CN109993966A - A kind of method and device of building user portrait - Google Patents
A kind of method and device of building user portrait Download PDFInfo
- Publication number
- CN109993966A CN109993966A CN201810002979.4A CN201810002979A CN109993966A CN 109993966 A CN109993966 A CN 109993966A CN 201810002979 A CN201810002979 A CN 201810002979A CN 109993966 A CN109993966 A CN 109993966A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- portrait
- label
- target user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
- B60W40/09—Driving style or behaviour
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Mathematical Physics (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of method and devices of building user portrait, to the user's portrait for solving the problems, such as that more comprehensive and accurate driver cannot be constructed in the prior art.Since central node is after the vehicle traveling information and the corresponding road information of the vehicle traveling information received, road information and information of vehicles are clustered, it will obtain multiple labels, after the driving user for needing to construct target user draws a portrait, according to the road information and information of vehicles in tag set, and the road information and information of vehicles of the target user received, the label of the target user is determined, so that it is determined that the driver user of the target user draws a portrait.Since in the embodiment of the present invention, building driver user not only considers the information of vehicles of driver when drawing a portrait, road information when driver drives has been allowed also for, therefore more comprehensively can accurately construct user's portrait of driver.
Description
Technical field
The present invention relates to vehicle networking technical field, in particular to a kind of method and device of building user portrait.
Background technique
After internet gradually steps into big data era, a series of change inevitably is brought to enterprise and consumer behaviour
Become and remolds.Maximum variation is no more than, and all behaviors of consumer seem it all will will be " visualization " in face of enterprise.
User draw a portrait (User Profile), as the foundation of big data, it ideally takes out the information overall picture of a user, for into
One step is accurate, rapidly analyzes the important informations such as user behavior habit, consumption habit, provides enough data basis, establishes
The foundation stone of big data era.Car networking user portrait is then mainly by analyzing data of the driver in driving procedure, packet
Number of bringing to a halt, anxious deceleration number, lane change number, oil consumption etc. is included precisely to be analyzed come the driving behavior etc. to driver.
The method of building car networking user portrait is mainly from the angle of big data in the prior art, by excavating and dividing
User behavior is analysed, finally for each user is tagged and the weight of the label.However only excavate the behavior of individual subscriber
Feature has certain limitation, needs for the feature of user to be put into specific environment and make a concrete analysis of.Such as building driver
User portrait, the same driver congested link and unimpeded section driving behavior may it is entirely different, it is bad encountering
Driving behavior when driver may also be entirely different with driving behavior usually, therefore relies solely on the row for excavating and extracting user
It is characterized and carries out user's portrait with certain limitation to driver.
In conclusion user's portrait that the prior art more comprehensive and accurate cannot construct driver.
Summary of the invention
The present invention provide it is a kind of building user portrait method and device, to solve in the prior art cannot more comprehensively
Accurately the problem of user's portrait of building driver.
The embodiment of the present invention provides a kind of method of building user portrait, this method comprises:
Central node is according to the road information and information of vehicles of label in tag set, and the road of target user received
Road information and information of vehicles determine the label of the target user, wherein the label in the tag set is the centromere
Point basis clusters the vehicle traveling information and the corresponding road information of the vehicle traveling information that receive；
The central node determines that the driver user of the target user draws a portrait according to the label of the target user.
The embodiment of the present invention provides a kind of method of building user portrait, this method comprises:
Fringe node determines information of vehicles according to the driving information that vehicle termination reports, and determines vehicle running path
Road information；
The information of vehicles and the road information are reported to central node by the fringe node, so that the centromere
Point clusters vehicle traveling information and the corresponding road information of the vehicle traveling information to obtain the determining mesh of tally set merging
Mark the corresponding driver user's portrait of label of the user in the tag set.
The embodiment of the present invention provides a kind of device of building user portrait, comprising: processor and transceiver:
The processor, for the road information and information of vehicles according to label in tag set, and the target received
The road information and information of vehicles of user, determines the label of the target user, wherein the label in the tag set is institute
Central node is stated cluster according to the vehicle traveling information and the corresponding road information of the vehicle traveling information that receive
It arrives, determines that the driver user of the target user draws a portrait according to the label of the target user.
The embodiment of the present invention provides a kind of device of building user portrait, comprising: processor and transceiver:
The processor, the driving information for being reported according to vehicle termination determines information of vehicles, and determines vehicle row
Sail the road information in path；The information of vehicles and the road information are reported to central node, so that the central node
Vehicle traveling information and the corresponding road information of the vehicle traveling information are clustered to obtain the determining target of tally set merging
The corresponding driver user's portrait of label of the user in the tag set.
The embodiment of the present invention also provides a kind of device of building user portrait, which includes: at least one processing unit
And at least one storage unit, wherein the storage unit is stored with program code, when said program code is by the processing
When unit executes, so that the step of processing unit implementation center node building user's portrait；Or execute fringe node building
The step of user draws a portrait.
