[go: up one dir, main page]

CN111127035A - A method and system for confidence detection based on trajectory data - Google Patents

A method and system for confidence detection based on trajectory data Download PDF

Info

Publication number
CN111127035A
CN111127035A CN201911244965.4A CN201911244965A CN111127035A CN 111127035 A CN111127035 A CN 111127035A CN 201911244965 A CN201911244965 A CN 201911244965A CN 111127035 A CN111127035 A CN 111127035A
Authority
CN
China
Prior art keywords
user
data
factor
confidence
model
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
Application number
CN201911244965.4A
Other languages
Chinese (zh)
Other versions
CN111127035B (en
Inventor
赵岩
邓伟
杨俊京
张志平
胡道生
夏曙东
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Xinglu Chelian Technology Co ltd
Original Assignee
Beijing Transwiseway Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Transwiseway Information Technology Co Ltd filed Critical Beijing Transwiseway Information Technology Co Ltd
Priority to CN201911244965.4A priority Critical patent/CN111127035B/en
Publication of CN111127035A publication Critical patent/CN111127035A/en
Application granted granted Critical
Publication of CN111127035B publication Critical patent/CN111127035B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06Q30/00—Commerce
    • G06Q30/01—Customer relationship services
    • G06Q30/012—Providing warranty services
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/31—User authentication
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06Q30/00—Commerce
    • G06Q30/018—Certifying business or products
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Finance (AREA)
  • Computer Security & Cryptography (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Computer Hardware Design (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Primary Health Care (AREA)
  • Tourism & Hospitality (AREA)
  • Traffic Control Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application discloses a confidence detection method and a system based on track data, which comprises the following steps: acquiring a track factor and a correlation factor according to user data, and determining a feature vector; training a prediction model according to the feature vector and the label, and determining the identity category of the user by using the trained model; acquiring audit data of a user, and determining an operation factor according to vehicle track data; training a confidence coefficient model according to the identity category and the operation factor; and determining the confidence of the user according to the trained confidence model. Determining a feature vector according to user data, training a prediction model according to the feature vector and a label, and determining the identity category of a user by using the trained model; determining an operation factor according to the audit data of the user and the vehicle track data; the confidence coefficient model is trained through the identity category and the operation factor, the confidence coefficient of the user is determined, and the identity of the user can be judged and the confidence coefficient of the operation condition can be detected by using other data.

