CN115565379B - Method and system for replacing abnormal passenger flow data in historical passenger flow data - Google Patents
Method and system for replacing abnormal passenger flow data in historical passenger flow data Download PDFInfo
- Publication number
- CN115565379B CN115565379B CN202211553355.4A CN202211553355A CN115565379B CN 115565379 B CN115565379 B CN 115565379B CN 202211553355 A CN202211553355 A CN 202211553355A CN 115565379 B CN115565379 B CN 115565379B
- Authority
- CN
- China
- Prior art keywords
- passenger flow
- outbound
- value
- normal
- abnormal
- 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
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
Landscapes
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention relates to the technical field of intelligent transportation, and discloses a method and a system for replacing abnormal passenger flow data in historical passenger flow data, wherein the method for replacing the abnormal passenger flow data in the historical passenger flow data comprises the steps of calling the historical passenger flow data of a subway station, calculating characteristic passenger flow data according to the historical passenger flow data, and replacing the abnormal passenger flow data in the historical passenger flow data with the characteristic passenger flow data; a system for replacing abnormal passenger flow data in historical passenger flow data comprises a data calling module, a characteristic passenger flow data calculating module and an abnormal passenger flow data replacing module. The invention can process the abnormal passenger flow data in the historical passenger flow data, and can generate the passenger flow data which is continuous in time and has higher quality after the processing.
Description
Technical Field
The invention relates to the technical field of intelligent transportation, in particular to a method and a system for replacing abnormal passenger flow data in historical passenger flow data.
Background
At present, historical passenger flow data is generally used for passenger flow prediction of subway stations, and because the passenger flow prediction has very high quality requirements on the historical passenger flow data, abnormal passenger flow data in the historical passenger flow data needs to be processed, and the existing method mostly eliminates the abnormal passenger flow data in the historical passenger flow data, but the method can cause discontinuous time of the historical passenger flow data and affect the subsequent passenger flow prediction effect.
Disclosure of Invention
The invention aims to provide a method and a system for replacing abnormal passenger flow data in historical passenger flow data, which not only can process the abnormal passenger flow data in the historical passenger flow data, but also can generate passenger flow data which are continuous in time and have higher quality after processing.
In order to solve the technical problems, the invention adopts the following scheme:
in one aspect, a method for replacing abnormal traffic data in historical traffic data includes the steps of:
s1: calling historical passenger flow data of a subway station, wherein the historical passenger flow data comprises abnormal passenger flow data and normal passenger flow data;
s2: calculating characteristic passenger flow data according to the historical passenger flow data;
s3: and replacing the abnormal passenger flow data in the historical passenger flow data with the characteristic passenger flow data.
Further, the historical passenger flow data comprises a historical time period, an inbound passenger flow value and an outbound passenger flow value in any time period in the historical time period, the abnormal passenger flow data comprises an abnormal inbound passenger flow value in the inbound passenger flow value, an abnormal outbound passenger flow value in the outbound passenger flow value, an abnormal inbound time period corresponding to the abnormal inbound passenger flow value and an abnormal outbound time period corresponding to the abnormal outbound passenger flow value, and the normal passenger flow data comprises a normal inbound passenger flow value in the inbound passenger flow value, a normal outbound passenger flow value in the outbound passenger flow value, a normal inbound time period corresponding to the normal inbound passenger flow value and a normal outbound time period corresponding to the normal outbound passenger flow value.
Further, the characteristic passenger flow data includes a characteristic inbound value and a characteristic outbound value, and the S2 includes:
s21: calculating a characteristic arrival value according to the abnormal arrival current value, the abnormal arrival time period, the normal arrival current value and the normal arrival time period;
s22: and calculating a characteristic outbound value according to the abnormal outbound current value, the abnormal outbound time period, the normal outbound current value and the normal outbound time period.
Further, the step S21 includes:
s211: dividing the historical time period into a plurality of continuous historical period time periods with the length of the passenger flow period T;
s212: marking a normal inbound time period corresponding to the abnormal inbound time period in all the historical period time periods as a characteristic inbound time period, and calling the normal inbound passenger flow value of all the characteristic inbound time periods;
s213: judging whether the normal incoming passenger flow values of all the characteristic incoming time periods meet normal distribution or not;
s214: if the normal incoming passenger flow values of all the characteristic incoming time periods meet the normal distribution, calculating a first maximum likelihood value of the normal distribution met by the normal incoming passenger flow values of all the characteristic incoming time periods, and assigning the first maximum likelihood value to the characteristic incoming value; if the normal incoming current values of all the characteristic incoming time periods do not meet the normal distribution, the median of the normal incoming current values of all the characteristic incoming time periods is assigned to the characteristic incoming value.