The embodiment of the present invention also provides a kind of calculating device-readable storage medium, including program code, when described program generation
When code is run on the computing device, said program code is used to that the calculating equipment implementation center node to be made to construct user's portrait
Step executes the step of fringe node building user draws a portrait.
In the embodiment of the present invention, central node is receiving vehicle traveling information and the corresponding road of the vehicle traveling information
After information, road information and information of vehicles are clustered, it will multiple labels are obtained, when the driving for needing to construct target user
After user's portrait, according to the road information and information of vehicles in tag set, and the road information of target user that receives and
Information of vehicles determines the label of the target user, so that it is determined that the driver user of the target user draws a portrait.Due to this hair
In bright embodiment, building driver user not only considers the information of vehicles of driver when drawing a portrait, and has allowed also for and has driven
The road information when person of sailing drives, therefore more comprehensively can accurately construct user's portrait of driver.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly introduced, it should be apparent that, drawings in the following description are only some embodiments of the invention, for this
For the those of ordinary skill in field, without any creative labor, it can also be obtained according to these attached drawings
His attached drawing.
Fig. 1 is a kind of system schematic of building user portrait of the embodiment of the present invention；
Fig. 2 is the system architecture schematic diagram that the embodiment of the present invention constructs user's portrait；
Fig. 3 is a kind of structural schematic diagram of central node side of the embodiment of the present invention；
Fig. 4 is a kind of structural schematic diagram of fringe node side of the embodiment of the present invention；
Fig. 5 is the structural schematic diagram of another kind of embodiment of the present invention central node side；
Fig. 6 is the structural schematic diagram of another kind of embodiment of the present invention fringe node side；
Fig. 7 is a kind of schematic device of building user portrait of the embodiment of the present invention；
Fig. 8 is a kind of flow chart of building user portrait central node side method of the embodiment of the present invention；
Fig. 9 is a kind of flow chart of building user portrait fringe node side method of the embodiment of the present invention；
Figure 10 is a kind of flow chart of the complete method of building user portrait of the embodiment of the present invention.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing to the present invention make into
It is described in detail to one step, it is clear that the described embodiments are only some of the embodiments of the present invention, rather than whole implementation
Example.Based on the embodiments of the present invention, obtained by those of ordinary skill in the art without making creative efforts
All other embodiment, shall fall within the protection scope of the present invention.
As shown in Figure 1, the embodiment of the present invention provides a kind of system of building user portrait, which includes: central node
100 and fringe node 101.
Central node 100, for the road information and information of vehicles according to label in tag set, and the target received
The road information and information of vehicles of user, determines the label of the target user, wherein the label in the tag set is institute
Central node is stated cluster according to the vehicle traveling information and the corresponding road information of the vehicle traveling information that receive
It arrives；The central node determines that the driver user of the target user draws a portrait according to the label of the target user.
Fringe node 100, the driving information for being reported according to vehicle termination determine information of vehicles, and determine vehicle row
Sail the road information in path；The information of vehicles and the road information are reported to central node, so that the central node
Vehicle traveling information and the corresponding road information of the vehicle traveling information are clustered to obtain the determining target of tally set merging
The corresponding driver user's portrait of label of the user in the tag set.
In the embodiment of the present invention, central node is in the vehicle traveling information and the corresponding road of the vehicle traveling information received
Road information, clusters road information and information of vehicles, it will multiple labels is obtained, when the driving for needing to construct target user
After user's portrait, according to the road information and information of vehicles in tag set, and the road information of target user that receives and
Information of vehicles determines the label of the target user, so that it is determined that the driver user of the target user draws a portrait.Due to this hair
In bright embodiment, building driver user not only considers the information of vehicles of driver when drawing a portrait, and has allowed also for and has driven
The road information when person of sailing drives, therefore more comprehensively can accurately construct user's portrait of driver.
As shown in Fig. 2, it is found that in this hair embodiment from the system architecture diagram that the building user of the embodiment of the present invention draws a portrait
It include: central node, fringe node, base station, car-mounted terminal.
Central node, for example, can centered on V2X computing platform, uploaded for collecting in all areas via fringe node
Information, finally show that the user of driver draws a portrait by global calculating analysis.
Fringe node refers to being distributed Edge Server within a certain area, for example can calculate section for edge V2X
Point, for collecting the information of vehicles within the scope of its and recording the road information in the region.
Car-mounted terminal is mounted on driving vehicle, can be divided into preceding entrucking mounted terminal and rear entrucking mounted terminal, is used for collecting cart
Information.
Wherein, the preceding entrucking mounted terminal is before automobile factory, and a part designed as a whole is assembled in production line
Car-mounted terminal into automobile is responsible for buying and installation by automaker；Entrucking mounted terminal refers in automobile production after described
Afterwards, the car-mounted terminal of installation is sold by car dealer or vehicle-mounted product dealer.
Base station is used to be responsible for the communication between vehicle and fringe node and leading between fringe node and central node
Letter.