Description

Confidence detection method and system based on track data
Technical Field
The present application relates to the field of confidence detection, and in particular, to a method and a system for confidence detection based on trajectory data.
Background
In the prior art, a confidence monitoring mode based on vehicle operation cost exists, but most of the confidence monitoring modes need to rely on a large amount of determined data provided by a user to carry out identity judgment and operation analysis. And under the condition that the provided data is insufficient, calculation can not be performed according to other data, and identity judgment and operation analysis can not be performed on the user.
In view of the foregoing, it is desirable to provide a method and system for determining the identity of a user and performing confidence detection on an operation condition by using other data in the case that determined data is insufficient.
Disclosure of Invention
In order to solve the above problems, the present application provides a confidence detection method and system based on trajectory data.
In one aspect, the present application provides a confidence detection method based on trajectory data, including:
acquiring a track factor and a correlation factor according to user data, and determining a feature vector;
training a prediction model according to the feature vector and the label to obtain a trained prediction model, and determining the identity category of the user by using the trained prediction model;
acquiring audit data of a user, and determining an operation factor according to vehicle track data;
training a confidence coefficient model according to the identity category and the operation factor to obtain a trained confidence coefficient model;
and determining the confidence of the user according to the trained confidence model.
Preferably, the obtaining a trajectory factor and a correlation factor according to the user data and determining the feature vector includes:
determining a trajectory factor from user data
Determining a correlation factor according to the user data;
and extracting the track factors and the correlation factors of the confirmed identity users as feature vectors.
Preferably, the determining a trajectory factor according to the user data includes:
determining the number of vehicles matched by the user according to the user data;
determining a user stop point according to the mobile phone data in the user data and a clustering algorithm;
obtaining the type of the staying point, counting the frequency, and obtaining the type and the staying times of the staying point;
counting the number of the stay points in a period of time, taking the number as the dispersion of the position of the stay points, and determining the number of the stay points;
counting the long-distance moving frequency and the mobile phone position span of the user according to the mobile phone data;
the track factor is composed of the number of vehicles matched by the user, the type of the stop points, the stop times, the number of the stop points, the long-distance moving frequency and the position span of the mobile phone.
Preferably, the determining a correlation factor according to the user data includes:
counting the use frequency of key functions in the mobile phone of the user;
determining the number of the authentication vehicles and the number of the concerned vehicles of the user according to the user data;
the key function usage frequency, the number of certified vehicles, and the number of vehicles of interest form a correlation factor.
Preferably, the key functions include: refueling, vehicle checking, goods finding, insurance and ETC.
Preferably, the determining the identity category of the user by using the trained model comprises:
and inputting user data to the trained prediction model to obtain the identity category of the user.
Preferably, the obtaining of the audit data of the user and the determining of the operation factor according to the vehicle trajectory data includes:
acquiring vehicle data of the user according to the audit data of the user;
determining the number of the authenticated vehicles and the operating mileage of each vehicle according to the vehicle data of the user;
determining the total operating mileage and the average operating mileage of all vehicles according to the number of the authenticated vehicles and the operating mileage of each vehicle;
the number of the certification vehicles, the total operating mileage and the average operating mileage constitute an operating factor.
Preferably, the training a confidence model according to the identity category and the operation factor to obtain a trained confidence model further includes:
and training a confidence coefficient model according to the identity category, the operation factors and the external data to obtain the trained confidence coefficient model.
Preferably, the determining the number of the matched vehicles of the user according to the user data comprises:
determining the number of matched vehicles of the user by using the existing data and/or determining the number of matched vehicles of the user according to the user data and the vehicle data.
In a second aspect, the present application provides a confidence detection system based on trajectory data, including:
the identity judgment module is used for acquiring the track factor and the related factor according to the user data and determining the characteristic vector; training a prediction model according to the feature vector and the label to obtain a trained prediction model, and determining the identity category of the user by using the trained prediction model;
the operation analysis module is used for acquiring audit data of a user and determining an operation factor according to the vehicle track data;
the comprehensive detection module is used for training a confidence coefficient model according to the identity category and the operation factor to obtain a trained confidence coefficient model; and determining the confidence of the user according to the trained confidence model.
The application has the advantages that: determining a feature vector through user data, training a prediction model according to the feature vector and a label, and determining the identity category of a user by using the trained model; determining an operation factor according to the audit data of the user and the vehicle track data; the confidence coefficient model is trained through the identity category and the operation factor, the confidence coefficient of the user is determined, and the identity of the user can be judged and the confidence coefficient of the operation condition can be detected by using other data.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to denote like parts throughout the drawings. In the drawings:
FIG. 1 is a schematic diagram illustrating the steps of a confidence detection method based on trajectory data according to the present application;
