CN113673571A - Taxi abnormal order identification method based on density clustering method - Google Patents
Taxi abnormal order identification method based on density clustering method Download PDFInfo
- Publication number
- CN113673571A CN113673571A CN202110829406.0A CN202110829406A CN113673571A CN 113673571 A CN113673571 A CN 113673571A CN 202110829406 A CN202110829406 A CN 202110829406A CN 113673571 A CN113673571 A CN 113673571A
- Authority
- CN
- China
- Prior art keywords
- order
- abnormal
- data
- orders
- density clustering
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 104
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000009826 distribution Methods 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 23
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 238000006243 chemical reaction Methods 0.000 claims abstract description 7
- 238000004140 cleaning Methods 0.000 claims abstract description 7
- 238000004590 computer program Methods 0.000 claims description 7
- 230000004931 aggregating effect Effects 0.000 claims description 6
- 238000011160 research Methods 0.000 claims description 5
- 238000004220 aggregation Methods 0.000 claims description 3
- 230000002776 aggregation Effects 0.000 claims description 3
- 238000013500 data storage Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 5
- 206010000117 Abnormal behaviour Diseases 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Computational Biology (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a taxi abnormal order identification method based on a density clustering method. Firstly, preprocessing original data, including coordinate system conversion of the data and cleaning of the data; then, carrying out gridding processing on the preprocessed data; then, identifying abnormal sample points in each similar order cluster by a density clustering-based method; and finally, analyzing the abnormal recognition result to obtain the space-time distribution characteristics of the possible abnormal orders. The method is based on the clustering algorithm, can realize the automatic identification of the possible abnormal orders, integrates the similar orders through grid division, corrects the result and can obviously improve the accuracy of the algorithm.
Description
Technical Field
The invention relates to the field of traffic big data application, in particular to an abnormal order identification method based on a density clustering method.
Background
In real life, a phenomenon that a taxi driver detours to increase income may occur. Such behavior is usually found by active reporting of passengers, but since there may be situations where passengers are unfamiliar with the route, etc., some abnormal behavior cannot be dealt with in time. With the continuous improvement of the informatization degree, the popularization rate of the vehicle-mounted GPS equipment is higher and higher, so that relevant characteristics can be extracted through vehicle order information, and further possible abnormal orders can be identified and further analyzed and processed by relevant departments.
The clustering algorithm and the abnormal recognition algorithm in the prior art are separated, secondary judgment is needed for order data, and the detection efficiency and the detection precision are not high.
Disclosure of Invention
The invention aims to solve the technical problem of providing an abnormal order identification method based on a density clustering method, so that possible abnormal orders in the taxi operation process are identified, abnormal behaviors are identified, and data support is further provided for further processing of relevant departments.
In order to solve the technical problem, the invention provides an abnormal order identification method based on a density clustering method, which comprises the following steps:
step 1: preprocessing original data, including coordinate system conversion and data cleaning;
step 2: carrying out gridding processing on the preprocessed data;
and step 3: identifying abnormal sample points in each similar order cluster by a density clustering-based method;
and 4, step 4: and analyzing the abnormal recognition result to obtain the space-time distribution characteristics of the possible abnormal orders.
An abnormal order identification system based on a density clustering method comprises the following modules:
a data preprocessing module: the system comprises a data acquisition module, a data storage module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring original data;
a gridding module: the data processing device is used for carrying out gridding processing on the preprocessed data;
an abnormal order identification module: the method comprises the steps of identifying abnormal sample points in similar order clusters;
an abnormal order analysis module: and the method is used for analyzing the abnormal recognition result to obtain the space-time distribution characteristics of the possible abnormal orders.
Compared with the prior art, its beneficial effect lies in:
(1) the method is based on the clustering algorithm, can realize the automatic identification of the possible abnormal orders, integrates the similar orders through grid division, corrects the result and can obviously improve the accuracy of the algorithm;
(2) according to the invention, result analysis is carried out after the abnormal vehicle order is identified, the space-time distribution characteristics of the abnormal order are analyzed, and a basic analysis result and law enforcement basis can be provided for relevant departments.