The embodiment of the present invention is described in detail the embodiment of the present invention according to the system architecture of building user's portrait below.
Driver is mounted on the traveling letter of vehicle described in the car-mounted terminal real-time collecting on driving vehicle when driving vehicle
Breath, and the driving information is uploaded to the fringe node in current region by the base station in current region, wherein the row
Sailing information includes but is not limited to some or all of in following message:
The speed, acceleration of vehicle, angular speed, angular acceleration, steering wheel angle, accelerator pedal position, brake pedal position
It sets, the information of the reflection current driver's behavior such as engine speed, operating range, Fuel Oil Remaining.
Correspondingly, the fringe node records the vehicle row while being collected into the driving information of car-mounted terminal upload
Sail the road information in region, wherein the road information includes but is not limited to some or all of in following message:
Whether weather condition traffic lights situation, the real-time speed of road, vehicle flow, has special car to pass through.
For example, the weather condition can recorde as fine day, cloudy, the weather conditions such as light rain；Whether there is special car logical
Whether cross can recorde to have the vehicle of the specific uses such as police car, ambulance to pass through.
After reaching the cycle time of setting, driving information root of the fringe node to car-mounted terminal upload in the period
Information of vehicles is then determined according to preset in advance establish rules really, wherein the duration in the period, determining rule are by this field staff
Sets itself according to actual needs, the information of vehicles include but is not limited to some or all of in following message: vehicle plus
Speed, number of bringing to a halt, anxious acceleration times, lane change number, oil consumption etc..
For example, the cycle duration set is 3 day, it is preset to establish rules really then are as follows: the driving information reported according to car-mounted terminal
In speed determine bring to a halt, lane change, the number promptly accelerated, the acceleration in driving information, the oil that car-mounted terminal is reported
Consumption etc. is transformed to change curve.
Then after reaching the cycle time of setting, driving information that the fringe node is reported according to car-mounted terminal in 3 days
In speed determine that the number brought to a halt is 1 time, lane change number 3 times, promptly accelerate number for 3 times, car-mounted terminal is reported
Acceleration, oil consumption in driving information etc. are transformed to change curve.
The fringe node is after the driving information reported according to vehicle termination determines information of vehicles, by information of vehicles and road
Road information is uploaded to the central node by base station.
Correspondingly, the central node is in the statistics knot for receiving the information of vehicles that the fringe node uploads by base station
After fruit and road information, the vehicle traveling information and the corresponding road information of the vehicle traveling information that receive cluster
To tag set.
For example, with information of vehicles be bring to a halt, the number that promptly accelerates, oil consumption, road information is weather condition, traffic lights
It is clustered to obtain multiple labels for the real-time speed of situation, road, as shown in table 1:
Table 1: label information table
The central node clusters the vehicle traveling information received and the corresponding road information of the vehicle traveling information
When can use clustering algorithm, such as k-means algorithm, k-medoids algorithm, Clara algorithm.
Wherein, n object is divided into k cluster using k as parameter by the k-means algorithm, is made with higher similar in cluster
Degree, and the similarity between cluster is lower.The treatment process of k-means algorithm is as follows: firstly, it is randomly chosen k object, it is each right
As initially representing the average value or center of a cluster；It, will according to it at a distance from each cluster center to remaining each object
It is assigned to nearest cluster；Then the average value of each cluster is recalculated, this process constantly repeats, until criterion function is restrained.
K-medoids method chooses an object mediod to replace the effect at the center of k-means algorithm, this
One medoid of sample just identifies this class, and such a point is chosen from current cluster, centered on point, this point
Sum of the distance to other all (in current cluster) points is minimum.
The thought of the Clara algorithm is that entire data are replaced with the sampling of real data, then again in these sampling
Data on using K-medoids algorithm obtain optimal medoids.Clara algorithm extracts multiple samplings from real data,
Corresponding (O1, O2 ... Oi ... Ok) is obtained with K-medoids algorithm in each sampling, it is minimum that E is then chosen in this
One as final result.
Correspondingly, the central node is to the vehicle traveling information and the corresponding road of the vehicle traveling information received
After the tag set that information is clustered, using the tag set as being used in subsequent builds driver users portrait
The data set of sorting algorithm.
What needs to be explained here is that: it, can be direct when needing to construct driver user's portrait after obtained tag set
The data set of the sorting algorithm of middle use used as subsequent builds driver user portrait, and can be according to the actual situation
It regularly updates.
For example, leading to the driving of building when increasing other new information using the information of vehicles and road information that determine label
When member's user's portrait is not comprehensive, the label can be redefined；Or a cycle duration is manually set, when reaching the period
Data are resurveyed after length and determine the label, to guarantee that driver user's portrait is comprehensively accurate.
When the driver user for needing to construct target user draws a portrait, the target user that the central node will receive
Road information and information of vehicles be input in sorting algorithm and classify, such as neural network algorithm, decision tree, Bayes,
And the label for exporting the sorting algorithm, the label as the target user.