Further, the step S22 includes:
s221: dividing the historical time period into a plurality of continuous historical period time periods with the length of the passenger flow period T;
s222: marking a normal outbound time period corresponding to the abnormal outbound time period in all the historical period time periods as a characteristic outbound time period, and calling the normal outbound current value of all the characteristic outbound time periods;
s223: judging whether the normal outbound guest flow values of all the characteristic outbound time periods meet normal distribution;
s224: if the normal outbound passenger flow values of all the feature outbound time periods meet the normal distribution, calculating a second maximum likelihood value of the normal distribution met by the normal outbound passenger flow values of all the feature outbound time periods, and assigning the second maximum likelihood value to the feature outbound value; if the normal outbound guest values of all the feature outbound time periods do not meet the normal distribution, the median of the normal outbound guest values of all the feature outbound time periods is assigned to the feature outbound values.
Further, the passenger flow period is a minimum time interval in which the total number of passengers entering from the subway station is equal to the total number of passengers exiting from the subway station.
Further, the step S3 includes:
s31: replacing the abnormal inbound guest value of the abnormal inbound time period with a characteristic inbound value corresponding to the abnormal inbound time period;
s32: and replacing the abnormal outbound guest value of the abnormal outbound time period with the characteristic outbound value corresponding to the abnormal outbound time period.
In another aspect, a system for replacing abnormal traffic data in historical traffic data includes:
a memory;
one or several processors;
one or several modules stored in a memory and configured to be executed by the one or several processors, the one or several modules comprising:
a data calling module for calling historical passenger flow data of the subway station;
a characteristic passenger flow data calculation module for calculating characteristic passenger flow data according to the historical passenger flow data;
and an abnormal passenger flow data replacement module for replacing the abnormal passenger flow data in the historical passenger flow data with the characteristic passenger flow data.
Further, the characteristic passenger flow data calculating module includes:
the characteristic inbound value calculation module calculates characteristic inbound values according to the abnormal inbound current value, the abnormal inbound time period, the normal inbound current value and the normal inbound time period;
and the characteristic outbound value calculation module is used for calculating the characteristic outbound value according to the abnormal outbound current value, the abnormal outbound time period, the normal outbound current value and the normal outbound time period.
Further, the module for replacing abnormal passenger flow data in the historical passenger flow data with characteristic passenger flow data comprises:
an abnormal inbound guest value replacement module that replaces the abnormal inbound guest value of the abnormal inbound time period with the characteristic inbound value corresponding to the abnormal inbound time period;
and an abnormal outbound passenger flow value replacement module for replacing the abnormal outbound passenger flow value of the abnormal outbound time period with the characteristic outbound value corresponding to the abnormal outbound time period.
The invention has the beneficial effects that:
1. the invention provides a method and a system for replacing abnormal passenger flow data in historical passenger flow data, wherein a data calling module calls the historical passenger flow data and outputs the historical passenger flow data to a characteristic passenger flow data calculating module, the characteristic passenger flow data calculating module calculates characteristic passenger flow data according to the historical passenger flow data and outputs the characteristic passenger flow data to an abnormal passenger flow data replacing module, and the abnormal passenger flow data replacing module replaces the abnormal passenger flow data in the historical passenger flow data with the characteristic passenger flow data.
2. In the invention, a characteristic passenger flow data calculation module is arranged to judge whether the inbound passenger flow value and the outbound passenger flow value of all characteristic outbound time periods accord with normal distribution, if the normal distribution is met, the maximum likelihood value corresponding to the normal distribution is assigned to the characteristic inbound value and the characteristic outbound value; if the normal distribution is not satisfied, the inbound guest flow value and the median of the outbound guest flow values in all the characteristic outbound time periods are correspondingly assigned to the characteristic inbound value and the characteristic outbound value, and the quality of the characteristic guest flow data obtained by the method is higher.
Drawings
FIG. 1 is a general flow chart of a method of replacing abnormal traffic data in historical traffic data in accordance with the present invention;
FIG. 2 is a flowchart showing the embodiment of S21 in the present invention;
FIG. 3 is a flowchart showing the step S22 of the present invention;
fig. 4 is a general structural diagram of a system for replacing abnormal traffic data in historical traffic data according to the present invention.