FIG. 2 is a schematic diagram of a confidence detection system based on trajectory data provided herein;
fig. 3 is a schematic flowchart of a confidence detection system based on trajectory data according to the present application.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
According to an embodiment of the present application, a confidence detection method based on trajectory data is provided, as shown in fig. 1, including:
s101, acquiring a track factor and a correlation factor according to user data, and determining a feature vector;
s102, training a prediction model according to the feature vector and the label to obtain a trained prediction model, and determining the identity category of the user by using the trained prediction model;
s103, acquiring audit data of a user, and determining an operation factor according to vehicle track data;
s104, training a confidence coefficient model according to the identity category and the operation factor to obtain a trained confidence coefficient model;
and S105, determining the confidence of the user according to the trained confidence model.
According to user data, acquiring a track factor and a correlation factor, and determining a feature vector, wherein the method comprises the following steps:
determining a trajectory factor from user data
Determining a correlation factor according to the user data;
and extracting the track factors and the correlation factors of the users with confirmed identities as feature vectors.
Determining a trajectory factor from the user data, comprising:
determining the number of vehicles matched by the user according to the user data;
determining a user stop point according to mobile phone data in the user data and a clustering algorithm;
obtaining the type of the stop point, counting the frequency, and obtaining the type and the stop times of the stop point;
counting the number of the stop points in a period of time, taking the number as the dispersion of the positions of the stop points, and determining the number of the stop points;
counting the long-distance moving frequency and the mobile phone position span of a user according to the mobile phone data;
the number of vehicles matched by the user, the types of the stop points, the stop times, the number of the stop points, the long-distance moving frequency and the position span of the mobile phone form a track factor.
Determining a correlation factor from the user data, comprising:
counting the use frequency of key functions in the mobile phone of the user;
determining the number of the authentication vehicles and the number of the concerned vehicles of the user according to the user data;
the frequency of key function usage, the number of authorized vehicles and the number of vehicles of interest form a correlation factor.
Key functions, including: refueling, vehicle checking, goods finding, insurance and ETC.
Determining the identity category of the user using the trained model, comprising:
and inputting user data to the trained prediction model to obtain the identity category of the user.
Obtaining audit data of a user, and determining an operation factor according to vehicle track data, wherein the operation factor comprises the following steps:
acquiring vehicle data of the user according to the audit data of the user;
determining the number of the authenticated vehicles and the operating mileage of each vehicle according to the vehicle data of the user;
determining the total operating mileage and the average operating mileage of all vehicles according to the number of the vehicles to be authenticated and the operating mileage of each vehicle;
the number of vehicles to be authenticated, the total operating mileage, and the average operating mileage constitute an operating factor.
Training a confidence coefficient model according to the identity category and the operation factor to obtain a trained confidence coefficient model, and further comprising:
and training the confidence coefficient model according to the identity category, the operation factor and the external data to obtain the trained confidence coefficient model.
A prediction model and a confidence model, each comprising: and (5) classifying the models.
Determining the number of vehicles matched by the user according to the user data comprises:
and determining the number of the matched vehicles of the users by using the existing data and/or determining the number of the matched vehicles of the users according to the user data and the vehicle data.
Not all users have an audit, so not all users have audit data.
External data includes other retrievable data such as credit ratings of banking systems, consumption records of payment software and consumption platforms, etc.
The confidence model includes: overall confidence determination and classification confidence determination. During training, selection can be performed according to needs. Because the data obtained by the operation factors is only used for the car owners, when the users for determining the confidence level include non-car owners or car owners who do not drive the car, the overall confidence level determination cannot calculate the confidence level of the users more accurately.
The dwell Point may represent a Point of Interest (POI) of the user. In the geographic information system, one POI may be one house, one shop, one mailbox, one bus station, and the like.
The tag (user identity tag) is obtained by the user data of the confirmed identity.
The user data includes: user mobile phone data and vehicle track data of the user.
In a second aspect, according to an embodiment of the present application, there is further provided a confidence detection system based on trajectory data, as shown in fig. 2, including:
the identity judgment module 101 is used for acquiring a track factor and a correlation factor according to user data and determining a feature vector; training a prediction model according to the feature vector and the label to obtain a trained prediction model, and determining the identity category of the user by using the trained prediction model;
the operation analysis module 102 is configured to obtain audit data of a user, and determine an operation factor according to vehicle trajectory data;
the comprehensive detection module 103 is used for training a confidence coefficient model according to the identity category and the operation factor to obtain a trained confidence coefficient model; and determining the confidence of the user according to the trained confidence model.
In the following, the embodiment of the present application is further explained, taking a shipping user as an example, as shown in fig. 3.
The identity judgment module judges the identity of the user by using a machine learning method, inputs the track data in the mobile phone data of the freight user and the track data of the freight vehicle, and finally outputs a label of the identity category of the target user.
The method comprises the following specific steps:
1. trajectory factor calculation