Wherein, the Decision Tree Algorithm is one of the major technique for classifying and predicting, decision tree learning be with
Induced learning algorithm based on example, it, which is conceived to, infers from one group of out of order, random example with decision tree table
The classifying rules shown.The purpose for constructing decision tree is the relationship found out between attribute and classification, and unknown classification in the future is predicted with it
Record classification.It uses top-down recursive fashion, in the comparison of the internal node progress attribute of decision tree, and according to
Different attribute value judges the branch downward from the node, decision tree leaf node it is concluded that.
Wherein, Bayes (Bayes) sorting algorithm is a kind of algorithm classified using probability statistics knowledge, such as
Naive Bayesian (Naive Bayes) algorithm.These algorithms mainly predict the sample of a unknown classification using Bayes theorem
Select wherein final classification of the maximum classification of possibility as the sample a possibility that belonging to each classification.
After the label for determining the target user, correspondence that the central node is drawn a portrait according to label and driver user
Relationship determines the corresponding driver user's portrait of the label of the target user.
Driver user portrait some or all of includes but does not limit in following:
It is radical drive, mild drivings, normal driving, oil consumption is lower, oil consumption is higher, rainy day violence driving etc..
For example, with information of vehicles be bring to a halt, the number that promptly accelerates, oil consumption, road information is weather condition, traffic lights
It is clustered to obtain the corresponding relationship of multiple label As, B, C, D and driver user's portrait for the real-time speed of situation, road, such as
Table 2 shows:
Table 2: the corresponding relationship of label and driver user's portrait
Wherein, the corresponding relationship of the label and driver user's portrait is tested by those skilled in the art according to experimental data comparison
It is bound, can be showed after card by table or other forms, the embodiment of the present invention is to this good restriction；It is marked when redefining
When label, need to redefine the corresponding relationship of the label and driver user's portrait, to guarantee that driver user's portrait is complete
Face is accurate.
For example, central node according to the vehicle traveling information and the corresponding road information of the vehicle traveling information received into
Row cluster obtains multiple label As, B, C, D, and the central node is trained the data as sorting algorithm to label A, B, C, D
The information of vehicles of driver and road information are input to by collection when the driver user for needing to construct some driver draws a portrait
Label A, B, C, D are as in the sorting algorithm of data set, it will the label for obtaining the driver is A, then searches label and drive
The mapping table of the person of sailing user portrait, such as the corresponding mild driving of A, then the driver user of the driver draws a portrait mildly to drive
It sails.
What needs to be explained here is that it is true to resurvey data when the driver user of building portrait is no longer comprehensively accurate
Determine driver user's portrait；Or a cycle duration is manually set, data determination is resurveyed after reaching cycle duration drives
The person of sailing user portrait, to guarantee that driver user's portrait is comprehensively accurate.
As shown in figure 3, the embodiment of the present invention provides a kind of device of building user portrait, comprising: processor 300 and receipts
Hair machine 301:
The processor 300, for the road information and information of vehicles according to label in tag set, and the mesh received
The road information and information of vehicles for marking user, determine the label of the target user, wherein the label in the tag set is
The central node is clustered according to the vehicle traveling information and the corresponding road information of the vehicle traveling information that receive
It obtains；Driver user's portrait of the target user is determined according to the label of the target user.
Optionally, the processor 300 is specifically used for:
The vehicle traveling information received and the corresponding road information of the vehicle traveling information are carried out using clustering algorithm
Cluster obtains tag set.
Optionally, the processor 300 is specifically used for:
The road information of the target user received and information of vehicles are input in sorting algorithm and classified, wherein described
The data set of sorting algorithm is the central node to the vehicle traveling information and the corresponding road of the vehicle traveling information received
The tag set that road information is clustered；The label that the sorting algorithm is exported, the label as the target user.
Optionally, the processor 300 is specifically used for:
According to the corresponding relationship that label and driver user draw a portrait, the corresponding driver of the label of the target user is determined
User's portrait.
Optionally, the road information includes some or all of in following message:
Whether weather condition traffic lights situation, the real-time speed of road, vehicle flow, has special car to pass through；
The information of vehicles includes some or all of in following message:
The acceleration of vehicle, number of bringing to a halt, anxious acceleration times, lane change number, oil consumption.
Optionally, driver user portrait includes some or all of in following:
Radical driving, mild driving, normal driving, oil consumption is lower, oil consumption is higher, rainy day violence drives.
As shown in figure 4, the embodiment of the present invention provides a kind of device of building user portrait, comprising: processor 400 and receipts
Hair machine 401:
The processor, the driving information for being reported according to vehicle termination determines information of vehicles, and determines vehicle row
Sail the road information in path；The information of vehicles and the road information are reported to central node, so that the central node
Vehicle traveling information and the corresponding road information of the vehicle traveling information are clustered to obtain the determining target of tally set merging
The corresponding driver user's portrait of label of the user in the tag set.