The invention will be further illustrated by the following description and the accompanying drawings.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
FIG. 2 is a sample distribution diagram of similar orders at the starting point and the ending point according to an embodiment of the present invention.
Fig. 3 is a clustering result cluster distribution diagram in the embodiment of the present invention.
FIG. 4 is a diagram illustrating a possible abnormal order identification result in accordance with an embodiment of the present invention.
FIG. 5 is a diagram illustrating a distribution of possible orders with exceptions on different days, according to an embodiment of the present invention.
FIG. 6 shows driver information with more possible abnormal orders according to an embodiment of the present invention
FIG. 7 is a diagram illustrating possible abnormal order distributions for different characteristic days and characteristic times in an embodiment of the present invention.
Detailed Description
A taxi abnormal order recognition method based on a density clustering method comprises the following steps:
step 1: the original data is processed for storage conveniently, and meanwhile, error data also exists, so that the original data needs to be preprocessed, including coordinate system conversion of the data and cleaning of the data, specifically:
step 1-1: in the raw data, the latitude and longitude are stored in the form of a character string, and the decimal point is omitted. Therefore, according to the characteristics of the research area, the longitude and latitude are restored and converted into a numerical type;
converting the latitude and longitude stored in the form of character strings in the original data into numerical values;
step 1-2: and eliminating error data and repeated data, wherein the error data comprises data with missing longitude and latitude and data with longitude and latitude exceeding a target research area, and the repeated data is data repeatedly appearing in the same trip order.
Step 2: the original order data comprises start and end point POI information of the order, but due to the small granularity of the POI, the order is counted according to a grid where the start and end point is located by considering a gridding processing means, information with larger granularity and statistical significance is obtained, and meanwhile, the reasonability of the result is ensured by reasonably setting the size of the grid;
therefore, the gridding processing is performed on the preprocessed data, specifically:
step 2-1: because the WGS-84 geodetic coordinate system belongs to a spherical coordinate system, the direct linear offset of the WGS-84 coordinate system to load the grid can cause nonlinear offset, which is different from the actual condition;
the method adopts UTM plane coordinates, projects WGS-84 geodetic coordinates onto the UTM plane, and linearly shifts the grids to complete grid loading;
step 2-2: determining the grid number of the starting point and the ending point of each order in the data according to the boundary of the selected area:
wherein xiAnd yiCoordinates representing the start or end of the order, yupAnd xleftThe north and south latitude and longitude of the selected area are shown, and gridsize shows the size of the grid.
And step 3: identifying abnormal sample points in each similar order cluster by a density clustering-based method, which specifically comprises the following steps:
step 3-1: extracting order features, comprising:
travel time: obtaining the consumed time of the order according to the starting time of the order;
starting and ending point distance: after the grid division, actual getting-on and getting-off coordinates under the same grid may not be the same, so that the parameter is increased to perform more refined division on different orders;
euclidean speed: according to the linear distance of the starting point and the ending point of the order and the travel time of the order, the Euclidean speed of the order is obtained, the speed does not represent the real travel speed, but can represent the speed of the vehicle to a certain degree;
whether the order is in a peak time period or not is also a factor to be considered, because the road condition in the peak time period is obviously different from that in a peak time period, the time spent on the order is also greatly influenced;
the order time interval is a working day or a rest day, and for the same time interval, the road conditions of the working day and the rest day may be greatly different, so that the factor needs to be considered.
