CN107784597A - Trip mode recognition methods, device, terminal device and storage medium - Google Patents
Trip mode recognition methods, device, terminal device and storage medium Download PDFInfo
- Publication number
- CN107784597A CN107784597A CN201710846069.XA CN201710846069A CN107784597A CN 107784597 A CN107784597 A CN 107784597A CN 201710846069 A CN201710846069 A CN 201710846069A CN 107784597 A CN107784597 A CN 107784597A
- Authority
- CN
- China
- Prior art keywords
- trip mode
- user
- data
- cluster
- training
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of trip mode recognition methods, device, terminal device and storage medium.The trip mode recognition methods, including：Active user's track data is obtained, active user's track data includes at least one current signature data；User trajectory data model is obtained, the user trajectory data model includes at least two cluster class clusters, and each cluster class cluster corresponding one assesses trip mode；Based on active user's track data and the user trajectory data model, the target cluster class cluster corresponding with least one current signature data is obtained from least two cluster class clusters；Based on trip mode is assessed corresponding to target cluster class cluster, target trip mode is obtained.The trip mode recognition methods can identify the specific trip mode of user, assessed for vehicle insurance and provide correct data, while this method can identify abnormal data, purify sample data, improve the accuracy that vehicle insurance is assessed.
Description
Technical field
The present invention relates to computer identify field, more particularly to a kind of trip mode recognition methods, device, terminal device and
Storage medium.
Background technology
During vehicle insurance is handled, insurance institution need to gather user's to assess the risk situation that user handles vehicle insurance
The driving data such as duration and driving habit is driven, and is assessed based on driving data.Specifically, insurance institution by user with
Mobile phone, flat board or other mobile terminals collection GPRS data that body carries, and can describe to drive based on GPRS data generation
The characteristic vector of the driving data such as duration and driving habit, then gather Random Forest model and this feature vector is identified, with
Determine whether to drive for user, in order to assess the risk situation that user handles vehicle insurance.But the GPRS of mobile terminal collection
Data are probably the data that user gathers when driving vehicle driving, it is also possible to user in walking, ride a bicycle, take public transport
Car, the data for taking subway, taking high ferro and collecting during the trip mode trip in addition to vehicle is driven such as airplane.When
In preceding user's vehicle insurance evaluation process, fail to identify the trip mode of user so that handle the risk situation of vehicle insurance to assessing user
Assessment result it is not accurate enough.
The content of the invention
The embodiment of the present invention provides a kind of trip mode recognition methods, device, terminal device and storage medium, to solve to work as
The problem of preceding vehicle insurance evaluation process can not identify the trip mode of user and cause assessment result not accurate enough.
In a first aspect, the embodiment of the present invention provides a kind of trip mode recognition methods, including：
Active user's track data is obtained, active user's track data includes at least one current signature data；
User trajectory data model is obtained, the user trajectory data model includes at least two cluster class clusters, Mei Yisuo
State cluster class cluster corresponding one and assess trip mode；
Based on active user's track data and the user trajectory data model, from least two cluster class clusters
It is middle to obtain the target cluster class cluster corresponding with least one current signature data；
Based on the assessment trip mode corresponding to target cluster class cluster, target trip mode is obtained.
Second aspect, the embodiment of the present invention provide a kind of trip mode identification device, including：
Active user's track data acquisition module, for obtaining active user's track data, active user track number
According to including at least one current signature data；
User trajectory data model acquisition module, for obtaining user trajectory data model, the user trajectory data mould
Type includes at least two cluster class clusters, and each cluster class cluster corresponding one assesses trip mode；
Target clusters class cluster acquisition module, for based on active user's track data and the user trajectory data mould
Type, the target cluster class corresponding with least one current signature data is obtained from least two cluster class clusters
Cluster；
Target trip mode acquisition module, for clustering the assessment trip mode corresponding to class cluster based on the target,
Obtain target trip mode.
The third aspect, the embodiment of the present invention provide a kind of terminal device, including memory, processor and are stored in described
In memory and the computer program that can run on the processor, realized described in the computing device during computer program
The step of trip mode recognition methods.
Fourth aspect, the embodiment of the present invention provide a kind of computer-readable recording medium, the computer-readable storage medium
Matter is stored with computer program, and the computer program realizes the step of the trip mode recognition methods when being executed by processor
Suddenly.
In trip mode recognition methods, device, terminal device and storage medium that the embodiment of the present invention is provided, based on work as
Trip mode is assessed corresponding to each cluster class cluster in preceding user trajectory data and user trajectory data model, determines that target is gone on a journey
Mode, to help the trip mode of vehicle insurance company identification user, assessed for vehicle insurance and accurate data reference is provided.
Brief description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention
The accompanying drawing needed to use is briefly described, it should be apparent that, drawings in the following description are only some implementations of the present invention
Example, for those of ordinary skill in the art, without having to pay creative labor, can also be according to these accompanying drawings
Obtain other accompanying drawings.
Fig. 1 is a flow chart of trip mode recognition methods in the embodiment of the present invention 1.
Fig. 2 is another flow chart of trip mode recognition methods in the embodiment of the present invention 1.
Fig. 3 is a particular flow sheet of step S50 in Fig. 2.
Fig. 4 is a particular flow sheet of step S30 in Fig. 1.
Fig. 5 is a step S70 particular flow sheet.
Fig. 6 is a theory diagram of trip mode identification device in the embodiment of the present invention 2.
Fig. 7 is a schematic diagram of terminal device in the embodiment of the present invention 4.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is part of the embodiment of the present invention, rather than whole embodiments.Based on this hair
Embodiment in bright, the every other implementation that those of ordinary skill in the art are obtained under the premise of creative work is not made
Example, belongs to the scope of protection of the invention.
Embodiment 1
Fig. 1 shows the flow chart of trip mode recognition methods in the present embodiment.The trip mode recognition methods, which is applied, to be protected
In the vehicle insurance evaluation system of dangerous mechanism, for identifying the trip mode of user, duration and driving habit etc. are driven so as to extract
Driving data, the risk that vehicle insurance is handled to assess user provide reference.As shown in figure 1, the trip mode recognition methods is included such as
Lower step：
S10：Active user's track data is obtained, active user's track data includes at least one current signature data.
Active user's track data is the track data for being used to embody trip mode that user collects in trip.Currently
User can use at least one of walking, bicycle, light cavalry, bus, car, railway and aircraft mode of transportation when going on a journey
Trip, the track data such as speed, acceleration, angle, angular acceleration differs corresponding to different modes of transportation, each traffic side
Formula corresponds to a kind of trip mode.Wherein, current signature data include but is not limited to active user trip when collect speed,
The track datas such as acceleration, angle and angular acceleration.