As shown in figure 5, the embodiment of the present invention also provides a kind of device of building user portrait, which includes:
Receiving module 500, for the road information and information of vehicles according to label in tag set, and the target received
The road information and information of vehicles of user determine the label of the target user, wherein the label in the tag set is described
Central node is clustered to obtain according to the vehicle traveling information and the corresponding road information of the vehicle traveling information that receive
's；
Determining module 501, for determining that the driver user of the target user draws according to the label of the target user
Picture.
Optionally, the determining module 501 is also used to:
The vehicle traveling information received and the corresponding road information of the vehicle traveling information are carried out using clustering algorithm
Cluster obtains tag set.
Optionally, the determining module 501 is also used to:
The road information of the target user received and information of vehicles are input in sorting algorithm and classified, wherein described
The data set of sorting algorithm is the central node to the vehicle traveling information and the corresponding road of the vehicle traveling information received
The tag set that road information is clustered；The label that the sorting algorithm is exported, the label as the target user.
Optionally, the determining module 501 is also used to:
According to the corresponding relationship that label and driver user draw a portrait, the corresponding driver of the label of the target user is determined
User's portrait.
Optionally, the road information includes some or all of in following message:
Whether weather condition traffic lights situation, the real-time speed of road, vehicle flow, has special car to pass through；
The information of vehicles includes some or all of in following message:
The acceleration of vehicle, number of bringing to a halt, anxious acceleration times, lane change number, oil consumption.
Optionally, driver user portrait includes some or all of in following:
Radical driving, mild driving, normal driving, oil consumption is lower, oil consumption is higher, rainy day violence drives.
Based on the same inventive concept, the method for building user's portrait is additionally provided in the embodiment of the present invention, due to this method
Corresponding central node is the central node of building user's portrait of the embodiment of the present invention, and the principle that solves the problems, such as of this method and
Central node is similar, therefore the implementation of this method may refer to the implementation of system, and overlaps will not be repeated.
As shown in fig. 6, the embodiment of the present invention also provides a kind of device of building user portrait, which includes:
Execution module 600, the driving information for being reported according to vehicle termination determines information of vehicles, and determines vehicle row
Sail the road information in path；
Reporting module 601, for the information of vehicles and the road information to be reported to central node, so that in described
Heart node clusters vehicle traveling information and the corresponding road information of the vehicle traveling information to obtain tally set merging really
The corresponding driver user's portrait of label of the user in the tag set that set the goal.
As shown in fig. 7, the embodiment of the present invention also provides a kind of device of building user portrait, which includes: at least one
A processing unit 700 and at least one storage unit 701, wherein the storage unit 701 is stored with program code, works as institute
When stating program code and being executed by the processing unit 700, so that 700 implementation center's node of processing unit building user's portrait
The step of；Or the step of executing fringe node building user's portrait.
The embodiment of the present invention also provides a kind of calculating device-readable storage medium, including program code, when described program generation
When code is run on the computing device, said program code is used to that the calculating equipment implementation center node to be made to construct user's portrait
Step；Or the step of executing fringe node building user's portrait.
Based on the same inventive concept, the method for building user's portrait is additionally provided in the embodiment of the present invention, due to this method
Corresponding central node is the central node of building user's portrait of the embodiment of the present invention, and the principle that solves the problems, such as of this method and
Central node is similar, therefore the implementation of this method may refer to the implementation of system, and overlaps will not be repeated.
As shown in figure 8, the embodiment of the present invention provides a kind of method of building user portrait, this method comprises:
Step 800, central node are according to the road information and information of vehicles of label in tag set, and the target received
The road information and information of vehicles of user, determines the label of the target user, wherein the label in the tag set is institute
Central node is stated cluster according to the vehicle traveling information and the corresponding road information of the vehicle traveling information that receive
It arrives；
Step 801, the central node determine that the driver of the target user uses according to the label of the target user
Family portrait.
Optionally, the central node believes the vehicle traveling information received and the corresponding road of the vehicle traveling information
Breath is clustered to obtain multiple labels, comprising:
The central node is corresponding to the vehicle traveling information and the vehicle traveling information that receive using clustering algorithm
Road information is clustered to obtain tag set.
Optionally, the central node determines the driver user of the target user according to the label of the target user
Portrait, comprising:
The road information of the target user received and information of vehicles are input in sorting algorithm and carry out by the central node
Classification, wherein the data set of the sorting algorithm is the central node to the vehicle traveling information and the vehicle driving received
The tag set that the corresponding road information of information is clustered；
The label that the central node exports the sorting algorithm, the label as the target user.
Optionally, the central node determines the driver user of the target user according to the label of the target user
Portrait, comprising:
The corresponding relationship that the central node is drawn a portrait according to label and driver user, determines the label of the target user
Corresponding driver user's portrait.
Optionally, the road information includes some or all of in following message:
Whether weather condition traffic lights situation, the real-time speed of road, vehicle flow, has special car to pass through；
Optionally, driver user portrait includes some or all of in following:
The acceleration of vehicle, number of bringing to a halt, anxious acceleration times, lane change number, oil consumption.