Step 3-2: aggregating orders, namely aggregating orders with the same starting point and ending point grid numbers in the target area based on a grid division method, wherein the order durations of the orders with the starting point and ending point linear distances close to each other (characterized by the starting point and ending point linear distances), so that the samples are distributed and have aggregation;
step 3-3: clustering the order based on a density clustering method (DBSCAN) and the characteristics extracted in the step 3-1, which specifically comprises the following steps:
based on a density clustering method, clustering the orders according to the parameters extracted in the step 3-1, and separating sample points in different areas;
because the abnormal order is far away from the normal sample point, distinguishing different clustering clusters obtained by identification according to the order duration;
for each cluster, the judgment is carried out through the median of the order duration and a set threshold value, and the formula is as follows:
wherein liIs the label value of cluster i, 1 represents a normal sample, -1 represents an abnormal sample, tm,iOrder duration median, T, for cluster imThe order duration median of all samples;
because some normal samples are far away from the area with high density in the sample space (such as unusual vehicle-entering and vehicle-leaving points), after the DBSCAN algorithm is carried out, the cluster of the normal samples is marked as-1; and for the orders with the clustering cluster mark of-1, comparing the order duration with a set threshold value one by one.
And 4, step 4: analyzing the abnormal recognition result to obtain the space-time distribution characteristics of the possible abnormal orders, wherein the analysis indexes are as follows:
the overall proportion of the order is as follows: the proportion of possible abnormal orders to the total amount of orders is referred to;
distribution on different dates: the system is used for monitoring the absolute quantity and the occupied proportion of abnormal orders on different dates, and further detecting reasons when indexes fluctuate abnormally;
different drivers may have abnormal order quantities: counting the number of possible abnormal orders of different drivers, and further surveying the drivers with higher number;
abnormal order distribution on different characteristic days and different characteristic time periods: abnormal orders are obtained by counting different characteristic days and different characteristic time periods.
An abnormal order identification system based on a density clustering method comprises the following modules:
a data preprocessing module: the system comprises a data acquisition module, a data storage module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring original data;
a gridding module: the data processing device is used for carrying out gridding processing on the preprocessed data;
an abnormal order identification module: the method comprises the steps of identifying abnormal sample points in similar order clusters;
an abnormal order analysis module: and the method is used for analyzing the abnormal recognition result to obtain the space-time distribution characteristics of the possible abnormal orders.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
step 1: preprocessing original data, including coordinate system conversion and data cleaning;
step 2: carrying out gridding processing on the preprocessed data;
and step 3: identifying abnormal sample points in each similar order cluster by a density clustering-based method;
and 4, step 4: and analyzing the abnormal recognition result to obtain the space-time distribution characteristics of the possible abnormal orders.
A computer-storable medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
step 1: preprocessing original data, including coordinate system conversion and data cleaning;
step 2: carrying out gridding processing on the preprocessed data;
and step 3: identifying abnormal sample points in each similar order cluster by a density clustering-based method;
and 4, step 4: and analyzing the abnormal recognition result to obtain the space-time distribution characteristics of the possible abnormal orders.
The present invention is further illustrated by the following examples.
Examples
With reference to fig. 1, a taxi abnormal order identification method based on a density clustering method includes the following steps:
step 1: the original data is processed for storage conveniently, and meanwhile, error data also exists, so that the original data needs to be preprocessed, including coordinate system conversion of the data and cleaning of the data, specifically:
step 1-1: in the raw data, the latitude and longitude are stored in the form of a character string, and the decimal point is omitted. Therefore, according to the characteristics of the research area, the longitude and latitude are restored and converted into a numerical type;
converting the latitude and longitude stored in the form of character strings in the original data into numerical values;
step 1-2: and eliminating error data and repeated data, wherein the error data comprises data with missing longitude and latitude and data with longitude and latitude exceeding a target research area, and the repeated data is data repeatedly appearing in the same trip order.