Detailed Description
The present invention will be described in further detail below with reference to the drawings and detailed description for better understanding of the technical solutions of the present invention to those skilled in the art.
Example 1:
a method for replacing abnormal traffic data in historical traffic data as shown in fig. 1-3, comprising the steps of:
s1: calling historical passenger flow data of a subway station, wherein the historical passenger flow data comprises abnormal passenger flow data and normal passenger flow data;
s2: calculating characteristic passenger flow data according to the historical passenger flow data;
s3: and replacing the abnormal passenger flow data in the historical passenger flow data with the characteristic passenger flow data.
Specifically, the historical passenger flow data comprises a historical time period, an inbound passenger flow value and an outbound passenger flow value in any time period in the historical time period, the abnormal passenger flow data comprises an abnormal inbound passenger flow value in the inbound passenger flow value, an abnormal outbound passenger flow value in the outbound passenger flow value, an abnormal inbound time period corresponding to the abnormal inbound passenger flow value and an abnormal outbound time period corresponding to the abnormal outbound passenger flow value, and the normal passenger flow data comprises a normal inbound passenger flow value in the inbound passenger flow value, a normal outbound passenger flow value in the outbound passenger flow value, a normal inbound time period corresponding to the normal inbound passenger flow value and a normal outbound time period corresponding to the normal outbound passenger flow value.
Specifically, the characteristic passenger flow data includes a characteristic inbound value and a characteristic outbound value, and the S2 includes:
s21: calculating a characteristic arrival value according to the abnormal arrival current value, the abnormal arrival time period, the normal arrival current value and the normal arrival time period;
s22: and calculating a characteristic outbound value according to the abnormal outbound current value, the abnormal outbound time period, the normal outbound current value and the normal outbound time period.
Specifically, the step S21 includes:
s211: dividing the historical time period into a plurality of continuous historical period time periods with the length of the passenger flow period T;
s212: marking a normal inbound time period corresponding to the abnormal inbound time period in all the historical period time periods as a characteristic inbound time period, and calling the normal inbound passenger flow value of all the characteristic inbound time periods;
s213: judging whether the normal incoming passenger flow values of all the characteristic incoming time periods meet normal distribution or not;
s214: if the normal incoming passenger flow values of all the characteristic incoming time periods meet the normal distribution, calculating a first maximum likelihood value of the normal distribution met by the normal incoming passenger flow values of all the characteristic incoming time periods, and assigning the first maximum likelihood value to the characteristic incoming value; if the normal incoming current values of all the characteristic incoming time periods do not meet the normal distribution, the median of the normal incoming current values of all the characteristic incoming time periods is assigned to the characteristic incoming value.
Specifically, the step S22 includes:
s221: dividing the historical time period into a plurality of continuous historical period time periods with the length of the passenger flow period T;
s222: marking a normal outbound time period corresponding to the abnormal outbound time period in all the historical period time periods as a characteristic outbound time period, and calling the normal outbound current value of all the characteristic outbound time periods;
s223: judging whether the normal outbound guest flow values of all the characteristic outbound time periods meet normal distribution;
s224: if the normal outbound passenger flow values of all the feature outbound time periods meet the normal distribution, calculating a second maximum likelihood value of the normal distribution met by the normal outbound passenger flow values of all the feature outbound time periods, and assigning the second maximum likelihood value to the feature outbound value; if the normal outbound guest values of all the feature outbound time periods do not meet the normal distribution, the median of the normal outbound guest values of all the feature outbound time periods is assigned to the feature outbound values.
Specifically, the passenger flow period is a minimum time interval in which the total number of passengers entering from the subway station is equal to the total number of passengers exiting from the subway station.
Specifically, the step S3 includes:
s31: replacing the abnormal inbound guest value of the abnormal inbound time period with a characteristic inbound value corresponding to the abnormal inbound time period;
s32: and replacing the abnormal outbound guest value of the abnormal outbound time period with the characteristic outbound value corresponding to the abnormal outbound time period.
For example, the history period is 140 days, the length T of the passenger flow period is 7 days, and the history period is divided into 20 consecutive history period periods of 7 days.
The working principle of the embodiment is as follows:
according to the invention, a passenger flow period is defined as a minimum time interval in which the total number of passengers entering from a subway station is equal to the total number of passengers exiting from the subway station, and a great number of researches show that the change curves of the passenger flow value entering from most of the subway stations and the passenger flow value exiting from the subway station in two adjacent time periods with the length of the passenger flow period are basically consistent, so that the passenger flow value change curve entering from the subway station in the time period with the length of the passenger flow period and the passenger flow value change curve exiting from the subway station can basically reflect the general entering characteristic and the general exiting characteristic of the subway station.