Optionally, the corresponding relationship of the label and driver user's portrait includes some or all of in following:
Radical driving, mild driving, normal driving, oil consumption is lower, oil consumption is higher, rainy day violence drives.
Based on the same inventive concept, the method for building user's portrait is additionally provided in the embodiment of the present invention, due to this method
Corresponding fringe node is the fringe node of building user's portrait of the embodiment of the present invention, and the principle that solves the problems, such as of this method and
Fringe node is similar, therefore the implementation of this method may refer to the implementation of system, and overlaps will not be repeated.
As shown in figure 9, the embodiment of the present invention provides a kind of method of building user portrait, this method comprises:
Step 900, fringe node determine information of vehicles according to the driving information that vehicle termination reports, and determine vehicle row
Sail the road information in path；
The information of vehicles and the road information are reported to central node by step 901, the fringe node, so that institute
It states central node vehicle traveling information and the corresponding road information of the vehicle traveling information are clustered to obtain tag set
And determine the corresponding driver user's portrait of label of the target user in the tag set.
As shown in Figure 10, the embodiment of the present invention provides a kind of complete method of building user portrait, this method comprises:
Step 1000, car-mounted terminal report driving information to fringe node；
Step 1001, fringe node determine information of vehicles according to the driving information that vehicle termination reports；
Step 1002, the fringe node determine the road information of vehicle running path；
The information of vehicles and the road information are reported to central node by step 1003, the fringe node；
Step 1004, the central node believe the vehicle traveling information received and the vehicle driving using clustering algorithm
Corresponding road information is ceased to cluster to obtain tag set；
The road information of the target user received and information of vehicles are input to classification and calculated by step 1005, the central node
Classify in method；
The label that step 1006, the central node export the sorting algorithm, the label as the target user；
The corresponding relationship that step 1007, the central node are drawn a portrait according to label and driver user, determines the target
The corresponding driver user's portrait of the label of user.
Above by reference to showing according to the method, apparatus (system) of the embodiment of the present application and/or the frame of computer program product
Figure and/or flow chart describe the application.It should be understood that can realize that block diagram and or flow chart is shown by computer program instructions
The combination of the block of a block and block diagram and or flow chart diagram for figure.These computer program instructions can be supplied to logical
With computer, the processor of special purpose computer and/or other programmable data processing units, to generate machine, so that via meter
The instruction that calculation machine processor and/or other programmable data processing units execute creates for realizing block diagram and or flow chart block
In specified function action method.
Correspondingly, the application can also be implemented with hardware and/or software (including firmware, resident software, microcode etc.).More
Further, the application can take computer usable or the shape of the computer program product on computer readable storage medium
Formula has the computer realized in the medium usable or computer readable program code, to be made by instruction execution system
It is used with or in conjunction with instruction execution system.In the present context, computer can be used or computer-readable medium can be with
It is arbitrary medium, may include, stores, communicates, transmits or transmit program, is made by instruction execution system, device or equipment
With, or instruction execution system, device or equipment is combined to use.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (16)
1. a kind of method of building user portrait, which is characterized in that this method comprises:
Central node is according to the road information and information of vehicles of label in tag set, and the road letter of target user received
Breath and information of vehicles, determine the label of the target user, wherein the label in the tag set is the central node root
According to what is clustered to the vehicle traveling information and the corresponding road information of the vehicle traveling information that receive；
The central node determines that the driver user of the target user draws a portrait according to the label of the target user.
2. the method as described in claim 1, which is characterized in that the label in the tag set be the central node according to
The vehicle traveling information and the corresponding road information of the vehicle traveling information that receive are clustered, comprising:
The central node is using clustering algorithm to the vehicle traveling information and the corresponding road of the vehicle traveling information received
Information is clustered to obtain tag set.
3. the method as described in claim 1, which is characterized in that the central node is determined according to the label of the target user
The driver user of the target user draws a portrait, comprising:
The road information of the target user received and information of vehicles are input in sorting algorithm by the central node classifies,
Wherein the data set of the sorting algorithm is the central node to the vehicle traveling information and the vehicle traveling information received
The tag set that corresponding road information is clustered；
The label that the central node exports the sorting algorithm, the label as the target user.
4. the method as described in claim 1, which is characterized in that the central node is determined according to the label of the target user
The driver user of the target user draws a portrait, comprising:
The corresponding relationship that the central node is drawn a portrait according to label and driver user determines that the label of the target user is corresponding
Driver user portrait.
5. the method as described in claim 1, which is characterized in that the road information includes the part or complete in following message
Portion:
Whether weather condition traffic lights situation, the real-time speed of road, vehicle flow, has special car to pass through；
The information of vehicles includes some or all of in following message:
The acceleration of vehicle, number of bringing to a halt, anxious acceleration times, lane change number, oil consumption.
6. the method as described in claim 1, which is characterized in that driver user's portrait includes the part or complete in following
Portion:
Radical driving, mild driving, normal driving, oil consumption is lower, oil consumption is higher, rainy day violence drives.
