CN107784597B - Travel mode identification method and device, terminal equipment and storage medium - Google Patents
Travel mode identification method and device, terminal equipment and storage medium Download PDFInfo
- Publication number
- CN107784597B CN107784597B CN201710846069.XA CN201710846069A CN107784597B CN 107784597 B CN107784597 B CN 107784597B CN 201710846069 A CN201710846069 A CN 201710846069A CN 107784597 B CN107784597 B CN 107784597B
- Authority
- CN
- China
- Prior art keywords
- travel mode
- data
- trajectory data
- cluster
- 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.)
- Active
Links
Images
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)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a travel mode identification method, a travel mode identification device, terminal equipment and a storage medium. The travel mode identification method comprises the following steps: acquiring current user track data, wherein the current user track data comprises at least one current characteristic data; acquiring a user track data model, wherein the user track data model comprises at least two clustering clusters, and each clustering cluster corresponds to an estimated travel mode; acquiring a target cluster class corresponding to at least one current characteristic data from at least two cluster classes based on the current user track data and the user track data model; and acquiring a target trip mode based on the evaluation trip mode corresponding to the target cluster. The travel mode identification method can identify the specific travel mode of the user, provide correct data for vehicle insurance evaluation, and meanwhile can identify abnormal data, purify sample data and improve the accuracy of vehicle insurance evaluation.
Description
Technical Field
The invention relates to the field of computer identification, in particular to a travel mode identification method and device, terminal equipment and a storage medium.
Background
In the car insurance handling process, in order to evaluate the risk condition of the car insurance handling by the user, the insurance mechanism needs to collect driving data such as the driving time length and driving habits of the user and evaluate the driving data. Specifically, the insurance mechanism collects GPRS data through a mobile phone, a tablet or other mobile terminals carried by a user, generates a characteristic vector capable of describing driving data such as driving duration and driving habits based on the GPRS data, and then collects a random forest model to identify the characteristic vector so as to determine whether the user drives himself or not, so that the risk condition of handling car insurance by the user can be evaluated conveniently. However, the GPRS data collected by the mobile terminal may be data collected by the user when the user drives a vehicle to go out, or may be data collected by the user when the user goes out in a mode other than driving the vehicle, such as walking, riding a bicycle, riding a bus, riding a subway, riding a high-speed rail, riding an airplane, and the like. In the current vehicle insurance evaluation process of the user, the trip mode of the user cannot be identified, so that the evaluation result of the risk condition of handling the vehicle insurance by the user is not accurate enough.
Disclosure of Invention
The embodiment of the invention provides a travel mode identification method and device, terminal equipment and a storage medium, and aims to solve the problem that the travel mode of a user cannot be identified in the current automobile insurance evaluation process, so that the evaluation result is not accurate enough.
In a first aspect, an embodiment of the present invention provides a travel mode identification method, including:
acquiring current user track data, wherein the current user track data comprises at least one current characteristic data;
acquiring a user track data model, wherein the user track data model comprises at least two clustering clusters, and each clustering cluster corresponds to an estimated travel mode;
acquiring a target cluster class corresponding to at least one current characteristic data from at least two cluster classes based on the current user track data and the user track data model;
and acquiring a target travel mode based on the evaluation travel mode corresponding to the target cluster.
In a second aspect, an embodiment of the present invention provides a travel mode identification apparatus, including:
a current user trajectory data acquisition module, configured to acquire current user trajectory data, where the current user trajectory data includes at least one current feature data;
the system comprises a user trajectory data model acquisition module, a user trajectory data model generation module and a user trajectory data model generation module, wherein the user trajectory data model acquisition module is used for acquiring a user trajectory data model which comprises at least two clustering clusters, and each clustering cluster corresponds to an estimated travel mode;
a target cluster acquisition module, configured to acquire a target cluster corresponding to at least one piece of current feature data from at least two clusters based on the current user trajectory data and the user trajectory data model;
and the target travel mode acquisition module is used for acquiring a target travel mode based on the evaluation travel mode corresponding to the target cluster.
In a third aspect, an embodiment of the present invention provides a terminal device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the travel pattern recognition method when executing the computer program.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the steps of the travel pattern recognition method are implemented.
In the travel mode identification method, the travel mode identification device, the terminal device and the storage medium provided by the embodiment of the invention, the target travel mode is determined based on the current user track data and the estimated travel mode corresponding to each cluster in the user track data model, so as to help the vehicle insurance company to identify the travel mode of the user and provide accurate data reference for vehicle insurance estimation.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
Fig. 1 is a flowchart of a travel mode identification method in embodiment 1 of the present invention.
Fig. 2 is another flowchart of the travel mode identification method in embodiment 1 of the present invention.
Fig. 3 is a specific flowchart of step S50 in fig. 2.
Fig. 4 is a specific flowchart of step S30 in fig. 1.
Fig. 5 is a detailed flowchart of step S70.
Fig. 6 is a schematic block diagram of a travel mode identification apparatus in embodiment 2 of the present invention.