Based on the principle, the technical scheme firstly segments a historical time period by taking a passenger flow period as a reference, the historical time period is divided into a plurality of continuous historical period time periods with the length of the passenger flow period T, the change curves of the incoming passenger flow value and the outgoing passenger flow value of the subway station in the adjacent two time periods with the length of the passenger flow period are basically consistent, but abnormal passenger flow data with larger difference from normal passenger flow data still exist, the common incoming characteristic and outgoing characteristic of the subway station can be reflected by the normal incoming passenger flow value and the normal outgoing passenger flow value which are basically consistent, so that the normal incoming passenger flow value and the normal outgoing passenger flow value which correspond to the abnormal incoming passenger flow value and the abnormal outgoing passenger flow value in the whole historical period time period are extracted, the characteristic incoming passenger flow value and the characteristic outgoing passenger flow value are calculated according to the normal incoming passenger flow value and the normal outgoing passenger flow value, and finally the abnormal incoming passenger flow value and the abnormal outgoing passenger flow value are replaced with the corresponding characteristic incoming passenger flow value and the characteristic outgoing value, compared with the passenger flow data generated by the scheme, the passenger flow data generated by the scheme is continuous, and the passenger flow quality of the passenger flow is predicted according to the abnormal passenger flow is better than the current and the abnormal passenger flow.
Example 2:
as shown in fig. 4, a system for replacing abnormal passenger flow data in historical passenger flow data includes:
a memory;
one or several processors;
a data calling module for calling historical passenger flow data of the subway station;
a characteristic passenger flow data calculation module for calculating characteristic passenger flow data according to the historical passenger flow data;
and an abnormal passenger flow data replacement module for replacing the abnormal passenger flow data in the historical passenger flow data with the characteristic passenger flow data.
Specifically, the characteristic passenger flow data calculation module includes:
the characteristic inbound value calculation module calculates characteristic inbound values according to the abnormal inbound current value, the abnormal inbound time period, the normal inbound current value and the normal inbound time period;
and the characteristic outbound value calculation module is used for calculating the characteristic outbound value according to the abnormal outbound current value, the abnormal outbound time period, the normal outbound current value and the normal outbound time period.
Specifically, the module for replacing abnormal passenger flow data in the historical passenger flow data with characteristic passenger flow data includes:
an abnormal inbound guest value replacement module that replaces the abnormal inbound guest value of the abnormal inbound time period with the characteristic inbound value corresponding to the abnormal inbound time period;
and an abnormal outbound passenger flow value replacement module for replacing the abnormal outbound passenger flow value of the abnormal outbound time period with the characteristic outbound value corresponding to the abnormal outbound time period.
The working principle of the embodiment is as follows:
in the invention, a data calling module calls historical passenger flow data and outputs the historical passenger flow data to a characteristic passenger flow data calculating module; the characteristic inbound value calculation module and the characteristic outbound value calculation module in the characteristic passenger flow data calculation module calculate a characteristic inbound value and a characteristic outbound value according to the historical passenger flow data and output the characteristic inbound value and the characteristic outbound value to the abnormal passenger flow data replacement module; the abnormal incoming passenger flow value replacement module in the abnormal passenger flow data replacement module replaces abnormal incoming passenger flow data in the historical passenger flow data with a characteristic incoming value, the abnormal outgoing passenger flow value replacement module in the abnormal passenger flow data replacement module replaces abnormal outgoing passenger flow data in the historical passenger flow data with a characteristic outgoing value, and the system can generate passenger flow data which are continuous in time relative to eliminating the abnormal passenger flow data in the historical passenger flow data.
Example 3:
the embodiment describes in detail a method and a system for replacing abnormal passenger flow data in historical passenger flow data from the perspective of overall flow, as shown in fig. 1 to 4:
the technical scheme of the invention comprises a process for calling historical passenger flow data, a process for calculating characteristic passenger flow data and a process for replacing abnormal passenger flow data, and specifically comprises the following steps:
calling historical passenger flow data: the data calling module calls historical passenger flow data with a historical time period of 140 days;
calculating characteristic passenger flow data: the characteristic passenger flow data calculation module divides the historical time period into 20 continuous historical period time periods with the length of 7 days; the characteristic inbound value calculation module marks a normal inbound time period corresponding to the abnormal inbound time period in all the historical period time periods as a characteristic inbound time period, calls normal inbound guest values of all the characteristic inbound time periods, judges whether the normal inbound guest values of all the characteristic inbound time periods meet normal distribution, calculates a first maximum likelihood value of the normal distribution met by the normal inbound guest values of all the characteristic inbound time periods if the normal inbound guest values of all the characteristic inbound time periods meet the normal distribution, assigns the first maximum likelihood value to the characteristic inbound value, and assigns the median of the normal inbound guest values of all the characteristic inbound time periods to the characteristic inbound value if the normal inbound guest values of all the characteristic inbound time periods do not meet the normal distribution; similarly, the characteristic outbound value calculation module divides the historical time period into 20 continuous historical period time periods with the length of 7 days, marks the normal outbound time periods corresponding to the abnormal outbound time periods in all the historical period time periods as characteristic outbound time periods, calls normal outbound guest values of all the characteristic outbound time periods, judges whether the normal outbound guest values of all the characteristic outbound time periods meet normal distribution, calculates second maximum likelihood values of the normal distribution met by the normal outbound guest values of all the characteristic outbound time periods if the normal outbound guest values of all the characteristic outbound time periods meet the normal distribution, and assigns the second maximum likelihood values to the characteristic outbound values; if the normal outbound guest values of all the feature outbound time periods do not meet the normal distribution, the median of the normal outbound guest values of all the feature outbound time periods is assigned to the feature outbound values.
Replacement of abnormal passenger flow data: the abnormal arrival passenger flow value replacement module in the abnormal passenger flow data replacement module replaces the abnormal arrival passenger flow value of the abnormal arrival time period with the characteristic arrival value corresponding to the abnormal arrival time period; the abnormal outbound passenger flow value replacement module in the abnormal passenger flow data replacement module replaces the abnormal outbound passenger flow value of the abnormal outbound time period with the characteristic outbound value corresponding to the abnormal outbound time period.
According to the method and the device, the characteristic passenger flow data are calculated according to the normal passenger flow data in the historical passenger flow data, and the abnormal passenger flow data in the historical passenger flow data are replaced with the characteristic passenger flow data.
It is to be understood that the above embodiments are merely illustrative of the application of the principles of the present invention and the invention is not limited thereto. Various modifications and improvements may be made by those skilled in the art without departing from the spirit and substance of the invention, and are also considered to be within the scope of the invention.
Claims (4)
1. A method for replacing abnormal traffic data in historical traffic data, comprising the steps of:
s1: calling historical passenger flow data of a subway station, wherein the historical passenger flow data comprises abnormal passenger flow data and normal passenger flow data; the historical passenger flow data comprises a historical time period, an inbound passenger flow value and an outbound passenger flow value in any time period in the historical time period, the abnormal passenger flow data comprises an abnormal inbound passenger flow value in the inbound passenger flow value, an abnormal outbound passenger flow value in the outbound passenger flow value, an abnormal inbound time period corresponding to the abnormal inbound passenger flow value and an abnormal outbound time period corresponding to the abnormal outbound passenger flow value, and the normal passenger flow data comprises a normal inbound passenger flow value in the inbound passenger flow value, a normal outbound passenger flow value in the outbound passenger flow value, a normal inbound time period corresponding to the normal inbound passenger flow value and a normal outbound time period corresponding to the normal outbound passenger flow value;
s2: calculating characteristic passenger flow data according to the historical passenger flow data;
s3: replacing abnormal passenger flow data in the historical passenger flow data with characteristic passenger flow data;
the characteristic passenger flow data comprises a characteristic inbound value and a characteristic outbound value, and the S2 comprises:
s21: calculating a characteristic arrival value according to the abnormal arrival current value, the abnormal arrival time period, the normal arrival current value and the normal arrival time period;
s22: calculating a characteristic outbound value according to the abnormal outbound guest value, the abnormal outbound time period, the normal outbound guest value and the normal outbound time period;
the S21 includes:
s211: dividing the historical time period into a plurality of continuous historical period time periods with the length of the passenger flow period T;
s212: marking a normal inbound time period corresponding to the abnormal inbound time period in all the historical period time periods as a characteristic inbound time period, and calling the normal inbound passenger flow value of all the characteristic inbound time periods;
s213: judging whether the normal incoming passenger flow values of all the characteristic incoming time periods meet normal distribution or not;