Step 2: the original order data comprises start and end point POI information of the order, but due to the small granularity of the POI, the order is counted according to a grid where the start and end point is located by considering a gridding processing means, information with larger granularity and statistical significance is obtained, and meanwhile, the reasonability of the result is ensured by reasonably setting the size of the grid;
therefore, the gridding processing is performed on the preprocessed data, specifically:
step 2-1: because the WGS-84 geodetic coordinate system belongs to a spherical coordinate system, the direct linear offset of the WGS-84 coordinate system to load the grid can cause nonlinear offset, which is different from the actual condition;
the method adopts UTM plane coordinates, projects WGS-84 geodetic coordinates onto the UTM plane, and linearly shifts the grids to complete grid loading;
step 2-2: determining the grid number of the starting point and the ending point of each order in the data according to the boundary of the selected area:
wherein xiAnd yiCoordinates representing the start or end of the order, yupAnd xleftThe north and south latitude and longitude of the selected area are shown, and gridsize shows the size of the grid.
And step 3: identifying abnormal sample points in each similar order cluster by a density clustering-based method, which specifically comprises the following steps:
step 3-1: extracting order features, comprising:
travel time: obtaining the consumed time of the order according to the starting time of the order;
starting and ending point distance: after the grid division, actual getting-on and getting-off coordinates under the same grid may not be the same, so that the parameter is increased to perform more refined division on different orders;
euclidean speed: according to the linear distance of the starting point and the ending point of the order and the travel time of the order, the Euclidean speed of the order is obtained, the speed does not represent the real travel speed, but can represent the speed of the vehicle to a certain degree;
whether the order is in a peak time period or not is also a factor to be considered, because the road condition in the peak time period is obviously different from that in a peak time period, the time spent on the order is also greatly influenced;
the order time interval is a working day or a rest day, and for the same time interval, the road conditions of the working day and the rest day may be greatly different, so that the factor needs to be considered.
Step 3-2: aggregating orders, aggregating orders with the same starting and ending point grid numbers in the target area based on a grid division method, and for orders with the starting and ending point linear distances close (characterized by the starting and ending point linear distances), the order durations are close, so that the sample distribution has aggregation, as shown in fig. 2, the sample point distribution of partial orders with similar starting and ending points has an obvious cluster distribution characteristic.
Step 3-3: clustering the order based on a density clustering method (DBSCAN) and the characteristics extracted in the step 3-1, which specifically comprises the following steps:
based on a density clustering method, clustering the orders according to the parameters extracted in the step 3-1, and separating sample points in different areas;
fig. 3 shows the clustering result, and the dots with different sizes in the circles represent different clusters.
Because the abnormal order is far away from the normal sample point, distinguishing different clustering clusters obtained by identification according to the order duration;
for each cluster, the judgment is carried out through the median of the order duration and a set threshold value, and the formula is as follows:
wherein liIs the label value of cluster i, 1 represents a normal sample, -1 represents an abnormal sample, tm,iOrder duration median, T, for cluster imThe order duration median of all samples;
because some normal samples are far away from the area with high density in the sample space (such as unusual vehicle-entering and vehicle-leaving points), after the DBSCAN algorithm is carried out, the cluster of the normal samples is marked as-1; and for the orders with the clustering cluster mark of-1, comparing the order duration with a set threshold value one by one.
As shown in fig. 4, the points within the circle are possible abnormal order identification results.
And 4, step 4: analyzing the abnormal recognition result to obtain the space-time distribution characteristics of the possible abnormal orders, wherein the analysis indexes are as follows:
the overall proportion of the order is as follows: the proportion of possible abnormal orders to the total amount of orders is referred to;
taking 12 months in 2019, the first 100 hot spots OD are analyzed, 190855 orders are obtained, wherein 9198 possible abnormal orders are identified, accounting for about 5%, which also indicates that the abnormal orders are generated as a small probability event. Meanwhile, the part of abnormal orders may have various generation reasons, and further investigation is needed by relevant departments.