Fig. 7 is a schematic diagram of a terminal device in embodiment 4 of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
Fig. 1 shows a flowchart of a travel pattern recognition method in the present embodiment. The travel mode identification method is applied to a vehicle insurance evaluation system of an insurance institution and is used for identifying the travel mode of a user, so that driving data such as driving duration, driving habits and the like are extracted, and a reference is provided for evaluating the risk of handling vehicle insurance for the user. As shown in fig. 1, the travel mode identification method includes the following steps:
s10: and acquiring current user track data, wherein the current user track data comprises at least one current characteristic data.
The current user trajectory data is the trajectory data which is collected by the user when the user goes out and is used for reflecting a trip mode. When a user goes out, the user can travel by at least one of walking, bicycles, light rides, buses, cars, railways and planes, the corresponding trajectory data of speeds, accelerations, angles, angular accelerations and the like of different transportation modes are different, and each transportation mode corresponds to one travel mode. The current feature data includes, but is not limited to, trajectory data such as speed, acceleration, angle, angular acceleration and the like collected when the current user is traveling.
In the embodiment, a user completes registration on an Application program (APP for short) on a mobile terminal such as a mobile phone and a tablet in advance, so that a server corresponding to the Application program can obtain a corresponding user identifier, wherein the user identifier can be an identifier which can uniquely identify the user, such as a mobile phone number or an identity card number of the user, when the user carries the mobile terminal for trip, a sensor built in the mobile terminal can acquire current characteristic data such as speed, acceleration, angle, angular acceleration and the like at any time in the trip process of the user in real time, and can also acquire GPS positioning information at any time in real time and calculate and obtain corresponding current characteristic data based on the GPS positioning information, after the mobile terminal acquires the current characteristic data, the current characteristic data is uploaded to the server, so that the server stores the acquired current characteristic data in databases such as MySQL, Oracle and the like, and stores each track data in association with a user identification. When the travel mode of the user needs to be identified, current characteristic data associated with the user identification can be inquired and obtained from databases such as MySQL, Oracle and the like so as to obtain current user track data.
S20: and acquiring a user track data model, wherein the user track data model comprises at least two clustering clusters, and each clustering cluster corresponds to an estimated travel mode.
The user trajectory data model is a pre-trained model used for identifying an estimated travel mode corresponding to the current user trajectory data. The user track data model is obtained based on training of training user track data and stored in databases such as MySQL and Oracle, and when the terminal equipment identifies the travel mode, the user track data model can be called from the databases. In this embodiment, the user trajectory data model is obtained by clustering training user trajectory data through a K-means clustering algorithm. The training user trajectory data is trajectory data which is acquired by a user when the user goes out and is used for training a user trajectory data model, and the trajectory data includes but is not limited to at least one of speed, acceleration, angle, angular acceleration and the like acquired by the user at any time when the user goes out. The K-means clustering algorithm is a clustering algorithm for evaluating similarity based on distance, that is, the closer the distance between two objects is, the greater the similarity is. The estimated travel mode refers to a travel mode corresponding to the trajectory data of the training users in each cluster type.
Specifically, the user trajectory data model obtained after clustering by adopting the K-means clustering algorithm comprises at least two clustering clusters, and each clustering cluster corresponds to an estimated travel mode. Each cluster type comprises centroid user track data, and the travel mode corresponding to the centroid user track data is an estimated travel mode. In this embodiment, the trained user trajectory data model at least includes seven cluster clusters, each cluster represents walking, bicycle, light, bus, car, railway, and airplane, that is, each cluster represents a travel mode. The smaller the distance from the training track data to the centroid of the cluster class is, the more likely the training track data belongs to the travel mode corresponding to the cluster class.
In a specific embodiment, as shown in fig. 2, the travel mode identification method further includes:
s50: training a user trajectory data model based on training user trajectory data, the training user trajectory data including at least one training feature data.
The training feature data refers to data corresponding to features in data used for training a user trajectory data model, and includes but is not limited to data such as speed, acceleration, angle and angular acceleration acquired when a user goes out. In this embodiment, training the user trajectory data model based on the training user trajectory data means that a K-means clustering algorithm is adopted to cluster at least one training feature data in the training user trajectory data, a set of similar training user trajectory data is used as a cluster class cluster, so as to divide all training user trajectory data into at least two cluster class clusters, and a travel mode corresponding to each cluster class cluster is obtained, so that the user trajectory data model can be formed.
In this embodiment, as shown in fig. 3, in step S50, the training user trajectory data model is trained based on training user trajectory data, where the training user trajectory data includes at least one training feature data, and the method specifically includes the following steps:
s51: and clustering at least one training characteristic data in the training user trajectory data by adopting a K-means clustering algorithm to obtain at least two clustering clusters, wherein each clustering cluster corresponds to a centroid user trajectory data.
The K-means clustering algorithm is a clustering algorithm for evaluating similarity based on distance, that is, the closer the distance between two objects is, the greater the similarity is. The K-means clustering algorithm calculates the Euclidean distance between two objectsAnd evaluating the similarity of the two objects according to the magnitude of the Euclidean distance. Euclidean distance (also known as euclidean metric) refers to the true distance between two points in an m-dimensional space, or the natural length of a vector (i.e., the distance of the point from the origin). Any two n-dimensional vectors a (X)i1,Xi2,...,Xin) And b (X)j1,Xj2,...,Xjn) Euclidean distance of
The training user trajectory data is user trajectory data of a training user for training a user trajectory data model, the training user trajectory data comprises at least one training characteristic data, the at least one training characteristic data in the training user trajectory data is clustered by adopting a K-means clustering algorithm to obtain at least two cluster clusters, and each cluster comprises a plurality of training user trajectory data. In any cluster, mass center user trajectory data corresponding to a mass center exists in the training user trajectory data, so that the sum of distances from other training user trajectory data to the mass center user trajectory data is minimum. It is to be understood that the centroid user trajectory data is one of all training user trajectory data in any cluster class, and therefore, the centroid user trajectory data also includes at least one training feature data.
And setting training characteristic data corresponding to at least one characteristic in the training user trajectory data to form a user trajectory data matrix R, and clustering the values of the characteristic data in the user trajectory data matrix R by adopting a K-means clustering algorithm. The clustering process by adopting the K-means clustering algorithm is as follows: step (1), establishing an n-dimensional graph, and drawing m data points Ui in the n-dimensional graph according to the value of the feature data corresponding to each user track data in the user track data matrix R, wherein i belongs to m, and each data point Ui corresponds to training user track data. Step (2), predefining a value of K, according to which m data points can be divided into K data sets G [ G1, G2, G3, G4, … Gj …, Gk ], wherein K ≧ 2, j ∈ K. And (3) randomly selecting one data point Ui in each data set Gj as a centroid Ci, so that K centroids Ci exist in all data sets. And (4) calculating the Euclidean distance Di between any data point Ui in each data set Gj and K centroids Gi, and classifying the data point Ui into the data set Gj with the minimum Euclidean distance Di. And (5) executing the step (4) on all the data points Ui to form a new data set G. And (5) repeating the steps (3) and (5), when the new centroid Ci and the old centroid Ci in any data set Gj are smaller than a preset threshold value, terminating the K-means clustering algorithm to form K clustering clusters, wherein each clustering cluster has a centroid, and the centroid corresponds to the centroid user trajectory data.
S52: and counting the training user track data in the cluster type by adopting a K-nearest neighbor algorithm to obtain a corresponding evaluation trip mode.
The K Nearest Neighbor (KNN) algorithm classifies by measuring distances between different feature data values. The central idea of the K-nearest neighbor algorithm is that if most of the K most similar (i.e., nearest neighbor in feature space) samples in a feature space belong to a certain class, then the sample also belongs to this class. The KNN algorithm calculates euclidean distances or manhattan distances between objects as an index of non-similarity between the objects. Euclidean distance (also known as euclidean metric) refers to the true distance between two points in an m-dimensional space, or the natural length of a vector (i.e., the distance of the point from the origin). Any two n-dimensional vectors a (X)i1,Xi2,...,Xin) And b (X)j1,Xj2,...,Xjn) Euclidean distance of
Manhattan distance (manhattan distance) is the distance between two points in the north-south direction plus the distance in the east-west direction, and on a plane, the coordinate (X)i,Yi) Point i and coordinate (X)j,Yj) Manhattan distance | X of j pointi-Xj|+|Yi-Yj|。
In the step S52, a travel mode corresponds to each training user trajectory data in the cluster, that is, each training user trajectory data carries a label corresponding to a travel mode, and a K-nearest neighbor algorithm may be used to obtain a travel number corresponding to each travel mode based on the determined cluster, and an estimated travel mode corresponding to the cluster is determined according to the travel number.
In a specific embodiment, in step S52, statistics on the travel modes corresponding to all the training user trajectory data in the cluster class are first performed, and the travel number corresponding to each travel mode is obtained. Then, the proportion of the number of trips corresponding to each trip mode to the trajectory data of all the training users is calculated respectively, that is, the statistical proportion corresponding to each trip mode is obtained. Selecting a maximum value from the statistical proportions corresponding to all the travel modes, and judging whether the maximum value is greater than a preset proportion, wherein the preset proportion is a numerical value used for self-defining; and if the maximum value is larger than the preset proportion, taking the travel mode corresponding to the maximum value as an estimated travel mode corresponding to the cluster type. If in a cluster, the statistical proportions of riding buses, riding bicycles, driving vehicles and other ways are respectively 10%, 60%, 15% and 15%, and the preset proportion is 50%, the maximum value in the statistical proportions is 60% and is greater than the preset proportion by 50%, so that 60% of the bicycles are taken as the estimated travel ways corresponding to the cluster.
In another specific embodiment, in step S52, statistics on the travel modes corresponding to all the training user trajectory data in the cluster class need to be performed first, and the travel number corresponding to each travel mode is obtained. Then, the proportion of the number of trips corresponding to each trip mode to the trajectory data of all the training users is calculated respectively, that is, the statistical proportion corresponding to each trip mode is obtained. And selecting a maximum value and a second maximum value from the statistical proportions corresponding to all the travel modes, and calculating a proportion difference value based on the maximum value and the second maximum value. And then judging whether the proportion difference is larger than a preset difference, wherein the preset difference is a numerical value defined by a user. And if the proportion difference is larger than the preset difference, taking the trip mode corresponding to the maximum value as the estimated trip mode corresponding to the cluster. For example, in a cluster, the statistical proportions of riding buses, riding bicycles, driving vehicles and other manners are respectively 10%, 60%, 15% and 15%, a preset difference value is set to be 30%, the maximum value in the statistical proportions is 60%, the second maximum value is 10%, the proportion difference value between the two is 50%, and the proportion difference value is greater than the preset difference value, so that the riding bicycle corresponding to 60% is used as the estimated travel manner corresponding to the cluster.