And calculating track factors consisting of factors such as the number of vehicles matched by the user, the types and the stay times of mobile phone stay points, the number of the stay points, the long-distance moving frequency of the mobile phone data, the position span of the mobile phone and the like by utilizing the vehicle track data and the user track data (track data in the mobile phone data of the user).
The factors have the following meanings:
the number of matched vehicles of the user is as follows: the number of vehicles with the matching degree with the target user track meeting the threshold value is generally 0 for part of owners of the vehicles which do not drive and family members which do not drive the vehicles;
POI type and stay times of the mobile phone stay point: and clustering the report points of the user mobile phone by using DBSCAN, finding the central point of the high-density area as a stop point, inquiring POI data, obtaining the POI type of the target position, and counting the frequency. The types currently defined include gas stations, logistics parks, schools, residential areas, etc. A typical scenario is that the number of the frequently-staying points of a certain family is 3, and after POI analysis, 3 points are found to be a kindergarten, a residential area and an office building respectively;
number of mobile phone stop points: and counting the number of the stop points in a period of time, wherein the number is used for representing the dispersion of the position where the user appears. For drivers, the number of the stop points is higher, and for owners and family members, the number of the stop points is lower;
the mobile phone moves for a long distance frequently: counting the number of track segments with the moving distance of more than 50 kilometers (the number of kilometers can be set) in the track sequence of the target user to represent the frequency of long-distance movement of the user. For the driver and some car owners, the value will be high;
the position span of the mobile phone is as follows: including longitude and latitude spans, to characterize the user's maximum range of motion, which is high for the driver and some car owners.
2. Correlation factor calculation
The use frequency of users of each key function point in the mobile phone software is counted, such as refueling, vehicle searching, goods finding, insurance, ETC and the like, and users with different identities have statistical preference for each function. Further, factors such as the number of vehicles authenticated by the user and the number of vehicles paid attention by the user may be used as the correlation factors of the identity determination model.
3. Constructing feature vectors
Extracting track factors, correlation factors and user identity labels of the users with confirmed identities as marking data, including but not limited to vehicle number, mobile phone stop point POI types and stop times, mobile phone stop point number, mobile phone long-distance moving frequency, mobile phone position span, refueling function use times, vehicle checking function use times, cargo finding function use times, insurance function use times, ETC function use times, user authentication vehicle number, user attention vehicle number and the like matched with the users.
4. Model training and prediction
The basic model of the prediction model is a classification model, which comprises the following steps: logistic regression, support vector machines, decision trees, and the like. Preferably, for the decision tree model, the outputting the classification comprises: owner, driver, family members, and others.
And the operation analysis module evaluates the operation condition of the authenticated vehicle by using vehicle track data aiming at the user subjected to strict identity and people-vehicle relationship examination. The input of the operation analysis module is freight vehicle track data, and the output core factors comprise total operating mileage of all vehicles, average operating mileage of the vehicles, the number of the authenticated vehicles and the like.
The factors have the following meanings:
total mileage of all vehicle operations: representing the overall operating condition of the user-authenticated vehicle;
the average mileage of the vehicle operation is as follows: representing vehicle operating efficiency;
the number of authenticated vehicles: indicating the user vehicle asset condition.
The comprehensive detection module utilizes the identity category of the user and the operation condition of the vehicle to which the user belongs, and can also use other externally introduced data (external data, such as credit rating of a bank system, consumption condition records of payment software, a consumption platform and the like, public bad record number, credit product number in use, public bankruptcy record number, first loan time and the like) to construct the confidence coefficient of the user by combining with the default record of the target user.
The confidence model of the integrated detection module generally uses logistic regression or decision trees.
This module includes two implementations:
1. overall confidence detection
And the identity category of the user is used as the characteristic of the confidence coefficient model to finally obtain a uniform model.
2. Classification confidence detection
And respectively constructing an owner confidence coefficient model, a driver confidence coefficient model and a family confidence coefficient model according to the identity label of the user, so as to realize differentiated confidence coefficient detection.
Further explanation is made by taking classification confidence detection as an example.
The user a judges that the user a is the owner of the vehicle in the identity judgment module through user data and other related data, and then confidence detection can be carried out by utilizing an owner confidence model;
the user b judges the user b as a driver in the identity judgment module through user data and other related data, and confidence detection can be carried out by utilizing a driver confidence model;
and the user c judges the user c as a family in the identity judgment module through user data and other related data, and then confidence detection can be carried out by utilizing a family confidence model.
In the method, a characteristic vector is determined through user data, a prediction model is trained according to the characteristic vector and a label, and the identity category of a user is determined by using the trained model; determining an operation factor according to the audit data of the user and the vehicle track data; the confidence coefficient model is trained through the identity category and the operation factor, the confidence coefficient of the user is determined, and the identity of the user can be judged and the confidence coefficient of the operation condition can be detected by using other data.
The above description is only for the preferred embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (10)