Distribution on different dates: the system is used for monitoring the absolute quantity and the occupied proportion of abnormal orders on different dates, and further detecting reasons when indexes fluctuate abnormally; as shown in fig. 5, the number of possible abnormal orders and the ratio of possible abnormal orders in 12 months in 2019 have large absolute number fluctuation, and the ratio of possible abnormal orders is stable. Among them, the abnormal fluctuation of 29 days 11 and 11 in 2019 is a data problem, and the data of the day is less.
Different drivers may have abnormal order quantities: counting the number of possible abnormal orders of different drivers, and further surveying the drivers with higher number; fig. 6 shows the drivers who may have abnormal orders, and since the order duration is also influenced by the driving habits of the drivers, the road congestion conditions, etc., the vehicles can be further investigated according to the preliminary result.
Abnormal order distribution on different characteristic days and different characteristic time periods: abnormal orders are obtained by counting different characteristic days and different characteristic time periods.
Fig. 7 shows that the abnormal order occupation ratios of different characteristic days and characteristic time periods have no significant difference, so that the incidence rate of the abnormal order is judged to have small characteristic correlation with time.
The method is based on the clustering algorithm, can realize the automatic identification of the possible abnormal orders, integrates the similar orders through grid division, corrects the result and can obviously improve the accuracy of the algorithm; after the abnormal vehicle order is identified, result analysis is carried out, the space-time distribution characteristics of the abnormal order are analyzed, and basic analysis results and law enforcement bases can be provided for relevant departments.
The above examples are only preferred embodiments of the present invention, it should be noted that: it will be apparent to those skilled in the art that various modifications and equivalents can be made without departing from the spirit of the invention, and it is intended that all such modifications and equivalents fall within the scope of the invention as defined in the claims.
Claims (10)
1. A taxi abnormal order recognition method based on a density clustering method is characterized by comprising the following steps:
step 1: preprocessing original data, including coordinate system conversion and data cleaning;
step 2: carrying out gridding processing on the preprocessed data;
and step 3: identifying abnormal sample points in each similar order cluster by a density clustering-based method;
and 4, step 4: and analyzing the abnormal recognition result to obtain the space-time distribution characteristics of the possible abnormal orders.
2. The abnormal order identification method based on the density clustering method according to claim 1, wherein the preprocessing of the raw data in the step 1 is specifically:
step 1-1: converting the latitude and longitude stored in the form of character strings in the original data into numerical values;
step 1-2: and eliminating error data and repeated data, wherein the error data comprises data with missing longitude and latitude and data with longitude and latitude exceeding a target research area, and the repeated data is data repeatedly appearing in the same trip order.
3. The abnormal order identification method based on the density clustering method according to claim 1, wherein the gridding processing is performed on the preprocessed data in the step 2, specifically:
step 2-1: projecting the WGS-84 geodetic coordinates onto a UTM plane, and linearly shifting the grid to complete grid loading;
step 2-2: determining the grid number of the starting point and the ending point of each order in the data according to the boundary of the selected area:
wherein xiAnd yiCoordinates representing the start or end of the order, yupAnd xleftThe north and south latitude and longitude of the selected area are shown, and gridsize shows the size of the grid.
4. The abnormal order identification method based on the density clustering method as claimed in claim 1, wherein the possible abnormal order identification in the step 3 specifically comprises the following steps:
step 3-1: extracting order features;
step 3-2: aggregating orders, namely aggregating orders with the same starting point and ending point grid numbers in the target area based on a grid division method, wherein the order durations of the orders with the similar starting point and ending point linear distances are similar, so that the sample distribution has aggregation;
step 3-3: and (4) clustering the orders based on a density clustering method and the features extracted in the step 3-1.
5. The abnormal order identification method based on the density clustering method as claimed in claim 4, wherein the extracted order features in step 3-1 comprise:
travel time: obtaining the consumed time of the order according to the starting time of the order;
starting and ending point distance: after the grid division, actual getting-on and getting-off coordinates under the same grid may not be the same, so that the parameter is increased to perform more refined division on different orders;
euclidean speed: according to the linear distance of the starting point and the ending point of the order and the travel time of the order, the Euclidean speed of the order is obtained;
whether the order is in a peak period;
the order period is a workday or a holiday.