In the present embodiment, user in advance the application program on the mobile terminal such as mobile phone and flat board (i.e. (Application,
Abbreviation APP) on complete registration so that server corresponding to application program can obtain corresponding user mark.User mark can
Think cell-phone number or identification card number of user etc. can unique identification user mark.When user carries mobile terminal trip, move
Built-in sensor can gather the speed of any time, acceleration, angle, angle during user goes on a journey in real time and accelerate in dynamic terminal
The current signature data such as degree, also can any time in real time collection GPS location information, and calculated based on GPS location information
Current signature data corresponding to acquisition.The current characteristic is uploaded to clothes by acquisition for mobile terminal to after current signature data
Be engaged in device so that server by the current signature data storage got in the databases such as MySQL, Oracle, and make each
Track data and a user identify associated storage.When needing the trip mode to user to be identified, can from MySQL,
Inquiry obtains the current signature data associated with user's mark in the databases such as Oracle, to obtain active user track number
According to.
S20：User trajectory data model is obtained, user trajectory data model includes at least two cluster class clusters, Mei Yiju
Class class cluster corresponding one assesses trip mode.
Wherein, user trajectory data model is that good being used to identify corresponding to active user's track data of training in advance is assessed
The model of trip mode.The user trajectory data model trains to obtain and be stored in MySQL based on training user's track data,
In the databases such as Oracle, when terminal device carries out trip mode identification, the user trajectory data can be transferred from database
Model.In the present embodiment, user trajectory data model is that training user's track data is gathered by K-means clustering algorithms
The model obtained after class processing.Training user's track data is user obtained in trip be used for training user's track data
The track data of model, the track data include but is not limited to speed, the acceleration that user collects any time in trip
It is at least one in the data such as degree, angle and angular acceleration.Wherein, K-means clustering algorithms are that a kind of distance that is based on assesses phase
Like the clustering algorithm of degree, i.e., the distance of two objects is nearer, the bigger clustering algorithm of its similarity.Trip mode is assessed to refer to often
Trip mode in one cluster class cluster corresponding to training user's track data.
Specifically, the user trajectory data model obtained after being clustered using K-means clustering algorithms includes at least two
Individual cluster class cluster, each cluster class cluster corresponding one assess trip mode.Wherein, each cluster class cluster includes a barycenter user trajectory
Data, trip mode corresponding to barycenter user trajectory data are assessment trip mode.In the present embodiment, the user's rail trained
Mark data model comprises at least seven cluster class clusters, it is each cluster class cluster represent respectively walking, bicycle, light cavalry, bus,
Car, railway and aircraft, i.e., each cluster class cluster represents a kind of trip mode.Train track data to cluster class cluster barycenter away from
From smaller, then the training track data is more likely to belong to trip mode corresponding to the cluster class cluster.
In an embodiment, as shown in Fig. 2 the trip mode recognition methods also includes：
S50：Based on training user's track data training user's track data model, training user's track data is included at least
One training characteristics data.
Wherein, training characteristics data refer to the corresponding number of feature in the data for training user's track data model
According to the data such as speed, acceleration, angle and angular acceleration that including but not limited to user collects in trip.The present embodiment
In, referred to based on training user's track data training user's track data model using K-means clustering algorithms to training user
At least one training characteristics data are clustered in track data, using the set of similar training user's track data as a cluster
Class cluster, all training user's track datas are divided at least two cluster class clusters, and obtained corresponding to each cluster class cluster
Trip mode, you can form user trajectory data model.
In the present embodiment, as shown in figure 3, in step S50, based on training user's track data training user's track data mould
Type, training user's track data include at least one training characteristics data, specifically comprised the following steps：
S51：At least one training characteristics data in training user's track data are gathered using K-means clustering algorithms
Class, obtain at least two cluster class clusters, each corresponding barycenter user trajectory data of cluster class cluster.
K-means clustering algorithms are a kind of clustering algorithms that similarity is assessed based on distance, i.e., the distance of two objects is got over
Closely, the bigger clustering algorithm of its similarity.K-means clustering algorithms by calculate two objects Euclidean distance, according to Euclidean
The size of distance evaluates the similitude of two objects.Euclidean distance (euclidean metric, also known as euclidean metric) is
Refer to the actual distance in m-dimensional space between two points, or the natural length (i.e. the distance of the point to origin) of vector.Arbitrarily
Two n-dimensional vector a (Xi1,Xi2,...,Xin) and b (Xj1,Xj2,...,Xjn) Euclidean distance
Training user's track data is the user trajectory data for the training user of training user's track data model, instruction
Practicing user trajectory data includes at least one training characteristics data, using K-means clustering algorithms to training user's track data
In at least one training characteristics data clustered, with obtain at least two cluster class clusters, it is each cluster class cluster include it is multiple
Training user's track data.In any cluster class cluster, barycenter corresponding to a barycenter in multiple training user's track datas be present
User trajectory data, make other training user's track datas minimum apart from sum to barycenter user trajectory data.It is appreciated that
Ground, barycenter user trajectory data are one in all training user's track datas in any cluster class cluster, and therefore, the barycenter is used
Family track data also includes at least one training characteristics data.
If form user's rail based on training characteristics data corresponding at least one feature in multiple training user's track datas
Mark data matrix R, the value of characteristic in user trajectory data matrix R is clustered using K-means clustering algorithms.Using
It is as follows that K-means clustering algorithms carry out cluster process：Step (1), n dimension figures are established, according to each in user trajectory data matrix R
The value of characteristic corresponding to user trajectory data draws out m data point Ui in n dimension figures, wherein, i ∈ m, each data point
The corresponding training user's track datas of Ui.Step (2), K values are predefined, m data point can be divided into by K data according to K values
Collect G=[G1, G2, G3, G4 ... Gj ..., Gk], wherein, K >=2, j ∈ k.Step (3), randomly choosed in each data set Gj
One data point Ui is as barycenter Ci so that K barycenter Ci in all data sets be present.Step (4), calculate each data set Gj
Middle any data point Ui and K barycenter Gi Euclidean distance Di, data point Ui is included into a minimum data of Euclidean distance Di
Collect in Gj.Step (5), all data point Ui is performed step (4), form new data set G.Repeat step (3)-(5) so that
When new barycenter Ci and old barycenter Ci is less than default threshold value in any data set Gj, K-means clustering algorithms terminate, and are formed
K cluster class cluster, each class cluster that clusters have a barycenter, and the barycenter corresponds to barycenter user trajectory data.
S52：Training user's track data in cluster class cluster is counted using K- nearest neighbor algorithms, commented with obtaining corresponding one
Estimate trip mode.