1.一种基于轨迹数据的置信度检测方法，其特征在于，包括：1. a confidence detection method based on trajectory data, is characterized in that, comprises: 根据用户数据，获取轨迹因子和相关因子，确定特征向量；According to the user data, obtain the trajectory factor and correlation factor, and determine the feature vector; 根据所述特征向量和标签训练预测模型，得到训练好的预测模型，使用所述训练好的模型确定用户的身份类别；Train the prediction model according to the feature vector and the label, obtain a trained prediction model, and use the trained model to determine the identity category of the user; 获取用户的审核数据，根据车辆轨迹数据，确定运营因子；Obtain the user's audit data, and determine the operating factor according to the vehicle trajectory data; 根据所述身份类别和所述运营因子，训练置信度模型，得到训练好的置信度模型；According to the identity category and the operating factor, train a confidence model to obtain a trained confidence model; 根据训练好的置信度模型确定用户的置信度。Determine the user's confidence according to the trained confidence model. 2.如权利要求1所述的方法，其特征在于，所述根据用户数据，获取轨迹因子和相关因子，确定特征向量，包括：2. The method according to claim 1, wherein, according to the user data, obtaining the trajectory factor and the correlation factor, and determining the feature vector, comprising: 根据用户数据，确定轨迹因子；According to the user data, determine the trajectory factor; 根据用户数据，确定相关因子；According to the user data, determine the correlation factor; 抽取已确认身份用户的所述轨迹因子和所述相关因子作为特征向量。The trajectory factor and the correlation factor of the identified user are extracted as feature vectors. 3.如权利要求2所述的方法，其特征在于，所述根据用户数据，确定轨迹因子，包括：3. The method according to claim 2, wherein the determining the trajectory factor according to the user data comprises: 根据所述用户数据，确定用户匹配车辆数；According to the user data, determine the number of vehicles matched by the user; 根据所述用户数据中的手机数据和聚类算法，确定用户停留点；According to the mobile phone data and the clustering algorithm in the user data, determine the user stop point; 获取所述停留点的类型，统计频率，得到所述停留点的类型和停留次数；Obtain the type of the stop point, count the frequency, and obtain the type of the stop point and the number of times of stop; 统计一段时间内的所述停留点数量，作为所述停留点位置的离散度，确定停留点数量；Counting the number of stop points within a period of time, as the dispersion of the location of the stop points, to determine the number of stop points; 根据所述手机数据，统计用户的长距离移动频次和手机位置跨度；According to the mobile phone data, count the user's long-distance movement frequency and mobile phone location span; 所述用户匹配车辆数、停留点的类型、停留次数、停留点数量、长距离移动频次和手机位置跨度组成所述轨迹因子。The number of vehicles matched by the user, the type of stop point, the number of stops, the number of stop points, the frequency of long-distance movement, and the location span of the mobile phone constitute the trajectory factor. 4.如权利要求2所述的方法，其特征在于，所述根据用户数据，确定相关因子，包括：4. The method of claim 2, wherein the determining a correlation factor according to user data comprises: 统计用户手机中的关键功能使用频次；Statistics on the usage frequency of key functions in the user's mobile phone; 根据所述用户数据，确定用户的认证车辆数和关注车辆数；According to the user data, determine the number of authenticated vehicles and the number of concerned vehicles of the user; 所述关键功能使用频次、认证车辆数和关注车辆数组成相关因子。The frequency of use of the key functions, the number of certified vehicles, and the number of vehicles of interest constitute correlation factors. 5.如权利要求4所述的方法，其特征在于，所述关键功能，包括：加油、查车、找货、保险和ETC。5. The method according to claim 4, wherein the key functions include: refueling, vehicle checking, goods searching, insurance and ETC. 6.