s214: if the normal incoming passenger flow values of all the characteristic incoming time periods meet the normal distribution, calculating a first maximum likelihood value of the normal distribution met by the normal incoming passenger flow values of all the characteristic incoming time periods, and assigning the first maximum likelihood value to the characteristic incoming value; if the normal incoming current values of all the characteristic incoming time periods do not meet the normal distribution, the median of the normal incoming current values of all the characteristic incoming time periods is assigned to the characteristic incoming value;
the S22 includes:
s221: dividing the historical time period into a plurality of continuous historical period time periods with the length of the passenger flow period T;
s222: marking a normal outbound time period corresponding to the abnormal outbound time period in all the historical period time periods as a characteristic outbound time period, and calling the normal outbound current value of all the characteristic outbound time periods;
s223: judging whether the normal outbound guest flow values of all the characteristic outbound time periods meet normal distribution;
s224: if the normal outbound passenger flow values of all the feature outbound time periods meet the normal distribution, calculating a second maximum likelihood value of the normal distribution met by the normal outbound passenger flow values of all the feature outbound time periods, and assigning the second maximum likelihood value to the feature outbound value; if the normal outbound guest values of all the characteristic outbound time periods do not meet the normal distribution, assigning the median of the normal outbound guest values of all the characteristic outbound time periods to the characteristic outbound values;
the passenger flow period is a minimum time interval in which the total number of passengers entering from the subway station is equal to the total number of passengers exiting from the subway station.
2. A method of replacing abnormal traffic data in historical traffic data according to claim 1, wherein S3 comprises:
s31: replacing the abnormal inbound guest value of the abnormal inbound time period with a characteristic inbound value corresponding to the abnormal inbound time period;
s32: and replacing the abnormal outbound guest value of the abnormal outbound time period with the characteristic outbound value corresponding to the abnormal outbound time period.
3. A system for replacing abnormal traffic data in historical traffic data, comprising:
a memory;
one or several processors;
one or several modules stored in a memory and configured to be executed by the one or several processors, the one or several modules comprising:
the data calling module is used for calling historical passenger flow data of the subway station, wherein the historical passenger flow data comprises abnormal passenger flow data and normal passenger flow data; the historical passenger flow data comprises a historical time period, an inbound passenger flow value and an outbound passenger flow value in any time period in the historical time period, the abnormal passenger flow data comprises an abnormal inbound passenger flow value in the inbound passenger flow value, an abnormal outbound passenger flow value in the outbound passenger flow value, an abnormal inbound time period corresponding to the abnormal inbound passenger flow value and an abnormal outbound time period corresponding to the abnormal outbound passenger flow value, and the normal passenger flow data comprises a normal inbound passenger flow value in the inbound passenger flow value, a normal outbound passenger flow value in the outbound passenger flow value, a normal inbound time period corresponding to the normal inbound passenger flow value and a normal outbound time period corresponding to the normal outbound passenger flow value;
a characteristic passenger flow data calculation module for calculating characteristic passenger flow data according to the historical passenger flow data;
an abnormal passenger flow data replacement module for replacing the abnormal passenger flow data in the historical passenger flow data with the characteristic passenger flow data;
the characteristic passenger flow data comprises a characteristic inbound value and a characteristic outbound value, and the characteristic passenger flow data calculation module comprises:
calculating a characteristic arrival value according to the abnormal arrival current value, the abnormal arrival time period, the normal arrival current value and the normal arrival time period, wherein the characteristic arrival value specifically comprises:
dividing the historical time period into a plurality of continuous historical period time periods with the length of the passenger flow period T;
marking a normal inbound time period corresponding to the abnormal inbound time period in all the historical period time periods as a characteristic inbound time period, and calling the normal inbound passenger flow value of all the characteristic inbound time periods;
judging whether the normal incoming passenger flow values of all the characteristic incoming time periods meet normal distribution or not;
if the normal incoming passenger flow values of all the characteristic incoming time periods meet the normal distribution, calculating a first maximum likelihood value of the normal distribution met by the normal incoming passenger flow values of all the characteristic incoming time periods, and assigning the first maximum likelihood value to the characteristic incoming value; if the normal incoming current values of all the characteristic incoming time periods do not meet the normal distribution, the median of the normal incoming current values of all the characteristic incoming time periods is assigned to the characteristic incoming value;
calculating a characteristic outbound value according to the abnormal outbound guest flow value, the abnormal outbound time period, the normal outbound guest flow value and the normal outbound time period, and specifically comprising:
dividing the historical time period into a plurality of continuous historical period time periods with the length of the passenger flow period T;
marking a normal outbound time period corresponding to the abnormal outbound time period in all the historical period time periods as a characteristic outbound time period, and calling the normal outbound current value of all the characteristic outbound time periods;
judging whether the normal outbound guest flow values of all the characteristic outbound time periods meet normal distribution;
if the normal outbound passenger flow values of all the feature outbound time periods meet the normal distribution, calculating a second maximum likelihood value of the normal distribution met by the normal outbound passenger flow values of all the feature outbound time periods, and assigning the second maximum likelihood value to the feature outbound value; if the normal outbound guest values of all the characteristic outbound time periods do not meet the normal distribution, assigning the median of the normal outbound guest values of all the characteristic outbound time periods to the characteristic outbound values;
the passenger flow period is a minimum time interval in which the total number of passengers entering from the subway station is equal to the total number of passengers exiting from the subway station.
4. A system for replacing abnormal traffic data in historical traffic data according to claim 3, wherein the abnormal traffic data replacement module comprises:
an abnormal inbound guest value replacement module that replaces the abnormal inbound guest value of the abnormal inbound time period with the characteristic inbound value corresponding to the abnormal inbound time period;
and an abnormal outbound passenger flow value replacement module for replacing the abnormal outbound passenger flow value of the abnormal outbound time period with the characteristic outbound value corresponding to the abnormal outbound time period.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211553355.4A CN115565379B (en) | 2022-12-06 | 2022-12-06 | Method and system for replacing abnormal passenger flow data in historical passenger flow data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211553355.4A CN115565379B (en) | 2022-12-06 | 2022-12-06 | Method and system for replacing abnormal passenger flow data in historical passenger flow data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115565379A CN115565379A (en) | 2023-01-03 |
| CN115565379B true CN115565379B (en) | 2023-05-02 |
Family
ID=84769817
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211553355.4A Active CN115565379B (en) | 2022-12-06 | 2022-12-06 | Method and system for replacing abnormal passenger flow data in historical passenger flow data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115565379B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593976A (en) * | 2013-11-28 | 2014-02-19 | 青岛海信网络科技股份有限公司 | Road traffic state determining method and system based on detector |
| CN110570004A (en) * | 2018-06-05 | 2019-12-13 | 上海申通地铁集团有限公司 | subway passenger flow prediction method and system |
| CN113076349A (en) * | 2020-01-06 | 2021-07-06 | 阿里巴巴集团控股有限公司 | Data anomaly detection method, device and system and electronic equipment |
Family Cites Families (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104021430B (en) * | 2014-06-12 | 2017-03-22 | 东南大学 | Method for analyzing uncertainty of passenger flow of urban mass transit terminal |
| CN105224999A (en) * | 2015-09-10 | 2016-01-06 | 北京市交通信息中心 | The real-time passenger flow forecasting of urban track traffic based on AFC data and system |
| JP2018088225A (en) * | 2016-11-28 | 2018-06-07 | 日本コントロールシステム株式会社 | Abnormal value extraction system and method for analog waveform data using Gaussian fitting |
| CN107992449B (en) * | 2017-12-05 | 2021-04-30 | 北京工业大学 | Subway abnormal flow detection method based on low-rank representation |
| CN108154342A (en) * | 2017-12-25 | 2018-06-12 | 苏州大学 | Intelligent bus data collaborative method and its system based on cloud storage |
| CN108399277B (en) * | 2018-01-24 | 2021-09-21 | 华南理工大学 | Bridge damage identification method based on temperature and strain correlation |
| US11176589B2 (en) * | 2018-04-10 | 2021-11-16 | Ebay Inc. | Dynamically generated machine learning models and visualization thereof |
| CN109543268B (en) * | 2018-11-14 | 2023-05-05 | 大连理工大学 | TBM propulsion main influencing factor identification method based on kriging model |
| CN109726198A (en) * | 2018-12-06 | 2019-05-07 | 中科恒运股份有限公司 | Method for processing abnormal data and device |
| CN109615226B (en) * | 2018-12-12 | 2020-12-29 | 焦点科技股份有限公司 | Operation index abnormity monitoring method |
| CN110046764A (en) * | 2019-04-12 | 2019-07-23 | 成都四方伟业软件股份有限公司 | The method and device of passenger flow forecast amount |
| CN112734072A (en) * | 2019-10-28 | 2021-04-30 | 深圳市中电软件有限公司 | Power load prediction method, system, terminal device and medium |
| CN112598182B (en) * | 2020-12-25 | 2022-11-29 | 卡斯柯信号有限公司 | Intelligent scheduling method and system for rail transit |
| CN112699946B (en) * | 2020-12-31 | 2022-06-21 | 湖南工商大学 | Anomaly detection method and device for sensing monitoring data and related equipment |
| CN113987944A (en) * | 2021-10-29 | 2022-01-28 | 成都智元汇信息技术股份有限公司 | Subway station-entering passenger flow prediction method and device based on Prophet model |