Wherein, K- neighbours (K Nearest Neighbor, abbreviation KNN) algorithm is by measuring between different characteristic data value
Distance classified.The central idea of K- nearest neighbor algorithms is if the k in feature space, a sample is most like (i.e. special
It is closest in sign space) sample in it is most of belong to some classification, then the sample falls within this classification.KNN algorithms
By calculating Euclidean distance between object or manhatton distance is used as non-similarity index between each object.Euclidean away from
Refer to the actual distance in m-dimensional space between two points from (euclidean metric, also known as euclidean metric), or
The natural length (i.e. the distance of the point to origin) of vector.Any two n-dimensional vector a (Xi1,Xi2,...,Xin) and b (Xj1,
Xj2,...,Xjn) Euclidean distance((manhattan distance) refers to manhatton distance
2 points of distances in North and South direction are plus the distance on east-west direction, in the plane, coordinate (Xi,Yi) i points and coordinate
(Xj,Yj) j points manhatton distance | Xi-Xj|+|Yi-Yj|。
Each training user's track data corresponds to a kind of trip mode in class cluster is clustered, i.e., each training user track number
According to carrying corresponding to trip mode mark, in step S52 can the cluster class cluster based on determination obtained using K- nearest neighbor algorithms it is every
Trip quantity corresponding to a kind of trip mode, and assess trip mode according to corresponding to trip quantity determines the cluster class cluster.
In a kind of embodiment, in step S52, need first to all training user's track datas pair in cluster class cluster
The trip mode answered is counted, and obtains trip quantity corresponding to each trip mode.Then, each trip is calculated respectively
Corresponding to mode trip quantity is obtained corresponding to each trip mode relative to the ratio of all training user's track datas
Statistics ratio.Maximum is chosen from statistics ratio corresponding to all trip modes again, it is default to judge whether the maximum is more than
Ratio, the preset ratio are to be used for customized numerical value；If the maximum is more than preset ratio, will go out corresponding to the maximum
Line mode assesses trip mode as corresponding to the cluster class cluster.Such as in a cluster class cluster, count and take bus, ride certainly
Driving, driving vehicle and statistics ratio corresponding to other modes are respectively 10%, 60%, 15% and 15%, if preset ratio is
50%, then maximum is 60% in above-mentioned statistics ratio, is made more than preset ratio 50%, therefore by cycling corresponding to 60%
To assess trip mode corresponding to the cluster class cluster.
In another embodiment, in step S52, need first to all training user's track datas in cluster class cluster
Corresponding trip mode is counted, and obtains trip quantity corresponding to each trip mode.Then, each is calculated respectively to go out
It is corresponding to obtain each trip mode relative to the ratio of all training user's track datas for trip quantity corresponding to line mode
Statistics ratio.Maximum and Second Largest Value are chosen from statistics ratio corresponding to all trip modes again, based on maximum and
Second largest value calculates proportional difference.Then judge whether the proportional difference is more than preset difference value, the preset difference value is User Defined
Numerical value.If proportional difference is more than preset difference value, using trip mode corresponding to the maximum as corresponding to the cluster class cluster
Assess trip mode.Such as in a cluster class cluster, count and take bus, cycling, drive vehicle and other modes pair
The statistics ratio answered is respectively 10%, 60%, 15% and 15%, if preset difference value is 30%, then maximum in above-mentioned statistics ratio
It is worth for 60%, Second Largest Value 10%, both proportional differences are 50%, and the proportional difference is more than preset difference value, therefore general
Cycling corresponding to 60% is as assessment trip mode corresponding to the cluster class cluster.
S53：Based on cluster class cluster and trip mode is assessed, obtains user trajectory data model.
In the present embodiment, due to using K-means clustering algorithms by all training user's rails in user trajectory data matrix R
Mark data are divided into K cluster class cluster, and each barycenter user trajectory data for clustering class cluster are instructed with other in same cluster class cluster
It is similar to practice user trajectory data, can be trained trip mode corresponding to barycenter user trajectory data as other in the cluster class cluster
The assessment trip mode of user trajectory data, so that it is determined that user trajectory data model.
S60：User trajectory data model is stored in database.
In the present embodiment, the user trajectory data model trained in step S50 can be stored in MySQL, Oracle
Or in other databases, it can also be stored in based in the Hive storehouses in Hadoop framework.Hive storehouses can be by the number of structuring
It is a database table according to File Mapping, and complete SQL query function is provided, the database learning cost is low, passes through distribution
Formula stores, and can improve data storage capacities, mitigate the pressure of data processing.User trajectory data model is stored in database
In be easy in trip mode identifies, the good user trajectory data model of training in advance is called from database.
In this specific embodiment, step S20 includes：User trajectory data model is obtained from database.Due to
Family track data model training in advance is got well and is stored in database, it is required that user trajectory data model carries out trip side
When formula identifies, the user trajectory data model can be directly called from database, you can processing is identified, operating process is simple
Fast.
S30：Based on active user's track data and user trajectory data model, obtained from least two cluster class clusters with
The corresponding target cluster class cluster of at least one current signature data.
Wherein, target cluster class cluster refer to where the most similar barycenter user trajectory data of active user's track data
Cluster class cluster.Target cluster class cluster specifically refer to active user's track data that at least one current signature data are formed away from
From cluster class cluster corresponding to nearest barycenter user trajectory data.
In an embodiment, as shown in figure 4, step S30 specifically comprises the following steps：
S31：By active user's track data respectively with user trajectory data model at least two cluster class clusters barycenter
User trajectory data are calculated, and obtain at least two Euclidean distances.
In the present embodiment, K cluster class cluster, each corresponding barycenter of cluster class cluster are stored with user's driving data model
User trajectory data, if setting active user's track data as n-dimensional vector a (Xi1,Xi2,...,Xin), the barycenter of any cluster class cluster
User trajectory data are n-dimensional vector b (Xj1,Xj2,...,Xjn), then active user's track data and barycenter user trajectory data
Euclidean distanceWherein, vectorial a dimension n and current signature number in active user's track data
According to quantity it is corresponding；Correspondingly, vectorial b dimension n is relative with the quantity of training characteristics data in barycenter user trajectory data
Should.
S32：Choose the cluster class cluster corresponding to minimum value where barycenter user trajectory data at least two Euclidean distances
Class cluster is clustered as the target corresponding with least one current signature data.
Because Euclidean distance is the mode for evaluating the similitude of two objects, Euclidean distance is smaller, and expression two is right
As more similar, if obtaining K active user's track data and the Euclidean distance D of barycenter user trajectory data in step S31a,b, will
K Euclidean distance Da,bCluster class cluster corresponding to middle selection minimum value where barycenter user trajectory data, is defined as with currently using
Cluster class cluster where the most like barycenter user trajectory data of family track data, so as with active user track number
The target cluster class cluster that at least one current signature data are corresponding in.
S40：Based on trip mode is assessed corresponding to target cluster class cluster, target trip mode is obtained.