如权利要求1所述的方法，其特征在于，所述使用所述训练好的模型确定用户的身份类别，包括：6. The method according to claim 1, wherein the determining the user's identity category using the trained model comprises: 输入用户数据至所述训练好的预测模型，得到用户的身份类别。Input user data into the trained prediction model to obtain the identity category of the user. 7.如权利要求1所述的方法，其特征在于，所述获取用户的审核数据，根据车辆轨迹数据，确定运营因子，包括：7. The method of claim 1, wherein the obtaining user's audit data, and determining the operation factor according to the vehicle trajectory data, comprises: 根据所述用户的审核数据，获取用户的车辆数据；Obtain the user's vehicle data according to the user's audit data; 根据用户的所述车辆数据，确定认证车辆数量，各车辆的运营里程；According to the vehicle data of the user, determine the number of certified vehicles and the operating mileage of each vehicle; 根据所述认证车辆数量和各所述车辆的运营里程，确定全部车辆的运营总里程和平均运营里程；Determine the total operating mileage and average operating mileage of all vehicles according to the number of certified vehicles and the operating mileage of each of the vehicles; 所述认证车辆数量、运营总里程和平均运营里程组成运营因子。The number of certified vehicles, total operating mileage and average operating mileage constitute an operating factor. 8.如权利要求1所述的方法，其特征在于，所述根据所述身份类别和所述运营因子，训练置信度模型，得到训练好的置信度模型，还包括：8. The method of claim 1, wherein, according to the identity category and the operating factor, training a confidence model to obtain a trained confidence model, further comprising: 根据所述身份类别、所述运营因子和外部数据，训练置信度模型，得到训练好的置信度模型。According to the identity category, the operation factor and the external data, a confidence model is trained to obtain a trained confidence model. 9.如权利要求3所述的方法，其特征在于，所述根据所述用户数据，确定用户匹配车辆数包括：9. The method according to claim 3, wherein the determining the number of vehicles matched by the user according to the user data comprises: 使用已有的数据确定所述用户匹配车辆数和/或根据用户数据和车辆数据，确定所述用户匹配车辆数。The number of vehicles matched by the user is determined using existing data and/or the number of vehicles matched by the user is determined based on user data and vehicle data. 10.一种基于轨迹数据的置信度检测系统，其特征在于，包括：10. A confidence detection system based on trajectory data, comprising: 身份判定模块，用于根据用户数据，获取轨迹因子和相关因子，确定特征向量；根据所述特征向量和标签训练预测模型，得到训练好的预测模型，使用所述训练好的模型确定用户的身份类别；The identity determination module is used to obtain the trajectory factor and correlation factor according to the user data, and determine the feature vector; train the prediction model according to the feature vector and the label, obtain the trained prediction model, and use the trained model to determine the identity of the user category; 运营分析模块，用于获取用户的审核数据，根据车辆轨迹数据，确定运营因子；The operation analysis module is used to obtain the user's audit data, and determine the operation factor according to the vehicle trajectory data; 综合检测模块，用于根据所述身份类别和所述运营因子，训练置信度模型，得到训练好的置信度模型；根据训练好的置信度模型确定用户的置信度。The comprehensive detection module is used to train a confidence model according to the identity category and the operation factor, and obtain a trained confidence model; and determine the user's confidence according to the trained confidence model.
CN201911244965.4A 2019-12-06 2019-12-06 Confidence detection method and system based on track data Active CN111127035B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911244965.4A CN111127035B (en) 2019-12-06 2019-12-06 Confidence detection method and system based on track data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911244965.4A CN111127035B (en) 2019-12-06 2019-12-06 Confidence detection method and system based on track data

Publications (2)

Publication Number Publication Date
CN111127035A true CN111127035A (en) 2020-05-08
CN111127035B CN111127035B (en) 2023-04-21

Family

ID=70497766

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911244965.4A Active CN111127035B (en) 2019-12-06 2019-12-06 Confidence detection method and system based on track data

Country Status (1)

Country Link
CN (1) CN111127035B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113205403A (en) * 2021-03-30 2021-08-03 北京中交兴路信息科技有限公司 Method and device for calculating enterprise credit level, storage medium and terminal
CN113760997A (en) * 2021-09-10 2021-12-07 成都知道创宇信息技术有限公司 Data confidence calculation method and device, computer equipment and readable storage medium

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101692314A (en) * 2009-10-15 2010-04-07 康华武 Method for identifying vehicle identity by using vehicle position information and application
WO2012017436A1 (en) * 2010-08-05 2012-02-09 Hi-Tech Solutions Ltd. Method and system for collecting information relating to identity parameters of a vehicle
US20120116559A1 (en) * 2010-11-04 2012-05-10 Davis Bruce L Smartphone-Based Methods and Systems
CN105197131A (en) * 2015-08-31 2015-12-30 王保进 Vehicle anti-theft method and system
CN107633047A (en) * 2017-09-15 2018-01-26 广州汇智通信技术有限公司 A kind of method and system of passenger's identification
WO2018150244A1 (en) * 2017-02-18 2018-08-23 Yogesh Chunilal Rathod Registering, auto generating and accessing unique word(s) including unique geotags
CN108876270A (en) * 2018-09-19 2018-11-23 惠龙易通国际物流股份有限公司 Automatic source of goods auditing system and method
CN109145982A (en) * 2018-08-17 2019-01-04 上海汽车集团股份有限公司 The personal identification method and device of driver, storage medium, terminal
CN110213723A (en) * 2019-05-16 2019-09-06 武汉数矿科技股份有限公司 A kind of method and apparatus quickly determining suspect according to track

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101692314A (en) * 2009-10-15 2010-04-07 康华武 Method for identifying vehicle identity by using vehicle position information and application
WO2012017436A1 (en) * 2010-08-05 2012-02-09 Hi-Tech Solutions Ltd. Method and system for collecting information relating to identity parameters of a vehicle
US20120116559A1 (en) * 2010-11-04 2012-05-10 Davis Bruce L Smartphone-Based Methods and Systems
CN105197131A (en) * 2015-08-31 2015-12-30 王保进 Vehicle anti-theft method and system
WO2018150244A1 (en) * 2017-02-18 2018-08-23 Yogesh Chunilal Rathod Registering, auto generating and accessing unique word(s) including unique geotags
CN107633047A (en) * 2017-09-15 2018-01-26 广州汇智通信技术有限公司 A kind of method and system of passenger's identification
CN109145982A (en) * 2018-08-17 2019-01-04 上海汽车集团股份有限公司 The personal identification method and device of driver, storage medium, terminal
CN108876270A (en) * 2018-09-19 2018-11-23 惠龙易通国际物流股份有限公司 Automatic source of goods auditing system and method
CN110213723A (en) * 2019-05-16 2019-09-06 武汉数矿科技股份有限公司 A kind of method and apparatus quickly determining suspect according to track

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
CHIH-WEI WU等: "Vehicle Re-Identification With the Space-Time Prior" *
王良民等: "基于车辆身份的车联网结构与安全" *
肖永清: "迎接以车联网为代表的汽车后市场时代" *
陈坚: "GPS车辆监控管理中心系统在燃气行业的应用" *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113205403A (en) * 2021-03-30 2021-08-03 北京中交兴路信息科技有限公司 Method and device for calculating enterprise credit level, storage medium and terminal
CN113760997A (en) * 2021-09-10 2021-12-07 成都知道创宇信息技术有限公司 Data confidence calculation method and device, computer equipment and readable storage medium

Also Published As

Publication number Publication date
CN111127035B (en) 2023-04-21

Similar Documents

Publication Publication Date Title
Chen et al. A short-term traffic prediction model in the vehicular cyber–physical systems
CN112447041B (en) Method and device for identifying operation behavior of vehicle and computing equipment
CN112543427B (en) Method and system for analyzing and identifying urban traffic corridor based on signaling track and big data
CN110543999B (en) Method and device for store site selection
Shokoohyar et al. On the determinants of Uber accessibility and its spatial distribution: Evidence from Uber in Philadelphia
Milenković et al. Decision‐Support Framework for Selecting the Optimal Road Toll Collection System
CN113792782B (en) Track monitoring method and device for operation vehicle, storage medium and computer equipment
CN105488046A (en) Big data analysis system based on vehicle insurance services
Bhat et al. Accommodating immigration status and self-selection effects in a joint model of household auto ownership and residential location choice
CN111144446B (en) A driver identification method and system based on spatio-temporal grid
CN115293336A (en) Risk assessment model training method and device and server
CN107016042B (en) Address information verification system based on user position log
CN107872767A (en) A recognition method and recognition system for online car-hailing swiping behavior
CN105355045A (en) Method and device for assisting in determining driver identity
CN111078973B (en) Big data based car identification method, equipment and storage media
CN111127035A (en) A method and system for confidence detection based on trajectory data
Niroomand et al. Segment-based CO₂ emission evaluations from passenger cars based on deep learning techniques
Niroomand et al. Estimating average vehicle mileage for various vehicle classes using polynomial models in deep classifiers
CN120071633B (en) Illegal operation vehicle identification system and method based on space-time diagram neural network
JP7105176B2 (en) Machine learning device, judgment device, program and machine learning method
KR102245888B1 (en) System and method of building big data for estimating house price using space information
CN114862560B (en) A method for identifying automobile anti-fraud risks and related equipment
Sayeg et al. Estimating changes in emissions from bus rapid transit: making best use of transport sector experience
CN117273281A (en) Smart tourism data analysis method and system based on RFID technology
Holian et al. Household demand for low carbon public policies: Evidence from California

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
CP03 Change of name, title or address
CP03 Change of name, title or address

Address after: 100176 block a, qianfang building, No.27, Zhongguancun Software Park, No.8, Dongbeiwang West Road, Haidian District, Beijing

Patentee after: Beijing Tranwiseway Information Technology Co.,Ltd.

Country or region after: China

Address before: 100176 block a, qianfang building, No.27, Zhongguancun Software Park, No.8, Dongbeiwang West Road, Haidian District, Beijing

Patentee before: BEIJING TRANWISEWAY INFORMATION TECHNOLOGY Co.,Ltd.

Country or region before: China

TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20250701

Address after: 101116 Beijing Tongzhou District, Beilangying Village, No. 1 Building 2, 3rd Floor, Room 101

Patentee after: Beijing Xinglu Chelian Technology Co.,Ltd.

Country or region after: China

Address before: 100176 block a, qianfang building, No.27, Zhongguancun Software Park, No.8, Dongbeiwang West Road, Haidian District, Beijing

Patentee before: Beijing Tranwiseway Information Technology Co.,Ltd.

Country or region before: China