S53: and acquiring a user track data model based on clustering and trip mode evaluation.
In this embodiment, since the K-means clustering algorithm is adopted to divide all training user trajectory data in the user trajectory data matrix R into K clustering clusters, the centroid user trajectory data of each clustering cluster is similar to other training user trajectory data in the same clustering cluster, and the travel mode corresponding to the centroid user trajectory data can be used as the estimated travel mode of other training user trajectory data in the clustering cluster, thereby determining the user trajectory data model.
S60: the user trajectory data model is stored in a database.
In this embodiment, the user trajectory data model trained in step S50 may be stored in MySQL, Oracle, or other databases, or may be stored in a Hive library based on a Hadoop architecture. The hive library can map the structured data file into a database table and provide a complete SQL query function, the database is low in learning cost, and the data storage capacity can be improved and the data processing pressure can be relieved through distributed storage. The user trajectory data model is stored in the database, so that the user trajectory data model trained in advance can be called from the database in the travel mode identification.
In this embodiment, step S20 includes: and acquiring a user track data model from the database. Because the user track data model is trained in advance and stored in the database, when the user track data model needs to be identified in a trip mode, the user track data model can be directly called from the database, so that identification processing can be performed, and the operation process is simple and rapid.
S30: and acquiring a target cluster class corresponding to at least one current characteristic datum from the at least two cluster classes based on the current user track data and the user track data model.
The target cluster type is a cluster type in which centroid user track data closest to current user track data is located. The target cluster type specifically refers to a cluster type corresponding to the centroid user trajectory data closest to the current user trajectory data formed by at least one current characteristic data.
In a specific embodiment, as shown in fig. 4, step S30 specifically includes the following steps:
s31: and respectively calculating the current user track data and the centroid user track data of at least two cluster clusters in the user track data model to obtain at least two Euclidean distances.
In this embodiment, K cluster classes are stored in the user driving data model, each cluster class corresponds to a centroid user trajectory data, and if the current user trajectory data is set as the n-dimensional vector a (X)i1,Xi2,...,Xin) The centroid user track data of any cluster is n-dimensional vector b (X)j1,Xj2,...,Xjn) Then the Euclidean distance between the current user track data and the centroid user track data
The dimension n of the vector a corresponds to the number of current feature data in the current user trajectory data; accordingly, the dimension n of the vector b corresponds to the number of training feature data in the centroid user trajectory data.
S32: and selecting the cluster where the centroid user trajectory data corresponding to the minimum value in the at least two Euclidean distances is located as a target cluster corresponding to the at least one current characteristic data.
Since the euclidean distance is a way to evaluate the similarity between two objects, the smaller the euclidean distance, the more similar the two objects are, and if the euclidean distance D between the K current user trajectory data and the centroid user trajectory data is obtained in step S31a,bDividing K Euclidean distances Da,bThe focus of the centroid user track data corresponding to the minimum value is selectedAnd determining the cluster in which the centroid user track data most similar to the current user track data is located, and further using the cluster as a target cluster corresponding to at least one current characteristic data in the current user track data.
S40: and acquiring a target trip mode based on the evaluation trip mode corresponding to the target cluster.
The target trip mode is a trip mode corresponding to the current user trajectory data, and in this embodiment, the evaluation trip mode corresponding to the target cluster is determined as the target trip mode. In step S52, a K-nearest neighbor algorithm is used to perform statistical calculation on the training user trajectory data in each cluster class, and an estimated travel mode corresponding to the centroid user trajectory data is obtained, so as to determine the estimated travel mode of the target cluster class corresponding to the centroid user trajectory data, and output the estimated travel mode as the target travel mode.
In a specific embodiment, after step S40, the travel mode identification method further includes:
s70: and acquiring training driving data for training a driving model based on the target travel mode.
The training driving data is data used for training a driving model, and whether the target travel mode corresponding to the current user trajectory data is the driving mode or not can be judged through the target travel mode obtained in step S40 to determine whether the current user trajectory data is the driving data or not, based on the judgment result, the current user trajectory data which is the driving data is kept as the training driving data, the current user trajectory data corresponding to the non-driving data is deleted to collect a sufficient amount of training driving data, so that the training driving data is used for training the driving model, and the accuracy of the driving model is improved.
In this embodiment, each target travel mode obtained in step S70 corresponds to a travel mode ID. The travel mode ID is an identifier corresponding to each target travel mode, and is an identifier for distinguishing from other travel modes. As shown in fig. 5, in step S70, the method for obtaining training driving data used for training a driving model based on the target trip method specifically includes the following steps:
s71: and acquiring a travel mode query instruction, wherein the travel mode query instruction comprises a driving mode ID.
The travel mode query instruction is an instruction for querying whether a target travel mode corresponding to the current user trajectory data is a driving mode. The travel mode query instruction carries a driving mode ID, and the driving mode ID is an identifier corresponding to the travel mode as the driving mode. The driving mode refers to a mode that a user drives a car or other vehicles to go out. It can be understood that the travel mode query instruction in step S71 may carry the driving mode ID, and may also carry other travel mode IDs, so as to provide an accurate user trajectory data reference for obtaining the driving data of the user and evaluating the car risk or other dangerous species, and therefore, the travel mode query instruction in this embodiment carries the driving mode ID.
S72: and judging whether the travel mode ID corresponding to the current user track data is consistent with the driving mode ID in the query instruction.
Specifically, whether the travel mode corresponding to the current user trajectory data is the driving mode can be judged by comparing whether the travel mode ID corresponding to the current user trajectory data is consistent with the driving mode ID in the query instruction. In this embodiment, the target cluster in step S32 is obtained based on the current user trajectory data and the user trajectory data model, and the travel mode ID corresponding to the current user trajectory data is obtained based on the estimated travel mode corresponding to the target cluster; and then, whether the travel mode ID is consistent with the driving mode ID in the travel mode query instruction acquired in step S71 is judged to judge whether the travel mode corresponding to the current user trajectory data is the driving mode, which is beneficial to collecting the current user trajectory data with the target travel mode as the driving mode, so as to train a model for identifying whether the current user trajectory data is the driving mode of the user, and provide data support for handling car insurance or other dangerous types.
S73: and if the travel mode ID corresponding to the current user trajectory data is consistent with the driving mode ID in the query instruction, determining that the target travel mode is the driving mode, and storing the current user trajectory data as training driving data.
Specifically, when the travel mode ID corresponding to the current user trajectory data is consistent with the driving mode ID in the query instruction, it is determined that the target travel mode corresponding to the current user trajectory data is the driving mode, that is, the travel mode of the current user is the driving mode, and the current user trajectory data is stored in the database as training driving data for training the driving model. At this time, the current user trajectory data includes information such as driving duration, driving habits and the like of the current user, when the current user handles car insurance or other dangerous types and needs to evaluate the car insurance or other dangerous types, the insurance company can extract training driving data from the database to perform driving model training, so that the trained driving model is used for identifying the user trajectory data collected in real time, whether the user drives the user himself is judged, data related to the car insurance or other dangerous types is obtained, and data reference is provided for evaluating the risk of handling the car insurance or other dangerous types by the current user.
S74: and if the travel mode ID corresponding to the current user trajectory data is not consistent with the driving mode ID in the query instruction, determining that the target travel mode is not the driving mode, and deleting the current user trajectory data.
Specifically, when the travel mode ID corresponding to the current user trajectory data is inconsistent with the driving mode ID in the query instruction, it is determined that the target travel mode corresponding to the current user trajectory data is not the driving mode, that is, the travel mode of the current user is not the driving mode, and then the current user trajectory data is deleted to save the space of the database. And if the target travel mode corresponding to the current user trajectory data is identified as a boarding airplane, deleting the current user trajectory data corresponding to the boarding airplane as the boarding airplane does not belong to the driving mode. Since the current user trajectory data corresponding to the boarding plane or other non-driving modes cannot reflect the driving information of the current user, such as the driving duration, driving habits and the like, if the driving information is not deleted, the driving information is stored in the database, and interference may be caused to the training and recognition of the driving model when the current user trajectory data corresponding to the current user is subsequently called to train the user driving model. Therefore, when it is determined that the target travel mode corresponding to the current user trajectory data is not the driving mode, the current user trajectory data needs to be deleted.
In the travel mode identification method provided by this embodiment, a target travel mode is determined based on current user trajectory data and an estimated travel mode corresponding to each cluster in a user trajectory data model, and then whether the target travel mode is a driving mode is determined based on the target travel mode, driving information of a user in the driving mode is extracted, and an insurance company is helped to provide accurate data reference for the current user to perform insurance estimation.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
Example 2
Fig. 6 is a schematic block diagram of a travel pattern recognition apparatus corresponding to the travel pattern recognition method according to embodiment 1. As shown in fig. 6, the travel pattern recognition apparatus includes a current user trajectory data obtaining module 10, a user trajectory data model obtaining module 20, a target cluster class obtaining module 30, and a target travel pattern obtaining module 40. The implementation functions of the current user trajectory data obtaining module 10, the user trajectory data model obtaining module 20, the target cluster class obtaining module 30, and the target travel mode obtaining module 40 correspond to the steps corresponding to the travel mode identification method in embodiment 1 one to one, and for avoiding redundancy, detailed descriptions are not provided in this embodiment.
A current user trajectory data obtaining module 10, configured to obtain current user trajectory data, where the current user trajectory data includes at least one current feature data;
a user trajectory data model obtaining module 20, configured to obtain a user trajectory data model, where the user trajectory data model includes at least two cluster clusters, and each cluster corresponds to an estimated trip mode;
a target cluster acquisition module 30, configured to acquire a target cluster corresponding to at least one current feature data from at least two clusters based on current user trajectory data and a user trajectory data model;
and the target travel mode obtaining module 40 is configured to obtain a target travel mode based on the estimated travel mode corresponding to the target cluster.
Preferably, the target cluster acquisition module 30 includes a euclidean distance acquisition unit 31 and a target cluster selection unit 32.
And the euclidean distance obtaining unit 31 is configured to calculate current user trajectory data and centroid user trajectory data of at least two cluster classes in the user trajectory data model, respectively, to obtain at least two euclidean distances.
And the target cluster selecting unit 32 is configured to select a cluster in which the centroid user trajectory data corresponding to the minimum value of the at least two euclidean distances is located as a target cluster corresponding to the at least one current feature data.
Preferably, the travel mode identifying apparatus further includes a user trajectory data model training module 50 and a user trajectory data model storage module 60.
A user trajectory data model training module 50 for training a user trajectory data model based on training user trajectory data, the training user trajectory data including at least one training feature data.
A user trajectory data model storage module 60 for storing the user trajectory data model in a database.
And a user trajectory data model obtaining module 20, configured to obtain a user trajectory data model from a database.
Preferably, the user trajectory data model training module 50 includes a cluster class obtaining unit 51, an estimated travel mode obtaining unit 52 and a user trajectory data model obtaining unit 53.
The cluster acquisition unit 51 is configured to cluster at least one training feature data in the training user trajectory data by using a K-means clustering algorithm to acquire at least two cluster clusters, where each cluster corresponds to a centroid user trajectory data.
And an estimated trip mode obtaining unit 52, configured to use a K-nearest neighbor algorithm to perform statistics on the trajectory data of the training users in the cluster class, so as to obtain a corresponding estimated trip mode.
And a user trajectory data model obtaining unit 53, configured to obtain a user trajectory data model based on the cluster type and the travel mode evaluation.
Preferably, the trip mode identifying apparatus further includes a training driving data obtaining module 70, configured to obtain training driving data used for training a driving model based on a target trip mode, where the target trip mode corresponds to a trip mode ID.
The training driving data acquisition module 70 includes a travel mode query instruction acquisition unit 71, a driving mode determination unit 72, a current user trajectory data storage unit 73, and a current user trajectory data deletion unit 74.
A travel mode query instruction obtaining unit 71, configured to obtain a travel mode query instruction, where the travel mode query instruction includes a driving mode ID; .
And a driving manner judging unit 72, configured to judge whether the travel manner ID corresponding to the current user trajectory data is consistent with the driving manner ID in the query instruction.
And a current user trajectory data saving unit 73, configured to determine that the target travel mode is the driving mode when the travel mode ID corresponding to the current user trajectory data is consistent with the driving mode ID in the query instruction, and save the current user trajectory data as training driving data.
And a current user trajectory data deleting unit 74, configured to determine that the target travel mode is not the driving mode when the travel mode ID corresponding to the current user trajectory data is not consistent with the driving mode ID in the query instruction, and delete the current user trajectory data.
Example 3
This embodiment provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the travel mode identification method in embodiment 1 is implemented, and details are not described here for avoiding redundancy. Alternatively, the computer program, when executed by the processor, implements the functions of each module/unit in the travel mode identification apparatus in embodiment 2, and is not described herein again to avoid redundancy.
Example 4
Fig. 7 is a schematic diagram of a terminal device according to an embodiment of the present invention. As shown in fig. 7, the terminal device 70 of this embodiment includes: a processor 71, a memory 72, and a computer program 73 stored in the memory 72 and operable on the processor 71, the processor 71 implementing the steps of the travel pattern recognition method in embodiment 1, such as steps S10, S20, S30, and S40 shown in fig. 1, when the computer program 73 is executed by the processor 71. Alternatively, the processor 71, when executing the computer program 73, implements the functions of the modules/units of the travel pattern recognition apparatus in embodiment 2, such as the functions of the current user trajectory data obtaining module 10, the user trajectory data model obtaining module 20, the target cluster class obtaining module 30 and the target travel pattern obtaining module 40 shown in fig. 6.
Illustratively, the computer program 73 may be divided into one or more modules/units, which are stored in the memory 72 and executed by the processor 71 to carry out the invention. One or more of the modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of the computer program 73 in the terminal device 70. For example, the computer program 73 may be divided into the current user trajectory data acquisition module 10, the user trajectory data model acquisition module 20, the target cluster class acquisition module 30, and the target travel pattern acquisition module 40.
The terminal device 70 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The terminal equipment may include, but is not limited to, a processor 71, a memory 72. Those skilled in the art will appreciate that fig. 7 is merely an example of a terminal device 70 and does not constitute a limitation of terminal device 70 and may include more or fewer components than shown, or some components may be combined, or different components, e.g., the terminal device may also include input-output devices, network access devices, buses, etc.
The Processor 71 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 72 may be an internal storage unit of the terminal device 70, such as a hard disk or a memory of the terminal device 70. The memory 72 may also be an external storage device of the terminal device 70, such as a plug-in hard disk provided on the terminal device 70, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like. Further, the memory 72 may also include both an internal storage unit of the terminal device 70 and an external storage device. The memory 72 is used for storing computer programs and other programs and data required by the terminal device. The memory 72 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain other components which may be suitably increased or decreased as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media which may not include electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (9)
1. A travel mode identification method is characterized by comprising the following steps:
acquiring current user track data, wherein the current user track data comprises at least one current characteristic data;
clustering at least one training characteristic data in the training user trajectory data by adopting a K-means clustering algorithm to obtain at least two clustering clusters, wherein each clustering cluster corresponds to a centroid user trajectory data, and each training user trajectory data corresponds to a trip mode;
counting the training user track data in the clustering cluster by adopting a K-nearest neighbor algorithm to obtain the trip quantity of each estimated trip mode, and determining the corresponding estimated trip mode of the clustering cluster according to the trip quantity;
acquiring a user track data model based on the cluster clusters and the estimated travel mode, wherein the user track data model comprises at least two cluster clusters, each cluster corresponds to one estimated travel mode, and the travel mode corresponding to the centroid user track data is the estimated travel mode;
acquiring a target cluster class corresponding to at least one current characteristic data from at least two cluster classes based on the current user track data and the user track data model;
and acquiring a target trip mode based on the evaluation trip mode corresponding to the target cluster.
2. A travel mode identification method according to claim 1, wherein after the obtaining of the user trajectory data model based on the cluster class and the estimated travel mode, the travel mode identification method further comprises:
storing the user trajectory data model in a database;
before obtaining a target cluster class corresponding to at least one current feature data from at least two cluster classes based on the current user trajectory data and the user trajectory data model, the method includes: and acquiring the user track data model from the database.
3. A travel mode identification method according to claim 1, wherein said obtaining a target cluster class corresponding to at least one of said current feature data from at least two of said cluster classes based on said current user trajectory data and said user trajectory data model comprises:
calculating the current user track data and centroid user track data of at least two clustering clusters in the user track data model respectively to obtain at least two Euclidean distances;
and selecting the cluster class where the centroid user trajectory data corresponding to the minimum value in at least two Euclidean distances is located as the target cluster class corresponding to at least one current characteristic data.
4. A travel mode identification method according to claim 2, wherein a target travel mode is obtained based on an estimated travel mode corresponding to the target cluster class, and then further comprising: acquiring training driving data used for training a driving model based on the target travel mode, wherein the target travel mode corresponds to a travel mode ID;
the acquiring of the training driving data for training the driving model based on the target travel mode includes:
acquiring a travel mode query instruction, wherein the travel mode query instruction comprises a driving mode ID;
judging whether the travel mode ID corresponding to the current user track data is consistent with the driving mode ID in the query instruction or not;
if the travel mode ID corresponding to the current user trajectory data is consistent with the driving mode ID in the query instruction, determining that the target travel mode is the driving mode, and storing the current user trajectory data as the training driving data;
and if the travel mode ID corresponding to the current user trajectory data is not consistent with the driving mode ID in the query instruction, determining that the target travel mode is not the driving mode, and deleting the current user trajectory data.
5. A travel mode recognition apparatus, comprising:
a current user trajectory data acquisition module, configured to acquire current user trajectory data, where the current user trajectory data includes at least one current feature data;
the user trajectory data model training module is used for training the user trajectory data model based on training user trajectory data, and the training user trajectory data comprises at least one training characteristic data;
the user trajectory data model training module comprises:
a cluster acquisition unit, configured to cluster at least one training feature data in training user trajectory data by using a K-means clustering algorithm to acquire at least two cluster clusters, where each cluster corresponds to a centroid user trajectory data, and each training user trajectory data corresponds to a travel mode;
an estimated travel mode obtaining unit, configured to use a K-nearest neighbor algorithm to perform statistics on the training user trajectory data in the cluster class to obtain a travel number of each estimated travel mode, and determine a corresponding estimated travel mode of the cluster class according to the travel number;
a user trajectory data model obtaining unit, configured to obtain a user trajectory data model based on the cluster clusters and the estimated travel mode, where the user trajectory data model includes at least two cluster clusters, and each cluster corresponds to an estimated travel mode, where a travel mode corresponding to the centroid user trajectory data is an estimated travel mode;
the user track data model acquisition module is used for acquiring the user track data model;
a target cluster acquisition module, configured to acquire a target cluster corresponding to at least one piece of current feature data from at least two clusters based on the current user trajectory data and the user trajectory data model;
and the target travel mode acquisition module is used for acquiring a target travel mode based on the estimated travel mode corresponding to the target cluster.
6. A travel pattern recognition apparatus according to claim 5, wherein the travel pattern recognition apparatus further comprises:
the user track data model storage module is used for storing the user track data model in a database;
the user track data model acquisition module is used for acquiring the user track data model from the database;
the target cluster acquisition module comprises:
the Euclidean distance acquisition unit is used for calculating the current user track data and centroid user track data of at least two clustering clusters in the user track data model respectively to acquire at least two Euclidean distances;
and the target cluster selecting unit is used for selecting a cluster in which the centroid user trajectory data corresponding to the minimum value in the at least two Euclidean distances is located as the target cluster corresponding to the at least one current feature data.
7. A travel mode identifying apparatus according to claim 5, further comprising a training driving data acquiring module configured to acquire training driving data for training a driving model based on the target travel mode, the target travel mode corresponding to a travel mode ID;
the training driving data acquisition module comprises:
a travel mode query instruction acquisition unit, configured to acquire a travel mode query instruction, where the travel mode query instruction includes a driving mode ID;
a driving mode judging unit, configured to judge whether a travel mode ID corresponding to the current user trajectory data is consistent with a driving mode ID in the query instruction;
a current user trajectory data storage unit, configured to determine that the target travel mode is a driving mode when a travel mode ID corresponding to the current user trajectory data is consistent with a driving mode ID in the query instruction, and store the current user trajectory data as the training driving data;
and a current user trajectory data deleting unit, configured to determine that the target travel mode is not the driving mode when the travel mode ID corresponding to the current user trajectory data is inconsistent with the driving mode ID in the query instruction, and delete the current user trajectory data.
8. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the travel pattern recognition method according to any one of claims 1 to 4 when executing the computer program.
9. A computer-readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the steps of the travel pattern recognition method according to any one of claims 1 to 4.
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 CN107784597A (en) | 2018-03-09 |
| CN107784597B true 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) |
Families Citing this family (16)
| 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 |
| 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 |
| CN109272032A (en) * | 2018-09-05 | 2019-01-25 | 广州视源电子科技股份有限公司 | Trip mode recognition methods, 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 |
| CN117129003A (en) * | 2019-12-03 | 2023-11-28 | Oppo广东移动通信有限公司 | Navigation state acquisition method and device, storage medium and electronic equipment |
| CN111163425B (en) * | 2020-01-02 | 2020-09-18 | 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 |
| CN113543032B (en) * | 2020-04-21 | 2022-12-16 | 中国移动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 |
| 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 |
| 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 |
| CN115022810A (en) * | 2021-03-05 | 2022-09-06 | 中国移动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 |
| 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 |
| CN117093889A (en) * | 2023-07-05 | 2023-11-21 | 广东海洋大学 | Track prediction method for clustering and distinguishing |
| 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 |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Family Cites Families (12)
| 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 |
| 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 |
| 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 |
| US9558660B1 (en) * | 2015-07-31 | 2017-01-31 | Here Global B.V. | Method and apparatus for providing state classification for a travel segment with multi-modal speed profiles |
| CN105608505B (en) * | 2015-12-22 | 2020-02-11 | 重庆邮电大学 | Resident rail transit trip mode identification method based on mobile phone signaling data |
| 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 |
| CN106227859B (en) * | 2016-07-29 | 2019-07-23 | 四川大学 | The method of the vehicles is identified from GPS data |
| 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 (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN105740904A (en) * | 2016-01-29 | 2016-07-06 | 东南大学 | Travel and activity mode identification method based on DBSCAN clustering algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107784597A (en) | 2018-03-09 |
| WO2019056680A1 (en) | 2019-03-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107784597B (en) | Travel mode identification method and device, terminal equipment and storage medium | |
| CN108513676B (en) | Road condition identification method, device and equipment | |
| CN107944020B (en) | Face image searching method and device, computer device and storage medium | |
| Khaliq et al. | A holistic visual place recognition approach using lightweight cnns for significant viewpoint and appearance changes | |
| CN108352072B (en) | Object tracking method, object tracking device, and recording medium | |
| US10810870B2 (en) | Method of processing passage record and device | |
| WO2021218314A1 (en) | Event identification method and apparatus based on position locating, and device and storage medium | |
| US10235332B2 (en) | License plate distributed review systems and methods | |
| US20210188290A1 (en) | Driving model training method, driver identification method, apparatuses, device and medium | |
| CN111898642B (en) | Key point detection method and device, electronic equipment and storage medium | |
| CN112035591B (en) | Road network matching method, device, equipment and storage medium | |
| CN105956560A (en) | Vehicle model identification method based on pooling multi-scale depth convolution characteristics | |
| CN108510400B (en) | Automobile insurance information processing method and device, server and readable storage medium | |
| CN111476225B (en) | In-vehicle human face identification method, device, equipment and medium based on artificial intelligence | |
| EP4209959A1 (en) | Target identification method and apparatus, and electronic device | |
| CN108304852B (en) | Method and device for determining road section type, storage medium and electronic device | |
| CN116257663A (en) | Abnormality detection and association analysis method and related equipment for unmanned ground vehicle | |
| CN114926540A (en) | Lane line calibration method and device, terminal equipment and readable storage medium | |
| CN117542195A (en) | Traffic running state identification method, device, equipment and medium | |
| CN112612917B (en) | Song recommendation method, device, equipment and storage medium | |
| CN116071569A (en) | Image selection method, computer equipment and storage device | |
| CN114169247A (en) | Method, device and equipment for generating simulated traffic flow and computer readable storage medium | |
| CN115456060A (en) | Processing method and device for predicted track | |
| CN114724128A (en) | License plate recognition method, device, equipment and medium | |
| CN116109145B (en) | Risk assessment method, risk assessment device, risk assessment terminal and risk assessment storage medium for vehicle driving route |
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 |