| CN113988477A (en) * | 2021-11-26 | 2022-01-28 | 西安化奇数据科技有限公司 | Photovoltaic power short-term prediction method and device based on machine learning and storage medium |
| CN115204478A (en) * | 2022-06-30 | 2022-10-18 | 北京航空航天大学 | Public traffic flow prediction method combining urban interest points and space-time causal relationship |
-
2022
- 2022-12-06 CN CN202211553355.4A patent/CN115565379B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593976A (en) * | 2013-11-28 | 2014-02-19 | 青岛海信网络科技股份有限公司 | Road traffic state determining method and system based on detector |
| CN110570004A (en) * | 2018-06-05 | 2019-12-13 | 上海申通地铁集团有限公司 | subway passenger flow prediction method and system |
| CN113076349A (en) * | 2020-01-06 | 2021-07-06 | 阿里巴巴集团控股有限公司 | Data anomaly detection method, device and system and electronic equipment |
Non-Patent Citations (3)
| Title |
|---|
| 卫铮铮.基于客运大数据平台的铁路客流预测系统.《铁路计算机应用》.2022,第31卷(第1期),37-42. * |
| 基于HHT的电力负荷影响因素分析及预测;张豪杰;《中国优秀硕士学位论文全文数据库 (工程科技Ⅱ辑)》;20160215(第02期);C042-1050 * |
| 李瀚文.基于时序分解和LSTM神经网络的城市轨道交通短时客流预测.《中国优秀硕士学位论文全文数据库 (工程科技Ⅱ辑)》.2021,(第3期),C033-562. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115565379A (en) | 2023-01-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shi et al. | Operations design of modular vehicles on an oversaturated corridor with first-in, first-out passenger queueing | |
| CN107358319A (en) | Flow Prediction in Urban Mass Transit method, apparatus, storage medium and computer equipment | |
| CN1571348A (en) | An apparatus and method for implementing data dynamic alignment bandwidth in transmission equipment | |
| CN115565379B (en) | Method and system for replacing abnormal passenger flow data in historical passenger flow data | |
| CN1147168C (en) | CDMA cellular communication system | |
| KR102504273B1 (en) | DRT request information clustering method for allocating DRT cars and system thereof | |
| US5509102A (en) | Voice encoder using a voice activity detector | |
| CN115858161A (en) | Method, device, equipment and storage medium for intelligently managing resources of data middleboxes | |
| CN113987944A (en) | Subway station-entering passenger flow prediction method and device based on Prophet model | |
| CN113537596B (en) | Short-time passenger flow prediction method for new line station of urban rail transit | |
| CN110920695B (en) | Interconnection and interworking-based vehicle configuration optimization method and device | |
| CN112389445A (en) | Vehicle driving regulation and control method and device, vehicle-mounted equipment and readable storage medium | |
| CN112465177A (en) | Bus route optimization system and method based on big data analysis | |
| CN110705802A (en) | Power distribution network flexible load prediction method based on multi-factor segmentation | |
| AU2002358737A1 (en) | Method and system for determining the itinerary travelled by a vehicle | |
| CN112118581B (en) | Multi-carrier processing method, device, system and computer readable storage medium | |
| JP2000259978A (en) | Traveling time information processor | |
| CN113743685B (en) | Method for determining bus timetable and electronic equipment | |
| CN114912854A (en) | Subway train operation adjusting method and device, electronic equipment and storage medium | |
| CN117313980A (en) | Method, system, equipment and medium for estimating traffic capacity of self-adaptive platform of rapid bus station | |
| CN1310453C (en) | Distribution method and device for CDMA vocoder time chip resources | |
| CN115294785B (en) | Subway dynamic operation adjustment method and device based on mobile phone signals | |
| CN117689185B (en) | Equipment data scheduling optimization method based on Internet of things | |
| CN115965114A (en) | Urban rail transit OD passenger flow estimation method based on machine learning | |
| CN112866693B (en) | Method and device for dividing coding unit CU, electronic equipment and storage medium |
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 |