7. a kind of method of building user portrait, which is characterized in that this method comprises:
Fringe node determines information of vehicles according to the driving information that vehicle termination reports, and determines the road of vehicle running path
Information；
The information of vehicles and the road information are reported to central node by the fringe node, so that the central node vehicle
Driving information and the corresponding road information of the vehicle traveling information, which are clustered to obtain tally set to merge, determines target user
The corresponding driver user's portrait of label in the tag set.
8. a kind of device for building user's portrait characterized by comprising processor and transceiver:
The processor, for the road information and information of vehicles according to label in tag set, and the target user received
Road information and information of vehicles, the label of the target user is determined, wherein the label in the tag set is in described
Heart node is according to clustering the vehicle traveling information and the corresponding road information of the vehicle traveling information that receive；
Driver user's portrait of the target user is determined according to the label of the target user.
9. device as claimed in claim 8, which is characterized in that the processor is specifically used for:
The vehicle traveling information and the corresponding road information of the vehicle traveling information that receive are clustered using clustering algorithm
Obtain tag set.
10. device as claimed in claim 8, which is characterized in that the processor is specifically used for:
The road information of the target user received and information of vehicles are input in sorting algorithm and classified, wherein the classification
The data set of algorithm is that the central node believes the vehicle traveling information received and the corresponding road of the vehicle traveling information
Cease the tag set clustered；The label that the sorting algorithm is exported, the label as the target user.
11. device as claimed in claim 8, which is characterized in that the processor is specifically used for:
According to the corresponding relationship that label and driver user draw a portrait, the corresponding driver user of the label of the target user is determined
Portrait.
12. device as claimed in claim 8, which is characterized in that the road information includes the part or complete in following message
Portion:
Whether weather condition traffic lights situation, the real-time speed of road, vehicle flow, has special car to pass through；
The information of vehicles includes some or all of in following message:
The acceleration of vehicle, number of bringing to a halt, anxious acceleration times, lane change number, oil consumption.
13. device as claimed in claim 8, which is characterized in that driver user portrait include part in following or
All:
Radical driving, mild driving, normal driving, oil consumption is lower, oil consumption is higher, rainy day violence drives.
14. a kind of device of building user portrait characterized by comprising processor and transceiver:
The processor, the driving information for being reported according to vehicle termination determines information of vehicles, and determines vehicle driving road
The road information of diameter；The information of vehicles and the road information are reported to central node, so that the central node is to vehicle
Driving information and the corresponding road information of the vehicle traveling information, which are clustered to obtain tally set to merge, determines target user
The corresponding driver user's portrait of label in the tag set.
15. a kind of device of building user portrait, which is characterized in that the equipment includes: at least one processing unit and at least
One storage unit, wherein the storage unit is stored with program code, when said program code is executed by the processing unit
When, so that the step of processing unit perform claim requires 1~6 any the method；Or perform claim requires 7 the methods
The step of.
16. a kind of calculating device-readable storage medium, which is characterized in that including program code, when said program code is calculating
When running in equipment, said program code is for making the calculating equipment perform claim require 1~6 any the method or execution
The step of claim 7 method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810002979.4A CN109993966A (en) | 2018-01-02 | 2018-01-02 | A kind of method and device of building user portrait |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810002979.4A CN109993966A (en) | 2018-01-02 | 2018-01-02 | A kind of method and device of building user portrait |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109993966A true CN109993966A (en) | 2019-07-09 |
Family
ID=67128355
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810002979.4A Pending CN109993966A (en) | 2018-01-02 | 2018-01-02 | A kind of method and device of building user portrait |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109993966A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110414459A (en) * | 2019-08-02 | 2019-11-05 | 中星智能系统技术有限公司 | Establish the associated method and device of people's vehicle |
| CN110505083A (en) * | 2019-07-31 | 2019-11-26 | 北京比利信息技术有限公司 | Mixed architecture operation method and system based on data center and local edge calculations |
| CN111210620A (en) * | 2019-12-19 | 2020-05-29 | 广州航天海特系统工程有限公司 | Method, device and equipment for generating driver portrait and storage medium |
| CN112256667A (en) * | 2020-09-16 | 2021-01-22 | 珠海市新德汇信息技术有限公司 | Multi-biological characteristic normalization method |
| CN112749323A (en) * | 2019-10-31 | 2021-05-04 | 北京沃东天骏信息技术有限公司 | Method and device for constructing user portrait |
| CN114398633A (en) * | 2021-12-29 | 2022-04-26 | 北京永信至诚科技股份有限公司 | Portrait analysis method and device for honeypot attackers |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101633359A (en) * | 2008-07-24 | 2010-01-27 | 通用汽车环球科技运作公司 | Adaptive vehicle control system with driving style recognition |
| WO2014013985A1 (en) * | 2012-07-17 | 2014-01-23 | 日産自動車株式会社 | Driving assistance system and driving assistance method |
| CN106022810A (en) * | 2015-02-13 | 2016-10-12 | 成都易驾科技有限公司 | Advertisement audience targeting and putting system based on driving behavior of car owner |
| CN106095963A (en) * | 2016-06-17 | 2016-11-09 | 上海经达信息科技股份有限公司 | Vehicle drive behavior analysis big data public service platform under the Internet+epoch |
| CN106372817A (en) * | 2016-10-25 | 2017-02-01 | 先锋智道（北京）科技有限公司 | Method, device and system for generating driving behavior of driver |
-
2018
- 2018-01-02 CN CN201810002979.4A patent/CN109993966A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101633359A (en) * | 2008-07-24 | 2010-01-27 | 通用汽车环球科技运作公司 | Adaptive vehicle control system with driving style recognition |
| WO2014013985A1 (en) * | 2012-07-17 | 2014-01-23 | 日産自動車株式会社 | Driving assistance system and driving assistance method |
| CN106022810A (en) * | 2015-02-13 | 2016-10-12 | 成都易驾科技有限公司 | Advertisement audience targeting and putting system based on driving behavior of car owner |
| CN106095963A (en) * | 2016-06-17 | 2016-11-09 | 上海经达信息科技股份有限公司 | Vehicle drive behavior analysis big data public service platform under the Internet+epoch |
| CN106372817A (en) * | 2016-10-25 | 2017-02-01 | 先锋智道（北京）科技有限公司 | Method, device and system for generating driving behavior of driver |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110505083A (en) * | 2019-07-31 | 2019-11-26 | 北京比利信息技术有限公司 | Mixed architecture operation method and system based on data center and local edge calculations |
| CN110414459A (en) * | 2019-08-02 | 2019-11-05 | 中星智能系统技术有限公司 | Establish the associated method and device of people's vehicle |
| CN112749323A (en) * | 2019-10-31 | 2021-05-04 | 北京沃东天骏信息技术有限公司 | Method and device for constructing user portrait |
| CN111210620A (en) * | 2019-12-19 | 2020-05-29 | 广州航天海特系统工程有限公司 | Method, device and equipment for generating driver portrait and storage medium |
| CN112256667A (en) * | 2020-09-16 | 2021-01-22 | 珠海市新德汇信息技术有限公司 | Multi-biological characteristic normalization method |
| CN112256667B (en) * | 2020-09-16 | 2024-03-22 | 珠海市新德汇信息技术有限公司 | Multi-biological characteristic normalization method |
| CN114398633A (en) * | 2021-12-29 | 2022-04-26 | 北京永信至诚科技股份有限公司 | Portrait analysis method and device for honeypot attackers |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109993966A (en) | A kind of method and device of building user portrait | |
| CN107492251B (en) | Driver identity recognition and driving state monitoring method based on machine learning and deep learning | |
| Ma et al. | Driving style recognition and comparisons among driving tasks based on driver behavior in the online car-hailing industry | |
| CN106781503B (en) | Method and apparatus for monitoring driving behavior | |
| CN109840612A (en) | User's driving behavior analysis method and system | |
| CN108074396A (en) | The evaluation method that drives safely and system | |
| CN110675626B (en) | Traffic accident black point prediction method, device and medium based on multidimensional data | |
| CN110443185B (en) | Driver identification method, driver identification device, electronic device, and storage medium | |
| CN109658272A (en) | Driving behavior evaluation system and Insurance Pricing system based on driving behavior | |
| CN110458214B (en) | Driver replacement recognition method and device | |
| CN116168356B (en) | Vehicle damage judging method based on computer vision | |
| CN113792782A (en) | Track monitoring method and device for operating vehicle, storage medium and computer equipment | |
| Xue et al. | A context-aware framework for risky driving behavior evaluation based on trajectory data | |
| CN113570862A (en) | XGboost algorithm-based large traffic jam early warning method | |
| CN111027859B (en) | Driving risk prevention method and system based on motor vehicle state monitoring data mining | |
| CN114743382B (en) | Vehicle violation behavior identification method and device based on intelligent lamp pole system | |
| CN114492544A (en) | Model training method and device and traffic incident occurrence probability evaluation method and device | |
| CN111914138A (en) | Working condition analysis method, device and system based on Internet of vehicles big data | |
| CN113505955A (en) | User driving behavior scoring method based on TSP system | |
| Huang et al. | Detection of abnormalities in driving style based on moving object trajectories without labels | |
| Ma et al. | Lane change analysis and prediction using mean impact value method and logistic regression model | |
| Yang et al. | Dynamic safety estimation of airport pick-up area based on video trajectory data | |
| CN117746632B (en) | Bus driving risk assessment and early warning system and method based on intelligent network | |
| CN112937592B (en) | Method and system for identifying driving style based on headway | |
| Wang et al. | Drivers' Rear-end Conflict Risk Avoidance Behaviors Prediction Based on Natural Driving Data |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190709 |
|
| RJ01 | Rejection of invention patent application after publication |