6. The abnormal order identification method based on the density clustering method as claimed in claim 4, wherein the aggregated order in the step 3-3 is specifically:
based on a density clustering method, clustering the orders according to the parameters extracted in the step 3-1, and separating sample points in different areas;
because the abnormal order is far away from the normal sample point, distinguishing different clustering clusters obtained by identification according to the order duration;
for each cluster, the judgment is carried out through the median of the order duration and a set threshold value, and the formula is as follows:
wherein liIs the label value of cluster i, 1 represents a normal sample, -1 represents an abnormal sample, tm,iOrder duration median, T, for cluster imThe order duration median of all samples;
and for the cluster mark of-1, comparing the order duration with a set threshold value one by one.
7. The abnormal order identification method based on the density clustering method as claimed in claim 1, wherein the abnormal identification result in the step 4 is analyzed, and the analysis index is specifically:
the overall proportion of the order is as follows: the proportion of possible abnormal orders to the total amount of orders is referred to;
distribution on different dates: the system is used for monitoring the absolute quantity and the occupied proportion of abnormal orders on different dates, and further detecting reasons when indexes fluctuate abnormally;
different drivers may have abnormal order quantities: counting the number of possible abnormal orders of different drivers, and further surveying the drivers with higher number;
abnormal order distribution on different characteristic days and different characteristic time periods: abnormal orders are obtained by counting different characteristic days and different characteristic time periods.
8. An abnormal order identification system based on a density clustering method is characterized by comprising the following modules:
a data preprocessing module: the system comprises a data acquisition module, a data storage module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring original data;
a gridding module: the data processing device is used for carrying out gridding processing on the preprocessed data;
an abnormal order identification module: the method comprises the steps of identifying abnormal sample points in similar order clusters;
an abnormal order analysis module: and the method is used for analyzing the abnormal recognition result to obtain the space-time distribution characteristics of the possible abnormal orders.
9. A computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method according to any of claims 1-7 are implemented by the processor when executing the computer program.
10. A computer-storable medium having a computer program stored thereon, wherein the computer program is adapted to carry out the steps of the method according to any one of claims 1-7 when executed by a processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110829406.0A CN113673571A (en) | 2021-07-22 | 2021-07-22 | Taxi abnormal order identification method based on density clustering method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110829406.0A CN113673571A (en) | 2021-07-22 | 2021-07-22 | Taxi abnormal order identification method based on density clustering method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113673571A true CN113673571A (en) | 2021-11-19 |
Family
ID=78539838
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110829406.0A Pending CN113673571A (en) | 2021-07-22 | 2021-07-22 | Taxi abnormal order identification method based on density clustering method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113673571A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109871876A (en) * | 2019-01-22 | 2019-06-11 | 东南大学 | A kind of Freeway Conditions identification and prediction technique based on floating car data |
CN110750573A (en) * | 2019-08-28 | 2020-02-04 | 广东工业大学 | Traffic jam evolution rule identification method based on gridding and space-time clustering |
CN110992072A (en) * | 2018-11-30 | 2020-04-10 | 北京嘀嘀无限科技发展有限公司 | Abnormal order prediction method and system |
WO2020169053A1 (en) * | 2019-02-21 | 2020-08-27 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for identifying abnormalities |