Target trip mode is to identify trip mode corresponding to active user's track data, in the present embodiment, by target
Trip mode, which is assessed, corresponding to cluster class cluster is defined as target trip mode.In step S52, using K- nearest neighbor algorithms, to every
Training user's track data carries out statistics calculating in one cluster class cluster, and acquisition evaluates with barycenter user trajectory data corresponding one
Line mode, so that it is determined that the assessment trip mode of target cluster class cluster corresponding to the barycenter user trajectory data, as mesh
Mark line mode output.
In an embodiment, after step S40, the trip mode recognition methods also includes：
S70：Based on target trip mode, the training driving data for training driving model is obtained.
Wherein, training driving data refers to the data for training driving model, the target that can be obtained by step S40
Trip mode, judge whether target trip mode corresponding to active user's track data is drive manner, to determine the current use
Whether family track data is driving data, and based on judged result, reservation is active user's track data of driving data as instruction
Practice driving data, delete active user's track data corresponding to non-driving data, to gather sufficient amount of training driving data,
To carry out driving model training using the training driving data, to improve the accuracy of driving model.
In the present embodiment, each target trip mode obtained in step step S70 corresponds to a trip mode ID.Trip side
Formulas I D refers to the mark corresponding to each target trip mode, is the mark for being different from other trip modes.Such as Fig. 5 institutes
Show, in step S70, based on target trip mode, obtain the training driving data for training driving model, specifically include as follows
Step：
S71：Trip mode query statement is obtained, trip mode query statement includes drive manner ID.
Wherein, trip mode query statement refers to be used to inquire about target trip mode corresponding to active user's track data and be
The no instruction for drive manner.Drive manner ID is carried in the trip mode query statement, drive manner ID is trip side
Formula is the mark corresponding to drive manner.Drive manner refers to that user drives car or the mode of other vehicle drivings.Can
So that with understanding, the trip mode query statement in step S71 can carry drive manner ID, can also carry other trip modes
ID, to obtain the driving data of user, assess and accurate user trajectory data reference is provided for vehicle insurance or other insurance kinds, therefore,
Trip mode query statement in the present embodiment carries drive manner ID.
S72：Whether judge trip mode ID corresponding to the active user's track data and drive manner ID in query statement
Unanimously.
Specifically, by comparing trip mode ID corresponding to active user's track data and the drive manner in query statement
Whether ID is consistent, it can be determined that whether trip mode corresponding to active user's track data is drive manner.In the present embodiment, base
Class cluster is clustered in the target that active user's track data and user trajectory data model are obtained in step S32, is gathered based on the target
Trip mode is assessed corresponding to class class cluster and obtains trip mode ID corresponding to active user's track data；The trip mode is judged again
Whether ID is consistent with the drive manner ID in the trip mode query statement that step S71 is got, to judge active user track
Whether trip mode corresponding to data is drive manner, is advantageous to gather active user's rail that target trip mode is drive manner
Mark data, in order to train the model for identifying whether to drive for user, offer number is handled for vehicle insurance or other insurance kinds
According to support.
S73：If trip mode ID corresponding to active user's track data is consistent with the drive manner ID in query statement,
It is drive manner to determine target trip mode, and active user's track data is saved as into training driving data.
Specifically, it is consistent with the drive manner ID in query statement in trip mode ID corresponding to active user's track data
When, determine that target trip mode corresponding to the current user trajectory data is drive manner, i.e. the trip mode of active user is
Drive manner, then active user's track data is stored in database as the training driving data of training driving model.This
When, the current user trajectory data include the information such as the driving duration of active user, driving habit, and vehicle insurance is handled to active user
Or during other insurance kinds, when need to carry out vehicle insurance or the assessment of other insurance kinds, insurance company can extract training from database and drive
Data, driving model training is carried out, to be carried out using the driving model trained to the user trajectory data collected in real time
Identification, to determine whether that user drives, to obtain the data related to vehicle insurance or other insurance kinds, to be done to active user
The risk assessment for managing vehicle insurance or other insurance kinds provides data reference.
S74：If trip mode ID corresponding to active user's track data and the drive manner ID in query statement are inconsistent,
It is not drive manner then to determine the target trip mode, and active user's track data is deleted.
Specifically, the drive manner ID in trip mode ID and query statement corresponding to active user's track data differs
During cause, it is not the trip side of drive manner, i.e. active user to determine target trip mode corresponding to the current user trajectory data
Formula is not drive manner, then deletes active user's track data, to save the space of database.Such as identify active user's rail
Target trip mode corresponding to mark data is to take a flight, and drive manner is not belonging to due to taking a flight, then will be with airplane
Corresponding active user's track data is deleted.Due to taking a flight or other are not active user tracks corresponding to drive manner
Data can not reflect the driving informations such as the driving duration of active user, driving habit, if not deleting and being stored in database,
, may be to the instruction of driving model corresponding to subsequent calls active user during active user's track data training user's driving model
Practice and identification interferes.Therefore, when it is determined that target trip mode corresponding to active user's track data is not drive manner,
The current user trajectory data need to be deleted.
In the trip mode recognition methods that the present embodiment is provided, based on active user's track data and user trajectory data
Trip mode is assessed corresponding to each cluster class cluster in model, determines target trip mode, then based on target trip mode, judge
Whether target trip mode is drive manner, extracts the driving information of user under drive manner, helps vehicle insurance company to be used to be current
Family carries out vehicle insurance and assesses the accurate data reference of offer.
It should be understood that the size of the sequence number of each step is not meant to the priority of execution sequence, each process in above-described embodiment
Execution sequence should determine that the implementation process without tackling the embodiment of the present invention forms any limit with its function and internal logic
It is fixed.
Embodiment 2
Fig. 6 shows the principle frame with the one-to-one trip mode identification device of trip mode recognition methods in embodiment 1
Figure.As shown in fig. 6, the trip mode identification device includes active user's track data acquisition module 10, user trajectory data mould
Type acquisition module 20, target cluster class cluster acquisition module 30 and target trip mode acquisition module 40.Wherein, active user track
Data acquisition module 10, user trajectory data model acquisition module 20, target cluster class cluster acquisition module 30 and target trip side
Formula acquisition module 40 realizes that function step corresponding with trip mode recognition methods in embodiment 1 corresponds, to avoid going to live in the household of one's in-laws on getting married
State, the present embodiment is not described in detail one by one.
Active user's track data acquisition module 10, for obtaining active user's track data, active user's track data
Including at least one current signature data；
User trajectory data model acquisition module 20, for obtaining user trajectory data model, user trajectory data model
Including at least two cluster class clusters, each cluster class cluster corresponding one assesses trip mode；
Target cluster class cluster acquisition module 30, for based on active user's track data and user trajectory data model, from
The target cluster class cluster corresponding with least one current signature data is obtained at least two cluster class clusters；
Target trip mode acquisition module 40, for based on trip mode is assessed corresponding to target cluster class cluster, obtaining mesh
Mark line mode.
Preferably, target cluster class cluster acquisition module 30 includes Euclidean distance acquiring unit 31 and target cluster class cluster is chosen
Unit 32.
Euclidean distance acquiring unit 31, for by active user's track data respectively with user trajectory data model at least
The barycenter user trajectory data of two cluster class clusters are calculated, and obtain at least two Euclidean distances.
Target cluster class cluster chooses unit 32, for choosing barycenter user corresponding to minimum value at least two Euclidean distances
Cluster class cluster where track data clusters class cluster as the target corresponding with least one current signature data.
Preferably, trip mode identification device also includes user trajectory data model training module 50, user trajectory data
Model memory module 60.
User trajectory data model training module 50, for based on training user's track data training user's track data mould
Type, training user's track data include at least one training characteristics data.
User trajectory data model memory module 60, for user trajectory data model to be stored in database.
User trajectory data model acquisition module 20, for obtaining user trajectory data model from database.
Preferably, user trajectory data model training module 50 includes cluster class cluster acquiring unit 51, assesses trip mode
Acquiring unit 52 and user trajectory data model acquiring unit 53.
Class cluster acquiring unit 51 is clustered, for using K-means clustering algorithms in training user's track data at least one
Individual training characteristics data are clustered, and obtain at least two cluster class clusters, each corresponding barycenter user trajectory number of cluster class cluster
According to.
Trip mode acquiring unit 52 is assessed, for using K- nearest neighbor algorithms to training user's track data in cluster class cluster
Counted, trip mode is assessed to obtain corresponding one.
User trajectory data model acquiring unit 53, for based on cluster class cluster and assessment trip mode, obtaining user's rail
Mark data model.
Preferably, trip mode identification device also includes training driving data acquisition module 70, for being gone on a journey based on target
Mode, obtain the training driving data for training driving model, the corresponding trip mode ID of target trip mode.
Driving data acquisition module 70 is trained to include trip mode query statement acquiring unit 71, drive manner judging unit
72nd, active user's track data storage unit 73 and active user's track data delete unit 74.
Trip mode query statement acquiring unit 71, for obtaining trip mode query statement, trip mode query statement
Including drive manner ID；.
Drive manner judging unit 72, for judging trip mode ID and query statement corresponding to active user's track data
In drive manner ID it is whether consistent.
Active user's track data storage unit 73, in trip mode ID corresponding to active user's track data with looking into
When drive manner ID in inquiry instruction is consistent, it is drive manner to determine target trip mode, and active user's track data is preserved
To train driving data.
Active user's track data deletes unit 74, for trip mode ID corresponding to active user's track data and looking into
When drive manner ID in inquiry instruction is inconsistent, it is not drive manner to determine target trip mode, by active user's track data
Delete.
Embodiment 3
The present embodiment provides a computer-readable recording medium, and computer journey is stored with the computer-readable recording medium
Sequence, the computer program realize trip mode recognition methods in embodiment 1 when being executed by processor, to avoid repeating, here not
Repeat again.Or the computer program realize when being executed by processor in embodiment 2 each module in trip mode identification device/
The function of unit, to avoid repeating, repeat no more here.
Embodiment 4
Fig. 7 is the schematic diagram for the terminal device that one embodiment of the invention provides.As shown in fig. 7, the terminal of the embodiment is set
Standby 70 include：Processor 71, memory 72 and it is stored in the computer journey that can be run in memory 72 and on processor 71
Sequence 73, processor 71 realizes each step of trip mode recognition methods in embodiment 1 when performing computer program 73, such as schemes
Step S10, S20, S30 and S40 shown in 1.Or realize during the execution computer program 73 of processor 71 and gone on a journey in embodiment 2
The function of each module/unit of mode identification device, active user's track data acquisition module 10 as shown in Figure 6, user trajectory number
According to the function of model acquisition module 20, target cluster class cluster acquisition module 30 and target trip mode acquisition module 40.
Exemplary, computer program 73 can be divided into one or more module/units, one or more mould
Block/unit is stored in memory 72, and is performed by processor 71, to complete the present invention.One or more module/units can
To be the series of computation machine programmed instruction section that can complete specific function, the instruction segment is for describing computer program 73 at end
Implementation procedure in end equipment 70.For example, computer program 73 can be divided into active user's track data acquisition module 10,
User trajectory data model acquisition module 20, target cluster class cluster acquisition module 30 and target trip mode acquisition module 40.
The terminal device 70 can be the computing devices such as desktop PC, notebook, palm PC and cloud server.
Terminal device may include, but be not limited only to, processor 71, memory 72.It will be understood by those skilled in the art that Fig. 7 is only
The example of terminal device 70, the restriction to terminal device 70 is not formed, parts more more or less than diagram can be included, or
Person combines some parts, or different parts, such as terminal device can also include input-output equipment, network insertion is set
Standby, bus etc..
Alleged processor 71 can be CPU (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other PLDs, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor can also be any conventional processor
Deng.
Memory 72 can be the internal storage unit of terminal device 70, such as the hard disk or internal memory of terminal device 70.Deposit
Reservoir 72 can also be the plug-in type hard disk being equipped with the External memory equipment of terminal device 70, such as terminal device 70, intelligence
Storage card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card (Flash Card)
Deng.Further, memory 72 can also both include the internal storage unit of terminal device 70 or including External memory equipment.Deposit
Reservoir 72 is used to store computer program and other programs and data needed for terminal device.Memory 72 can be also used for temporarily
When store the data that has exported or will export.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each work(
Can unit, module division progress for example, in practical application, can be as needed and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device are divided into different functional units or module, more than completion
The all or part of function of description.Each functional unit, module in embodiment can be integrated in a processing unit, also may be used
To be that unit is individually physically present, can also two or more units it is integrated in a unit, it is above-mentioned integrated
Unit can both be realized in the form of hardware, can also be realized in the form of SFU software functional unit.In addition, each function list
Member, the specific name of module are not limited to the protection domain of the application also only to facilitate mutually distinguish.Said system
The specific work process of middle unit, module, the corresponding process in preceding method embodiment is may be referred to, will not be repeated here.
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, and is not described in detail or remembers in some embodiment
The part of load, it may refer to the associated description of other embodiments.
Those of ordinary skill in the art are it is to be appreciated that the list of each example described with reference to the embodiments described herein
Member and algorithm steps, it can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
Performed with hardware or software mode, application-specific and design constraint depending on technical scheme.Professional and technical personnel
Described function can be realized using distinct methods to each specific application, but this realization is it is not considered that exceed
The scope of the present invention.
In embodiment provided by the present invention, it should be understood that disclosed device/terminal device and method, can be with
Realize by another way.For example, device described above/terminal device embodiment is only schematical, for example, institute
The division of module or unit is stated, only a kind of division of logic function, there can be other dividing mode when actually realizing, such as
Multiple units or component can combine or be desirably integrated into another system, or some features can be ignored, or not perform.Separately
A bit, shown or discussed mutual coupling or direct-coupling or communication connection can be by some interfaces, device
Or INDIRECT COUPLING or the communication connection of unit, can be electrical, mechanical or other forms.
The unit illustrated as separating component can be or may not be physically separate, show as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units it is integrated in a unit.Above-mentioned integrated list
Member can both be realized in the form of hardware, can also be realized in the form of SFU software functional unit.
If the integrated module/unit realized in the form of SFU software functional unit and as independent production marketing or
In use, it can be stored in a computer read/write memory medium.Based on such understanding, the present invention realizes above-mentioned implementation
All or part of flow in example method, by computer program the hardware of correlation can also be instructed to complete, described meter
Calculation machine program can be stored in a computer-readable recording medium, and the computer program can be achieved when being executed by processor
The step of stating each embodiment of the method.Wherein, the computer program includes computer program code, the computer program generation
Code can be source code form, object identification code form, executable file or some intermediate forms etc..The computer-readable medium
It can include：Any entity or device, recording medium, USB flash disk, mobile hard disk, the magnetic of the computer program code can be carried
Dish, CD, computer storage, read-only storage (ROM, Read-Only Memory), random access memory (RAM,
Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It is it should be noted that described
The content that computer-readable medium includes can carry out appropriate increasing according to legislation in jurisdiction and the requirement of patent practice
Subtract, such as in some jurisdictions, according to legislation and patent practice, computer-readable medium do not include be electric carrier signal and
Telecommunication signal.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although with reference to foregoing reality
Example is applied the present invention is described in detail, it will be understood by those within the art that：It still can be to foregoing each
Technical scheme described in embodiment is modified, or carries out equivalent substitution to which part technical characteristic；And these are changed
Or replace, the essence of appropriate technical solution is departed from the spirit and scope of various embodiments of the present invention technical scheme, all should
Within protection scope of the present invention.
Claims (10)
- A kind of 1. trip mode recognition methods, it is characterised in that including：Active user's track data is obtained, active user's track data includes at least one current signature data；User trajectory data model is obtained, the user trajectory data model includes at least two cluster class clusters, each described poly- Class class cluster corresponding one assesses trip mode；Based on active user's track data and the user trajectory data model, obtained from least two cluster class clusters The target corresponding with least one current signature data is taken to cluster class cluster；Based on trip mode is assessed corresponding to target cluster class cluster, target trip mode is obtained.
- 2. trip mode recognition methods as claimed in claim 1, it is characterised in that the acquisition user trajectory data model it Before, the trip mode recognition methods also includes：The user trajectory data model is trained based on training user's track data, training user's track data is included at least One training characteristics data；The user trajectory data model is stored in database；The acquisition user trajectory data model, including：The user trajectory data model is obtained from the database.
- 3. trip mode recognition methods as claimed in claim 2, it is characterised in that described to be instructed based on training user's track data Practice the user trajectory data model, including：At least one training characteristics data in training user's track data are gathered using K-means clustering algorithms Class, obtain at least two cluster class clusters, each corresponding barycenter user trajectory data of cluster class cluster；Training user's track data described in the cluster class cluster is counted using K- nearest neighbor algorithms, to obtain the correspondence One assesses trip mode；Based on the cluster class cluster and the assessment trip mode, the user trajectory data model is obtained.
- 4. trip mode recognition methods as claimed in claim 1, it is characterised in that described to be based on active user track number According to the user trajectory data model, from least two it is described cluster class clusters in obtain with least one current signature number Class cluster is clustered according to corresponding target, including：By active user's track data respectively with the user trajectory data model at least two cluster class clusters Barycenter user trajectory data are calculated, and obtain at least two Euclidean distances；Choose the cluster class cluster conduct corresponding to minimum value where barycenter user trajectory data at least two Euclidean distances The target cluster class cluster corresponding with least one current signature data.
- 5. trip mode recognition methods as claimed in claim 2, it is characterised in that based on corresponding to target cluster class cluster Trip mode is assessed, target trip mode is obtained, also includes afterwards：Based on the target trip mode, obtain and driven for training Sail the training driving data of model, the corresponding trip mode ID of the target trip mode；It is described to be based on the target trip mode, the training driving data for training driving model is obtained, including：Trip mode query statement is obtained, the trip mode query statement includes drive manner ID；Whether judge trip mode ID corresponding to the active user's track data and drive manner ID in the query statement Unanimously；If trip mode ID is consistent with the drive manner ID in the query statement corresponding to active user's track data, It is drive manner to determine the target trip mode, and active user's track data is saved as into the training driving data；If trip mode ID corresponding to active user's track data and the drive manner ID in the query statement are inconsistent, It is not drive manner then to determine the target trip mode, and active user's track data is deleted.
- A kind of 6. trip mode identification device, it is characterised in that including：Active user's track data acquisition module, for obtaining active user's track data, active user's track data bag Include at least one current signature data；User trajectory data model acquisition module, for obtaining user trajectory data model, the user trajectory data model bag At least two cluster class clusters are included, each cluster class cluster corresponding one assesses trip mode；Target clusters class cluster acquisition module, for based on active user's track data and the user trajectory data model, The target corresponding with least one current signature data, which is obtained, from least two cluster class clusters clusters class cluster；Target trip mode acquisition module, for based on trip mode is assessed corresponding to target cluster class cluster, obtaining target Trip mode.
- 7. trip mode identification device as claimed in claim 6, it is characterised in that the trip mode identification device also wraps Include：User trajectory data model training module, for training the user trajectory data mould based on training user's track data Type, training user's track data include at least one training characteristics data；User trajectory data model memory module, for the user trajectory data model to be stored in database；User trajectory data model acquisition module, for obtaining the user trajectory data model from the database；The user trajectory data model training module includes：Class cluster acquiring unit is clustered, for using K-means clustering algorithms at least one in training user's track data The training characteristics data are clustered, and obtain at least two cluster class clusters, each corresponding barycenter user trajectory of cluster class cluster Data；Trip mode acquiring unit is assessed, for clustering training user track number described in class cluster to described using K- nearest neighbor algorithms According to being counted, trip mode is assessed to obtain the correspondence one；User trajectory data model acquiring unit, for based on the cluster class cluster and assessment trip mode, described in acquisition User trajectory data model；The target cluster class cluster acquisition module includes：Euclidean distance acquiring unit, for by active user's track data respectively with the user trajectory data model extremely The barycenter user trajectory data of few two cluster class clusters are calculated, and obtain at least two Euclidean distances；Target cluster class cluster chooses unit, for choosing barycenter user rail corresponding to minimum value at least two Euclidean distances Cluster class cluster where mark data clusters class cluster as the target corresponding with least one current signature data.
- 8. trip mode identification device as claimed in claim 6, it is characterised in that the trip mode identification device also includes Driving data acquisition module is trained, for based on the target trip mode, obtaining for training the training of driving model to drive Data, the corresponding trip mode ID of the target trip mode；The training driving data acquisition module includes：Trip mode query statement acquiring unit, for obtaining trip mode query statement, the trip mode query statement bag Include drive manner ID；Drive manner judging unit, for judging that trip mode ID corresponding to active user's track data refers to the inquiry Whether the drive manner ID in order is consistent；Active user's track data storage unit, for trip mode ID corresponding to active user's track data with it is described When drive manner ID in query statement is consistent, it is drive manner to determine the target trip mode, by active user's rail Mark data save as the training driving data；Active user's track data deletes unit, in trip mode ID corresponding to active user's track data and described When drive manner ID in query statement is inconsistent, it is not drive manner to determine the target trip mode, by the current use Family track data is deleted.
- 9. a kind of terminal device, including memory, processor and it is stored in the memory and can be on the processor The computer program of operation, it is characterised in that realize such as claim 1 to 5 described in the computing device during computer program The step of any one trip mode recognition methods.
- 10. a kind of computer-readable recording medium, the computer-readable recording medium storage has computer program, and its feature exists In realizing the trip mode recognition methods as described in any one of claim 1 to 5 when the computer program is executed by processor Step.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710846069.XA CN107784597B (en) | 2017-09-19 | 2017-09-19 | Travel mode identification method and device, terminal equipment and storage medium |
| PCT/CN2018/073619 WO2019056680A1 (en) | 2017-09-19 | 2018-01-22 | Travel mode identification method and apparatus, terminal device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710846069.XA CN107784597B (en) | 2017-09-19 | 2017-09-19 | Travel mode identification method and device, terminal equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107784597A true CN107784597A (en) | 2018-03-09 |
| CN107784597B CN107784597B (en) | 2021-09-28 |
Family
ID=61437624
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710846069.XA Active CN107784597B (en) | 2017-09-19 | 2017-09-19 | Travel mode identification method and device, terminal equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107784597B (en) |
| WO (1) | WO2019056680A1 (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108986255A (en) * | 2018-07-13 | 2018-12-11 | 平安科技（深圳）有限公司 | Electronic device, driving behavior methods of marking and storage medium |
| CN109146694A (en) * | 2018-07-13 | 2019-01-04 | 平安科技（深圳）有限公司 | Electronic device, the preferential rank of user's vehicle insurance determine method and storage medium |
| CN109272032A (en) * | 2018-09-05 | 2019-01-25 | 广州视源电子科技股份有限公司 | Travel mode identification method and device, computer equipment and storage medium |
| CN110148298A (en) * | 2019-06-24 | 2019-08-20 | 重庆大学 | Private car rule travel behaviour based on motor vehicle electronic mark data finds method |
| CN111076741A (en) * | 2019-12-03 | 2020-04-28 | Oppo广东移动通信有限公司 | Navigation state acquisition method and device, storage medium and electronic equipment |
| CN111163425A (en) * | 2020-01-02 | 2020-05-15 | 中国平安财产保险股份有限公司 | LBS track-based identity recognition method, electronic device and readable storage medium |
| CN112131454A (en) * | 2020-08-26 | 2020-12-25 | 汉海信息技术(上海)有限公司 | Method and device for pushing user information during train trip and server |
| CN114187489A (en) * | 2021-12-14 | 2022-03-15 | 中国平安财产保险股份有限公司 | Vehicle abnormal driving risk detection method and device, electronic equipment and storage medium |
| CN116681184A (en) * | 2023-07-28 | 2023-09-01 | 厦门农芯数字科技有限公司 | Method, device and equipment for predicting growth index of live pigs and readable storage medium |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113543032B (en) * | 2020-04-21 | 2022-12-16 | ***通信集团广东有限公司 | Model training method and device, user identification method and device, and electronic device |
| CN111653096B (en) * | 2020-05-29 | 2022-10-04 | 南京瑞栖智能交通技术产业研究院有限公司 | Urban trip mode identification method based on mobile phone signaling data |
| CN112035644A (en) * | 2020-09-01 | 2020-12-04 | 北京四维图新科技股份有限公司 | Vehicle insurance scheme adjusting method and device, electronic equipment and storage medium |
| CN112215261A (en) * | 2020-09-18 | 2021-01-12 | 武汉理工大学 | Vehicle OD point clustering method, system, device and storage medium based on meta-learning |
| CN112309126B (en) * | 2020-10-30 | 2022-07-05 | 杭州海康威视数字技术股份有限公司 | License plate detection method and device, electronic equipment and computer readable storage medium |
| CN112597189A (en) * | 2020-12-28 | 2021-04-02 | 广州羊城通有限公司 | Travel track adjusting method and device based on riding record |
| CN115022810B (en) * | 2021-03-05 | 2024-06-25 | ***通信集团江苏有限公司 | Method and device for identifying travel mode based on mobile phone signaling data and electronic equipment |
| CN117093889A (en) * | 2023-07-05 | 2023-11-21 | 广东海洋大学 | Track prediction method for clustering and distinguishing |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104376057A (en) * | 2014-11-06 | 2015-02-25 | 南京邮电大学 | Self-adaptation clustering method based on maximum distance, minimum distance and K-means |
| CN105608505A (en) * | 2015-12-22 | 2016-05-25 | 重庆邮电大学 | Cellular signaling data based track traffic travel mode identification method for resident |
| CN105740904A (en) * | 2016-01-29 | 2016-07-06 | 东南大学 | Travel and activity mode identification method based on DBSCAN clustering algorithm |
| CN105989062A (en) * | 2015-02-04 | 2016-10-05 | 南京乐行天下智能科技有限公司 | Defining method based on electric vehicle travelling track characteristics and data mining technology |
| CN105989224A (en) * | 2015-02-04 | 2016-10-05 | 南京乐行天下智能科技有限公司 | Mode recognition technique for different travel modes |
| CN106126637A (en) * | 2016-06-23 | 2016-11-16 | 东软集团股份有限公司 | A kind of vehicles classification recognition methods and device |
| CN106227859A (en) * | 2016-07-29 | 2016-12-14 | 四川大学 | The method identifying the vehicles from gps data |
| US20170032667A1 (en) * | 2015-07-31 | 2017-02-02 | Here Global B.V. | Method and apparatus for providing state classification for a travel segment with multi-modal speed profiles |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5440080B2 (en) * | 2009-10-02 | 2014-03-12 | ソニー株式会社 | Action pattern analysis system, portable terminal, action pattern analysis method, and program |
| CN103810851B (en) * | 2014-01-23 | 2015-10-21 | 广州地理研究所 | A kind of traffic trip mode identification method based on mobile phone location |
| CN106408026B (en) * | 2016-09-20 | 2020-04-28 | 百度在线网络技术（北京）有限公司 | User travel mode identification method and device |
| CN106778652A (en) * | 2016-12-26 | 2017-05-31 | 东软集团股份有限公司 | Physical activity recognition methods and device |
| CN106682703A (en) * | 2017-01-13 | 2017-05-17 | 北京航空航天大学 | Method for recognizing travel mode of driver based on OBD data |
| CN107169521A (en) * | 2017-05-24 | 2017-09-15 | 上海评驾科技有限公司 | A kind of traffic pattern recognition method based on mobile phone acceleration sensor |
-
2017
- 2017-09-19 CN CN201710846069.XA patent/CN107784597B/en active Active
-
2018
- 2018-01-22 WO PCT/CN2018/073619 patent/WO2019056680A1/en active Application Filing
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104376057A (en) * | 2014-11-06 | 2015-02-25 | 南京邮电大学 | Self-adaptation clustering method based on maximum distance, minimum distance and K-means |
| CN105989062A (en) * | 2015-02-04 | 2016-10-05 | 南京乐行天下智能科技有限公司 | Defining method based on electric vehicle travelling track characteristics and data mining technology |
| CN105989224A (en) * | 2015-02-04 | 2016-10-05 | 南京乐行天下智能科技有限公司 | Mode recognition technique for different travel modes |
| US20170032667A1 (en) * | 2015-07-31 | 2017-02-02 | Here Global B.V. | Method and apparatus for providing state classification for a travel segment with multi-modal speed profiles |
| CN105608505A (en) * | 2015-12-22 | 2016-05-25 | 重庆邮电大学 | Cellular signaling data based track traffic travel mode identification method for resident |
| CN105740904A (en) * | 2016-01-29 | 2016-07-06 | 东南大学 | Travel and activity mode identification method based on DBSCAN clustering algorithm |
| CN106126637A (en) * | 2016-06-23 | 2016-11-16 | 东软集团股份有限公司 | A kind of vehicles classification recognition methods and device |
| CN106227859A (en) * | 2016-07-29 | 2016-12-14 | 四川大学 | The method identifying the vehicles from gps data |
Non-Patent Citations (1)
| Title |
|---|
| 李斯凡: "基于无监督学习技术的位置大数据分析", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108986255A (en) * | 2018-07-13 | 2018-12-11 | 平安科技（深圳）有限公司 | Electronic device, driving behavior methods of marking and storage medium |
| CN109146694A (en) * | 2018-07-13 | 2019-01-04 | 平安科技（深圳）有限公司 | Electronic device, the preferential rank of user's vehicle insurance determine method and storage medium |
| CN109146694B (en) * | 2018-07-13 | 2024-02-02 | 平安科技（深圳）有限公司 | Electronic device, user vehicle insurance preference level determining method and storage medium |
| WO2020010715A1 (en) * | 2018-07-13 | 2020-01-16 | 平安科技（深圳）有限公司 | Electronic device, driving behavior scoring method, and storage medium |
| CN109272032A (en) * | 2018-09-05 | 2019-01-25 | 广州视源电子科技股份有限公司 | Travel mode identification method and device, computer equipment and storage medium |
| CN110148298B (en) * | 2019-06-24 | 2022-03-18 | 重庆大学 | Private car regular travel behavior discovery method based on motor vehicle electronic identification data |
| CN110148298A (en) * | 2019-06-24 | 2019-08-20 | 重庆大学 | Private car rule travel behaviour based on motor vehicle electronic mark data finds method |
| CN111076741A (en) * | 2019-12-03 | 2020-04-28 | Oppo广东移动通信有限公司 | Navigation state acquisition method and device, storage medium and electronic equipment |
| CN111163425A (en) * | 2020-01-02 | 2020-05-15 | 中国平安财产保险股份有限公司 | LBS track-based identity recognition method, electronic device and readable storage medium |
| CN112131454A (en) * | 2020-08-26 | 2020-12-25 | 汉海信息技术(上海)有限公司 | Method and device for pushing user information during train trip and server |
| CN114187489A (en) * | 2021-12-14 | 2022-03-15 | 中国平安财产保险股份有限公司 | Vehicle abnormal driving risk detection method and device, electronic equipment and storage medium |
| CN114187489B (en) * | 2021-12-14 | 2024-04-30 | 中国平安财产保险股份有限公司 | Method and device for detecting abnormal driving risk of vehicle, electronic equipment and storage medium |
| CN116681184A (en) * | 2023-07-28 | 2023-09-01 | 厦门农芯数字科技有限公司 | Method, device and equipment for predicting growth index of live pigs and readable storage medium |
| CN116681184B (en) * | 2023-07-28 | 2023-10-10 | 厦门农芯数字科技有限公司 | Method, device and equipment for predicting growth index of live pigs and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019056680A1 (en) | 2019-03-28 |
| CN107784597B (en) | 2021-09-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107784597A (en) | Trip mode recognition methods, device, terminal device and storage medium | |
| CN103582884A (en) | Robust feature matching for visual search | |
| CN106506705A (en) | Listener clustering method and device based on location-based service | |
| CN107766876A (en) | Driving model training method, driver's recognition methods, device, equipment and medium | |
| CN107704918A (en) | Driving model training method, driver's recognition methods, device, equipment and medium | |
| CN105518658A (en) | Apparatus, systems, and methods for grouping data records | |
| US11638119B2 (en) | Neural network classifier for detection of travel mode associated with computing devices | |
| CN105493085B (en) | Create method, system and the computer readable storage medium of the sample of database table | |
| CN104346444B (en) | A kind of the best site selection method based on the anti-spatial key inquiry of road network | |
| CN116186594B (en) | Method for realizing intelligent detection of environment change trend based on decision network combined with big data | |
| CN109447110A (en) | The method of the multi-tag classification of comprehensive neighbours' label correlative character and sample characteristics | |
| CN105183792B (en) | Distributed fast text classification method based on locality sensitive hashing | |
| CN113656690B (en) | Product recommendation method and device, electronic equipment and readable storage medium | |
| CN108229658A (en) | The implementation method and device of object detector based on finite sample | |
| CN112699142A (en) | Cold and hot data processing method and device, electronic equipment and storage medium | |
| CN116662839A (en) | Associated big data cluster analysis method and device based on multidimensional intelligent acquisition | |
| CN113343306B (en) | Differential privacy-based data query method, device, equipment and storage medium | |
| CN103295026B (en) | Based on the image classification method of space partial polymerization description vectors | |
| CN113505273B (en) | Data sorting method, device, equipment and medium based on repeated data screening | |
| CN106126943A (en) | The state of an illness acquisition method derived based on association symptom | |
| CN110955804B (en) | Adaboost method for user space-time data behavior detection | |
| CN108170837A (en) | Method of Data Discretization, device, computer equipment and storage medium | |
| CN111652281B (en) | Information data classification method, device and readable storage medium | |
| CN103927560A (en) | Feature selection method and device | |
| CN115034839A (en) | Office area state detection method and device, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |