to that the corresponding attribute is used for describing the characteristics of the vehicle before the current time, the time limit attribute refers to that the corresponding attribute is used for describing the characteristics of the vehicle in a second preset time period before the current time, and the duration of the second preset time period is greater than that of the first preset time period. Therefore, the searched vehicle profile can be updated according to the target vehicle profile in the following two cases, step 103 and step 104.

Step 103, for any attribute a in the plurality of attributes included in the target vehicle profile, if the attribute statistical type corresponding to the attribute a is an accumulated attribute, merging the attribute value of the attribute a in the target vehicle profile into the found attribute value of the attribute a in the vehicle profile, where the accumulated attribute is an attribute corresponding to which is used to describe the characteristic of the vehicle before the current time.

When the attribute statistical type corresponding to the attribute A is the accumulated attribute, only the attribute value of the attribute A in the target vehicle file needs to be merged into the found attribute value of the attribute A in the vehicle file.

For example, the first time period is 1 day, and if the attribute a is the number of times that the driver does not fasten the seat belt, the attribute a is an accumulated attribute. At this time, for any data source, since the data source records data within 1 day before the current time, the number of times of the primary driving without fastening the seat belt of the target vehicle file obtained in step 103 refers to the number of times of the vehicle without fastening the seat belt within 1 day before the current time, and therefore, the number of times of the primary driving without fastening the seat belt in the target vehicle file and the number of times of finding that the vehicle does not fasten the seat belt in the vehicle file need to be combined to obtain the number of times of the vehicle without fastening the seat belt before the current time. That is, the attribute value of the attribute a in the target vehicle profile is merged into the found attribute value of the attribute a in the vehicle profile.

And 104, if the attribute statistical type corresponding to the attribute A is a time limit attribute, combining the attribute values of the attribute A in the target vehicle file into the found attribute values of the attribute A in the vehicle file, and deleting the attribute values which do not belong to the second preset time period in the combined attribute values of the attribute A, wherein the time limit attribute refers to that the corresponding attribute is used for describing the characteristics of the vehicle in the second preset time period before the current time, and the duration of the second preset time period is longer than that of the first preset time period.

When the attribute statistical type corresponding to the attribute a is the time limit attribute, after the attribute value of the attribute a in the target vehicle profile is merged into the found attribute value of the attribute a in the vehicle profile, the expired data in the merged attribute value of the attribute a needs to be deleted.

For example, if the attribute a indicates the number of urban entries in the last 7 days and the current time is No. 1 month 8, the number of urban entries in the target vehicle file is No. 1 month 8. At this time, the number of times of entering the city in the target vehicle file is found to be the number of times of entering the city within 7 days from No. 1 month to No. 1 month 7, and therefore, after the number of times of entering the city in the target vehicle file and the number of times of entering the city in the found vehicle file are combined, the expired data (number of times of entering the city of No. 1 month 1) of the vehicle in the found vehicle file needs to be deleted. After the expiration data is deleted, the number of times the vehicle enters the city in the searched vehicle file is the number of times the vehicle enters the city in the time period from 1 month 2 to 1 month 7.

It should be noted that, when N is greater than 1, in the above steps 101 to 104, a plurality of vehicle profiles are obtained according to a plurality of data sources, and then the stored vehicle profile is updated according to the obtained vehicle profile. Alternatively, when N is 1, in the above steps 101 to 104, a plurality of vehicle profiles are obtained from one data source, and then the stored vehicle profile is updated according to the obtained vehicle profile, at this time, if there are a plurality of data sources, the plurality of data sources may be sequentially processed in the above steps 101 to 104 until all the data sources are processed.

For example, there are currently 3 data sources, which are respectively marked as a first data source, a second data source and a third data source, and N in steps 101 to 104 is 1. A plurality of vehicle profiles are obtained according to a first data source through steps 101 to 104, stored vehicle profiles are updated according to the obtained plurality of vehicle profiles, and each updated vehicle profile is stored. Then, a plurality of vehicle profiles are obtained according to the second data source through steps 101 to 104, and each vehicle profile after the latest update is continuously updated according to the plurality of vehicle profiles obtained at this time. Finally, a plurality of vehicle files are obtained according to the third data source through steps 101 to 104, and each vehicle file after the latest update is continuously updated according to the plurality of vehicle files obtained at the moment.

In the embodiment of the invention, a plurality of vehicle files are determined according to N data sources, and the vehicle file of the same vehicle corresponding to the target vehicle file is searched from the stored vehicle files, wherein the target vehicle file is one of the plurality of vehicle files. And for any attribute A in the plurality of attributes included in the target vehicle file, if the attribute statistical type corresponding to the attribute A is the accumulated attribute, combining the attribute value of the attribute A in the target vehicle file into the searched attribute value of the attribute A in the vehicle file. And if the attribute statistical type corresponding to the attribute A is the time limit attribute, combining the attribute values of the attribute A in the target vehicle file into the found attribute values of the attribute A in the vehicle file, and deleting the attribute values which do not belong to the second preset time period in the combined attribute values of the attribute A. In the embodiment of the invention, the vehicle file of each vehicle is determined according to the N data sources, and when the data sources are different, the information types of the determined vehicles are also different, so that the information included in the determined vehicle file is relatively comprehensive, excessive human resources are not required to be spent, and the popularization of the vehicle information management method is facilitated. In addition, the statistical types of the attributes in the vehicle files comprise accumulated attributes and time limit attributes, and after a plurality of vehicle files are determined according to the N data sources, the searched vehicle files can be correspondingly updated according to the attribute statistical type corresponding to the attribute A, so that the flexibility of vehicle information management is improved.

Fig. 2 is a vehicle information management apparatus according to an embodiment of the present invention, and as shown in fig. 2, the apparatus 200 includes a determining module 201, a searching module 202, a first merging module 203, and a second merging module 204:

the determining module 201 is configured to determine a plurality of vehicle profiles according to N data sources, where each vehicle profile includes a plurality of attributes of the same vehicle and an attribute value of each attribute, each attribute is used to describe a driving feature of a corresponding vehicle or a vehicle own feature, data included in the N data sources is data acquired in a first preset time period before a current time, and N is a positive integer greater than or equal to 1;

the searching module 202 is used for searching a vehicle file of the same vehicle corresponding to a target vehicle file from the stored vehicle files, wherein the target vehicle file is one of a plurality of vehicle files;

the first merging module 203 is configured to, for any attribute a in the plurality of attributes included in the target vehicle profile, merge an attribute value of the attribute a in the target vehicle profile into a found attribute value of the attribute a in the vehicle profile if the attribute statistical type corresponding to the attribute a is an accumulated attribute, where the accumulated attribute is an attribute used for describing a feature of the vehicle before the current time;

the second merging module 204 is configured to merge the attribute value of the attribute a in the target vehicle file into the found attribute value of the attribute a in the vehicle file if the attribute statistical type corresponding to the attribute a is a time limit attribute, and delete an attribute value not within a second preset time period in the merged attribute value of the attribute a, where the time limit attribute is used for describing a feature of the vehicle within the second preset time period before the current time, and a duration of the second preset time period is longer than a duration of the first preset time period.

Optionally, the determining module 201 includes:

an acquisition unit for acquiring N data sources;

a determination unit configured to determine at least one attribute of each vehicle appearing in each data source and an attribute value of each of the at least one attribute, based on a plurality of pieces of data included in each data source;

and the merging unit is used for merging the attributes of all vehicles appearing in the N data sources according to the mode of merging the attributes of the same vehicle to obtain a plurality of vehicle files, and each vehicle file comprises a plurality of attributes of the same vehicle and an attribute value of each attribute.

a determination unit, specifically configured to:

Optionally, there is an attribute of which the type is a dictionary attribute in the plurality of attributes included in each vehicle record, where a dictionary attribute means that the corresponding attribute includes a plurality of dictionaries, each dictionary is an instance of the corresponding attribute, and each dictionary corresponds to a dictionary value, and the dictionary value is used to describe the number of occurrences of the corresponding dictionary;

a determination unit, specifically configured to:

Optionally, the merging unit is specifically configured to:

determining a plurality of attribute sets, wherein each attribute set comprises all attributes of the same vehicle appearing in N data sources and an attribute value of each attribute;

and eliminating the attribute which repeatedly appears in each attribute set and the attribute value of the attribute which repeatedly appears, and generating a vehicle file of the corresponding vehicle according to each attribute set after elimination.

Optionally, the N data sources include at least one of a data source corresponding to a license plate recognition database, a data source corresponding to a vehicle management database, a data source corresponding to a cloud analysis database, and a data source corresponding to a study database, the license plate recognition database includes a plurality of pieces of license plate recognition data, each piece of license plate recognition data includes at least one of license plate number information and license plate color information recognized by a camera from a photographed license plate picture, photographing time information when the camera photographs the license plate picture, and position information of a corresponding vehicle when the camera photographs the license plate picture, each piece of vehicle management database data in the vehicle management database includes at least one of license plate information, vehicle owner information, manufacturer information, vehicle inspection information, and vehicle size information of the corresponding vehicle, and cloud analysis data in the cloud analysis database refers to data obtained by a server analyzing a video picture acquired by the camera for the vehicle, the study and judgment data in the study and judgment database refers to data determined by a vehicle study and judgment algorithm.

the static attributes comprise at least one of fixed attributes, license plate attributes, vehicle management library attributes, secondary recognition vehicle attributes and model attributes, the fixed attributes are used for identifying corresponding vehicles, the license plate attributes are used for describing license plate information of the corresponding vehicles, the vehicle attributes are used for describing at least one of brand information, annuity information and appearance information of the corresponding vehicles, the secondary recognition vehicle attributes are attributes of information of the vehicles obtained after collected video pictures of the corresponding vehicles are analyzed and recognized, and the model attributes refer to models obtained by learning information of the corresponding vehicles through preset learning models;

the behavior attributes are used to describe the driving behavior of the corresponding vehicle.

It should be noted that: the vehicle information management device provided in the above embodiment is only illustrated by dividing the functional modules when managing the vehicle information, and in practical applications, the functions may be distributed by different functional modules according to needs, that is, the internal structure of the device may be divided into different functional modules to complete all or part of the functions described above. In addition, the vehicle information management device provided by the above embodiment and the vehicle information management method embodiment belong to the same concept, and specific implementation processes thereof are detailed in the method embodiment and are not described herein again.

Fig. 3 is another vehicle information management apparatus according to an embodiment of the present invention, and as shown in fig. 3, the apparatus 300 includes a Central Processing Unit (CPU)301, a system memory 304 including a Random Access Memory (RAM)302 and a Read Only Memory (ROM)303, and a system bus 305 connecting the system memory 304 and the central processing unit 301. The apparatus 300 also includes a basic input/output system (I/O system) 306, which facilitates the transfer of information between devices within the computer, and a mass storage device 307, which stores an operating system 313, application programs 314, and other program modules 315.

The basic input/output system 306 comprises a display 308 for displaying information and an input device 309, such as a mouse, keyboard, etc., for a user to input information. Wherein a display 308 and an input device 309 are connected to the central processing unit 301 through an input output controller 310 connected to the system bus 305. The basic input/output system 306 may also include an input/output controller 310 for receiving and processing input from a number of other devices, such as a keyboard, mouse, or electronic stylus. Similarly, an input-output controller 310 may also provide output to a display screen, a printer, or other type of output device.

The mass storage device 307 is connected to the central processing unit 301 through a mass storage controller (not shown) connected to the system bus 305. The mass storage device 307 and its associated computer-readable media provide non-volatile storage for the apparatus 300. That is, the mass storage device 307 may include a computer-readable medium (not shown) such as a hard disk or CD-ROM drive.

Without loss of generality, computer readable media may comprise computer storage media and communication media. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes RAM, ROM, EPROM, EEPROM, flash memory or other solid state memory technology, CD-ROM, DVD, or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices. Of course, those skilled in the art will appreciate that computer storage media is not limited to the foregoing. The system memory 304 and mass storage device 307 described above may be collectively referred to as memory.

According to various embodiments of the present application, the apparatus 300 may also operate as a remote computer connected to a network via a network, such as the Internet. That is, the apparatus 300 may be connected to the network 312 through the network interface unit 311 connected to the system bus 305, or may be connected to other types of networks or remote computer systems (not shown) using the network interface unit 311.

The memory further includes one or more programs, and the one or more programs are stored in the memory and configured to be executed by the CPU. The one or more programs include instructions for performing the above-described method for vehicle information management provided by the embodiments of the present application.

Embodiments of the present invention also provide a non-transitory computer-readable storage medium, where instructions in the storage medium, when executed by a processor of a mobile terminal, enable the mobile terminal to perform the method for managing vehicle information according to the foregoing embodiments.

Embodiments of the present invention further provide a computer program product containing instructions, which when run on a computer, cause the computer to execute the method for managing vehicle information described in the above embodiments.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims

1. A vehicle information management method, characterized by comprising:

determining a plurality of vehicle files according to N data sources, wherein each vehicle file comprises a plurality of attributes of the same vehicle and an attribute value of each attribute, each attribute is used for describing driving characteristics or self characteristics of the corresponding vehicle, the data in the N data sources is data collected in a first preset time period before the current time, N is a positive integer greater than or equal to 1, the N data sources comprise a data source corresponding to a card identification database, a data source corresponding to a vehicle management library, a data source corresponding to a cloud analysis database and a data source corresponding to a study and judgment database, the card identification database comprises a plurality of card identification data, each card identification data comprises at least one of license plate number information and license plate color information which are identified from a photographed license plate picture by a camera, photographing time information when the license plate picture is photographed by the camera and position information of the corresponding vehicle when the license plate picture is photographed by the camera, each vehicle management library data in the vehicle management library comprises at least one of license plate information, vehicle owner information, manufacturer information, vehicle inspection information and vehicle size information of a corresponding vehicle, the cloud analysis data in the cloud analysis database refers to data obtained by analyzing a video picture acquired by a camera for the vehicle by a server, the judging data in the judging database refers to data determined by a vehicle judging algorithm, the judging data comprises data used for describing whether the vehicle is a fake-plate vehicle and/or a fake-plate vehicle, the attributes comprise static attributes, statistical attributes and behavior attributes, the static attributes comprise secondary identification vehicle attributes, the static attributes further comprise at least one of fixed attributes, license plate attributes, vehicle management library attributes and model attributes, and the fixed attributes are used for identifying the corresponding vehicle, the license plate attribute is used for describing license plate information of a corresponding vehicle, the vehicle attribute is used for describing at least one of brand information, yearly money information and appearance information of the corresponding vehicle, the secondary recognition vehicle attribute is an attribute about vehicle self information obtained after analyzing and recognizing collected video pictures of the corresponding vehicle, the secondary recognition vehicle attribute comprises the number of times that the corresponding vehicle is a yellow-mark vehicle, whether dangerous goods exist or not and whether hanging decorations exist or not, the model attribute is a model obtained by learning the information of the corresponding vehicle through a preset learning model, the statistical attribute comprises at least one of an activity attribute and a secondary recognition behavior attribute, the activity attribute is used for describing activity information of the corresponding vehicle on time and/or space dimensions, and the secondary recognition behavior attribute is an attribute about personnel information in the vehicle obtained after analyzing the collected video pictures of the corresponding vehicle, the secondary identification behavior attribute comprises at least one of the times of opening the sun shield by a main driver/assistant driver at night, the times of not fastening a safety belt by the main driver/assistant driver, the times of making a call by the main driver, the times of front-row children and the times of standing people in a skylight, and the behavior attribute is used for describing position information and driving track information of a corresponding vehicle, wherein the position information comprises violation times, fake times, out-of-town times, night driving times, foot landing points;

2. The method of claim 1, wherein determining a plurality of vehicle profiles from N data sources comprises:

acquiring N data sources;

3. The method of claim 2, wherein each data source comprises a plurality of pieces of data each corresponding to a set of license plate numbers and license plate colors, the set of license plate numbers and license plate colors identifying a vehicle;

4. The method of claim 2, wherein there is an attribute of the type dictionary attribute in the plurality of attributes included in each vehicle profile, the dictionary attribute being that the corresponding attribute includes a plurality of dictionaries, each dictionary being an instance of the corresponding attribute, and each dictionary corresponding to a dictionary value describing a number of occurrences of the corresponding dictionary;

5. The method according to any one of claims 2 to 4, wherein said merging attributes of all vehicles present in said N data sources in a manner that attributes of the same vehicle are merged to obtain a plurality of vehicle profiles comprises:

6. A vehicle information management apparatus, characterized in that the apparatus comprises:

a determining module, configured to determine a plurality of vehicle files according to N data sources, where each vehicle file includes a plurality of attributes of the same vehicle and an attribute value of each attribute, each attribute is used to describe a driving feature or a vehicle self-feature of a corresponding vehicle, data included in the N data sources is data collected in a first preset time period before a current time, N is a positive integer greater than or equal to 1, the N data sources include a data source corresponding to a card recognition database, a data source corresponding to a vehicle management library, a data source corresponding to a cloud analysis database, and a data source corresponding to a judging database, the card recognition database includes a plurality of card recognition data, and each card recognition data includes license plate number information and license plate color information recognized by a camera from a photographed license plate picture, photographing time information when the camera photographs the license plate picture, and position information of the corresponding vehicle when the camera photographs the license plate picture One of the vehicle management database data is less, each piece of vehicle management database data in the vehicle management database comprises at least one of license plate information, vehicle owner information, manufacturer information, vehicle inspection information and vehicle size information of a corresponding vehicle, the cloud analysis data in the cloud analysis database refers to data obtained by analyzing a video picture acquired by a camera for the vehicle by a server, the judging data in the judging database refers to data determined by a vehicle judging algorithm, the judging data comprises data used for describing whether the vehicle is a fake-plate vehicle and/or a fake-plate vehicle, the attributes comprise static attributes, statistical attributes and behavior attributes, the static attributes comprise secondary identification vehicle attributes, the static attributes further comprise at least one of fixed attributes, license plate attributes, vehicle management database attributes and model attributes, and the fixed attributes are used for identifying the corresponding vehicle, the license plate attribute is used for describing license plate information of a corresponding vehicle, the vehicle attribute is used for describing at least one of brand information, yearly money information and appearance information of the corresponding vehicle, the secondary recognition vehicle attribute is an attribute about vehicle self information obtained after analyzing and recognizing collected video pictures of the corresponding vehicle, the secondary recognition vehicle attribute comprises the number of times that the corresponding vehicle is a yellow-mark vehicle, whether dangerous goods exist or not and whether hanging decorations exist or not, the model attribute is a model obtained by learning the information of the corresponding vehicle through a preset learning model, the statistical attribute comprises at least one of an activity attribute and a secondary recognition behavior attribute, the activity attribute is used for describing activity information of the corresponding vehicle on time and/or space dimensions, and the secondary recognition behavior attribute is an attribute about personnel information in the vehicle obtained after analyzing the collected video pictures of the corresponding vehicle, the secondary identification behavior attribute comprises at least one of the times of opening the sun shield by a main driver/assistant driver at night, the times of not fastening a safety belt by the main driver/assistant driver, the times of making a call by the main driver, the times of front-row children and the times of standing people in a skylight, and the behavior attribute is used for describing position information and driving track information of a corresponding vehicle, wherein the position information comprises violation times, fake times, out-of-town times, night driving times, foot landing points;

7. The apparatus of claim 6, wherein the determining module comprises:

an acquisition unit for acquiring N data sources;

8. The apparatus of claim 7, wherein each data source comprises a plurality of pieces of data each corresponding to a set of license plate numbers and license plate colors, the set of license plate numbers and license plate colors identifying a vehicle;

the determining unit is specifically configured to:

9. The apparatus of claim 7, wherein each vehicle profile includes a plurality of attributes, and wherein there is an attribute of which a type is a dictionary attribute, the dictionary attribute means that the corresponding attribute includes a plurality of dictionaries, each dictionary is an instance of the corresponding attribute, and each dictionary corresponds to a dictionary value describing a number of occurrences of the corresponding dictionary;

the determining unit is specifically configured to:

10. The apparatus according to any one of claims 7 to 9, wherein the merging unit is specifically configured to:

11. A vehicle information management apparatus, characterized in that the apparatus comprises:

a processor;

a memory for storing processor-executable instructions;

wherein the processor is configured to perform the steps of any of the methods of claims 1-5.

12. A computer-readable storage medium having instructions stored thereon, wherein the instructions, when executed by a processor, implement the steps of any of the methods of claims 1-5.