WO2020206996A1 (en) * | 2019-04-12 | 2020-10-15 | 江苏智通交通科技有限公司 | Method and system for estimating od travel time reliability based on robust statistics |
CN112784000A (en) * | 2021-01-27 | 2021-05-11 | 长沙理工大学 | Passenger searching method based on taxi track data |
CN113095393A (en) * | 2021-04-06 | 2021-07-09 | 兰州交通大学 | High-income taxi driver and extraction method, equipment and storage medium of experience track of taxi driver |
-
2021
- 2021-07-22 CN CN202110829406.0A patent/CN113673571A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110992072A (en) * | 2018-11-30 | 2020-04-10 | 北京嘀嘀无限科技发展有限公司 | Abnormal order prediction method and system |
CN109871876A (en) * | 2019-01-22 | 2019-06-11 | 东南大学 | A kind of Freeway Conditions identification and prediction technique based on floating car data |
WO2020169053A1 (en) * | 2019-02-21 | 2020-08-27 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for identifying abnormalities |
WO2020206996A1 (en) * | 2019-04-12 | 2020-10-15 | 江苏智通交通科技有限公司 | Method and system for estimating od travel time reliability based on robust statistics |
CN110750573A (en) * | 2019-08-28 | 2020-02-04 | 广东工业大学 | Traffic jam evolution rule identification method based on gridding and space-time clustering |
CN112784000A (en) * | 2021-01-27 | 2021-05-11 | 长沙理工大学 | Passenger searching method based on taxi track data |
CN113095393A (en) * | 2021-04-06 | 2021-07-09 | 兰州交通大学 | High-income taxi driver and extraction method, equipment and storage medium of experience track of taxi driver |
Non-Patent Citations (2)
Title |
---|
胡圆 等: "基于密度聚类的出租车异常轨迹检测", 《计算机与现代化》, no. 6, pages 53 - 58 * |
胡圆;李晖;陈梅;: "基于密度聚类的出租车异常轨迹检测", 计算机与现代化, no. 06 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109871876B (en) | Expressway road condition identification and prediction method based on floating car data | |
CN107977476B (en) | Method for estimating remaining endurance mileage of automobile | |
CN101694743A (en) | Method and device for predicting road conditions | |
CN112669190B (en) | Detection method and device for abnormal emission behavior of pollution source and computer equipment | |
CN112562330A (en) | Method and device for evaluating road operation index, electronic equipment and storage medium | |
CN110969190A (en) | Illegal operation vehicle detection method, medium, equipment and device | |
RU2747317C2 (en) | Method for predicting the nature of traffic in the road system | |
Wemegah et al. | Big data challenges in transportation: A case study of traffic volume count from massive Radio Frequency Identification (RFID) data | |
CN111612334A (en) | Driving behavior risk rating judgment method based on Internet of vehicles data | |
CN116502125B (en) | Vehicle event dividing method and device and vehicle networking server | |
CN113673571A (en) | Taxi abnormal order identification method based on density clustering method | |
CN116704750B (en) | Traffic state identification method based on clustering algorithm, electronic equipment and medium | |
CN108597224B (en) | Method and system for identifying to-be-improved traffic facilities based on space-time trajectory data | |
CN113393011B (en) | Method, device, computer equipment and medium for predicting speed limit information | |
CN114407661A (en) | Data-driven electric vehicle energy consumption prediction method, system, device and medium | |
CN111369790B (en) | Vehicle passing record correction method, device, equipment and storage medium | |
CN111898878A (en) | Vehicle risk space-time distribution analysis method based on early warning big data | |
CN116665342B (en) | New energy automobile driving behavior analysis method, system and equipment | |
CN114013285B (en) | Actual driving range evaluation method for electric automobile | |
CN116109145B (en) | Risk assessment method, risk assessment device, risk assessment terminal and risk assessment storage medium for vehicle driving route | |
CN112000653B (en) | Space and time-based regional gridding driving behavior data preprocessing method | |
CN114898340A (en) | Method and system for evaluating driving behavior risk based on positioning data | |
CN116776104B (en) | Method and system for analyzing change rule of atmospheric components based on machine learning | |
CN115100856A (en) | Vehicle flow direction analysis method from multiple departure places to multiple destinations | |
CN116861212A (en) | Heavy engineering vehicle driving performance evaluation method based on natural driving data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |